Machine intelligence quotient: its measurements and applications

• Published in: Fuzzy sets and systems Vol. 127; no. 1; pp. 3 - 16
• Main Authors: Bien, Zeungnam, Bang, Won-Chul, Kim, Do-Yoon, Han, Jeong-Su
• Format: Journal Article Conference Proceeding
• Language: English
• Published: Amsterdam Elsevier B.V 01.04.2002; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Computer science; control theory; systems; Exact sciences and technology; Fuzzy integrals; General logic; Intelligent systems; Logic and foundations; Machine intelligence; Mathematical logic, foundations, set theory; Mathematics; MIQ; Sciences and techniques of general use; MIQ; Intelligent systems; Fuzzy integrals; Machine intelligence; Machine intelligence measurment; Machine intelligence quoteint; Artificial intelligence; Intelligent system; Fuzzy integral; Intelligence quotient
• ISSN: 0165-0114; 1872-6801
• DOI: 10.1016/S0165-0114(01)00149-X

We have investigated the notion of machine intelligence, based on extensive literature survey and have proposed two methods to measure intelligence of a machine. Specially, we have first analyzed those engineering systems or products that are said to be intelligent and have extracted four common constructs, each of which consists of several variables. Based on them, we have then suggested two typical models, which are represented as entities in three-dimensional construct space. In order to find a number, called machine intelligence quotient (MIQ), we adopt two fuzzy integrals, Sugeno fuzzy integral and Choquet fuzzy integral. Two application examples are given for the typical models using two fuzzy integrals, and comparative comments are made.