Author/Authors :
Kamsing, Patcharin Air-Space Control - Optimization and Management Laboratory - Department of Aeronautical Engineering - International Academy of Aviation Industry - King Mongkut’s Institute of Technology, Ladkrabang, Bangkok, tailand , Torteeka, Peerapong National Astronomical Research Institute of Tailand, ChiangMai, +ailand , Boonpook, Wuttichai Department of Geography - Faculty of Social Sciences - Srinakharinwirot University, Bangkok, Tailand , Cao, Chunxiang University of Chinese Academy of Sciences, Beijing, China
Abstract :
To enhance the performance of image classification and speech recognition, the optimizer is considered an important factor forachieving high accuracy. (e state-of-the-art optimizer can perform to serve in applications that may not require very highaccuracy, yet the demand for high-precision image classification and speech recognition is increasing. (is study implements anadaptive method for applying the particle filter technique with a gradient descent optimizer to improve model learning per-formance. Using a pretrained model helps reduce the computational time to deploy an image classification model and uses a simple deep convolutional neural network for speech recognition. (e applied method results in a higher speech recognition accuracy score—89.693% for the test dataset—than the conventional method, which reaches 89.325%. (e applied method also performs well on the image classification task, reaching an accuracy of 89.860% on the test data set, better than the conventional method, which has an accuracy of 89.644%. Despite a slight difference in accuracy, the applied optimizer performs well in this data set overall.
