Research

Optimization, learning, and decisions under uncertainty.

Our work sits at the intersection of nature-inspired computation and real problems — from tuning an algorithm's mutation strategy to deciding which supplier a hospital should trust.

01

Evolutionary Algorithms

Differential Evolution (DE) and Genetic Algorithms (GA) form the theoretical backbone of the lab's work. We study mutation and crossover strategies, adaptive parameter control, hybridization with other metaheuristics, and convergence behaviour on constrained and multi-objective problems. This line of work includes one of the group's most-cited papers, a comprehensive review of two decades of differential evolution research.

02

Swarm Intelligence

Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) algorithms, and their hybrids, are applied to engineering design, image watermarking, thresholding, and feature selection. Much of this research focuses on improving exploration–exploitation balance through modified velocity updates, guiding-force strategies and diversity mechanisms.

03

Multi-Criteria Decision Making & DEA

Using MCDM techniques (TOPSIS, AHP, fuzzy weighting) and Data Envelopment Analysis, the lab evaluates efficiency and ranks alternatives in contexts such as sustainable supplier selection, higher-education institution assessment, reverse logistics and sugarcane industry performance — often combining classical operations research with machine learning.

04

Machine Learning & AI for Healthcare

A growing body of work applies deep learning and explainable AI to medical imaging (brain tumor and Alzheimer's classification, skin cancer detection), mental health assessment, vaccine side-effect analysis, and ICU treatment optimization via reinforcement learning.

05

Applied Optimization in Industry

Beyond algorithm design, the group works on applied problems including reservoir operation, water distribution network design, vehicle routing, nurse scheduling, stock selection, and sustainable supply chains — usually pairing a metaheuristic core with a domain-specific cost model.

Highly cited work

A few papers that shaped the field.

1,216 citations

Differential Evolution: A Review of More Than Two Decades of Research

Bilal, M. Pant, H. Zaheer, L. Garcia-Hernandez, A. Abraham — Engineering Applications of Artificial Intelligence, 2020.

1,155 citations

A Comprehensive Review on NSGA-II for Multi-objective Combinatorial Optimization

S. Verma, M. Pant, V. Snasel — IEEE Access, 2021.

458 citations

Particle Swarm Optimization: Hybridization Perspectives & Experimental Illustrations

R. Thangaraj, M. Pant, A. Abraham, P. Bouvry — Applied Mathematics and Computation, 2011.