S. Roostaee; H.R Ghaffary
Abstract
Data analysis in cardiovascular diseases is difficult due to large massive of information. All of features are not impressive in the final results. So it is very important to identify more effective features. In this study, the method of feature selection with binary cuckoo optimization algorithm is ...
Read More
Data analysis in cardiovascular diseases is difficult due to large massive of information. All of features are not impressive in the final results. So it is very important to identify more effective features. In this study, the method of feature selection with binary cuckoo optimization algorithm is implemented to reduce property. According to the results, the most appropriate classification for support vector machine is featured diagnoses heart disease. The main purpose of this article is feature reduction and providing a more precise diagnosis of the disease. The proposed method is evaluated using three measures: accuracy, sensitivity and specificity. For comparison, a data set of Machine Learning Repository database including information about 303 people with 14 features was used. In addition to the high accuracy of current methods, are expensive and time-consuming. The results indicate that the proposed method is superior on other algorithms in terms of Performance, accuracy and run time.
S. Mohseni; G. Ardeshir; N. Zarei
Abstract
Automatic analysis of human facial expressions is one of the challenging problems in machine vision systems. It has many applications in human-computer interactions such as, social signal processing, social robots, deceit detection, interactive video and behavior monitoring. In this paper, we develop ...
Read More
Automatic analysis of human facial expressions is one of the challenging problems in machine vision systems. It has many applications in human-computer interactions such as, social signal processing, social robots, deceit detection, interactive video and behavior monitoring. In this paper, we develop a new method for automatic facial expression recognition based on facial muscle anatomy and human face structure. The algorithm finds approximate location of effective facial muscles and extracts features by measuring skin texture in 11 local patches. Seven facial expressions, including neutral are being classified in this study using AdaBoost classifier and other classifiers on MMI databases. Experimental results show that analyzing skin texture from selected local patches gives accurate and efficient information in order to identify different facial expressions.
