A Type-2 Fuzzy Logic Based Explainable AI Approach for the Easy Calibration of AI models in IoT Environments

Rozman, Josip; Hagras, Hani; Andreu-Pérez, Javier; Clarke, Damien; Müller, Beate; Fitz, Steve

doi:10.1109/fuzz45933.2021.9494522

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, in the last three years of studies on higher-order types of FLS in particular, the designed and developed applications of interval type-2 fuzzy logic have increased significantly [48][49][50][51][52][53][54]. These type-2-based FLS applications have been identified in artificial intelligence (AI) [55][56][57][58][59], adaptive control [60][61][62][63][64][65][66], electric motor control [67][68][69][70][71][72], Internet of Things (IoT) [73][74][75][76][77], digital image processing [78][79][80][81][82][83][84] and other areas [85][86][87]. Of course, the application of interval type-2 fuzzy logic in the domain of control has recently attracted a lot of attention due to its better performance under uncertain conditions.…”

Section: Number Of Output Fuzzy Membership Functionsmentioning

confidence: 99%

Real-Time Metaheuristic Algorithm for Dynamic Fuzzification, De-Fuzzification and Fuzzy Reasoning Processes

2022

View full text Add to dashboard Cite

This paper presents a systematic approach to designing a dynamic metaheuristic fuzzy logic controller (FLC) to control a piece of non-linear plant. The developed controller is a multiple-input–multiple-output (MIMO) system. However, with the proposed control mechanism is possible to adapt it to single-input–single-output (SISO) systems as well. During real-time operation, the dynamic behavior of the proposed fuzzy controller is influenced by a metaheuristic particle swarm optimization (PSO) mechanism. Nevertheless, to analyze the performance of the developed dynamic metaheuristic FLC as a piece of non-linear plant, a 1 kW four-wheel independent-drive electric rover is controlled under different road constraints. The test results show that the proposed dynamic metaheuristic FLC maintains the wheel slip ratio of all four wheels to less than 0.35 and a top recorded translational speed of 90 km/h is maintained for a fixed orientation.

show abstract