My research interests are centered on Applied Artificial Intelligence (AI), with a dual focus on medical diagnostic systems and cybersecurity frameworks. As an engineer with a strong background in signal processing and coding skills, I became deeply interested in how machine learning can be harnessed to interpret complex data, whether it be a patient’s physiological signals or an enterprise network’s traffic patterns. In my role as an Associate Professor, I have led multiple projects that apply AI to healthcare (e.g., neural networks for disease detection from bio-signals) and cybersecurity (e.g., intelligent intrusion detection systems). For instance, our AI-based framework for chronic disease detection and a zero-day intrusion detection system with 98.9% accuracy have shown promising results in real-world contexts. This twin focus addresses two of society’s most critical sectors: improving healthcare outcomes and protecting the information infrastructure. I approach these domains with a common philosophy: to combine advanced algorithms with domain knowledge to create intelligent systems that are accurate, explainable, and practically deployable. Through PhD supervision and interdisciplinary collaboration, I have developed applied research frameworks, particularly in RF and embedded systems, with practical impact while guiding AI-related investigations that address real-world problems in clinical and network settings.
AI for Medical Diagnostics and Edge Intelligence
In the AI domain, I focus on sensor-driven diagnostics and resource-efficient edge intelligence. For example, we have applied machine learning to noninvasive medical screening: a recent study on chronic lung disease showed how ML models trained on patient sensor data can detect early-stage obstructive lung conditions. This work was co-designed with clinicians to ensure practical relevance. We have also tackled multimodal sensing tasks, such as fusing images, inertial, and physiological signals to recognize complex human actions, yielding a unified deep‐feature classifier for activity recognition. Current AI projects include synthesis frameworks for broadband analog multiplexers in microwave and millimeter-wave applications, object recognition systems (emotion detection, sea pollution, ocular-image-based early diabetes, and space debris classification), and explainable AI-based detection of zero-day cyberattacks.
Edge AI and Federated Learning
To support these applications, we investigated edge AI methods. I co-authored a book chapter on “Resource-Efficient Models for Edge Devices,” which surveys techniques (quantization, pruning, TinyML) for deploying AI on constrained hardware. This chapter emphasizes privacy and energy efficiency by enabling local data processing, and analyzes how lightweight architectures preserve accuracy while supporting real-time inference. My team is implementing these ideas in embedded health sensor prototypes and exploring federated TinyML for secure, distributed learning.
AI for Cybersecurity and Explainable Intrusion Detection
The second pillar of my research is AI-enabled cybersecurity. I develop intelligent intrusion detection systems (IDS) capable of identifying novel threats in network and IoT environments. In one project, we built an ensemble IDS using convolutional and feedforward neural networks, achieving 99.7% accuracy. Optimization via genetic algorithms and PSO tuned the ANN components. We embedded SHAP and LIME to make alerts interpretable, enhancing trust and auditability for analysts.
In another IoT security study (Scientific Reports), we trained a deep Residual DNN on a merged dataset (UNSWNB15 + CICIDS2017) with metaheuristic tuning. The optimized model reached 98.7% accuracy. Tuning SHAP/LIME parameters improved fidelity by 10–11% without additional computational cost—demonstrating that metaheuristics can enhance both performance and interpretability.
Zero-Day Attack Detection
Beyond known attacks, zero-day detection is a major focus. In a recent NCAA2025 paper, we proposed an unsupervised autoencoder-based IDS trained solely on benign traffic. Evaluated on CIC-IDS2017, it achieved 98.9% accuracy and outperformed classical Isolation Forest models. We plan to incorporate transformer-based anomaly models with XAI tools to make these systems even more transparent and generalizable.
Federated and Privacy-Preserving Learning
Privacy-preserving learning is critical in federated learning environments. We are developing edge IDS systems that train models locally without transferring raw logs, protecting sensitive data. Initial work with federated convolutional autoencoders has yielded strong results on IoT datasets with reduced communication overhead. XAI integration for federated systems is also underway.
Quantum-Resilient AI Systems
Anticipating future threats, I explore the intersection of AI and quantum security. In a landmark review, we assessed quantum-safe encryption (e.g., CRYSTALS-Kyber, Dilithium), quantum key distribution, and quantum-enhanced ML (QSVMs, QNNs). I now supervise post-quantum cryptography (PQC) research and evaluate NIST-standard algorithms in practical systems like encrypted telemetry. Collaborations with De Montfort continue to expand our work on QML defenses and the ethics of quantum cryptography.
Leadership, Supervision, and Capacity Building
My role extends beyond research to leadership and education. I have supervised 9 PhD dissertations, 21 MSc theses, and 18 undergraduate projects spanning AI, RF, and cybersecurity. Notably, a former PhD student is now a Senior Lecturer at De Montfort University, with whom I continue to collaborate. As a Master Trainer in HEC’s PhD supervision program, I mentor early-career faculty and lead IEEE educational initiatives across the region.
