A Novel Neuro-Fuzzy Model to Detect Human Emotions Using Different Set of Vital Factors with Performance Index Measure

• Main Authors: Abeer Issa Albashiti, Mohammad Malkawi, Mohammed A Khasawneh, Omayya Murad
• Format: Article
• Language: English
• Published: Croatian Communications and Information Society (CCIS) 2018-03-01
• Series: Journal of Communications Software and Systems
• Subjects: Adaptive Neuro-Fuzzy Inference System; Emotion Detection; Exhaustive Search; Performance measure index
• Online Access: https://jcomss.fesb.unist.hr/index.php/jcomss/article/view/392

A novel optimization algorithm is proposed for detecting human emotions(responses) using artificial intelligence techniques such as exhaustive search, fuzzy logic and neural networks. Previous models for detecting human emotions have used fourteen measurable physical and physiological input factors to detect twenty two human emotions. This paper presents an optimization method to reduce the number of input factors required to detect a set of emotions. The proposed method utilizes twelve optimization procedures (cases) each one has unique error values, and different input factors. Optimization is sought to reduce the cost and complexity of implementing human emotion detection systems. A performance measure index is used to evaluate the effectiveness of the proposed model. This study shows that using less than half of the factors (6-8 factors) is the most cost effective set of input parameters for the human emotions detection system.