Vol.19 No.4 JAN - JUNE, 2020

Research Articles

ELAS: An Extended Lightweight Authentication Scheme for Secure M2M Communications
       B. Satyanarayana Murthy, Dr. L. Sumalatha
In the recent advancements in the industrial applications, machine-to-machine (M2M) verbal exchange generation is taken into consideration as a key underlying era, in which Machine Type Communication Devices (MTCDs) are adopted to switch over statistics with each different in an independent manner with no person interference. Conversely, maximum of the prevailing M2M protocols are also used in business field offer protection strategies depends on traditional asymmetric ciphering consequential in excessive calculation overhead. As a result, the inhibited nodes aren't intelligent to help them properly therefore, numerous safety issues get up for the M2M background. Consequently, lightweight safety approaches are necessary for M2M transportation with a purpose to offer safety. As a modern step, in this paper, we advocate an extended light-weight authentication mechanism, based handiest on easy signature schemes and certificates, for light weight communications in business environment. The projected scheme is comprised by way of low processing cost, transmission, and storage space overhead, even as attaining communal verification among the nodes in a M2M communication, i.e, the scheme offers a way of mutual authentication between any two nodes in a network.

Study on the cost allocation method to maximize the benefit of e-commerce enterprises in the cloud computing environment
       Jinfang Zhao
Cloud computing is a brand-new IT service delivery model. It is a key strategic technology and means to lead the innovation of the information industry in the future. It can effectively solve the dynamic demand and final cost of e-commerce enterprise resources, and it can reduce costs for e-commerce enterprises to improve management, promote information development, and achieve resource integration. It is a key factor in shaping and enhancing the competitiveness of enterprises.Fuzzy paradigm should be understood and used at the level of world view and methodology, and should be recognized that it has different forms and properties in different disciplines. Based on the cloud computing environment, this paper proposes a task allocation model, taking into account the utility functions of different users, and maximizing the overall terminal benefits by assigning computational tasks on a large number of terminals to virtual machine instances. The simulation results show that the overall benefit of the terminal under this allocation model is significantly higher than that of the overall terminal under the centralized task allocation model.

The Computer Desktop Image Compression Based on Clustering Algorithm
       Dawei Gui
With the rapid development of computer software and hardware technology and network technology, aiming at the limitations of the traditional image compression standards and the deficiencies of the existing computer desktop image compression methods, By analyzing the characteristics of computer desktop image, according to the characteristics of desktop compression, a compression scheme based on HEVC and color clustering is proposed, which divides blocks into text/graphics blocks, natural image blocks and mixed blocks based on the features of histogram information and texture information of blocks. In block division and classification, an adaptive dynamic block classification algorithm is proposed which is different from the traditional block partitioning. Compared with the traditional method, the new block classification algorithm can save the code stream and improve the classification accuracy.

Research on the inheritance and protection of data mining technology in national sports
       Dongmei Li, Feng Xiao, Yanjun Zheng2*
In order to improve the ability of inheritance and protection of national sports, the association data mining model of inheritance and protection of national sports is proposed based on feature extraction of association rules. In this paper, a new neural fuzzy normal form system is designed, which can perform both feature analysis and SI(sine) integration. The time series analysis model of the inheritance and protection correlation data in the national sports are constructed, the overall frame model of the inheritance and protection correlation data mining in the national sports is designed. The ability of adaptive data fusion and feature registration is improved. The simulation results show that the proposed method has good accuracy and strong ability of feature matching in the correlation data mining of inheritance and protection in national sports, and it can improve the function of inheritance and protection of national sports

Research on Single Chip Microcomputer Teaching Platform Based on Wireless Communication
       Guo Liqiang
In view of the contradiction between the increasingly extensive application of single-chip microcomputer technology in home appliances, digital products, medical equipment, automobile industry, aerospace and other fields and the long learning cycle of the technology, which is not easy to master, a new single-chip microcomputer teaching platform for high school students is designed. The teaching platform adopts the processing of completely transparent and moderately encapsulated in technical details, and learners can easily use the software and hardware resources to develop projects. This teaching platform can meet the learning needs of different levels of students in general technology courses of ordinary high school, play a positive role in improving the technical literacy of middle school students and enhancing the ability of technology application, and lay a good foundation for high school students to participate in student scientific research activities in colleges and universities in the future

Research on multi-source mobile commerce service recommendation model of data fusion based on tree network
       Wenqiang Zhu
With the rapid development of e-commerce and computer technology, the recommendation service in business activities has no longer implemented by people, but by software technology. In general, the ecommerce website recommendation service can have divided into two types: standardization and personalization. The design of the recommendation service should be as follows, the content presentation should meet the consumer's shopping needs; we need to provide different processing level information according to the consumer's cognitive level; appropriately select the expression and strengthen the credibility of the recommendation. This paper proposes a multi-source data fusion strategy of mobile commerce service recommendation for tree-based networks. On this basis, the tree-node relationship is stored through redundant data, thus achieving complete decoupling between tree-type nodes and reaching the tree. The purpose is to have the efficient storage and access of structured data. For the multimedia mobile device is limited by hardware conditions, limited storage capacity, weak computing power, etc., using client-side cached partial data and ondemand sequence request server data and other strategies, making full use of the hierarchical structure of tree structure to design efficient The tree synchronization model enables efficient buffering and accessing of server data by mobile devices

Urban Spatial Location Service Prediction Algorithm Based on FAGA-LSSVM under the Background of Internet of Things
       Xiangli Xia, Wei Cheng* , Liu Yang
With the hot issues such as smart city and ecological city put forward, the development of intelligence and informatization of urban space has been established, especially the Internet of Things. With the wide application of location-based social networks (LBSNs), users can share their location of interest in location. By analyzing users' historical geographic information, location service recommendation can recommend geographic locations to users to help users obtain better access experience. Combined with genetic algorithm (GA) algorithm, a recommendation algorithm based on geographic location service optimization is proposed, which can better recommend to users. Aiming at the problem of slow convergence speed of GA, a fast adaptive genetic algorithm (FAGA) method is proposed to optimize location services. In the experimental part, comparing several functions, FAGA's test effect and convergence are ideal. By comparing FAGA-LSSVM algorithm with other methods in location service recommendation, FAGA-LSSVM method has more advantages.

A study on the devising and deploying of electro-hydraulic pumping unit for smart manufacturing
       Deming Zhu, Yongling Fu*, Mingkang Wang, Xu Han
Studies are conducted on hydraulic systems operating under different working conditions. In line with the Industry 4.0, design techniques and manufacturing techniques are improved to carry out such systems. In this paper, we propose an electro-hydraulic pumping unit on the basis of axial piston pump specifically targeting at smart manufacturing. Within the system, the electric motor and the hydraulic pump are integrated to meet the demand of smart component. According to the working principle, the controlling strategy as well as the energy management strategy are established. We evaluate the working performance of the proposed system by a prototype of the pumping unit. The implementation of the proposed pumping unit is carried out on a CNC(Computer Numerical Control) machine. Experimental results verifies the effectiveness of the electro-hydraulic pumping unit in practical use.

Evolutionary Game Analysis between Businesses and Consumers under the Background of Internet Rumors Running Head: Evolutionary Game Analysis under the Background of Internet Rumors
       Bowen Li, Hua Li, Qiubai Sun, Xuebo Chen
In order to analyze the behavior of businesses and consumers under the impact of internet rumors, this study constructs an evolutionary game model between consumers and businesses based on the Evolutionary Game Model proposed by Smith J M and with the introduction of a new parameter, i.e. the degree of psychological identity consumers have on businesses. By analyzing the equilibrium point and the Evolution Stability Strategy, it is concluded that: 1) When the cost of investigating rumors is greater than the additional income obtained after the investigation, businesses will choose negative response, while consumers’ purchase will is decided by the relationship between the cost of investigation paid by consumers and the cost of searching for a substitute. 2) When the cost for investigating rumors is less than the additional income obtained later, both the probability of positive response by businesses and the probability of purchasing by consumers are in direct proportion to the degree of psychological identity consumers have on businesses. Conclusions of this article will provide theories and references of decision-making for businesses influenced by internet rumors.

A New Image Encryption Algorithm Based on Optimized Lorenz Chaotic System
       TU Li, WANG Yan*, Zhang Chi
In this paper, an improved Lorenz system was constructed, in the first stage, a nonlinear term in general Lorenz system was replaced by the sum of term of exponential function and term of the square of single variable, then the dynamic characteristics of the improved Lorenz system were analyzed through the analysis on the phase diagrams and its Lyapunov exponents, and it’s proved that the new system has good chaotic characteristics. In the second stage, to improve the security and anti-attack ability of image encryption algorithm, a new image encryption algorithm was proposed based on this improved Lorenz chaotic system, which was used to generate two groups of key sequences which were used in scrambling encryption and alternative encryption. In the scrambling encryption stage, the gray values of image pixels were sorted in ascending order, and combining with the sequence of scrambled encryption key, the pixel position scrambling was realized. In the phase of the pixel value replacement encryption stage, the gray values of the pixels were changed by the method of cipher text feedback. In the third stage, the quantitative analysis of the effect of encryption was carried out by using histogram, information entropy, correlation coefficient of adjacent pixels. The experimental results show that the improved Lorenz formula is a nonlinear chaotic system, the encrypted algorithm based on this chaotic system can effectively resist chosen plaintext attack, in the encrypted image, the grey value shave random-like distribution behavior and the adjacent pixels have zero correlation. The algorithm has a 299 bit key space and it is very sensitive to the key

Application of KJ / AHP / QFD integrated ankle rehabilitation nursing robot in orthopaedics
       Chenyu Zhang, Rodrigues Marlene
This article takes the KJ / AHP / QFD method integration as the theoretical support, systematically summarizes the user needs of patients and rehabilitation physicians, and studies its mapping relationship with technical characteristics to provide innovative design for ankle rehabilitation nursing robot Design references and methodological guidance. The AHP method is used to calculate the user demand weights to construct a comparison judgment matrix, and sort them according to the weight values. Combine the technical characteristics summarized by the technical staff to build a house of quality, determine the relationship matrix between the two and the technical characteristic autocorrelation matrix, analyse the conflicting technical characteristics to obtain a solution, and guide the specific design of the ankle rehabilitation nursing robot. The KJ / AHP / QFD method is integrated into the design of an ankle rehabilitation nursing robot, and the mapping relationship between the target user's needs and technical characteristics is reasonably converted into design guidance, which reduces the design cost, realizes intelligent product functions, and improves. The efficiency and quality of ankle rehabilitation training provide method guidance for the design of related rehabilitation nursing robots, and provide theoretical support for the application of rehabilitation nursing robots in orthopaedics.

Machine Learning based Research on the Re-lationship between Exercise Physiological In-dexes and Neural Activity Risk Warning
       Caohui Wang*†, Chenwei An
First of all, this article analyzes the heart rate during exercise, the heart rate during recovery period, and the resting heart rate under the premise of long-term aerobic exercise, and uses machine learning to find out the effect of exercise on cardiac autonomic nerve activity and the effect of exercise on Impact of other physical health indicators. Secondly, the paper analyzes the physiological trends of exercise and analyzes the changes and complexity of heart rate under different exercise intensities. It is verified that heart rate can reflect the activity of cardiac dynamics control system. It is often used for health monitoring, exercise intensity assessment and physiological arousal measurement. in conclusion. Finally, the paper analyzes the changes in resting heart rate and other physical health indicators under the premise of long-term aerobic exercise.

