シャ　キンカ   Jinhua She   佘　錦華    所属   工学部 機械工学科    職種   教授
言語種別	英語
発行・発表の年月	2018/02
形態種別	学術論文
査読	査読あり
標題	Softmax regression based deep sparse autoencoder network for facial emotion recognition in human-robot interaction
執筆形態	共著
掲載誌名	Information Sciences
掲載区分	国外
出版社・発行元	Elsevier
巻・号・頁	428,pp.49-61
担当範囲	All
著者・共著者	Luefeng Chen, Mengtian Zhou, Wanjuan Su, Min Wu, and Jinhua She
概要	Deep neural network (DNN) has been used as a learning model for modeling the hierarchical architecture of human brain. However, DNN suffers from problems of learning efficiency and computational complexity. To address these problems, deep sparse autoencoder network (DSAN) is used for learning facial features, which considers the sparsity of hidden units for learning high-level structures. Meanwhile, Softmax regression (SR) is used to classify expression feature. In this paper, Softmax regression-based deep sparse autoencoder network (SRDSAN) is proposed to recognize facial emotion in human-robot interaction. It aims to handle large data in the output of deep learning by using SR, moreover, to overcome local extrema and gradient diffusion problems in the training process, the overall network weights are fine-tuned to reach the global optimum, which makes the entire depth of the neural network more robust, thereby enhancing the performance of facial emotion recognition. Results show that the average recognition accuracy of SRDSAN is higher than that of the SR and the convolutional neural network. The preliminarily application experiments are performed in the developing emotional social robot system (ESRS) with two mobile robots, where emotional social robot is able to recognize emotions such as happiness and angry.
外部リンクURL	https://www.sciencedirect.com/science/article/pii/S0020025517310496#