Facial Expression Recognition (FER) has long been a challenging task in the field of computer vision. Most of the existing FER methods extract facial features on the basis of face pixels, ignoring the relative geometric position dependencies of facial landmark points. This article presents a hybrid feature extraction network to enhance the discriminative power of emotional features. The proposed network consists of a Spatial Attention Convolutional Neural Network (SACNN) and a series of Long Short-term Memory networks with Attention mechanism (ALSTMs). The SACNN is employed to extract the expressional features from static face images and the ALSTMs is designed to explore the potentials of facial landmarks for expression recognition. A deep geometric feature descriptor is proposed to characterize the relative geometric position correlation of facial landmarks. The landmarks are divided into seven groups to extract deep geometric features, and the attention module in ALSTMs can adaptively estimate the importance of different landmark regions. By jointly combining SACNN and ALSTMs, the hybrid features are obtained for expression recognition. Experiments conducted on three public databases, FER2013, CK+, and JAFFE, demonstrate that the proposed method outperforms the previous methods, with the accuracies of 74.31%, 95.15%, and 98.57%, respectively. The preliminary results of Emotion Understanding Robot System (EURS) indicate that the proposed method has the potential to improve the performance of human-robot interaction.
On the premise of ensuring profits, how to give a relatively dispersed portfolio selection result reasonably and rapidly is a challenging problem in both theory and practice. Although the use of optimization models to make decision has been shown to be an essential approach towards portfolio selection, there still has an acute need for developing a knowledge-based expert model for portfolio selection so that this model can achieve better performance in reliability and real time, especially in leading more distributed investments. In this paper, a knowledge-based expert model is proposed for portfolio selection with the aid of analytic hierarchy process (AHP) and fuzzy sets. In the proposed model, the expert knowledge which can reflect the investment attitude and experience of different investors is mainly integrated into the criterion layer and represented by a reciprocal matrix, and the scheme layer is abstracted to a strictly consistent matrix by comparing and analyzing the state characteristics of investment objects. In order to characterize the state characteristics of investment objects under fuzzy environment, their corresponding time series data are quantified as fuzzy variables in advance. Experiments involving synthetic and real-world data demonstrate that the proposed model produces better performance than other typical portfolio selection models and gives more distributed investments.INDEX TERMS Decision-making, portfolio selection, analytic hierarchy process (AHP), consistency, expert knowledge.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.