Hybrid Medical and Secure Artificial Intelligence Laboratory
Triggering Transformation through Trusted Medical AI
Nazarbayev University · Astana, Kazakhstan
HMedsAI Lab (Hybrid Medical and Secure Artificial Intelligence Laboratory) is a research group focused on developing trustworthy, secure, and clinically meaningful artificial intelligence for healthcare and intelligent systems.
The laboratory brings together research in medical imaging, biomedical signal processing, machine learning, deep learning, cybersecurity, privacy-preserving AI, explainable AI, multimodal learning, digital twins, and IoT-enabled healthcare. Our goal is to connect methodological innovation with practical problems through reproducible, responsible, and impactful research.
Assistant Professor, Department of Computer Science
School of Computing and Artificial Intelligence (SCAI)
Nazarbayev University, Astana, Kazakhstan
Prof. Hari Mohan Rai received his Ph.D. from the Indian Institute of Technology (ISM), Dhanbad, India, in 2022, with research focused on the detection of fatal diseases from biomedical signals and images using hybrid deep neural network models. He is also a Gold Medalist in Master of Engineering (Control System Engineering).
His research spans Artificial Intelligence, Machine Learning, Deep Learning, Medical AI, Biomedical Signal Processing, Medical Image Analysis, Cybersecurity, and Secure Intelligent Systems.
Google Scholar · ORCID · Publons · Email
- Medical Artificial Intelligence — AI-assisted disease detection, diagnosis, classification, segmentation, and prognosis
- Medical Imaging — MRI, ultrasound, histopathology, and other biomedical imaging modalities
- Biomedical Signal Processing — ECG analysis, denoising, compression, and arrhythmia detection
- Machine Learning & Deep Learning — CNNs, Transformers, hybrid architectures, ensemble learning, and representation learning
- Trustworthy & Explainable AI — interpretable, robust, uncertainty-aware, and clinically meaningful AI systems
- Privacy-Preserving AI — federated learning, secure computation, and privacy-aware healthcare analytics
- Generative & Multimodal AI — synthetic data generation, multimodal fusion, and data augmentation
- Digital Twins & Intelligent Healthcare — predictive and personalized healthcare systems
- Cybersecurity & Secure AI — intrusion detection, IoT security, authentication, and intelligent cyber-defense
- Edge AI & Internet of Things — efficient and secure AI for connected healthcare and smart systems
Recent work by Prof. Rai and collaborators includes research on:
- AI and federated learning for pulmonary hypertension detection
- Secure and lightweight authentication for IoT-based smart-home surveillance
- AI-driven botnet detection in IoT networks
- Digital-twin monitoring for chronic disease patients
- Deep-learning models for brain tumor, breast cancer, lung cancer, colon cancer, leukemia, and ocular tumor analysis
- ECG compression, reconstruction, denoising, and arrhythmia detection
- Synthetic-data generation for medical imaging
- Network intrusion detection and cybersecurity analytics
- Secure AI and IoT frameworks for intelligent healthcare systems
- A Systematic Review of AI for Pulmonary Hypertension Detection: Performance, Gaps, and the Critical Need for Federated Learning — Archives of Computational Methods in Engineering, 2026
- Secure and Lightweight Authentication for IoT-Based Smart Home Surveillance — IEEE Internet of Things Journal, 2026
- AI-driven botnet detection in IoT networks: A comprehensive research review — Computer Science Review, 2026
- Advanced security in fog environments using encryption and adaptive user activity tracking — Scientific Reports, 2026
- An Efficient CSP-PDW Approach for ECG Signal Compression and Reconstruction for IoT-Based Healthcare — Computers, Materials & Continua, 2025
- ViT-DCNN: Vision Transformer with Deformable CNN Model for Lung and Colon Cancer Detection — Cancers, 2025
- LightweightUNet: Multimodal Deep Learning with GAN-Augmented Imaging Data for Efficient Breast Cancer Detection — Bioengineering, 2025
- Comparative analysis of machine learning and deep learning models for improved cancer detection — Expert Systems with Applications, 2024
- Two-Headed UNetEfficientNets for parallel execution of segmentation and classification of brain tumors — Journal of Cancer Research and Clinical Oncology, 2024
- The prediction of cardiac abnormality and enhancement in minority class accuracy from imbalanced ECG signals using modified deep neural network models — Computers in Biology and Medicine, 2022
Prof. Rai has contributed as an author and editor to books and chapters covering computational intelligence, AI, IoT, healthcare, cybersecurity, optimization, and generative AI. His recent edited and authored books include:
- Optimization Tools and Techniques for Enhanced Computational Efficiency — IGI Global, 2025
- AI and IoT-Driven Social Sensing for Smart City Innovation — IGI Global Scientific Publishing, 2026
- Blockchain Enabled AI Security Architectures — 2026
Research and innovation activities include patents and design registrations related to:
- Cloud-based IoT healthcare monitoring
- AI-based assistive systems for visually impaired people
- EEG signal enhancement
- IoT-based hydroponic systems
- Intelligent drones and UAV systems
- Drone-based air ambulance concepts
- Disaster-response technologies
Prof. Rai contributes to the research community through editorial, reviewing, conference, mentoring, and invited-speaker activities. His service includes work with journals and venues from IEEE, Elsevier, Springer Nature, Frontiers, IET, Taylor & Francis, and other academic publishers.
Editorial and reviewing activities include contributions to journals such as BMC Bioinformatics, Frontiers, IEEE Journal of Biomedical and Health Informatics, IEEE Access, Measurement, Biomedical Signal Processing and Control, Artificial Intelligence Review, Multimedia Tools and Applications, and others.
At Nazarbayev University, Prof. Rai teaches undergraduate and graduate courses in areas including:
- Artificial Intelligence
- Machine Learning: Theory and Practice
- Computer Systems and Organization
- Current Research Literature
- Research Seminar and Thesis Research
HMedsAI Lab welcomes motivated undergraduate, graduate, and doctoral students interested in conducting rigorous research and developing work suitable for high-quality publication.
We welcome interdisciplinary collaboration with researchers, clinicians, students, healthcare professionals, universities, research laboratories, and industry partners working in areas related to medical AI, intelligent healthcare, trustworthy AI, privacy, cybersecurity, and biomedical computing.
Potential collaborators and students are encouraged to contact the laboratory with a brief description of their research interests.
Prof. Hari Mohan Rai
Assistant Professor, Department of Computer Science
School of Computing and Artificial Intelligence (SCAI)
Nazarbayev University, Astana, Kazakhstan
📧 [email protected]
🔗 Google Scholar · ORCID · Publons
HMedsAI Lab
Hybrid Medical and Secure Artificial Intelligence Laboratory
Triggering Transformation through Trusted Medical AI