Search

A heart disease diagnosis method has been proposed for effective heart disease diagnosis. In the proposed method Machine Learning (ML) classifiers have been used for detection of heart disease. Chi square feature selection algorithm has been used for related feature selection to improve the prediction performance of machine learning models. Cross validation, method Hold out has been employed for model hyper parameters tuning and best model selection. Furthermore, performance evaluation metrics, such as classification accuracy, specificity, sensitivity, Matthews' correlation coefficient and execution time have been used for model performance evaluation. The Cleveland heart disease data set has been used for testing of the proposed method. The experimental results demonstrated that proposed method has achieved high performance as compared to state of the art methods. Furthermore, the proposed method performance has been compared with deep learning model. Thus, the proposed method will support the medical professional to diagnosis heart disease efficiently and could easily incorporated in healthcare for diagnosis of heart disease.

With the rapid development of medical imaging technology and information technology, digital medical image acquisition equipment is constantly updated, especially the rise of proton medical technology, which has higher requirements on human diseased cell imaging technology. In this paper, based on the image data acquired by the large aperture CT, the Monte Carlo calculation and analysis of edge-blurred electronic density images have carried out to achieve accurate diagnosis and provide a new method for efficient pathological treatment. This article made a preliminary study and analysis on the application of Monte Carlo method in radio surgical treatment planning. Monte Carlo method, which is known as random sampling or statistical test methods, can truly simulate the actual physical process, problem solving and actual in good compliance. It can be very successful results. Combined with the image processing method, this paper carries out the detection methods of image pre-processing, image segmentation, feature extraction, classification and recognition to the lesion area of human body to realize the effective recognition of the special lesion image area. Experimental results show that the edge of lesion area has obtained by image segmentation, contour extraction and Monte-Carlo calculation. Particle-space information has taken as input. Based on Monte Carlo method, the space-absorbed dose in phantom is analysed distributed. By using the computerized liver cancer diagnosis technology, the doctor’s working pressure and labour intensity are reduced, the doctor’s working efficiency is improved, the accuracy of the diagnosis is improved, the hospital saves many expenses and the patient’s burden is reduced. Therefore, the research of computer-aided diagnosis has important significance and application value.

Poliomyelitis is a disease which is spread through virus called enter virus. Its treatment is difficult but can be trim down through prevention strategies like on proper vaccination and management. For this purpose community awareness and mobilization is much needed factor, This disease is eradicated by the develop countries but still present in under develop countries due to the poor hygiene life style and lack of proper awareness about polio disease. Currently, Pakistan, Nigeria and Afghanistan are facing huge challenges to eradicate polio. It mostly affect children under age five and cause paraplegics condition to some part of the body, to cope with this problem a feature model has been proposed to resolve most of the network management issues required to communicate among the polio eradication health centers, like collecting the exact number of affected, missing and refusal children, launching a campaign in a proper hierarchical approach.

An internal gear ring for wind power generation is an important basic part of transmission mechanism for wind power generation. Hardening heat treatment is a key production process in the production of large gear rings. The problem of quenching hard and soft spots easily occurs in the gear ring at the inlet and outlet positions of the coil during the movement of the inductor. In this paper, an electromagnetic-thermal multi-field coupling prediction model was established with the coil movement factor being taken into account by analyzing the heat transfer process. With temperature nonuniformity being introduced as a measurable evaluation index, the laws of effect of the process of entry/exit of the inductor into/from the gear ring on this index were analyzed primarily. Comparison of the laws of distribution of electromagnetic field at the inlet, middle and outlet positions shows that it is possible to greatly reduce the temperature nonuniformity by changing the start and end positions of heating, thus to be favorable for improving the quality of heat treatment. The research results in this paper give a method and idea used as a reference for actively exploring relevant common problems in mobile electromagnetic heat treatment.

The safety of heavy equipment is directly determined by the quality of heavy-duty sprocket, which is a basic component in transmitting motion and power. However, local overheat of tooth surface, non-homogeneous hardness and microcracking are observed due to the skin effect, corner effect, and annular effect during traditional induction hardening of sprockets with conventional circular coils. Finite-element numerical computation and comparative analysis were carried out for sprocket heating processes between circular coil and profile coil, respectively. The maximum temperature difference of the sprocket along the tooth profile and the heating time required to meet heat treatment expectation were introduced to evaluate heating quality and efficiency. By analyzing and comparing the effects of various electromagnetic and geometric parameters on the evaluation indicators, it is found that the heat transfer process during sprocket induction heating can be changed by suitable profile coil parameters, consequently, the performance of gear type products can be improved.