Research on IOT and Human-Computer In-teraction with Mobile Medical Big Data
       Bing Li*†
In the context of the Internet of Things, the thesis follows the design concept of “focusing on health care service objects”, and based on the design principles of ease of use, safety, and effectiveness of medical devices, and various business models around health care services. The human-computer interaction design for big data collection of personal health information is explored and practiced, and the theory of human-computer interaction is applied to the interaction interface design of personal health equipment. The author has completed three main research contents: (1) application mode analysis of personal health information big data collection in the home environment, (2) functional requirements analysis of healthy mobile terminals, interactive process design, (3) human-machine interface Rapid prototyping and code implementation

Research on the Application of Cloud Technology and IOT in Brainwave Signals Acquisition and Analysis of Disabled Persons Autonomous Systems
       Yong Ding*†
In order to improve the quality of life of persons with disabilities, a research on self-help systems for persons with disabilities based on brain wave detection and Internet of Things technology is conducted. The system consists of information acquisition, servo control, and wireless communication modules. The information acquisition module is based on the TGAM chip, which collects, preprocesses, identifies, extracts, and classifies brain wave data to obtain relevant characteristic brain wave values. The servo control module uses PIC24HJ128GP506 as the main control single-chip microcomputer, outputs the control signal after secondary processing of the brain wave value, and controls the movement direction of the trolley. The wireless communication module uses NRF24L01 to form the Internet of Things for home appliances, and sends brain wave instructions to the home appliance side with the STC89C52RC as the main control chip to remotely control the home appliances. Test results show that the system can extract brain wave information, control wheelchair movements, and remotely control home appliances to meet the daily needs of people with disabilities.

Machine Learning based Health Learning Data Collection with Wearable Devices
       Min Lin, Zhaoliang Yang*†
Human activity assessment based on wearable devices has become a new research hotspot in the fields of pattern recognition and machine learning. How to make full use of rechargeable energy to achieve sustainable health monitoring while meeting the requirements of human activity monitoring is an urgent problem to be solved. Based on this, a human activity data acquisition device based on a piezoelectric energy harvester and a three-axis accelerometer is designed and implemented in this paper. A human daily activity data set containing motion energy and acceleration signals is constructed. This data set is a set of human activity data collected on three different parts of the human leg, waist and wrist using only a single sensor node using machine learning methods under natural unconstrained conditions. At the same time, the paper proposes a motion recognition method based on motion energy and acceleration, SRC-EA. This method uses multi-mode information generated by human motion to improve the system's recognition accuracy while reducing the sampling frequency of the acceleration sensor. Reduce system energy consumption. Finally, experiments show that the average recognition accuracy of the system is increased by 2.5% and 39.44%, respectively, and the power consumption of the system is reduced by 60%.

Evaluation Method of Fetus with Abnormal Glucose Metabolism in Late Pregnancy based on Complementary Ensemble Empirical Mode Decomposition Noise Reduction Algorithm in Ultrasound Imaging
       JunfengHuang1,CuitingWang2, XianxiaLi,YuqinJing*,Dudzik Jonathan,Asami Rei
To investigate the thesis pregnant women with abnormal glucose metabolism and fetal hemodynamic parameters predictive of poor pregnancy outcomes of pregnancy, and analyze the factors of poor pregnancy outcomes. Methods: trimester pregnant women with abnormal glucose metabolism during pregnancy 109 cases, 34 cases classified into 75 cases of poor prognosis and good prognosis groups based on pregnancy outcome. Color Doppler ultrasonography groups were measured fetal brain artery (the MCA), umbilical artery (UA) and hemodynamic parameters pregnant uterine artery (Ut-A), comprising: a peak systolic velocity / systolic blood speed (S / D), the resistance index (RI) and plasticity index (PI). Each predictive hemodynamic parameter plotted receiver operating characteristic (ROC) curve of adverse outcomes of pregnancy, and to determine the optimal cutoff value index. Analysis of pregnancy outcomes related factors Logistic regression. Results: MCA-PI poor prognosis group, MCA-RI, RI ratio (MCA / UA) are lower than the good prognosis group, Ut-A-PI is higher than the good prognosis group, the differences were statistically significant (P <0.05,). ROC curve analysis results show that when the MCA-PI 1.56, the sensitivity of the predicted adverse outcomes of pregnancy, the highest specificity <, was 91.18%, 80.00%, respectively. Logistic regression analysis of risk factors shows poor pregnancy outcomes include: pregnant women, older age, body mass index ≥24.0kg / m2 and a family history of diabetes; protective factors include: There are exercise during pregnancy, MCA-PI≥1.56, MCA-RI≥0.63 and RI The ratio (MCA / UA) ≥0.84. Conclusion: Color Doppler ultrasound measured MCA-PI <1.56 the most important indicators of poor pregnancy outcomes as abnormal glucose metabolism during pregnancy and predict the exact cutoff. Pregnant women, older age, body mass index ≥24.0kg / m2 and a family history of diabetes is abnormal glucose metabolism during pregnancy risk factors for adverse outcomes of pregnancy; pregnancy there is movement, MCA-PI≥1.56, MCA-RI≥0.63 and RI ratio (MCA / UA) ≥0.84 protective factors abnormal glucose metabolism during pregnancy adverse outcomes of pregnancy.

Application of B-ultrasound Information Image in Renal Puncture Biopsy Treatment and Nursing
       JunfengHuang,CuitingWang, XianxiaLi,YuqinJing*,Dudzik Jonathan,Asami Rei
To explore the application value of ultrasound-guided percutaneous renal biopsy in the diagnosis of chronic kidney disease, and to study the clinical effects and nursing of B-mode ultrasound-guided percutaneous renal biopsy. Methods: In 94 patients with chronic kidney disease in our hospital, ultrasound-guided percutaneous renal biopsy was performed to obtain tissue for pathological examination; patients were observed for symptoms such as low back pain, backache, hematuria, and subcapsular hematoma. Color Doppler ultrasonography was performed on the punctured patients on day 1, 2, and 3 to observe whether there was subrental hematoma. The pathological results were analyzed and the success rate of percutaneous renal biopsy under ultrasound guidance was analyzed. Before the patient was discharged, investigate the satisfaction with the nursing work. Results: All the 94 patients who underwent ultrasound-guided percutaneous renal biopsy were successfully obtained. The length of the samples was from 13 to 18 mm, and the puncture was performed 1-3 times according to the length of the samples. After the puncture, the patients were observed, 45 of the 94 patients reported that they had back pain and backache symptoms, of which 12 patients had subcapsular hematomas; 8 patients had gross hematuria, 62 patients had microscopic hematuria, and the rest the patient had no significant symptoms. All the 94 patients were satisfied, and the satisfaction rate was 100%. Only one case of perirenal hematoma appeared after surgery, and it was cured after clinical intervention. Conclusion: Ultrasound-guided renal biopsy is a safe and effective auxiliary examination method, which can improve the success rate of puncture and reduce postoperative complications. Percutaneous renal biopsy under the guidance of B-mode ultrasound has obvious effects. Effective nursing can reduce the incidence of postoperative complications and improve patient satisfaction

Analysis of the Efficacy of Rhodiola Rosea Based on DTI Image Segmentation Algorithm for Patients with Delayed Encephalopathy Caused by CO Poisoning
       Yuming Gao, Haitao Cui, Wei Ren, Bing Han*, Chin Michael
DTI paper using image segmentation algorithm investigate the effect of large plants Rhodiola injection on myocardial injury in patients with acute severe CO poisoning, and to explore the clinical and CT delayed encephalopathy after acute CO poisoning, MRI performance. The control group received hyperbaric oxygen, mannitol, dexamethasone, citicoline injection, gangliosides, dracone; observation group were large strain Rhodiola injection treatment group based on the 1 / d, 2 weeks of continuous treatment. After two weeks before treatment and were used to detect changes in the indicators, while on clinical head CT, head MRI results were analyzed retrospectively. The results showed that observed following treatment group hsCRP, ET-1 was VEGF significantly higher, differences were our statistics(P <0.01). were compared, no statistically significant difference (P> 0.05). 16 cases of head CT showed bilateral symmetry confluent lesions were blurred edge is low density half and periventricular egg garden centers. 12 cases of MRI, the lesions are in the cerebral cortex, white matter lateral ventricle and / or basal ganglia. Therefore, a large strain Rhodiola injection patients with acute severe CO poisoning, reduce myocardial vascular endothelial cell injury, improve cardiac function, protect the damaged myocardium. Meanwhile, after acute CO poisoning delayed encephalopathy early for CT, MRI examination facilitate analysis and prognosis of the disease.

Effect of Atorvastatin on Oxidative Stress in Diabetic Nephropathy Patients based on Multi-Phase CT Image Fusion
       LeiXu, QinYang, JiaoXue, XiaoyanZhang*, Filipek Slawomir, Catharino Rodrigo
Quantitative analysis of diabetic nephropathy (DN) by contrast-enhanced ultrasound (CEUS) in patients with renal blood perfusion parameters change, to explore the value of atorvastatin in changes in renal function in patients with early diagnosis of DN. Method: Forty patients were divided into normal albuminuria group (group Ⅰ) according to Mogensen staging and early DN group (Ⅱ group) and 15 healthy volunteers as a control group (N). Check all caught CEUS renal perfusion and atorvastatin treatment, and image analysis software with QontraXt select a region of interest (ROI) in the renal cortex, the generation time - intensity curve (the TIC), renal perfusion parameters obtained. Results: CEUS can clearly show the contrast agent in the renal perfusion process, compared with the N groups, the local patient renal blood volume group Ⅰ (RBV) increases, time to peak (TTP) and mean transit time (MTT) extended statistical difference significance (P <0.05), while the peak intensity (DPI) and the local blood flow (RBF) difference was not statistically significant (P groups> 0.05); N group and the comparison group ⅰ, ⅱ group patients RBV, TTP and MTT significantly increased, DPI, RBF decreased, differences were statistically significant (P <0.05). Conclusion: Atorvastatin joint technical analysis of CEUS change DN blood perfusion parameters in patients with early, can be assessed early DN patients with abnormal renal function.

Application of MRI Image Segmentation Algorithm for the Analysis of Serum IL-17 Expression in Preeclampsia
       Zenying Yu, Shengyan Zhou*, Zhen Tan, Guangmin Lu, Akiyoshi Kazunari
To study the expression level of IL-17 in peripheral blood and its effect on maternal-fetal tolerance in patients with eclampsia in late pregnancy using MRI image segmentation algorithm, and to explore Th17, Treg cells and their related cytokines IL-17, IL-10 Changes in peripheral blood in patients with preeclampsia and their correlation with the severity of preeclampsia. Methods: 39 patients with severe preeclampsia and eclampsia with brain symptoms were examined by cranial magnetic resonance imaging (MRI). At the same time, pregnant women were collected from peripheral blood samples at 32 weeks of pregnancy to detect the percentage of Th17 and Treg cells in CD4 + T lymphocytes and the expression of related cytokines IL-17 and IL-10 in peripheral blood. Results: 1. MRI examination was normal in 26 cases, 9 cases were reversible posterior encephalopathy syndrome, 3 cases were cerebral hemorrhage, and 1 case was intracranial cavernous sinus thrombosis. 2. Compared with the mild preeclampsia group, the relative number of Thl7 cells in peripheral blood increased and the relative number of Treg cells decreased in the severe preeclampsia group (P> 0.05). Conclusion: The major types of cerebrovascular diseases in severe preeclampsia and eclampsia are reversible posterior encephalopathy syndrome and cerebral hemorrhage. It is speculated that the damage to the blood-brain barrier associated with endothelial cell injury may play an important role in the pathogenesis. Attach importance to early cranial MRI examinations in order to obtain the correct diagnosis and data plan. At the same time, the balance of the relative number of Th17 cells / the relative number of Treg cells in the peripheral blood of patients with preeclampsia is more inclined to the Th17 cell-mediated pro-inflammatory state, and Treg cell-mediated immune tolerance decreases, and it becomes more obvious with the worsening of the disease.

