Learn More
We propose an intelligent e-learning system featuring with affective agent tutor. The agent tutor "Alice" is not only fully aware of the affective state of the students through facial expression, speech and text, but also fully capable of adapting to these states wisely guided by a case-based method with facial expression generation and emotional speech(More)
In this paper, we consider the problem of robust facial expression recognition and propose a novel scheme for facial expression recognition under facial occlusion. There are two main contributions in this work. Firstly, a novel method for facial occlusion detection based on robust principal component analysis (RPCA) and saliency detection performs(More)
OBJECTIVE Clinical and experimental studies demonstrate the important roles of vascular smooth muscle cells (VSMC) in the pathogenesis of atherosclerosis. We have previously determined that the osteogenic transcription factor Runx2 is essential for VSMC calcification. The present study characterized Runx2-regulated signals and their potential roles in(More)
In this contribution, we introduce a novel approach to combine acoustic information and emotional point information for a robust automatic recognition of a speaker’s emotion. Six discrete emotional states are recognized in the work. Firstly, a multi-level model for emotion recognition by acoustic features is presented. The derived features are selected by(More)
This paper proposes a new approach for emotion recognition based on a hybrid of hidden Markov models (HMMs) and artificial neural network (ANN), using both utterance and segment level information from speech. To combine the advantage on capability to dynamic time warping of HMMs and pattern recognition of ANN, the utterance is viewed as a series of voiced(More)
Speech emotion recognition as a significant part has become a challenge to artificial emotion. It is particularly difficult to recognize emotion independent of the person concentrating on the speech channel. In the paper, an integrated system of hidden Markov model (HMM) and support vector machine (SVM), which combining advantages on capability to dynamic(More)
ATP-sensitive potassium (K(ATP)) channels couple cellular metabolic status to changes in membrane electrical properties. Caffeine (1,2,7-trimethylxanthine) has been shown to inhibit several ion channels; however, how caffeine regulates K(ATP) channels was not well understood. By performing single-channel recordings in the cell-attached configuration, we(More)