Prostate cancer is regarded as the most prevalent cancer in the word and the main cause of deaths worldwide. Many traditional machine learning classification techniques has been applied to prostate patient survivability prediction, such as k Nearest Neighbors (KNN), Decision Tree (DT), Naive Bayes (NB)and Support Vector Machine (SVM). In recent years, deep learning has been proved as a strong technique and became a research hotspot. As a kind of deep learning method, in this study, artificial neural network and several traditional machine learning techniques are applied to SEER (the Surveillance, Epidemiology, and End Result program)database to classify mortality rate in two categories including less than 60 months and more than 60 months. The result shows that neural network has the best accuracy (85.64%)in predicting survivability of prostate cancer patients.

Review aspect terms extraction is an important task in the field of emotional analysis in natural language processing. This paper uses the method of ensemble learning to extract aspect terms of the E-commerce reviews. And this method has a very significant meaning. Because of the particularity of Ecommerce reviews, we choose the traditional method combined with machine learning method to extract the aspect terms of Ecommerce reviews emotional analysis, the experiment proved effective. First, we did word segmentation, POS tagging and other data preprocessing for the original Chinese E-commerce data. Then based on the training set construct the dictionary of aspect terms with the use of word-based reversed search method, for the test set tagging aspect terms. In addition, we train efficient CRF model and carry out aspect terms annotation on the comment data. Finally, based on the first two methods, the effect of model ensemble is improved.

Accurate 3D reconstruction of human tissue is a challenge problem in medical imaging. In this paper, a novel 3D reconstruction method of human brain MRI images is proposed based on the segmentation of human tissue. First, we propose a novel region-based growing algorithm to get points of an MRI image. Then, the moving cubes algorithm is used to reconstruct the accurate 3D object model. Further, in order to display well, a multiple angle observation is provided in our experiment. Experimental results show that the proposed method is better than the traditional methods.

Wireless Mesh Networks (WMNs) are widely used in many areas, such as industrial, commercial and public-safety environments. However, due to the open nature of wireless communication, it is relatively easy for an adversary to launch serious wormhole attack which can’t be even prevented by cryptographic protocols. To enhance the efficiency and facility of wormhole detection, we here propose a high efficiency wormhole detection algorithm based on 2-hop neighbor in WMNs, which is called Wormhole Detection based on Neighbor’s Neighbor scheme (WDNN). Then a simple Random Walk Route scheme (RWR) is proposed to prevent routes from wormholes, which attract traffic of the routing protocols based on least cost. In WDNN, through enlarging the transmission range of the 2-hop neighbor, the faked network topology resulted by wormholes can be detected without using extra hardware or clock synchronization. In RWR, the route is chosen without using the low latency link which is created by wormholes. Security analysis shows that the wormhole attacks can be detected and also be prevented using our schemes efficiently. And our simulation results also indicate that our schemes can obtain a 100% wormhole detection rate and prevent routes from being attacked by the adversary against traditional routing protocols.

Medical Big Data (MBD) is all concerned with the medical related bio-informatics data. The importance of medical investigations for disease identification and complications highly depend upon the quality data. This scientific era is the age of digital imaging and information processing. For every individual the medical record is collection of important data. Due to the smart telecommunication technology initiatives, MBD is very crucial research area. This data is in the form of images and video files, which are generated after technical examinations like CT scan, MRI, X-ray, ECG, and many others.

Wireless mesh network (WMN) is a new kind of distributed broadband network and has drawn great attention since it has good scalability, robustness and self-organization. However, routing protocols in traditional wireless networks such as wireless sensor network (WSN) and Ad Hoc network cannot be directly used in WMN, such as those minimum hops based routing protocols that have poor performance in WMN. To provide a routing protocol suitable for WMN, a load balance routing protocol in WMN is proposed based on crosslayer knowledge and takes Ad Hoc On-demand Distance Vector Routing (AODV) as a prototype, namely Load Balance Cross Layer based AODV (LBCL-AODV). In this protocol, not only the hop counts in AODV are considered, but also cross-layer information is used as metric to optimize route selection through using node load and packet delivery rate performance parameters. WMN always suffers from the load unbalance problem which degrades the network performance. To solve this problem, a load dynamically migration method is proposed which can migrate the traffic from busy routes to empty paths. The simulation results show that LBCL-AODV can reduce the end-to-end delay, increase the delivery rate and achieve the load balance.