Prenatal diagnosis of fetal cleft lip and palate with three-dimensional ultrasound information technology
       XinglongDeng, SuhuiHe, QiumeiWu, ZongjieWeng, MinminYang, MinLiu1*, Oldenhof Sander
To evaluate the three-dimensional ultrasound paper cleft lip and palate deformities in applications in prenatal diagnosis. Methods: 25 cases of cleft lip and palate fetus our hospital prenatal ultrasound examination, 20-32 weeks gestational age, maternal age 22-44 years old, conventional two-dimensional ultrasound examination after a cleft lip, the application of three-dimensional ultrasound imaging surface and a transparent imaging showed the fetus the alveolar process and palate. And the results of two-dimensional ultrasound and postnatal (or after induction) the results were compared. Results: 25 postpartum induction or found simply unilateral cleft lip 6 cases, 17 cases of unilateral cleft palate, bilateral cleft lip palate two cases. There was no significant (P> 0.05) difference of two and three-dimensional ultrasound detection rate pure cleft lip, cleft palate dimensional ultrasound detection rate of 36.8% (7/19), three-dimensional ultrasound cleft palate 89.5% detection rate (17/19). 2 methods were statistically significant (P <0.05) difference in the detection rate of cleft palate. Conclusion: Three-dimensional ultrasound can significantly improve the diagnostic accuracy of prenatal cleft palate

Application of Quantitative CT Imaging in Rehabilitation Nursing of Cerebral apoplexyPatients
       Bing Yan,Huanhuan Zhang, Jie Liu1*, Yamamoto Masaya
Electronic computed tomography (CT) is an important imaging method for the diagnosis of cerebral infarction. This paper explores the preventive effects of quantitative CT imaging and early rehabilitation nursing on patients with cerebral apoplexy and shoulder-hand syndrome. Methods: Sixty cerebral apoplexy patients treated from January to August 2016 were set as the control group and given routine care. Sixty cerebral apoplexy patients admitted from September 2016 to May 2017 were set as the observation group, and early rehabilitation nursing intervention was given based on the control group. The incidence of shoulder-hand syndrome and upper limb function were compared between the two groups. The effects of CT examination on improving the National Institutes of Health Cerebral apoplexy Scale (NIHSS) score and promoting the recovery of limb function were analyzed. Results: The incidence of shoulder-hand syndrome in the observation group after 3 months of intervention was lower than that in the control group, and the severity was less than that in the control group. <0.05); The Ashworth score of muscle tension in the observation group after 3 months of intervention was lower than that in the control group, and the simplified FMA score of the upper limbs was higher than that in the control group. Conclusion: Early rehabilitation nursing intervention after CT examination can prevent the occurrence of cerebral apoplexy and shoulder-hand syndrome and improve upper limb function, which is worthy of promotion

Value of Spiral CT Multi-parameter Combined Preoperative Evaluation of Microvascular Invasion in Small Liver Cancer
       Kun Li, Yongjun Peng, Hongzhe Tian, Hailin He*, Asami Rei
To explore the value of multi-slice spiral CT (MSCT) in predicting microvascular invasion in hepatocellular carcinoma (HCC). Methods: The CT and clinical data of 102 patients with HCC were collected in this paper. They were divided into two groups based on the pathological results with or without microvascular invasion. The independent sample t test was used to compare the age, alpha-fetoprotein (AFP) value, tumor size, and tumor enhancement of the two groups. CT value; χ2 test was used to compare gender, hepatitis type, liver function classification, degree of classification, degree of tumor smoothness, envelope, peripheral enhancement, etc. between the two groups. Results: There were 52 cases of non-microvascular invasion and 50 cases of microvascular invasion. The tumor size, grade, degree of margin, capsule, portal vein CT value, and peripheral enhancement were related to microvascular invasion. Conclusion: Microvascular invasion of HCC can be predicted by MSCT manifestations before surgery.

Low Intensity Pulsed Ultrasound Information Technology Intervention in Diagnosis andPrediction of Muscle Atrophy
       Zhijun Sun,*, Staehlke Susanne
Through the information technology intervention in diagnosis and the prediction of muscle atrophy, the effects and function of low-intensity pulse ultrasound on muscle atrophy are discussed and analyzed from various aspects. Method: the subjects are were divided into three different groups: control group, model group and weight-bearing exercise group. The mice are treated with low-intensity pulsed ultrasound, and are divided into low-intensity pulsed ultrasound intervention group and low-intensity pulsed ultrasound combined with weight-bearing exercise group. Then, according to different groups, different treatment methods are taken. Finally, the changes of body weight, grasping power, biochemical indexes and glycogen content of gastrocnemius muscle are analyzed and recorded to explore the effect and value of low-intensity pulsed ultrasound information technology intervention combined with intermittent weight-bearing exercise in the treatment of muscle atrophy Results: After weight-bearing running, the body weight of model (OVX) group, exercise (EX) group significance (P < 0.01). It is found that the weight of EX group is the largest and OVX group is the lightest. There is control group (P < 0.05). After low-intensity pulse ultrasound treatment, it is found that the weight of OVX group, EX group(P < 0.01). Conclusion: Low intensity pulsed ultrasound information technology intervention has a good effect on improving muscle atrophy, so as to effectively improve the weight of gastrocnemius muscle. The combined application of the two is better for the improvement of muscular atrophy.

Research on IMRT Images Based on Swarm Intelligence Algorithm in the Treatment of Nasopharyngeal Carcinoma and Pain
       Xiaoli Fu, Minxiang Li*, Mantian Yin, Qing Li, Ying Chen, Mondal Partha, Tanaka Ryoichi
To investigate the paper IMRT (IMRT) treatment of nasopharyngeal carcinoma term effect, toxicity and technical features. Methods: sliding windows dynamic CT image guided IMRT techniques on 31 patients for treatment of nasopharyngeal carcinoma radical radiotherapy, 30 to 33 min irradiation. Target prescription dose GTVnx, GTVnd, CTV1, CTV2 were 70 ~ 76Gy, 68 ~ 70Gy, 60 ~ 66Gy and 54Gy, while giving a dose of vital organs, the brain stem, and other restrictions to protect the parotid gland. Results: 3 to 18 months of follow-up for a median period of 10 months, 1-year locoregional patients’ progression free survival, distant metastasis-free survival and overall survival rates were 93.5%, 87.1% and 93.5%, respectively. Acute radiation reactions of grade Ⅰ and Ⅱ, xerostomia and radioactive stomatitis was not observed Ⅳ Acute reaction. IMRT DVH analysis showed increased total dose and the irradiation target volume divided doses, reduces OARs illuminated and the total dose divided doses.Conclusion: Intensity-modulated radiation therapy can achieve good short-term effects, significantly reduce the acute radiation response, and improve the quality of life of patients. It is worthy of promotion and application and in-depth research

The Value of Radiography Information Technology in the Treatment of Breast Cancer
       Shuang Liu, Feng Wei, Shuqin Ruan, Jiaxi Lu, Min Tang*, Kolinski Michal
The application of radiography information technologyto provide technical support. Method: The subjects in4 samples: preoperative radiotherapy sample (a), postoperative radiotherapy sample (b), preoperative and postoperative radiotherapy sample (c), untreated control sample. Group a receive 4.5Gy local radiation three days before operation, group B receive 4.5Gy local radiation two weeks after operation, group C receive 2.25Gy local radiation three days before operation and two weeks after operation. After the operation, the volume of hind limbs is measured by drainage method. At 24 weeks postoperatively, contrast media are injected into the hind limbs to show the distribution of lymphatics, and the images are processed by image filtering algorithm. Results: In group C, lymphedema is the most obvious, stable and lasting, and the mortality and complication rate are low. Lymphangiography show that the density of superficial lymphatics increases in sample A and B, but few lymphatics regenerate in sample C. The results of immune group show that the number of lymphatics in group C is less than that in group A and B (P < 0.05). Conclusion: the application of radiography information technology has a high value the accuracy

Construction and application of color fundus image segmentation algorithm based on multi-scale local combined global enhancement
       Yanjie Hao,Hongbo Xie, Rong Qiu*, Watanabe Mika
Aiming at the problem of low accuracy in extracting small blood vessels from existing retinal blood vessel images, a retinal blood vessel segmentation method based on a combination of a multi-scale linear detector and local and global enhancement is proposed. The multi-scale line detector is studied, and it is divided into two parts: small scale and large scale. The small scale is used to detect the locally enhanced image and the large scale is used to detect the globally enhanced image. Fusion the response functions at different scales to get the final retinal vascular structure. Experiments on two databases STARE and DRIVE, the results show that the average vascular accuracy rates obtained by the algorithm reach 96.62% and 96.45%, and the average true positive rates reach 75.52% and 83.07%, respectively. The segmentation accuracy is high, and better blood vessel segmentation results can be obtained

Exploring the NT-proBNP Expression in Premature Infants with PDA by Echocardiography
       Yunlong Shi,Jianwei Ji*,Chunying Wang, Trotier Fabienne, Filipek Slawomir
To investigate the correlation between echocardiographic indicators and the expression level of amino terminal brain natriuretic peptide precursor (NT-proBNP) in premature infants (PIs)with patent ductus arteriosus (PDA) and the value of NT-proBNP in diagnosing symptomatic PDA (sPDA) in PIs whose gestational age (GA)was less than 32 weeks. Methods: PIs, born in our Hospital from February 2019 to March 2020, at [28,32] weeks of GA, weighted ≤ 1500 g, and diagnosis of PDA within 48 hours after birth were selected as the research objects. NinetyPIs were selected, including 52 in the non-PDA group and 38 in the PDA group, of which 26 were symptomatic PDA (sPDA) and 12 were asymptomatic PDA (asPDA). The general information of these infants was recorded, including gender, delivery method, maternal infection, and serum NT-proBNP level on the 3rd day after birth. The PDA group and non-PDA group were screened by echocardiographic indicators based on an artificial intelligence convolutional neural network (AI-CNN). The PDA group was subdivided into the asPDA group and the sPDA group. The serum NT-proBNP levels of the two groups at the same age were compared. The Receiver Operating Characteristic (ROC) curves were illustrated to decide the serum NT-proBNP expression levels, thereby determining the specificity and sensitivity of sPDA and the correlation between serum sPDA NT-proBNP expression and echocardiographic indicators. Results:The expression level of serum NT-proBNP in the sPDA group was greater than that in the asPDA group and the non-PDA group, with statistical significance (P < 0.001). In the sPDA group, the area under the curve (AUC) of ROC was 0.973 (95% CI: 0878 ~ 1.000, P < 0.001), the critical value was 5821.4 pg/mL, the specificity was 95.2%, and the sensitivity was 89.7%. The serum NT-proBNP expression level was positively correlated with the diameter of the ductus arteriosus in the sPDA group (r = 0.462, P < 0.001); it was also positively correlated with the ratio of left atrium/aorta (LA/AO) (r = 0.573, P < 0.001), but was not correlated with left ventricular ejection fraction (LVEF) (r = -0.015, P = 0.747). Conclusion: The combination of serum NT-proBNP expression and echocardiography had clinical values in early diagnosis of PDA

Diagnosis and analysis of primary central nervous system lymphoma based on MRI segmentation algorithm
       Guanping Lu, Ying Li, XinqiangLiang, Zhengjun Zhao*, Samuel Raymond, Shishido Atsumasa
This paper summarizes the MRI imaging findings of primary central nervous system lymphoma (PCNSL) in the posterior cranial fossa to improve the accuracy of PCNSL diagnosis in the posterior cranial fossa. Methods: The paper retrospectively analyzed the MRI imaging manifestations of 15 PCNSL posterior cranial fossa cases confirmed by puncture or surgical pathology, including their occurrence sites, the number of lesions, MRI plain and enhanced manifestations, and diffusion-weighted imaging (DWI) and magnetic resonance spectroscopy. Imaging (MRS) performance. Results: A total of 15 cases were enrolled, including 10 cases of single cases and 5 cases of multiple cases. The total number of lesions was 25, which were in the cerebellar hemisphere and cerebellar vermis, midbrain, fourth ventricle, and pontine cerebellum. The lesions were round, irregular, nodular, patchy, with low or medium signals on T1WI, equal or slightly higher signals on T2WI, and enhanced with 25 meningiomas-like gray matter signals. All of them were significantly strengthened. "Acupoint sign" and "umbilical depression sign" were seen in 8 lesions. There were 17 massive and nodular enhancements, 4 striped enhancements, 3 patchy enhancements, and 1 circular enhancement. 5 cases of DWI showed homogeneous high signal, 2 cases showed uneven high signal, and 3 cases showed medium signal. The ADC value of tumor parenchyma in 10 patients was (0.62 ± 0.095) × 10-3mm2 / s. MRS examination showed obvious Lip peak in 2 cases. Conclusion: PCNSL in posterior cranial fossa has certain characteristics. DWI, ADC value and MRS are helpful to improve the correct diagnosis rate of PCNSL

Application of Ultrasound Molecular Imaging Based on Compressed Sensing Reconstruction Algorithm to Phase Change Drug-loaded PLGA Nanoparticles Targeting Breast Cancer MCF-7 Cells
       YufengYou*,WusongCheng, HongboChen, Hyslop Stephen
To study the ability of aptamer-modified nano-gold rods and liquid carbon-targeted PLGA nanoparticles to target in vitro using compressed sensing reconstruction algorithm, and observe the phenomenon of mediating ultrasound / photoacoustic imaging. Methods: PLGA nanoparticles were prepared by a double emulsification method, and the MUC1 aptamer was connected to the PLGA nanoparticles by the carbodiimide method to obtain an "aptamer-PLGA nanoparticle" targeted phase change contrast agent. Fluorescence microscopy was used to detect the in vitro targeting of breast cancer MCF-7 cells specifically identified by it, and three control groups were set up: the ordinary nanoparticle group, the aptamer interference group, and the HELA cell group. A photoacoustic instrument was used to observe the phenomenon of enhanced ultrasound / photoacoustic signal mediated in vitro. Results: Many targeted nanoparticles were clustered around MCF-7 cells and bound firmly, but no specific binding was observed in the non-targeted nanoparticles group, the aptamer interference group and the HELA cell group. After the targeted nanoparticle was excited by the photoacoustic instrument, the ultrasonic signal and the photoacoustic signal were significantly enhanced compared with before the excitation. Conclusion: The successfully prepared targeting nanoparticles have good targeting and specificity for breast cancer MCF-7 cells, and it has obvious effects on ultrasound / photoacoustic imaging, and has the potential to become a dual-mode ultrasound / photoacoustic targeted contrast agent The various characteristics provide experimental basis for subsequent in vivo targeting experiments and are expected to become good target diagnostic molecular probes.

Study on Active Rehabilitation Method for Patients with Acute Cerebral Infarction Based on MRI Image Analysis Based on Optimized CSMRI Algorithm
       Chao Zeng, Jing Chen, Wenbing Liu, Kang Liang, Hui Li, Jing Wang, Jingge Li, Haibo Xu*, Weiger Michael
The paper combines optimized CSMRI algorithm (CS) and magnetic resonance imaging (MRI) to shorten the scanning time of MRI image data and improve the imaging quality. At the same time, the paper applies functional magnetic resonance imaging (BOLD-fMRI) based on the principle of blood oxygen level dependence to explore the application value of the neurological functional reconstruction therapy system for the rehabilitation of active and passive motor function in patients with acute cerebral infarction. Methods: In this paper, 20 patients with acute cerebral infarction were collected. The random drawing method was divided into active group and passive group, each with 10 cases. Both groups were treated with conventional medication and acupuncture. The active group used the active mode of the neurological function reconstruction treatment system to guide the patients' limb Active exercise, all training in the passive group is performed by the nerve function reconstruction treatment system to passively exercise the patient's limbs, both groups undergo BOLD-fMRI examination before treatment and after 2 weeks of treatment, and observe the activated parts of the brain functional area and corresponding parts of the two groups before and after treatment Activate the volume, and at the same time score the ADL. Results: After treatment, the activation volume and ADL scores of brain functional areas in the two groups were significantly improved compared with those before treatment, and the difference was statistically significant (P <0.05). Conclusion: The combination of optimized CSMRI algorithm (CS) and magnetic resonance imaging (MRI) can be used to evaluate the early rehabilitation efficacy of patients with acute cerebral infarction, and has certain guiding value for clinical treatment

Application of MRI Images Based on Spatial Fuzzy Clustering Algorithm Guided by Neuroendoscopy in the Treatment of Tumors in the Saddle Region
       Peng Zhang, Lingdang Zhang, Rui Zhao*, Lakshm Vinoth
The paper applies spatial fuzzy clustering algorithm to explore the role and value of neuroendoscopic assisted technology in the operation of tumors in the saddle region, and analyze the MRI image characteristics of tumors in the saddle region. Methods: The clinical data of 63 patients who underwent neuroendoscopic assisted microscopy to remove tumors in the saddle area from 2015 to 2017 (neuroendoscopy-assisted group) were collected, and 76 patients who occupied the saddle area by microscopic resection only from 2013 to 2015 (Simple microscope group) clinical data, by comparing the patient's tumor resection rate, postoperative complication rate and postoperative recurrence rate, to evaluate the surgical effect. Results: The total resection rates of the tumors in the neuroendoscopy-assisted group and the microscope-only group were 95.24% (60/63) and 80.26% (61/76), and the incidence of postoperative vasospasm was 3.17% (2/63) and 13.16% (10/76), the incidence of nerve injury was 0 (0/63) and 6.58% (5/76), the difference was statistically significant (P <0.05). There was no significant difference in the incidence of postoperative infection, cerebrospinal fluid leakage and postoperative recurrence rate between the two groups (P> 0.05). Conclusion: Neuroendoscopy-assisted microscopy-based removal of the saddle area occupying space based on spatial fuzzy clustering algorithm can increase the total tumor resection rate and reduce the incidence of complications.

Analysis of Risk Factors of Infection after Interventional Embolization of Liver Cancer by Abdominal CT and Computer Information Health Analysis Based on Iterative Reconstruction Algorithm
       Haojie Wang, Yingxing Guo,Zhenwu Lei,Haiming Yang,Cunkai Ma,Zihao Mo,Yanzhen Li*
Based on an iterative reconstruction algorithm and using abdominal CT method, this paper explores the health analysis of risk factors related to infectious complications after TACE intervention for primary liver cancer. Methods: The paper collected the data of 730 cases of liver cancer diagnosed by our hospital from January to December 2017 underwent TACE interventional therapy. Patients with liver cancer underwent enhanced hepatic arterial and venous phase before TACE. Using three-dimensional VR, MIP, MPR technology to reconstruct three-dimensional images of blood vessels, and compared with DSA images during interventional therapy, 21 factors that may be related to the occurrence of infectious complications after intervention, using iterative reconstruction algorithm for single factor analysis. Results: CTA can show the three-dimensional structure of celiac artery and its main branches, and it is more convenient to observe the included angle with abdominal aorta than DSA. CTA found 13 cases of hepatic artery variation, which is in full agreement with DSA. Of the 730 patients, 41 had infectious complications after intervention, and the incidence of infectious complications after intervention was 5.62%. Multivariate Logistic regression analysis showed that the combination of chronic bronchitis, low albumin levels, ascites, ectopic embolism, and simultaneous partial spleen embolism were independent risk factors for infectious complications after intervention (P <0.05). Conclusion: Spiral CT three-dimensional angiography can show the running, distribution and variation of blood vessels of liver cancer.

Randomized Controlled Study of Non-invasive High-frequency Shock Ventilation Based on Chest X-rayReconstruction Algorithm for Neonatal Respiratory Distress Syndrome
       Xu Sang, Zhen Zhang, Yumeng Wu, Wansheng Peng, Xin Chen*
To explore the use of non-invasive high-frequency oscillatory ventilation and CPAP ventilation mode in the treatment of neonatal respiratory distress syndrome, and to compare the treatment effect and the incidence of complications, and whether it can reduce the time to go to the hospital and the number of hospital stays. Methods: Seventy-four children with RDS treated in our hospital from January 2018 to December 2019 selected and divided into 36 noninvasive high-frequency groups (NHVV group) and noninvasive positive pressure ventilation group (NCPAP group Thirty-eight cases were compared with the changes in arterial blood gas, the occurrence of complications, and the time on the machine before and after the operation on 12, 24, 48, and 72 hours. Results: In the NHFV group, PO2, a / APO2, and SaO2 were higher than those in the NCPAP group at 12, 24, 48, and 72 h after the respiratory support was given, and the differences were statistically significant (all P <0.05). PaCO2 in the NHFV group was given respiratory support. After support, 12, 24, 48, and 72 h were lower than the NCPAP group, and the difference was statistically significant (both P <0.05). The children in both groups were cured and discharged from the hospital, with air leakage, persistent pulmonary hypertension, bronchopulmonary dysplasia, there were no statistically significant differences in the incidence of complications such as retinopathy, pulmonary hemorrhage, and intracranial hemorrhage (P> 0.05). The NHFV group had less tracheal intubation, operation time, and hospital stays than the NCPAP group. The differences were significant. Statistical significance (P <0.05). Conclusion: Non-invasive high-frequency ventilation is effective in the treatment of RDS, and compared with CPAP ventilation mode, it can reduce CO2 retention, increase oxygenation index, reduce time of operation and length of hospital stay in children with RDS. It is worthy of clinical promotion and application.

Application of X-ray Image Measurement in the Early Diagnosis of Sports Injury of Ankle Ligament
       Shuqiao Meng, Wenxia Tong*, Shanshan Han
To study the value of X-ray analysis method of ankle fracture based on injury mechanism to improve the imaging diagnosis level of ankle fracture. Methods: The thesis collected 105 cases of fractures caused by sprained ankle joints in our hospital from January 2016 to December 2019 with plain radiographs and CT scans, a total of 105 cases, aged 21-81 years, with an average of 49.5 years. The traditional X-ray analysis method (group A) and the injury mechanism-based ankle fracture X-ray analysis method (group B) were used to analyze X-ray image data. Group B also performed Weber classification and Lauge-Hansen classification on cases. Installment. Results: Of the 105 patients with ankle fractures, 97 patients in Group B were able to make Lauge-Hansen classification. Of these 97 ankle fractures, 137 were found in group A, and 158 were found in group B. The misdiagnosis rate of fracture in group A was 18%, and the misdiagnosis rate of fracture in group B was 0.5%. There was a statistically significant difference between the two groups (P <0.05). Conclusion: The X-ray analysis method of ankle fractures based on injury mechanism can effectively improve the detection rate of hidden ankle fractures and high fibular fractures, and reduce the missed diagnosis, which is superior to the traditional X-ray analysis methods. At the same time, Weber classification, Lauge-Hansen classification and staging can be made for most cases, which is conducive to guiding clinical treatment.

