Publications & Projects

My research centers on ethical AI and predictive analytics. building machine learning systems that are accurate, fair, and human-centered. A core thread running through all my work is the question of how humans experience, trust, and are impacted by algorithmic systems.

Research Interests

Ethical & Responsible AI

  • Algorithmic fairness & bias mitigation
  • Transparency and explainability in ML
  • Accountability frameworks for AI systems
  • Societal impact of automated decisions

Predictive Analytics & ML

  • Supervised & unsupervised learning models
  • People analytics & workforce prediction
  • Behavioral modeling and pattern detection
  • Python, scikit-learn, ML pipelines

Human Factors in AI Systems

  • Human-AI interaction & trust
  • Cross-cultural technology adoption
  • User perception of algorithmic outputs
  • Human-centered design for AI

Applied Research & Education

  • Intelligent & adaptive learning systems
  • AI curriculum design & pedagogy
  • Mixed-methods research design
  • Translating ML research into practice

Selected Works

Dissertation

Human Factors in Cybersecurity: A Cross-Cultural Study on Trust

Isslam Alhasan  ·  Purdue University  ·  2023

Doctoral dissertation applying mixed-methods research and predictive modeling to examine how cultural context shapes trust and behavioral responses to digital threats. Identifies cross-cultural patterns in human perception of algorithmic and security systems, with implications for the design of ethical, culturally-aware AI and security technologies.

Conference Paper

Mapping the Landscape of Industrial Control Systems Cybersecurity: A Delphi Study

Co-authored  ·  IEEE Frontiers in Education (FIE)  ·  2021

Developed a comprehensive cybersecurity concept map for Industrial Control Systems using a Delphi methodology with domain experts. A structured research effort connecting technical knowledge mapping with human factors: examining how expertise is defined, communicated, and developed in high-stakes technical environments.

Technical Report

Curriculum Guidance Document: Industrial Control Systems Cybersecurity

Co-authored  ·  CERIAS, Purdue University  ·  2021

Published through the Center for Education and Research in Information Assurance and Security (CERIAS) at Purdue. Provides context for a scalable national network of cybersecurity institutes utilizing hub-and-spoke model locations in FEMA Region 5, with a plan for developing shareable ICS curriculum across institutions.

Book Chapter

SecTutor: An Intelligent Tutoring System for Secure Programming

Co-authored  ·  Information Security Education - Adapting to the Fourth Industrial Revolution  ·  IFIP / WISE 2022

Presents SecTutor, an adaptive online learning tool for secure programming that tailors educational pathways based on learner assessments. The system identifies knowledge gaps and suggests personalized resources to scaffold skill development. Presented at the IFIP World Conference on Information Security Education (WISE 2022), pp. 17-28.

Conference Paper

Toward Proactive Cybersecurity: A Cultural Risk Profiling Framework for Predictive Cybersecurity Analytics

Isslam Alhasan  ·  IEEE FLLM 2025  ·  Vienna, Austria  ·  2025

Proposes a cultural risk profiling framework that integrates Hofstede's cultural dimensions with trust factors to improve predictive cybersecurity analytics. Argues that most predictive models treat human behavior as universal, missing how culture shapes risk perception, trust, and security responses. Presents a focused research agenda for developing culturally-aware, ethical predictive models in real-world cybersecurity systems.

Journal Article

XGBoost-Powered Predictive Analytics for Early Identification of Thermal Runaway in Lithium-Ion Batteries

Alhasan, I. and Alrashdan, M.H.S.  ·  World Electric Vehicle Journal, Vol. 17, No. 2, Art. 68  ·  2026

Applies XGBoost-based predictive modeling to detect early-stage thermal runaway in lithium-ion batteries, a critical safety challenge in electric vehicles and energy storage. Demonstrates how machine learning can be deployed to improve real-time safety monitoring, with implications for responsible AI in high-stakes engineering applications.


Academic Profiles

View my full publication record and citation metrics on the following platforms: