Adaptive Personalized Diet Linguistic Recommendation Mechanism Based on Type-2 Fuzzy Sets and Genetic Fuzzy Markup Language

• Published in: IEEE transactions on fuzzy systems Vol. 23; no. 5; pp. 1777 - 1802
• Main Authors: Lee, Chang-Shing, Wang, Mei-Hui, Lan, Shun-Teng
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.10.2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptive Ontology; Computation; Diets; Fuzzy; Fuzzy logic; Fuzzy set theory; Fuzzy sets; Fuzzy systems; Genetic Fuzzy Markup Language; Genetic Learning; Genetics; Linguistics; Meals; Ontologies; Personalized; Personalized Diet Linguistic Recommendation; Pragmatics; Subject specialists; Sugar; Type-2 Fuzzy Set; Uncertainty; genetic learning; personalized diet linguistic recommendation; Type-2 fuzzy set; Adaptive ontology; genetic fuzzy markup language (GFML)
• ISSN: 1063-6706; 1941-0034
• DOI: 10.1109/TFUZZ.2014.2379256

Many different real-world applications with a high-level of uncertainty proved the good performance of the type-2 fuzzy sets (T2 FSs). Balanced diet means that the intake of each necessary nutrient meets its adequate demand and actual caloric intake balances with calories burned. Additionally, making a diversity of choice from various types of food is also essential to reduce the risk of developing various chronic diseases. Different people have a different goal and it is hard to measure how healthy the eaten meal is for those who are not the domain experts on the diet. This paper presents an adaptive personalized diet linguistic recommendation mechanism based on type-2 fuzzy logic system (T2 FLS) and genetic fuzzy markup language (GFML). First, an adaptive dietary assessment and recommendation ontology is constructed by domain experts, and then a T2 FS-based GFML, describing the fuzzy knowledge base and the fuzzy rule base of the proposed mechanism, is evolved by using genetic algorithms. Next, a T2 FS-based fuzzy inference mechanism infers the result of the dietary health level based on the evolved type-2 GFML (T2GFML). In addition, the balanced computation mechanism is also proposed to reduce the computational complexity of the T2 FLS for the diet domain knowledge. Finally, the linguistic knowledge discovery mechanism presents the discovered linguistic meaning about the meal's health level to show the involved subjects how to make a personalized diet linguistic recommendation. This type of information about the eaten meal can provide the subjects with a reference to gradually improve their unhealthy eating habit and then become healthier and healthier. Experimental results show that the results of the proposed mechanism for the T2 FLS are better than those for the type-1 fuzzy logic system (T1 FLS).