Artificial Intelligence (AI) Techniques Applied for the Development of a Clinical Decision Support System (CDSS) for Diagnosing Ischemic Heart Disease (IHD)

Heart Disease (IHD) is difficult to diagnose since most of the symptoms and clinical presentations are similar to other diseases. It is a very common, harmful disease, which is identified mostly during the mortality of an individual. The objective is to build a clinical decision support system, which will diagnose the presence of IHD with an integrated automated classifier using Artificial Intelligence (AI) techniques. A retrospective data set that included 800 clinical cases was taken for the work. A total of 88 sets were discarded during pre-processing. Tests were run on 712 cases using the Weka classifiers available in Weka 3.7.0. Out of 113 classifiers, 16 were identified to be the best based on the following parameters: sensitivity, specificity, accuracy, F- measure, kappa statistic, correctly classified cases, time taken to run the model, and the Receiver Operating Characteristic (ROC) curve. The diagnoses made by the Clinical Decision Support System (CDSS) were compared with those made by physicians during patient consultations. The KSTAR algorithm showed the best diagnoses with the highest accuracy 97.32%, sensitivity 98%, specificity 97% kappa 0.95, and ROC 0.995. The authors thus conclude that a CDSS can be developed to assist expert physicians in separating the positive and the negative cases of heart disease.

A Multiple Classifier System for Automatic Speech Recognition

Classifier System (MCS) is designed by combining two or more classifiers. MCS helps in increasing the accuracy of classification compared to the performance of the individual classifier. In this paper, Multiple Classifier System is implemented for automatic speech recognition. The combined classifier takes the final decision on predicted class label using a class label fuser (also called as classifier fuser). The class label fuser uses the predicted class labels of the two classifiers i.e Hidden Markov Model (HMM) and Support Vector Machines (SVM) and also involves the Dynamic Time Warping (DTW) technique for the final decision on the predicted label. There is an improvement in the accuracy of such classifier compared to the output of any individual classifier.

Design and Implementation of Appliance Controller using Traditional or Smart Phone

The Effect of Mobility Models and Traffic Patterns on the Performance of Routing Protocols in MANETs

Mobile ad-hoc networks (MANETs) are self-organizing networks which can form a communication network without any fixed infrastructure. Constant bit rate (CBR) traffic pattern is very well known traffic model for MANETs which generates data packets at a constant rate. Transmission Control Protocol (TCP) provides reliability to data transferring in all end-to-end data stream services on the MANETs. There are several TCP traffic patterns such as TCP Reno, TCP New Reno, TCP Vegas, and TCP Selective Acknowledgment (Sack). The traffic pattern plays an important role in so far as the performance of a routing protocol is concerned. In this paper, we study the effect of impact of mobility models and traffic patterns on the behavior of Reactive (AODV) and Proactive (DSDV, OLSR) routing protocols used in MANETs considering both CBR and TCP traffic patterns with different mobility models namely, Reference Point Group Mobility (RPGM) and Manhattan Grid (MG). The performance metrics used to evaluate the efficiency of the considered protocols are packet delivery ratio, average throughput and End-to-End Delay. The experimental results conducted using NS2 simulator show that the relative ranking of routing protocols may vary depending on both mobility models and traffic patterns.

Survey on Grid based Energy Efficient Routing Protocols in Wireless Sensor Networks

Sensor nodes in Wireless sensor networks (WSN’s) have limited energy, range, memory and computational power. In WSN, it is an important task to send measured data at regular intervals from an area of interest for time sensitive applications to a base station or sink for further processing to meet the enduser queries. For reducing energy consumption grid structure was used now-a-days. With the grid structure in place, query and data needs to be propagated to the grid points only. Since the sensor nodes have limited battery power, therefore, approaches have been proposed over the years to reduce energy consumption and to prolong network lifetimes. These approaches in WSN are called as Energy Efficient Routing (EER) protocols. In this paper, a comprehensive list of the grid based EER protocols have been studied with their relative advantages and disadvantages.

Distances, Hesitancy Degree and Flexible Querying via Neutrosophic Sets

Diagnosis of Breast Cancer using Clustering Data Mining Approach

The main objective of the research is to early diagnosis of the breast cancer patients. Nowadays Brest cancer becomes very major disease in many women not only in India but also in other country. For early diagnosis of the breast cancer patients, clustering data mining algorithm used to detect breast cancer. For the experimental purpose breast cancer dataset carried out form the UCI web data repository. The selection of appropriate clustering data mining technique is a challenge for the diagnosis of breast cancer. To get early result the challenges takes four clustering data mining techniques. This research becomes very helpful to doctor for diagnosis breast cancer and also helpful to patients for early treatment.

Automatic Road Distress Detection and Analysis

Fingerprint Minutiae Extraction using Fuzzy Logic

the oldest and most widespread biometric identification system are commonly used for criminal investigation in forensic Science; there is minute statistical theory on the Rareness of fingerprint minutiae. A critical step in studying the statistics of Fingerprint minutiae is to reliably extract minutiae from the fingerprint images. However, fingerprint images are rarely of perfect quality. They may be degraded and corrupted due to variations in skin and impression conditions. Thus, image Enhancement techniques are employed prior to minutiae extraction to obtain a more reliable estimation of minutiae locations.

Forecasting Chaotic Stock Market Data using Time Series Data Mining

An important financial subject that has attracted researchers’ attention for many years is forecasting stock return. Many researchers have contributed in this area of chaotic forecast in their ways. Among them data mining techniques have been successfully shown to generate high forecasting accuracy of stock price movement. Nowadays, instead of a single aspects of stock market, traders need to use various aspects’ forecasting to gain multiple signals and more information about the future of the markets. Aspects of Lyapunov, Entropy and Variance (ALEV) provide an approach for mining large stocks of time series data. This paper proposes a novel method for forecasting chaotic behavior of stock market’s opening, high, low and closing price with time series data mining. The outcome of this study tries to help the investors in the stock market to decide the better timing for buying or selling stocks based on the knowledge extracted from the historical prices of such stocks. General Terms Chaotic data mining, time series based data forecasting.