[Show abstract][Hide abstract] ABSTRACT: This paper discusses a methodology for handwritten character recognition applying feature subset selection to reduce number of features. Its novelty lies in the use of a genetic algorithm for the preparation of input data for a support vector machine which is employed to recognize the handwritten Persian digits in particular. Comprehensive experiments on handwritten Persian digits demonstrate the capability of such a classifier running on reduced extracted features.
Proceedings of the 2009 International Conference on Artificial Intelligence, ICAI 2009, July 13-16, 2009, Las Vegas Nevada, USA, 2 Volumes; 01/2009
[Show abstract][Hide abstract] ABSTRACT: Internet based services (online) offer customers splendid benefits such as enhanced control, ease of use and reduced transaction charges. Consequently, online services have grown rapidly and emerged as a leading edge of service industry. Online trading is defined as process of trading financial products especially stocks over the Internet, or the service which offered on the Internet for purchase and sale of shares. Studies show that online trading has significant effects on the level of traders' satisfaction comparing with conventional trading systems. Therefore, authorities decided to evaluate, if online trading has the same positive impact on satisfaction in Iran Stock Exchange or not? Regarding to current problems in trading processes in Tehran Stock Exchange, researchers decided to focus their studies on this national major trading issue and evaluate the impact of online trading system on Iranian traders satisfaction level. In this due, this paper covers a brief literature regarding mentioned subjects in first step and then describes research area and gives details of applied methodology. In next step, analyzing and findings of the research based on SERVQUAL model will be explained.