توجه: محتویات این صفحه به صورت خودکار پردازش شده و مقاله‌های نویسندگانی با تشابه اسمی، همگی در بخش یکسان نمایش داده می‌شوند.
۱A Hybrid Genetic Algorithm and Artificial Neural Networks (GANN) for Feature Reduction in Forest Fire Detection
اطلاعات انتشار: اولین کنفرانس بین المللی دستاوردهای نوین پژوهشی در مهندسی برق و کامپیوتر، سال
تعداد صفحات: ۲۰
Early fire detection is very important in fighting fires. To this end, researchers have carried out work on feature reduction in automatic fire detection systems. One such method used in the fire detection field is Self–Organizing Maps (SOM). SOM has some limitations such as exponential complexity in large search spaces. This paper proposed GANN method based on the combination of Genetic Algorithms (GAs) and Artificial Neural Networks (ANNs) for forest fire detection. Applying GA will result in reduced number of features which could be used as inputs to ANN. The fitness function of the GA chromosomes is defined as the output value returned by ANN. Also we compare our results with SOM, Principal Component Analysis (PCA) and Independent Component Analysis (ICA). To demonstrate the efficiency of these methods, we have used the Canadian forest fire management information systems dataset. In this paper the performance of algorithms are compared based on mean square error (MSE) rate. Our simulation results demonstrated that the MSE in the GANN is less than other methods and the proposed method can reduce features without any reduction in accuracy.<\div>
نمایش نتایج ۱ تا ۱ از میان ۱ نتیجه