Analysis of the Therapeutic Effect of PKP Guided by CT Images Based on SEPB Algorithm in the Treatment of Elderly Osteoporotic Thoracolumbar Vertebral Compression Fractures
       Yanming He1, Shujun Zhang, Xueguang Liu, Dong Mao, Zhenzhong Sun*
The paper uses the SEPB algorithm to explore the value of X-ray and CT diagnosis in elderly patients with osteoporotic lumbar compressive fractures, while observing percutaneous kyphoplasty (PKP) in the treatment of elderly osteoporotic compression fractures Clinical efficacy. Methods: The paper was included in the study from March 2018 to March 2019. 38 elderly patients with fractured osteoporotic compression fractures who came to our hospital for treatment were included. All patients were diagnosed by X-ray and CT, the clinical data of all patients were analyzed, the imaging findings related to X-ray and CT diagnosis were clarified, and the diagnostic coincidence rate was analyzed. At the same time, PKP treatment was applied and clinical efficacy and Imaging analysis. Followed up for 2 months after operation. Results: Compared with the X-ray diagnosis, the accuracy of CT diagnosis was 88.89% (32/38), and the difference between the groups was significant (P <0.05). 35 cases of low back pain disappeared after operation, and 3 cases of pain were significantly reduced without bone cement leakage. Postoperative imaging examination showed no space occupied in the spinal canal, and kyphosis deformity was significantly improved. The average height of the anterior vertebral column after injury was significantly increased (P <, 0.05). The Cobb angle returned to normal level, which was statistically significant compared with that before the operation (P <0.05). Conclusion: In the diagnosis of elderly patients with osteoporotic lumbar compression fractures, the coincidence rate of CT diagnosis is better than that of X-ray diagnosis. Therefore, the application rate of CT diagnostic methods in diagnosis is higher, which provides an effective basis for clinical diagnosis and treatment. PKP surgery is less invasive, safe, and has good clinical efficacy. It can quickly relieve pain and effectively restore the height of injured vertebrae. It is an ideal treatment method for elderly osteoporotic thoracolumbar vertebral compression fractures.

Three-Dimensional Reconstruction of Cerebrovascular and Algorithm Realization
       Linfeng Li, Xiaojing Jia*
In the three-dimensional reconstruction of CT cerebrovascular medical image registration, a new optimization algorithm based on the relative position information between the contours of various blood vessels in the image is proposed. Methods: Using the rule that the center of gravity of the vascular tissue structure on the series of slices has continuity, find the registration relationship between the contours of the vessels in the two adjacent slices. Because the shape of cerebrovascular contour is relatively symmetrical, its center of gravity is slightly away from its geometric center. Therefore, the geometric center is used to replace the center of gravity, and the "mass" of each contour is calculated according to the area of each contour to achieve the registration of the blood vessel contour. Results: The method has the characteristics of global optimization and stronger robustness. Conclusion: The cerebrovascular image obtained by this method is more realistic, and can be used for the import of various software, simulation training and later research, which provides an effective method for preoperative simulation of cerebrovascular intervention surgery.

High Resolution QSM Magnetic Resonance Imaging Study on Visualization of Subthalamic Nucleus Before DBS
       Yuanqin Liu,Qinglu Zhang,Lingchong Liu,Cuiling Li,Rongwei Zhang,Guangcun Liu*
The purpose of this study was to explore the ability of pre-DBS magnetic resonance multi-sequence scans to display STN nuclei in Parkinson's (PD) patients, to compare studies and to select the best MRI scan sequence to visualize STN nuclei. Methods: We included 10 normal people and 10 PD patients, all of which were scanned by Siemens 1.5T magnetic resonance in Germany. The scanning sequence included T2-TSE, FLAIR, T1-MPRAGE, T2-SPACE, T2 * -FLASH 2D (tar, cor, sag), SWI, we conduct a semi-quantitative evaluation of each sequence of images, and the scoring standard adopts a 6-point scoring system. For the sequence with the best STN direct visualization effect, it needs to have a higher consistency with the postoperative electrode position of the patient. Statistical analysis of the score results. Results: The Kappa values of each sequence of T1-MPRAGE, FLAI Rtra, T2-TSE, T2 * -Flash 2D sag were all less than 0.4, indicating that the sequence identity was poor. Conclusion: Using T2 * -FLASH 2D, T2-SPACE and SWI imaging sequences can accurately target the target location, greatly shorten the preparation time before surgery, improve the objectivity of target prediction, and thus can make the number of microelectrode detection during surgery Reduce, further shorten the operation time and reduce the operation risk

Application of Multi-Slice Spiral CT Imaging Technology in the Diagnosis of Patients with Chest Sarcoidosis
       Hongfei Ma, Liang Chen*
To study the qualitative value of multi-slice spiral CT (MSCT) dynamic enhancement scanning for solitary nodules (SPN) of the chest. Methods: In this paper, 40 cases of chest nodules (including 25 cases of malignant nodules, 8 cases of inflammatory nodules, and 7 cases of benign nodules) were first scanned to determine the scope of nodules. At the two rates of 5ml / s and 3ml / s, CT dynamic enhancement scans were performed at the center of the nodule, and the CT values, peak enhancement (PH) and peak time (PT) before and after SPN enhancement were recorded. It is mainly strengthened, with 80% (20/25) of net added value between 20 and 60 Hu, and 20% (5/25)> 60Hu or <20Hu. The enhancement peak and peak time are (31.31 ± 10.62) Hu and 45s respectively. The time-density curve (T-DC) showed a slowly rising type; the inflammatory nodules were mainly severely strengthened, with a net increase of> 40Hu. Enhance the peak value (49.25 ± 12.44) Hu, the peak time is 80s and 140s. There is a characteristic of rising and falling and then rising in the curve. Conclusion: Multi-slice spiral CT dynamic enhancement scan reflects the dynamic characteristics of chest nodular blood flow, which can be used to noninvasively evaluate and diagnose SPN.

Application of Magnetic Resonance Diffusion Tensor Imaging in Persistent Plant State
       Ying Zhao, DongmeiLu, Ling Qi*
This paper explores the application of magnetic resonance diffusion tensor imaging (DTI) and its application in the continuous plant state, and evaluates its correlation with patient prognosis. Methods: Thirty-seven patients diagnosed with severe persistent vegetative state, 20 normal volunteers (control group) underwent DTI examination, and measured the partial anisotropy (FA) of 6 regions of interest (ROI) on both sides of the cerebral hemisphere,and construct a three-dimensional diffusion tensor fiber bundle imaging map of the above site. Compare the average FA value in the region of interest in the subacute phase and the control group, analyze the grade correlation between the FA value of the whole brain white matter and the GCS score, and compare the difference between the FA value in the chronic phase and the subacute phase and the GOS score at 6 months after injury Do regression analysis on the relationship between them. Results: DTI can clearly observe the distribution and shape of the white matter fiber bundles in the brain, and can visually display the damage of important structural fiber bundles, and observe whether they are damaged or even broken. The average FA value in the sub-acute phase of the persistent plant state group was 0.52 ± 0.06, which was significantly lower than the control group ’s 0.64 ± 0.10 (P <0.05). The level of FA was positively correlated with the GCS score (r = 0.666P <0.05). The smaller the change in FA value in the chronic and subacute phases of patients in the persistent plant state group, the lower the GOS score and the worse the prognosis (R2 = 0.597). Conclusion: Diffusion tensor fiber bundle imaging technology can visually display the position and degree of persistent plant status. The change of FA value reflects the change of water molecule anisotropy degree of white matter fiber bundle in patients with persistent vegetative state, which is of great significance for assessing injury and prognosis.

Diagnostic Value of Magnetic Resonance diffusivity kurtosis imaging in Monitoring Renal Ischemia-Reperfusion Injury
       Guocan Han,Weifeng Lin, WeiLin*
In order to explore the value of magnetic resonance diffusivity kurtosis imaging (DKI) technology in monitoring the occurrence and development of renalischemia / reperfusion injury(IRI). Eight subjects in the control group and 1h, 1d, 3d, 7d, 14d, and 28d after modeling were randomly selected. The subjects underwent magnetic resonance examination. Immediately after the scan, venous blood was collected, and kidney tissues were for pathological examinations. DDKI values, fa values, and MK values of the cortex, outer medulla and inner medulla were measured. The layer parameter values, laboratory examination results and pathological results were statistically analyzed. The results showed that in the model group, except for the 1d group, the renal blood muscle distribution and urea nitrogen in the other time groups were not statistically different from the control group; in the renal cortex, the value of the lh-7d group was statistically different from the control group. However, there was no statistical difference in the fa value between the control group and the model group. In the outer layer of the extramedullary kidney, except for the 14d group, the values of the other model groups were reduced compared with the control group (CP <0.05). The fa value was lower than that of the control group (CPG <0.05); in the inner layer of the extramedullary kidney, the DKI values of the 1h-28d group were statistically different from those of the control group (p <0.05). The control group was statistically different. MK value was not statistically significant in each layer compared with the control group. In conclusion, Magnetic resonance DKI imaging is of great value in monitoring the progress of renal ischemia-reperfusion injury and judging the degree of renal injury

Comparative Analysis of the Role of X-ray and CT Three-dimensional Reconstruction Imaging Technology in Fracture Classification and Stability Evaluation
       Panpan Feng,Liang Liang,Jinyan Yao,Peiming Sang, Liping Zhang,Xiaogang Xue1
To analyze the value of X-ray and spiral CT three-dimensional reconstruction technology in the diagnosis of Lauge-Hansen classification of ankle fractures. Methods: The paper selected 96 patients with ankle fractures admitted to our hospital from December 2016 to December 2017. All patients received X-ray and spiral CT three-dimensional reconstruction before surgery, and the results of intraoperative exploration and MRI were the gold standard. To compare and analyze the accuracy of X-ray and spiral CT three-dimensional reconstruction techniques for Lauge-Hansen classification of ankle fractures. Results: Intraoperative exploration and preoperative MRI diagnosis showed 45 cases of inferior tibiofibular injury. The correct rate of X-ray diagnosis of inferior tibiofibular injury was 62.22%, which was significantly lower than that of spiral CT 88.89% (P <0.05); spiral CT The sensitivity, specificity, accuracy and Kappa value of Lauge-Hansen classification are higher than X-ray. Conclusion: Compared with X-ray, spiral CT three-dimensional reconstruction technology has greater advantages and higher accuracy in the diagnosis of Lauge-Hansen classification of ankle fractures. X-ray can provide the basic classification basis for most ankle fractures. If the X-ray examination results are in doubt or the inferior tibiofibular joint injury, CT examination should be combined.

