The medical diagnosis process can be interpreted as a decision making process, during which the physician induces the diagnosis of a new and unknown case from an available set of clinical data and from his/her clinical experience. This process can be computerized in order to present medical diagnostic procedures in a rational, objective, accurate and fast way. This paper presents a decision support system for heart disease classification based on support vector machine (SVM) and Artificial Neural Network (ANN). A multilayer perceptron neural network (MLPNN) with three layers is employed to develop a decision support system for the diagnosis of heart disease. The multilayer perceptron neural network is trained by back-propagation algorithm which is computationally efficient method. Results obtained show that a MLPNN with back-propagation can be successfully used for diagnosing heart disease than support vector machine.
Wireless sensor networks (WSN) has been extensively used in many real time wireless sensor networks applications. Due to limitations of hardware resources and restricted communication capabilities of sensor nodes, it is very challenging to use wireless sensor networks in real time data transmission. Data collection and routing is the main issue in such applications. To enhance the performance under such real time transmission scenario, it is essential to make the protocol intelligent to choose the appropriate path with change in network scenario. Now a days, many machine learning and deep learning algorithms are used for improving the real time data transmissions in WSNs. From the survey on existing methods, it is clear that using machine learning makes the computational methods more reliable, powerful and economical. This paper proposes a machine learning based Medium Access Control (MAC) protocol to handle real time traffic in wireless sensor networks. To deal with the limitations of WSN in real time application, the proposed scheme can help to increase the performance of time-critical wireless sensor network applications. Simulation results authorize our work and confirm the accuracy of the proposed ML-MAC protocol strategy is higher than the existing work.
Data streams mining have become a novel research topic of growing interest in knowledge discovery. The data streams which are generated from applications, such as network analysis, real time surveillance systems, sensor networks and financial generate huge data streams. These data streams consist of millions or billions of updates and must be processed to extract the useful information. Because of the high speed and huge size of data set in data streams, the traditional classification technologies are no longer applicable. In recent years a great deal of research has been done on this problem, most intends to efficiently solve the data streams mining problem with concept drift. This paper presents a novel approach for data stream classification which handles concept drift. This approach uses weighted majority approach with adaptive sliding window strategies. The experimental result shows that this novel approach works better than other methods.
Data Stream Mining Using Ensemble Classifier: A Collaborative Approach of Classifiers: 10.4018/978-1-5225-0489-4.ch013: A data stream is giant amount of data which is generated uncontrollably at a rapid rate from many applications like call detail records, log records, sensors
As an accident is very common scenario for today's world. This paper presents one more step towards safety of driving through an application called Crash Prediction System (CPS). That analyzes driver's behaviour in real time and predicts that whether driver is suitable or not for driving. This system requires various profile of driver's detail for accurate prediction and gives result like Fit, Unfit and Partially Fit. For this application a concept of Data Stream minning is used with Principle Component Analysis (PCA) and Hidden Markov Model (HMM) techniques. Other interactive feature for this application is that, it used for mobile device. A large range of application is running on mobile device which are facing problem like a memory, computational capability, battery and many more. For eliminating all these issues there is a platform known as Android which we used for this application. Experiment result of CPS on Google Android platform is presented, proving the effectiveness of the proposed system.