Explore chapters and articles related to this topic
State of the Art of Artificial Intelligence in Dentistry and Its Expected Future
Published in Lavanya Sharma, Mukesh Carpenter, Computer Vision and Internet of Things, 2022
Vukoman Jokanović, M. Živković, S. Živković
Fuzzy logic is an approach to computing based on the degrees of truth, rather than the usual true or false (1 or 0) logic. Therefore, it mimics human behavior, giving a certain result as partially true or false. It assumes that each output belongs somewhere between true and false, with different shades of green and blue instead of a completely green and blue. Fuzzy learning is a kind of AI used in medicine to diagnose, for example, diabetic neuropathy, or determine the required dose of the drug, based on the calculation of the brain volume, using MRI images. Based on such an approach, it is also possible to characterize ultrasound images or CT images of certain organs of the human body. Because these information are between partially correct and partially incorrect values, this method has limited application [19,21,33].
New Measurement of the Body Mass Index with Bioimpedance Using a Novel Interpretable Takagi-Sugeno Fuzzy NARX Predictive Model
Published in Richard Jiang, Li Zhang, Hua-Liang Wei, Danny Crookes, Paul Chazot, Recent Advances in AI-enabled Automated Medical Diagnosis, 2022
Changjiang He, Yuanlin Gu, Hua-Liang Wei, Qinggang Meng
Fuzzy logic combines objective knowledge and subjective knowledge via computing on ‘degree of truth’ rather than the traditional Boolean logic of ‘true or false’. Fuzzy logic handles uncertainty, small size data, and data sparsity better than other machine learning paradigms. Compared with the conventional modeling approaches, such as neural network, models based on fuzzy logic share significant advantages, such as being flexible, simple, and intuitive [19]. Fuzzy logic-based models have been wildly applied in biological research for the high complexity and uncertainty within these systems, especially in the area related to medical diagnosis [15, 20, 21]. These fuzzy logic-based systems have proved efficient and effective tools to support health condition analyses and clinical decisions. However, current existing fuzzy logic models developed for BMI prediction are limited to a few specific groups, such as athlete and obesity. The findings from the bioimpedance may allow for new and ground-breaking path-opening to the prediction of general human BMI with fuzzy logic-based model.
Routing in 3D UAV Swarm Networks
Published in Fei Hu, Xin-Lin Huang, DongXiu Ou, UAV Swarm Networks, 2020
Katelyn Isbell, Yang-Ki Hong, Fei Hu
In [15], the authors proposed dynamic 3D fuzzy routing based on traffic probability (DFTRP) to increase network lifetime and improve success rate of packet delivery. DFTRP uses hop-to-hop delivery in which the message is transmitted to a neighboring node based on fuzzy logic and local information until it reaches the destination. Fuzzy logic differs from Boolean logic in that it has degrees of “truth” rather than “false” or “true”. It uses the concept of human intuition to make decisions. An inference engine takes inputs, applies a fuzzy rule base, and produces outputs. A fuzzy set represents the relationship between an uncertain quantity x and a membership function (MF) μ in the range [0,1]. The fuzzy set A in the universe of discourse U can be represented by a set of ordered pairs such that A={(x,μA(x))|x∈U}
A novel combined Fuzzy-M5P model tree control applied to grid-tied PV system with power quality consideration
Published in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2022
Ahmed Bouhouta, Samir Moulahoum, Nadir Kabache
Fuzzy logic is an intelligent approach based on degrees of truth than the classical Boolean logic of true or false. This uncertainty reasoning can describe further types of linguistic variables such as very small, small, medium, and other criteria depending on the studied system. The fuzzy logic controller is one of the most important applications of fuzzy theory. It presents a type of expert system that uses fuzzy logic to make decisions. To solve a specified process problem, FLC uses a knowledge base represented in terms of fuzzy inference rules and fuzzy inference engine. Figure 2 shows the basic structure of FLC which is based on four modules that make up a general fuzzy controller named a fuzzy rule base, a fuzzy inference engine, a fuzzification module that provides fuzzy input sets, and a defuzzification module for producing quantifiable output results. FLC can be approached in two ways: The Mamdani method, Takagi and Sugeno’s strategy (Sarabakha, Changhong, and Kayacan 2019). The Mamdani method is based on linguistic fuzzy modeling and is known for its great interpretability and low accuracy, while Takagi and Sugeno’s technique uses accurate fuzzy modeling to achieve great accuracy at the expense of interpretability (Rezk and Fathy 2017).
Towards the cognitive and psychological perspectives of crowd behaviour: a vision-based analysis
Published in Connection Science, 2021
Elizabeth B. Varghese, Sabu M. Thampi
Fuzzy logic is a computing approach based on degrees of truth in the form of membership values between 1 (true) and 0 (false) (Vijayalakshmi & Muruganand, 2017). The fuzzy logic theory is based on these relative membership values and therefore is a function of the cognitive and mentation process. The conditional statements of fuzzy logic are formulated using the If-then rules which are of the form If x is A Then y is B where A and B represent linguistic variables that are defined by fuzzy sets (Xiang et al., 2016). The If-part is the antecedent and Then-part is the consequent of the fuzzy rule. The If-then rules are similar to human cognition based on mental rules. The human brain can formulate solutions based on a set of rules and the formation and usage of the rules generate the behaviour of the person.
A robust optimization for damage detection using multiobjective genetic algorithm, neural network and fuzzy decision making
Published in Inverse Problems in Science and Engineering, 2020
Patricia da Silva Lopes Alexandrino, Guilherme Ferreira Gomes, Sebastião Simões Cunha
Traditional logic works only with true or false (exact values), on the other hand, fuzzy logic (fuzzy set) works with ‘degrees of truth’ or ‘degrees of false’ (imprecise information). Expressions like ‘more or less’ and ‘maybe’ can be mapped with fuzzy logic. In fuzzy logic, due to the imprecise nature of the decision maker’s judgment, the i-th objective function of a solution on Pareto front is represented by a membership function [5]. The values of membership function designate the level of achievement of the objective functions of some problem, and these values are between 0 and 1. There are several kinds of membership functions, such as, linear, triangular, trapezoidal, or exponential membership functions [24–26]. In this work, a trapezoidal membership function was used (Equation (3)). where and are the minimum and maximum values of the i-th objective function, respectively. The values of and can be find after ranking the nondominated solutions on Pareto front. The worst solution for i-th objective solution is .