Human detection and motion recovery based on monocular vision
       Dongbo Liu
Human motion extraction based on monocular video, including restoration or reproduction of real human motion data in the video on an abstract human model.This will provide a wider range of realistic motion data and technology options for interactive games and human animation.Therefore, how to complete the position and attitude detection and motion recovery under monocular vision has become an important research direction.In view of the above problems, this paper improves the part-based human detection algorithm, and uses AdaBoost multi-instance learning algorithm to train the part detector.The blood pressure waveform measurement model was established by using the three-dimensional information of the pulse detected by the monocular visual pulse detection system. The linear relationship between the pulse signal and the blood pressure waveform was examined. A method for obtaining the blood pressure waveform based on the monocular vision pulse wave was proposed.The results show that the method of obtaining blood pressure waveform based on monocular vision pulse wave is feasible and has generalization.At the same time, this study also proposes a non-marked, non-initialized human motion recovery method based on monocular vision, including direct extraction of the human skeleton.The human skeleton model, the human appearance model, and the determination of the objective function were established to recover the 3D human motion information.By comparing the angle-time relationship curve of each joint's movement on the sagittal plane with normal gait, it can reflect the gait machine's evaluation of the joint training situation of the subject.The results show the feasibility and accuracy of the gait motion detection, motion recovery and analysis system for human lower limbs based on monocular vision.

Application of decision tree model based on C4.5 algorithm in nursing quality management evaluation
       Lei Ding, Xia Zeng*
In order to understand the application of decision tree model supported by C4.5 algorithm in nursing quality management evaluation. 40 nurses in a certain department of our hospital were selected as the research objects and divided into experimental group and control group, with 20 nurses in each group. All nurses were female and aged 19-41, including 1 nurse under 20 years old, 28 nurses between 20 and 30 years old, and 11 nurses over 30 years old. The control group chose the traditional nursing quality management method, and the experimental group used C4.5 algorithm for data mining to establish a decision tree model, and then collected the basic information of nursing staff, including the number, name, title and location of nursing staff, as well as the content of the basic information database. Then, the results of decision tree model analysis were taken as the guiding measures of nursing quality management, and the work quality scores of the two groups of nursing staff were studied by using the work ability evaluation scale developed by our hospital. The results were compared with those of the control group, at the same time, the scores of nursing staff in the experimental group on work ability were statistically significant (P<0.05), which indicates that the C4.5 algorithm and the decision tree model constructed have a very prominent effect on nursing quality management,which can provide reference for future work.

Based on the correlation between pathological reactivity and dynamic enhanced MRI after neoadjuvant chemotherapy in breast cancer
       Haiying Li, Ze Chen*, Yizhao Zhang
In order to analyze the correlation between pathological response and dynamic enhanced MRI (DCE-MRI) after neoadjuvant chemotherapy for breast cancer, the correlation between morphology and time signal intensity curve (TIC) type of DCE-MRI and pathological response was understood. A total of 50 breast cancer patients admitted to our hospital from January 2019 to December 2019 were selected as study subjects. All patients underwent neoadjuvant chemotherapy, and breast DCE-MRI was performed after neoadjuvant chemotherapy. Image workstation was used to observe and analyze the enhanced morphology and TIC type of residual tumor in patients, and the pathological reactivity of breast cancer chemotherapy surgical specimens was accurately assessed by specialist pathologists and graded. Grade 5 was complete pathological recovery and grade 4 was histological significant recovery. Finally, the correlation between the pathological grading of DCE-MRI and residual TIC enhancement was analyzed. The results showed that the pathological grade was 5, that is, 10 cases were cured, accounting for 20%. Pathology grade 4 was 38.0%, pathology grade 3 was 14, accounting for 28.0%, and pathology grade 1/2 was 7, accounting for 14.0%. In addition, the quality of the residual lesions, quality improved form in the activity of different pathological clear distribution level, suggest that we can clear the histologic response and to strengthen the close relationship between the tumor residues, was close to histology aspect, has the rich fibrous scar, no obvious tumor cells, but the surrounding nodular tumor cells is more intense. It can be seen that the assessment of pathological reactivity by MRI can be used as a reference to assess the distribution range of residual lesions, suggesting the correlation between non-mass residual enhancement, mass participation in enhancement and TIC histological response, providing more valuable information for diagnosis. In summary, the morphological and hemodynamic characteristics of DCE-MRI after neoadjuvant chemotherapy for breast cancer are closely related to the pathological response of patients after chemotherapy, and can be effectively determined by the significant histological response.

Cognition based spam mail text analysis using combined approach of deep neural network classifier and random forest
       S. Sumathi , Ganesh Kumar Pugalendhi
Email Spam is a variety of automated spam where unbidden messages, used for business purpose, sent extensively to multiple mailing lists, individuals or newsgroups. To build a fruitful system for spam detection, we introduced Random Forest integrated with Deep Neural network to find the classification accuracy. The Random Forest algorithm uses a preordained probability of attributes in constructing their decision trees. The Gini measure is examined to rank the important features. The main objective is to grade the features using RF algorithm and to train the data using Deep Neural Network Classifier. Deep Neural Network Classifier model (DNNs) are trained using backpropagation algorithm in batch learning mode, which requires the entire training data to learn at once. The detector process was dynamically fit to the new data patterns till it reaches the spam coverage. Experimental results shows that classification rate of DNN is higher than compared to KNN and Support Vector Machine(SVM) with an accuracy of 88.59% while considering the top ranked five features.

E Health Care Data Privacy Preserving Efficient File Retrieval from the Cloud Service Provider using Attribute Based File Encryption
       N. Deepa , P. Pandiaraja
File storing and retrieving is performed in the robust as well as secure manner by using the cloud computing technology. Various researchers have developed numerous mechanisms via attribute based encryption for the health care applications. Although, more protocols developed among them only very few techniques were efficient and robust for the quick retrieval of reports from the cloud but many protocols suffer by reason of less security, confidentiality and integrity. Existing techniques was based on encrypting the file based on the keyword. But in our proposed protocol, we have developed an attribute based encryption which will overcome the issues faced by the previous research techniques. The group of patient records are encrypted with single common attribute. From the survey, it is clear that the existing protocols suffer due to high computation and communication complexity. So as to rectify the existing issue, we proposed the effective recovery of files by using attribute based file encryption mechanism from cloud (ERFC). When comparing to the existing protocols, our proposed ERFC mechanism takes minimum computation and communication complexity for four working mechanisms namely, patient key computation, doctor index building computation, cloud working mechanism and finally patient report decryption. All these four working mechanisms are developed for effective recovery of files to the end users. Our proposed protocol is secure against some attacks like Eavesdropping, masquerade, replay and man in the middle attack. Our performance analysis section describes that our ERFC mechanism is better with communication as well as computation complexity when related to the other existing protocols.

SECURE STORAGE ALLOCATION SCHEME USING FUZZY BASEDHEURISTIC ALGORITHM FOR CLOUD
       M. Sivaram¹, M. Kaliappan², S. Jeya Shobana³, M. Viju Prakash³, V. Porkodi⁴, K. Vijayalakshmi², S. Vimal⁵, A. Suresh⁶
Cloud computing is a paradigm in the modern era for the development of secure storage and secure job scheduling process in a cloud-based system. The cloud technology provides a user interface in the sense of raw data management with the relational databases to improve flexibility and scalability. Fuzzy-based Heuristic algorithm is proposed for secure storage allocation in a cloud environment. In this work, client systems are clustered using a fuzzy-based rule mechanism. The server generates a distributed public key using RSA for ensuring security and resolve memory recycling issues. It enhances the usage of the client over the cloud data storage in secure manner. It also improves the efficiency of data storage globally by implementing heuristic techniques. The K-nearest neighbors approach is used for efficient query searching for data storage in the clusters by the client. The proposed load-balanced scheduling approach enhances power consumption and efficiency. In the simulation, the results reveal that the proposed scheme provides better performance than existing approaches in terms of load balancing with security.

Time Series Real Time Naive Bayes Electrocardiogram Signal Classification for Efficient Disease Prediction Using Fuzzy Rules
       S. T. Aarthy & J. L. Mazher Iqbal
Towards the problem of ECG classification and disease prediction, various approaches are analyzed and discussed. However, the methods suffer to achieve higher performance in classification or disease prediction. To improve the performance, an efficient time series real time Naive Bayes ECG classification and disease prediction approach using fuzzy rule is presented in this paper. The method reads the ECG signals available and performs noise removal initially. From the graphs available, the features mentioned above are extracted and if there exist any incomplete or missing signal then the ECG sample has been removed from the data set. Once the preprocessing and feature extraction are done, then the features extracted. With the learned features, the method generates fuzzy rule for different disease class. The proposed algorithm computes posterior probability according to the mapping of different features of fuzzy rule. The classification or disease prediction is performed by measuring multi-feature signal similarity (MFSS). Estimated MFFS value has been used to measure the cardiac disease prone weight (CDPW) towards various classes available. According to the value of CDPW has been used to perform classification or disease prediction.

Detection of Distributed Denial of Service Using Deep Learning Neural Network
       S.Sumathi*, N. Karthikeyan
The need for developing a neural network classifier in an intrusion detection system for network security purpose is a necessary. Today, worldwide various types of sophisticated attacks damage the network in both wire and wireless. The medium of wireless network is air used to transmit the data where several categories of attacks damage the network system. Among the attacks, Denial-of-Service (DoS) attack is easily access the network but it is very difficult to prevent from the network. Therefore, the protection of various resources in the network is a challenging one and the detection of DoS attack process is an important issue in the network. For this purpose, it requires high-performed machine learning classifier with less computational time, reduced false positive and high detection accuracy. This paper evaluates the network performance using deep learning neural network classifier through publicly available dataset. The performance of deep learning neural network classifier performance is increased using cost minimization strategy. The proposed approach utilizes the KDD Cup, DARPA 1999, DARPA 2000, and CONFICKER datasets. The performance metrics such as detection accuracy, cost per sample, average delay, packet loss, overhead, packet delivery ratio and throughput are used for the performance analysis. From the simulation result observed that DNN Cost minimization algorithm provides better result in terms of high detection accuracy 99% with less false reduction, high average delay, less packet loss, less overhead, high in packet delivery ratio and throughput is high compared to existing algorithm.

An Automated Neural Network Based Technique for Identifying Fundus Hemorrhage (NNTFH)
       R. Karthiyayini1 , S. Geetha1
Retina, the thin membranous tissue layer occupying the back of human eyes, provides vision to humans. As the age of a person increases the eyes may encounter a secondary growth, creating impairments in vision. Human eyes are prone to several diseases like retinal detachment or tear, glaucoma, macular degeneration or hole, diabetic retinopathy etc., where identifying retinal diseases at an early stage is necessary. The increasing number of eyeafected patients and efective diagnosis imposes a challenge on the clinical routines of treatment and monitoring after diagnosis. It is possible to diagnose eye diseases from retinal images with the help of machine learning techniques. This paper proposes a novel technique called NNTFH which is an automated neural network based technique for identifying hemorrhage of the eyes from Eye images. The initial phase of NNTFH, selects the pixel count and density from medical eye images and then classifes impaired eyes where it uses a neural network model. The retinal images are classifed as normal or with exudates or eyes with Hemorrhage.

Invariant packet feature with network conditions for efficient low rate attack detection in multimedia networks for improved QoS
       M. Suchithra , M. Baskar , J. Ramkumar , P. Kalyanasundaram , B. Amutha
The problem of low rate attack detection has been well studied in diferent situations. However the methods sufer to achieve higher performance in low rate attack detection. The multimedia transmission is focused on transmitting video and audio which claims higher bandwidth conditions. There exists no such algorithm in detecting low rate attacks for invariant network conditions. To solve this issue, an invariant feature based approach is presented in this paper. The method maintains the network features like the routes, bandwidth conditions and trafc. Based on these features, a set of routes has been identifed for each data transmission. Here, low rate attack detection is performed at the reception of any packet and the data transmission is performed using cooperative routing. From the packet features, and the route being followed, the method identifes the class of route, trafc and bandwidth conditions of the route. Using these features, the method computes Network Transmission Support measure. Based on the NTS value, the method performs low rate attack detection and improves the performance.

