A research programme built on one question

How can we design intelligent systems that adapt, optimize and create, not just compute?

Metaheuristics, games informatics and generative AI — one question, three ways of answering it, since 2012.

The terrain behind this page is generated live and the swarm crossing it is a real search climbing those ridges. Click anywhere to regenerate the landscape.

/ research program

Three pillars, one connected agenda.

PILLAR 01

Swarm intelligenceOpen →

Computational Intelligence & Optimization

Evolutionary and immune algorithms, swarm intelligence and metaheuristics — the search and optimization methods at the core of my work, applied to scheduling, assembly-line balancing and large-scale combinatorial problems.

EvolutionaryOptimization

PILLAR 02

Procedural dungeonOpen →

Games Informatics & Engagement Modelling

Game refinement theory and the “motion in mind” model, agent-based simulation and procedural content — measuring and optimizing what makes play engaging.

GamesSimulation

PILLAR 03

Latent flow fieldOpen →

Generative & Agentic AI

The emerging frontier — generative models, LLM foundation models and agentic content generation, extending the optimization-of-engagement programme into new domains.

Generative AIExpert Systems

/ see the research run · live

Three pillars, running live.

Each pillar demonstrated, not described — a showreel of the simulations rebuilt from the published work, playing one at a time. Open any one for the full, interactive version.

Generative AI · agentic

Agentic content generation

1 / 5

Generator and critic agents evolve a rough draft into a well-formed quest, matching a target difficulty arc.

Games & simulation · self-play

Game refinement

2 / 5

A game plays itself; its refinement value settles on the engagement spectrum toward the comfortable zone.

Optimization · immune algorithm

Assembly line balancing

3 / 5

An artificial immune system packs precedence-constrained tasks into stations, raising line efficiency.

Optimization · agent-based

Crowd evacuation

4 / 5

A navigation field routes shoppers to the exits while congestion and panic reshape the flow.

Optimization · immune algorithm

Production scheduling

5 / 5

Operations reorder around maintenance windows, compacting the Gantt chart to cut the makespan.

Generative AI · agentic

Agentic content generation

1 / 5

Generator and critic agents evolve a rough draft into a well-formed quest, matching a target difficulty arc.

Open the full simulation →

/ selected work

Selected articles.

A curated slice of the record, grouped by research pillar. The full body of work — 113 papers, filterable and mapped — lives on the publications page.

Computational Intelligence & Optimization

∗Q1Khalid, M. N. A. and Yusof, Umi Kalsom. “Leveraging bio-inspired knowledge-intensive optimization algorithm in the assembly line balancing problem.” IEEE Access 9 (2021): 117832–117844. https://doi.org/10.1109/ACCESS.2021.3106321→∗Khalid, M. N. A. and Yusof, Umi Kalsom. “Incorporating shifting bottleneck identification in assembly line balancing problem using an artificial immune system approach.” Flexible Services and Manufacturing Journal (2021). https://doi.org/10.1007/s10696-020-09389-1→

Games Informatics & Engagement Modelling

§Q2Khalid, M. N. A. “Ludogenic innovation: How playing incentivizes technological innovation.” Entertainment Computing 52 (2025): 100900. https://doi.org/10.1016/j.entcom.2024.100900→∗Q1Khalid, M. N. A. and Iida, Hiroyuki. “Objectivity and subjectivity in games: Understanding engagement and addiction mechanism.” IEEE Access 9 (2021): 65187–65205. https://doi.org/10.1109/ACCESS.2021.3075954→Q1Iida, Hiroyuki and Khalid, M. N. A. “Using games to study law of motions in mind.” IEEE Access 8 (2020): 138701–138709. https://doi.org/10.1109/access.2020.3012597→

Generative & Agentic AI

§Khalid, M. N. A. “Simulating AI-Human Collaborative Strategies in Sudoku Puzzle Generation.” In International Conference on Entertainment Computing, 2025.→∗Q3Khalid, M. N. A. and Kamarudin, Nazhatul Hafizah and Virgiyanti, Wiwied and Thurasamy, Ramayah. “Framework for Assisted Knowledge Management Practices Using Large Language Models: Preliminary Findings.” Asia-Pacific Journal of Information Technology and Multimedia 14 (2025). https://doi.org/10.17576/apjitm-2025-1402-05→Q1Tasir, Md All Moon and Khalid, M. N. A. “A novel deep neural model for efficient and scalable historical place image classification.” Scientific Reports 15 (2025): 42745. https://doi.org/10.1038/s41598-025-26897-y→Q2Khalid, M. N. A. and Al-Kadhimi, Amjed Ahmed and Singh, Manmeet Mahinderjit. “Recent Developments in Game-Theory Approaches for the Detection and Defense against Advanced Persistent Threats (APTs): A Systematic Review.” Mathematics 11, no. 6 (2023). https://doi.org/10.3390/math11061353→

View all 113 publications →

/ currently funded

Research in flight.

ACTIVECo-Investigator

Artificial Intelligence-Enhanced Pain Assessment in Postoperative Recovery: A Cross-Sectional Study of AI-Assisted Pain Assessment Tool with Patient Self-Reported Scores in the Post-Anaesthesia Care Unit

Geran Fundamental Fakulti Perubatan(GFFP)

2026 — 2030

ACTIVECo-Investigator

Enhancing Braille Literacy through Novel Interactive Features: A Multidisciplinary Approach to Improve User Engagement in Braille Learning Devices

Geran Translasi UKM (TR-UKM)

2024 — 2026

ACTIVECo-Investigator

Swarm-Based-Enhanced Hyperparameter Optimization for Advancing Random Forest Model in Healthcare Patient Prioritization

Fundamental Research Grant Scheme (FRGS)

2024 — 2027

Open to collaboration.

Postgraduate supervision (Master's & PhD), industry research collaboration, and conference invitations are always welcome.

Get in touch →