The University of Nottingham · School of Computer Science

Dr Chao Chen

Member of the Laboratory for Uncertainty in Data and Decision Making (LUCID) and the Intelligent Modelling and Analysis (IMA) Research Group. His research mainly addresses a central tension in AI: how to improve predictive performance without sacrificing interpretability. His work advances optimisation methods for inherently interpretable models, especially fuzzy inference systems, combining gradient-based, differentiable, and hybrid approaches to narrow the performance gap with modern deep learning while preserving transparent reasoning and principled uncertainty handling.

Explainable AI (XAI)Interpretable AIHuman-Centric AIUncertainty-Aware AIFuzzy SystemsDeep LearningOptimisationFuzzyR

View Research →Publications Google Scholar ↗

Publication ChairFUZZ-IEEE @ WCCI 2026, QAI 2026

Associate EditorIEEE Computational Intelligence Magazine

Special Session Co-organiserAdvances in Optimisation for Fuzzy Systems @ FUZZ-IEEE / IEEE WCCI 2026, Maastricht

ORCID ↗

Latest News

View all →

Dec 2025

Jun 2026

May 2026

Mar 2026

Selected Publications

View all →

C Chen, J Twycross, JM Garibaldi · PLOS ONE 2017

Time SeriesEvaluation MetricsForecasting

DOI ↗

C Chen, JM Mendel, JM Garibaldi · IEEE Transactions on Fuzzy Systems 2025

Fuzzy SystemsOptimisationMembership Functions

Code ↗DOI ↗

F Abbasov, C Chen, JM Garibaldi · IEEE International Conference on Fuzzy Systems 2025

Fuzzy SystemsMembership FunctionsDeep Learning

DOI ↗

Q Lin, X Chen, C Chen, JM Garibaldi · Information Sciences 2024

Medical AIFuzzy Rough SetsImage Segmentation

DOI ↗

C Chen, D Wu, JM Garibaldi, RI John, et al. · IEEE Transactions on Fuzzy Systems 2021

Type-2 FuzzyFuzzy SystemsAlgorithms

Code ↗DOI ↗

Open-Source Software

FuzzyRon CRAN

An open-source Fuzzy Logic Toolkit for the R programming language. Supports design, simulation, and optimisation of type-1 and interval type-2 fuzzy inference systems — used internationally for research and teaching.

Type-1 & Interval Type-2 FISANFIS OptimisationNon-Singleton FuzzificationHierarchical Fuzzy SystemsAccuracy Measures (UMBRAE)Interactive GUIAutomatic Differentiation

View on CRAN ↗

Related Publications

example.R

library(FuzzyR)
 
# Build a Type-1 Fuzzy Inference System
fis <- newfis("temperature")
fis <- addvar(fis, "input",  "temp", c(0, 40))
fis <- addvar(fis, "output", "fan",  c(0, 100))
 
# Define membership functions
fis <- addmf(fis, "input", 1, "cold", "trimf", c(-10,  0, 15))
fis <- addmf(fis, "input", 1, "warm", "trimf", c( 10, 22, 30))
fis <- addmf(fis, "input", 1, "hot",  "trimf", c( 25, 40, 50))
 
# Add rules and evaluate
fis <- addrule(fis, c(1,1,1,1))
evalfis(25, fis)   # → 65.0