Multisensor Data Fusion Technique for Energy Conservation in the Wireless Sensor Network Application “Condition-based Environment Monitoring”
       ¹A. Reyana, ²Dr. P. Vijayalakshmi
Due to the nature of the continuous and large volume of data transmission, energy conservation appears particularly tedious at WSN. This exhausts the energy faster, leading to failure of the sensor network. With the increase in the number of applications, there is high complexity in data transmission and more extensive accuracy requirements over the last few years, extended use of sensors challenges on the increase in sensors battery life-time too. In leveraging the display and control of the sensor operation, the multisensor data fusion technique plays a vital role. In the Condition-based Environment Monitoring System application, the proposed ADKF-DT-MF for the multisensor data fusion is implemented to detect natural and human disturbances to provide accurate and rapid environmental awareness. This paper describes the energy conservation module of the proposed system in concern to accuracy, processing efficiency, energy consumption, and the overall network operational life-time. The simulation results show a better accuracy of 97% with an energy consumption of 0.95 compared with the existing FIM, VWFFA, and Fuzzy algorithms. Keywords - Multisensor, Data Fusion, Environmental Awareness, Data Transmission, Energy Efficiency

Multi-Parameter Optimization for Load Balancing with Effective Task Scheduling and Resource Sharing
       N. Malarvizhi, J. Aswini, S. Sasikala, M. Hemanth Chakravarthy, E. A. Neeba
Cloud Computing is turning into an undeniably appreciated worldview that conveys superior figuring assets over the Internet to take care of the complex logical issues, yet at the same time, it has different moves that should be routed to execute logical work processes. The current research primarily centered around limiting completing time (makespan) or minimization of expense while meeting the nature of organization prerequisites. Be that as it may, a large portion of them do not think about fundamental normal for cloud and serious issues, for example, virtual machines (VMs) execution variety and procurement delay. Task scheduling for load balancing is one of the basic systems in the distributed computing condition. It is required for dispensing undertakings to be the best possible assets and streamlining the general framework execution. In recent research, the most popular scheduling algorithms named Particle Swarm Optimization (PSO) algorithm is utilized to maximize resource utilization. In any case, the PSO scheduling algorithm performance gets degraded when the task number is critical. In this paper, we propose a meta-heuristic practical, Multi-Objective Scheduling based Particle Swarm Optimization (MOSPSO) that limits the execution cost of the work process while complying with the time constraint in cloud computing condition. Multi-Objective Scheduling based on Particle Swarm Optimization (MOSPSO) is proposed under this research to give optimal allocation for a large number of tasks. This is accomplished by part of the submitted tasks into groups in a dynamic manner. The assets use state is considered in every creation for groups. In the wake of getting an imperfect answer for each group, the proposed method annexes all the problematic answers for clumps into the last assignment map. At last, MOSPSO attempts to adjust the loads over the last assignment map. The proposed calculation is contrasted and distinctive booking calculations in particular Particle Swarm Optimization (PSO) and Improved Particle Swarm Optimization (IPSO). The results of analyses demonstrate the effectiveness of the proposed algorithm as in terms of makespan, degree of load balance, and total execution time. Key terms: Task scheduling, Load balancing, Multi-Objective Scheduling Method, Particle Swarm Optimization (PSO), Multi-Objective Scheduling based Particle Swarm Optimization (MOSPSO)

Analyzing Uncertainty in Cardiotocogram Data for the Prediction of Fetal Risks based on Machine Learning Techniques using Rough Set
       E. Kannan Professor, S. Ravikumar, A.Anitha, Sathish A.P. Kumar, M. Vijayasarathy
The key focus of this venture is to evaluate the calibration of classifiers built on rules, trees, and functions by exploring the uncertain information that exists in the Cardiotocography (CTG) dataset. Classification is imperative in diagnosing the health of the foetus and newborn specifically in critical cases. It facilitates the obstetricians in acquiring the information of foetal well-being in pregnancy substantially for the woman with complications. The research aims to classify the CTG data points into normal, suspicious andpathologic. Rules, trees, and functions based classifiers are applied in machine learning for predicting the health of the newborn. Particle Swarm Optimization (PSO) is used in preprocessing for selecting the relevant features. Rough set approximations are exploited in extracting the uncertain information from the data set. The result reveals the importance of useful information present in the uncertain data during classification. In this paper, the overall highest accuracy is displayed by Random Forest classifier with 99.57% and a tree-basedapproach has shown its supremacy over other approaches. Keywords: Cardiotocography, Optimization, Feature Selection, Classification, Machine Learning, Rough Set, PSO.

Cloud Based Efficient Authentication for Mobile Payments using key distribution method
       A.Saranya¹ , R .Naresh^2*
The extensive usage of clever strategies fascinates numerous considerations on the innovation intended for mobile payment method in the background of cloud computing. Though, payment confidence and customer confidentiality still increase serious anxieties to the use of mobile payments. Subsequently, current authentication procedures for mobile payments moreover have high overhead on source inadequate smart scheme. These schemes cannot deliver customer secrecy in mobile payment. To resolve the tasks smartly we have present a Cloud Based Efficient Authentication for Mobile Payments using key distribution method. Based on the certificate less proxy re signature system, we have designed a different mobile payment procedure which not only attains secrecy; it also achieves the storage complexity by consuming fewer amounts of data. In our proposed method, the efficiency is particularly enhanced by retaining cost of computation in the Payment area. Furthermore, by seeing that the Payment area the Merchant Server wishes to achieve computation for every payment operation, the impression of batch authentication was implemented to remove the difficulties faced when more number of customers use the Payment area so that Merchant Server can solve the scalability dispute. By our security analysis discussed in this paper, the proposed method is verified to be safe by using the prolonged CDH issues. Furthermore, the performance results displays the proposed method is reasonable and quick for the source inadequate smart mobiles in cloud. Index Terms Privacy, authentication, certificate less cryptographic technique, mobile payments, cloud

Low Rate DDoS Mitigation using Real-time Multi Threshold Traffic Monitoring System
       ¹Dr. M. Baskar, ^2*Dr. J. Ramkumar, ³Dr. C. Karthikeyan, ⁴Dr. V. Anbarasu, ⁵Dr.Balaji A, ⁶Dr.Arulananth T S
The low rate distributed denial of service (DDoS) attack has been identified as most vulnerable to the network services which has been studied recently. The approaches consider only the high rate DoS attacks and ignore rest in low rate. The existing techniques suffer with poor detection of low rate attacks as they consider only limited features of network traffic. Variety of techniques mitigate such threats using different parameters like amount of data in service packet as payload, number of intermediate nodes, and so on. The previous techniques struggle to detect and mitigate them in efficient way. Towards improving the detection and mitigation performance of low rate threats, the author presents a novel real time traffic monitoring algorithm which uses multi threshold traffic analysis. By considering the payload, hop count, latency, packet counts, the method analyzes the real time traffic. Using the features obtained from the traffic, the method computes the low rate threat measure. Based on computed threat measure, the packets trustworthy have been validated. The method produces higher detection rate in low rate DDoS attack detection and produces efficient results. Keywords: Network Services, DDoS Attack, Low Rate Attack, Traffic Monitoring, Multi Threshold Analysis

Fractional-atom search algorithm-based Deep Recurrent Neural Network for cancer classification
       ¹D.Menaga, ²Dr.S. Revathi
Deep learning has been paid great attention in several fields for the good reason, and their results achieved were not before possible. In deep learning, the models are trained based on huge labelled dataset and the neural network architectures consist of several layers. Still, the methods suffer to achieve expected higher performance and introduce poor classification accuracy. Towards improving the classification performance, this paper introduces the deep learning networks for the cancer classification application. The main aim is to develop the optimized model for classification application. Accordingly, the input data is pre-processed using Log transformation for converting the data to its uniform value range. Then, the feature selection is done based on Wrapper approach to select the important features for classifying the cancer. Once the features are selected, the cancer classification is performed using Deep Recurrent Neural Network (Deep RNN), which is trained by the proposed Fractional-Atom Search Algorithm (Fractional-ASO). The Fractional-ASO is designed by integrating Fractional Calculus with Atom Search Optimization (ASO). The performance of the Fractional-ASO -based Deep RNN is evaluated in terms of accuracy, True Positive Rate (TPR) and True Negative Rate (TNR). The proposed Fractional-ASO -based Deep RNN method achieves the maximal accuracy of 92.87%, maximal TPR of 92.87%, and the maximal TNR of 93.48% using colon dataset. Keywords: Deep learning, Cancer classification, Atom Search Optimization Wrapper approach, Fractional Calculus.

An Efficient Partitioning and Placement based Fault TSV detection in 3D-IC Using Deep Learning Approach
       Radeep Krishna Radhakrishnan Nair¹ , Sivakumar Pothiraj^*2, T R Radhakrishnan Nair ³ , Korhan Cengiz⁴
Over topical eras, three dimensional Integrated Circuit (3D-IC) fabrications have become vital among the researchers and industrial people, owing to its wide range of amenities including smaller intersect lengths, advanced incorporation density, and enhanced performance. Still, fault Through Silicon Via (TSV) detection is a bottleneck, due to poor fabrication processes such as partitioning and placement. Besides, state of the art works have concentrated on redundant TSV allocation instead of detected fault TSV and hence, the area overhead and size of the circuit are increased. To resolve these shortcomings, this paper proposes an Efficient Partitioning and Placement based Fault TSV detection in 3D-IC. The proposed work comprises five processes: Quick cut oriented Partitioning, Multi-Objective based Placement, Deep learning based Fault TSV detection, Re-routing and Adaptive TDMA time slot. Initially, Quick Cut (QC) algorithm has been employed to partition the 3D-IC and it is easier for placement process. The placement is executed through Multi-Objective Brain Storm Optimization (MO-BSO) algorithm that selects the optimal place to position the cells in 3D-IC.The fault TSV in the 3D-IC is detected using the Adam Deep Neural Network (ADNN) algorithm. Further, Adam optimizer has been used to estimate weight for each input and it provides fast performance and better convergence rate compared to the traditional stochastic gradient algorithm. After obtaining the fault TSV, rerouting is performed to reroute the signals transmitted over the defected TSV to the nearby defect free TSV. The Adaptive Time Division Multiple Access (TDMA) algorithm has been used to provide time slot to TSV positioned in each partition. The proposed method has been implemented in MATLABR2017b tool. The results attained from the simulations are propitious in terms of the metrics such as Area, Wirelength, Delay, Run time and Temperature. Index Terms- Three Dimensional Integrated Circuit, Quick Cut, Placement, Fault Through Silicon Via, Re-routing, Adaptive Time slot.

