A Big Bang–Big Crunch Type-2 Fuzzy Logic System for Machine-Vision-Based Event Detection and Summarization in Real-World Ambient-Assisted Living

• Published in: IEEE transactions on fuzzy systems Vol. 24; no. 6; pp. 1307 - 1319
• Main Authors: Bo Yao, Hagras, Hani, Alghazzawi, Daniyal, Alhaddad, Mohammed J.
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.12.2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: 3-D machine vision; Algorithms; Cameras; Event summarization; Feature extraction; Fuzzy logic; Fuzzy systems; Graphical user interfaces; Human behavior; interval type-2 fuzzy logic systems (IT2FLS); Machine vision; New technology; People with disabilities; Sensors; Three-dimensional displays
• ISSN: 1063-6706; 1941-0034
• DOI: 10.1109/TFUZZ.2016.2514366

The area of ambient-assisted living (AAL) focuses on developing new technologies, which can improve the quality of life and care provided to elderly and disabled people. In this paper, we propose a novel system based on 3-D RGB-D vision sensors and interval type-2 fuzzy-logic-based systems (IT2FLSs) employing the big bang-big crunch algorithm for the real-time automatic detection and summarization of important events and human behaviors from the large-scale data. We will present several real-world experiments, which were conducted for AAL-related behaviors with various users. It will be shown that the proposed BB-BC IT2FLSs outperform the type-1 fuzzy logic system counterparts as well as other conventional nonfuzzy methods, and the performance improves when the number of subjects increases.