Search

This paper proposes a hybrid model to classify cardiac arrhythmias and select their features in an optimal way. In the proposed model, the Genetic Algorithm was used to optimally select the features, and the Decision Tree with the C4.5 algorithm was applied to the extracted features to classify and train the model. The proposed approach was used to classify data into normal and abnormal classes as well as a 16-class collection of arrhythmias. To evaluate the performance of the proposed model compared with similar methods, we used the UCI arrhythmia dataset along with accuracy, sensitivity, specificity, and average Sen-Spec metrics. The efficiency of the proposed method in both two-class and 16-class modes significantly improved the accuracy, sensitivity, the average of sensitivity and specificity parameters compared to similar methods. Our approach obtained values of 86.96%, 88.88%, and 86.55% for the two-class mode and 78.76%, 76.36%, and 78.69% for the 16-class mode classification in terms of accuracy, sensitivity, and the average Sen-Spec metrics respectively. The above-mentioned values are reported as the highest for the UCI arrhythmia dataset. Keywords: Classification, Feature selection, ECG, Arrhythmia, Decision tree, Genetic algorithm

In this paper intelligent search technique of variable structure learning automata (VSLA) has been used to solve single machine total weighted tardiness job scheduling problem. The goal is investigating reduction in delays result in late execution of the jobs after specified deadline as well as reducing the time required to find the best execution order of the jobs. For this reason, fixed structure learning automata and genetic algorithm approaches has been studied and then a new scheduling approach called VSLA-Scheduler has been proposed by employing variable structure learning automata technique. In order to identify strengths and weaknesses of the proposed method, its performance is compared with other intelligent techniques. In this regard, for performance evaluation of the proposed method and comparing it with other methods, computer simulations have been used. Finally, the results produced by the proposed and previous algorithms have been compared with the best solutions in OR library. Experimental results show that the proposed algorithm's performance (VSLA-Scheduler) is more acceptable than other methods.

In this paper an improved approach based on CBR-LA model is proposed for static task assignment in heterogeneous computing systems. The proposed model is composed of case based reasoning (CBR) and learning automata (LA) techniques. The LA is used as an adaptation mechanism that adapts previously experienced cases to the problem which must be solved (new case). The goal of this paper is to expressing some weak points of the CBR-LA and proposing new algorithm called ICBR-LA which has improved performance in terms of Makespan performance metric. The results of experiments have shown that the proposed model performs better than the previous one.