Deep Learning based Genome analysis and NGS-RNA LL identification with a novel hybrid model
       Madhumitha Ramamurthy ^*1, Ilango Krishnamurthi², S.Vimal³, Y. Harold Robinson⁴
The conventional image segmentation techniques have a lot of issues with highest computational cost and low level accuracy for medical image diagnosis and genome analysis. The deep learning based optimization models utilize to predict the liver cancer with RNA genome using CT images and the prediction of genome classification with NGS is a higher probable in recent medical disease classification . This paper proposes a hybrid deep learning technique constructs with SegNet, MultiResUNet, and Krill Herd optimization (KHO) algorithm to perform the extraction of the liver lesions and RNA sequencing that the optimization techniques used into the deep learning method. The proposed technique implements the SegNet for segregating the liver with genome from the CT scan; the MultiResUNet is constructed to perform the extractions of liver lesions. The KHO algorithm is combined with the deep learning approaches for tuning the hyper parameters to every Convolutional neural network model and enhances the segmentation process which may elaborately identifies the sequence that causes the liver classification disease. The proposed technique is compared with the related techniques on liver lesion classification(LL) for NGS in genome. The performance results show that the proposed technique is better to other algorithms on various performance metrics. Manuscript File Click here to view linked References Keywords:SegNet, MultiResUNet, Krill Herd optimization, Genome Sequencing, NGS disease prediction, Convolutional neural network,

Spatio-temporal variation in physio-chemical parameters over a 20-year period, potential future strategies for management: a case study of Dal Lake, NW Himalaya India
       Ishtiyaq Ahmad Rather^1*, Abdul Qayoom Dar²
Analysis of physio chemical parameters (pH, TDS, DO, COD, Ca2+, Na+ ,Mg2+ , K + , SO42- , HCO3 - , Cl- , NO3 -N and TP) were carried out at thirty-eight (38) sampling sites during pre and postmonsoon seasons from 2016 to 2019.Results show TP varied from (0.3-1.6mg/l with an average value of 0.9 mg/l), NO3 -N varied from (0.2-1.5mg/l with an average value of 0.7mg/l) and COD varied from (11-98mg/lwithan average value of 47.80mg/l)and were compared with previous results of 1997 and 2007 to determine the decadal changes and impact of anthropogenic activities. Comparative results showed that TP, NO3 -N, and COD had increased 2.3, 2.0, 1.75 times, respectively from 1997 to 2017 while the concentration of DO has decreased from the last two decades. The present experimental analysis indicates that Dal Lake is exposed to anthrourban intensification due to an increase in anthropogenic activities in the catchment area, affecting the overall hydrogeochemistry of lake water.Systemicinsitu pliability can prevail till exsitu lacustrine management fortifies euoecism. Certain remedial measures are provided to manage the lake and to conserve its natural quality if implemented properly. Keywords: Dal Lake, major ions, anthropogenic activities, decadal changes, GIS, builtup change, management, Spatio Temporal Variation, Physio chemical parameters.

Investigation of Maximum Observability of Standard Test Bus Systems with Phasor Measurement Units using Flower Pollination Algorithm
       R.Sudha^1*, D. Murali²
Novel and optimal PMU observability have been attained based on the Flower Pollination Algorithm (FPA). The prime objective is to select the optimal bus for placing the Phasor Measurement Units (PMU) to maximize the number of bus observance in the system. Many optimization techniques have been developed with an aim to optimize the PMUs required quantity with attaining full observability of the network. This paper proposes a new technique of Modified Flower Pollination Algorithm, which reduces the computation time and achieves greater accuracy. This approach also helps in achieving the maximum observability of Power system based on choosing the optimum buses to place the PMUs. The proposed algorithm would be best suited and offers highly accurate results when analyzing the system for maximum observability with the minimum number of allotted PMUs. The FPA algorithm is implemented on standard IEEE-14 bus, IEEE-30 bus and IEEE-118 bus system. The proposed FPA algorithm outperforms other evolutionary algorithms. It yields better overall performance than other algorithm methods, in terms of the minimum number of PMUs with maximum observability, including contingency analysis. Keywords: PMU, Flower Pollination Algorithm, Metaheuristic, maximum observability, optimization.

Retinal Image Analysis for Ocular disease Prediction using Rule mining algorithms
       Dr. R. Karthiyayini¹ , Dr. N. Shenbagavadivu²
Medical image processing is now gaining a significant momentum in clinical situation to undertake diagnosis of different anatomical defects. However with regard to eye diseases there is no such well-defined image processing technique in medical image analysis. The scope of this study is to automate computer analysis of ocular diseases related retinal images may ease the job of ophthalmologists to rule out the diseased condition. In this present work eye images are subjected for developing a reliable tool for processing the eye retinal fundus images. The primary objective is to effectively probe retinal image data for providing a holistic approach in automatic fundus disease detection and screening to help clinicians in addition with developed a reliable image processing technique combined with a rule based clustering method for automatic analysis of fundus images in a reduced time frame. More than 400 eye images available in online are examined. The images were preprocessed by grayscale conversion, retinal segmentation, ROI and crop ROI, image resizing and extraction in RGB channels. Then these images were segmented by NRR from RGB channels, centroids of rows and columns and NRR to binary image conversion. Then extraction of features like cup to disc area, Optic cup area, and NRR calculations prior to measuring ISNT. A unique algorithm named as EARMAM was introduced for the prediction of diseased image from healthy eye image pool is envisaged in this paper. The functional significance of the EARMAM algorithm was compared with other common classification algorithm of current practice such as SVM, Naïve Bayes, Random Forest and SMO. The results of confusion matrix have shown that there was 93% prediction accuracy which was higher than the predictive values of other algorithms. The above results are discussed with future improvement and application in clinical field. Keywords: Data mining, Association Rule Mining, clustering, FCM, Image processing.

A Novel SOSMC based SVPWM Control of Z-Source Inverter for AC Microgrid Applications
       A.Sangari^a, R.Umamaheswari^a, M.G Umamaheswari^b, LekshmiSree B^b
In this paper, analysis and control of Single stage Z-Source Inverter (ZSI) using Particle Swarm Optimization (PSO) tuned Proportional Integral (PI) based Space Vector Pulse Width Modulation (SVPWM) and Second Order Sliding Mode Control (SOSMC) based SVPWM for harmonic reduction and load voltage regulation are presented. To increase the reliability and to enhance the output voltage of ZSI, the Shoot-Through (ST) state is implemented. To decrease the number of sensors and to simplify the controller design, sixth order model of ZSI is transformed into second order model using Pade's approximation method. To analyse the steady state and transient response of the proposed system, the closed loop implementation is carried out using proposed control techniques. PSO tuned PI controller is utilized for outer voltage control to obtain the Shoot Through Duty Ratio (STDR). Inner current loop utilizes PSO tuned PI controller based SVPWM/SOSMC based SVPWM techniques. MATLAB/SIMULINK software tool is used to simulate the proposed system. From the simulation results, it is inferred that the SOSMC based SVPWM technique offers fast transient response, low % Total Harmonic Distortion (THD) and regulated output voltage when compared to PSO tuned PI based SVPWM control scheme. Hence, an experimental prototype model of 2 kW controlled by the SOSMC based SVPWM using Field Programmable Gate Array (FPGA) is constructed to validate the simulation results with the experimental results.

Low-Cost real-time Design and Implementation of Phasor Measurement Unit using Analog Discovery
       R.Sudha^a, D.Murali^b
The blackouts in the power grid are forced to premonitor the conditions of the grid. Phasor Measurement Units (PMU) have become highly inevitable in the Wide Area Measurement System (WAMS). Continuous measurement of current and voltage phasors has become more reliable owing to very high stability showcased by Non-recursive DFT algorithm. Design and Modelling of PMU are implemented both in software and hardware using NI LabVIEW Professional development system. The novelty in this paper is that the continuous monitoring and real-time implementation of portable Phasor Measurement Unit is achieved by using Analog Discovery 2 with modest design. The results are validated, and the proposed implementation is more cost effective than the conventional system.

Enhancing image processing architecture using deep learning for embedded vision systems
       R.Udendhran^a , M.Balamurugan^b, A.Suresh^c, R.Varatharajan^d
In recent years, the success and capabilities of embedded vision have showed up in embedded applications. The embedding of vision into electronic devices such as embedded medical applications is being driven by the availability of high-performance processors, integrating with deep learning algorithms, as well as advances in image processing technology. But, including image processing in embedded vision systems need huge amount of computational capabilities even to process a single image to detect an object and it’s extremely challenging to implement in embedded systems. Implementing deep learning algorithms and testing it on a task specific data set could provide enhanced results. In this paper, an approach for enhancing image processing architecture using deep learning for embedded vision systems is proposed and analyzed. Implementing deep learning algorithms and testing it on embedded vision yielded effective results.

Auto Encoder based Dimensionality reduction and classification using Convolutional Neural Networks for Hyperspectral Images
       Madhumitha Ramamurthy ^*1, Y. Harold Robinson², S.Vimal³, A.Suresh⁴
Hyperspectral images (HSI) are adjacent band images commonly used in remote sensing environment; the deep learning methodologies have the important feature for classification process. Additionally, the highest dimensionality of HSI enhances the computational complexity which affects the overall performance. Hence, the dimensionality reduction plays a vital role to enhance the performance while processing the Hyperspectral images. The HSI is initially segmented into the pixels, it belongs to the similar correlation and it is optimized using the neural network framework. Auto Encoder based dimensionality reduction is proposed for performance enhancement that denoising removed. The reconstructed pixel using vectors and also identifying the reconstructing loss enhances the overall accuracy. The Convolutional Neural network framework implements the classification process for Hyperspectral images. The performance analysis results on the proposed technique have improved accuracy and performance compared to the related techniques. Keywords: Dimensionality reduction; accuracy; classification; Auto encoder; Hyperspectral image; Convolutional neural networks.

ANALYSIS OF OBSTRUCTIVE SLEEP APNEA DISORDER WITH ACCURACY PREDICTION USING SVM FOR SMART ENVIRONMENT
       MadhumithaRamamurthy , Ilango Krishnamurthi , Vimal S , Suresh Annamalai
One of the most crucial sleep disorders that has a direct hit on the quality of life is sleep apnea disorder. Declined memory and disorders related to personality are some of the consequences of Sleep Apnea Disorder. Identifying the difference between normal and abnormal levels of snoring sound is important for the detection of sleep apnea. Diagnosis of the sleep apnea usually takes place in hospitals under the direct supervision of medical professionals. Frequent visits to hospital for diagnosis tend to be an inconvenience to the elderly. Along with it, usage of body monitors also acts as a parameter in disrupting sleep. To overcome them, the analysis equipment is placed in the usual sleeping environment of the patient and LM393 sound sensor is used to detect the snoring levels. The analysis between the normal and the acquired snoring levels using threshold values and SVM helps confirm the presence or absence of the sleep apnea disorder.

USER LOCATION PREDICTION USING HYPERGRAPH IMPACT FACTOR IN TWITTER WITH GLOBAL DATA COMMUNICATION
       Pradeepa S&Manjula K R
Twitter is one of the most prominent online media that acts as a global network for sharing sensitive real-time information like earthquake alerts, political news, product review, personality identification, criminal detection etc. along with regular usage, which is why knowing the location of a user in twitter gets at most important even though they do not tend to disclose it. In this paper, we propose a technique to detect the name of the locations for the twitter users. This technique involves a hypergraph-based map-reduce concept to represent the user tweets with their locations. The Helly property of the hypergraph was used to remove less potential words and the Impact Factor measure (IF) was introduced to calculate the score of each location for a particular user. The algorithm (HIF) was implemented in a big data environment provided by Hadoop and found to give an average accuracy of 78% which is well ahead of the existing methodologies. This method gives appreciable results, with high values of precision and recall for all locations.

Back to JWE Online Front Page