蔡維仁

Under the circumstance of limited, separated, and isolated social activities in the post-COVID-19 era, sentimental health becomes essential. The human interaction-enabled intelligent system requires the capability to meet the emotional response requirements, such as humanoid robots, intelligent agents. To deliver a proper response of emotion in time, primarily negative emotion, sensing emotion transition as forewarning is critical. This study's main objective is to develop the Emotion Recognition-and-Response Framework (Emotion R-R Framework) for enabling the computer to recognize human emotion transitioning from facial features, including the Emotion Transition Recognition Mechanism (ETRM) and the Emotional Response Mechanism (ERM). Also, this study conducted experiments for collecting data and model validation. The proposed method used the sliding window technique and support vector machine (SVM) to build classifiers to recognize emotions. This study used Information Gain (IG) and Chi-square to determine the robust feature set and examined the effectiveness of classifiers with different parameters of sliding windows. The experimental results confirmed that the proposed method has sufficient discriminatory capability. The recognition rates for basic emotions and transitional emotions were 99.13 and 92.40%, respectively. Also, through feature selection, training time was accelerated by 4.45 times, and the recognition rates for basic emotions and transitional emotions were 97.97 and 87.49%, respectively. This study experimented in a mathematical e-learning context to evaluate the performance of e-learning and the effectiveness of emotion regulation. The results of the emotion recognition classifier reached a 93.34% average recognition rate, and the participants of this experiment displayed a statistically significant decrease in targeted negative behaviors from baseline to intervention (p=0.00002) and significant improvements in mathematics learning performance (p=0.0045); however, responses to emotion regulation intervention varied among the participants. Implications for research and practice are discussed.

Cooperative learning is widely applied in education. However, it is not an ultimate solution for solving students' learning problems. Previous researches have shown that cognitive and social factors may weaken cooperative learning's benefits. In this paper, we proposed an expertise-based learning guidance mechanism to aid learner's cognitive process in cooperative learning, with a focus on learning destination, enhancing cognitive skills, and increasing students' comprehension.

• Methodologies of Recognizing Emotion

• Affective Computing

• Cooperative e-Learning

• Meta-Cognitive Based Knowledge Management

• Applications of Information Retrieval

• Applications of Machine Learning

• Journal

  • Chu, H.-C., Tsai, W. W.-J., Liao, M.-J., Chen, Y.-M. (2017), Facial Emotion Recognition with Transition Detection for Students with High Functioning Autism in Adaptive e-Learning, Soft Computing (Online) (SCI IF=2.367, 45/132, 5y SCI IF=2.204 @ 2017) doi:10.1007/s00500-017-2549-z.

  • Chu, H.-C., Tsai, W. W.-J., Liao, M.-J., Chen, Y.-M., Chen, J.-Y. (2020). Supporting E-Learning with Emotion Regulation for Students with Autism Spectrum Disorder. Educational Technology & Society, 23 (4), 124–146. (SCI IF=2.086, 88/263, 5y SCI IF=2.720 @2019)

• Conference

  • Chu, H.C., Tsai, W.W.J., Liao, M.J., Cheng, W.K., Chen, Y.M. & Wang, S.C. (2013). Facial Expression Based Real-Time Emotion Recognition Mechanism for Students with High-Functioning Autism. In J. Herrington, A. Couros & V. Irvine (Eds.), Proceedings of EdMedia: World Conference on Educational Media and Technology 2013 (pp. 1165-1173). Association for the Advancement of Computing in Education (AACE).

  • Hui-Chuan Chu, Min-Ju Liao, Wei-Kai Cheng, William W.-J. Tsai, Yuh-Min Chen(2012), Emotion Classification for Students with Autism in Mathematics e-learning using Physiological and Facial Expression Measures, WASET 2012, Paris, France (EI).

  • Hui-Chuan Chu, Min-Ju Liao, William W.-J. Tsai and Yuh-Min Chen (2011), On Development of Expertise-Based Learning Guidance for Cooperative e-Learning, e-Learn 2011, Honolulu, HI, USA.

• Journal

  • Kun-Lin Hsieh*, William Tsai, Neng-Mu. Shih, (2007), Applying PC-cluster into Clustering Analysis for Organism’s Codon Usage Based on MPI Techniques, WSEAS Transactions on Computers, 6(8), pp.1044-1049 (EI)

  • Kun-Lin Hsieh, Cheng-Chang Jeng, William Tsai, Chun-Hung Lee, (2006), “Computational Resource Integration via PC Cluster: A Case Study at Taiwanese University”, WSEAS Transaction on Computers, 5(12), pp.3091-3098. (EI)

• Conference

  • 朱慧娟、廖敏如、蔡維仁、溫俊誠、陳裕民，支援數位合作學習之專家智識學習引導，2010資訊管理暨電子商務經營管理研討會，2010年5月14~15日，台灣台東。

  • William Tsai, Neng-Mu Shih, and Kun-Lin Hsieh. 2007. Achieving organism clustering analysis by using PC cluster architecture with MPI techniques. In Proceedings of the 11th WSEAS International Conference on Computers (ICCOMP'07), N. E. Mastorakis, S. Kartalopoulos, D. Simian, A. Varonides, V. Mladenov, Z. Bojkovic, and E. Antonidakis (Eds.). World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, Wisconsin, USA, 537-541.

  • Kun-Lin Hsieh, Cheng-Chang Jeng, William Tsai, and Chun-Hung Lee. 2006. " Systematic viewpoint for integrating computational resources by using the technique of PC cluster". In Proceedings of the 6th WSEAS International Conference on Systems Theory & Scientific Computation (ISTASC'06), Athina Lazakidou and Konstantinos Siassiakos (Eds.). World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, Wisconsin, USA, 53-57.