Global Collaboration and Future Vision
Our work is inherently collaborative. I engage with medical professionals to validate clinical tools, and with cybersecurity experts to pilot solutions in live networks. International co-authorships with De Montfort, Essex, and York St. John universities reflect our global reach. I envision creating adaptive, trustworthy AI systems that operate securely on edge devices and are resilient to quantum-era threats. By integrating algorithmic innovation with explainability and rigorous testing, I aim to shape the future of AI-driven technology and mentor the next generation to lead it.
In the future, I will continue to push these frontiers. Whether refining our health-monitoring AI for edge devices or hardening networks against quantum attacks, my goal is to deliver technology that works in practice. By combining algorithmic innovation with explainability and rigorous validation, I aim to shape the future of secure AI-driven systems and train the next generation of researchers to do the same.
Sincerely,
Dr. Sohail Khalid (Ph.D.)
S. Khalid et al., “The intersection of artificial intelligence and assistive technologies in the diagnosis and intervention of mental health conditions,” Artificial Intelligence Review, 2026.
Rehman, A., Ghias, R., Sultan, N., Sherazi, H.I., Ayouni, S., Khalid, S. and Rehman, M.U., “Enhancing the efficacy of hormone therapy in prostate cancer through Conditional Super-Twisting Sliding Mode Control and Redfox optimization,” Biomedical Signal Processing and Control, 112, p.108895, 2026.
Zohaib, A., Akram, F., Khalid, S., Nawaz, H. and Rehman, M.U., “Hybrid deep learning based load forecasting and AI-driven energy management for grid-connected multi-microgrids,” Computers and Electrical Engineering, 131, p.110915, 2026.
Gogosh, N., Khalid, S., Malik, B.T. et al., “Electronically switchable dual-band capsule antenna for wireless endoscopic applications,” Nature, Scientific Reports, 2026.
S. Khalid et al., ”Shaping the Future of Cybersecurity: The Convergence of AI, Quantum Computing, and Ethical Frameworks for a Secure Digital Era,” Computer Science Review, 2025.
S. Khalid et al., "Power transformer health index and life span assessment: A comprehensive review of conventional and machine learning based approaches," Engineering Applications of Artificial Intelligence, 139, p.109474, 2025.
S. Khalid et al., “Metaheuristically Enhanced ANN-Based Intrusion Detection System with Explainable AI Integration,” International Joint Conference on Neural Networks (IJCNN), Rome, Italy, 2025.
S. Khalid et al., “Novel Zero-Day Attack Detection System Based on Autoencoder and Isolation Forest,” International Conference on Neural Computing for Advanced Applications, Hong Kong, 2025.
Shah, E.A., Ahsan, S.J., Qureshi, M.F., Khalid, S. and Ur Rehman, M., “Machine Learning and Multivariate Analysis Of Depression Prevalence and Predictors in Acute Coronary Syndrome,” IEEE Access, 2025.
Gogosh, N., Khalid, S., Malik, B.T. and Koziel, S., “Artificial magnetic conductor backed dual-mode sectoral cylindrical DRA for off-body biomedical telemetry,” Scientific Reports, 15(1), p.31870, 2025.
Raja, M.I., Tanveer, H., Rabani, H., Zohaib, A., Khalid, S. and Zad, H.S., “AI Based Smart Energy Saving and Consumption Management for Industries,” Pakistan Journal of Scientific Research, 4(2), pp.102-113, 2025.
Zad, H.S., Ulasyar, A., Zohaib, A. and Khalid, S., “Adaptive Observer-Based Robust Control of Mismatched Buck DC–DC Converters for Renewable Energy Applications,” Engineering Proceedings, 111(1), p.22, 2025.
Zad, H.S., Zohaib, A., Ulasyar, A. and Khalid, S., “An Improved Adaptive Sliding Mode Controller with Dynamic Surface Extension for Uncertain Robotic Manipulators,” Engineering Proceedings, 111(1), p.25, 2025.
S. Khalid et al., "Design of a miniaturized multi-resonance resonator-based highly selective dual wideband bandpass filter," Microelectronics Journal, Vol. 153, 2024.
S. Khalid et al., "Design of Tri-band Bandpass Filter Using Modified X-shaped Structure for IoT-Based Wireless Applications," IEEE Embedded Systems Letters, Oct 19, 2023.
S. Khalid et al., "Hrneto: human action recognition using unified deep features optimization framework," Computers, Materials and Continua, vol. 75, no.1, pp. 1089–1105, 2023.
S. Khalid et al., "Design of a Planar Four-Port Microstrip Triplexer using Stub-Loaded Coupled Line Resonator for Advanced Wireless Applications," 20th International Bhurban Conference on Applied Sciences and Technology (IBCAST), Pakistan, pp. 398-403, 2023.
S. Khalid et al., "Design and Analysis of Broadband Bandstop Filter using Dual Path Capacitive Coupled Resonator for 4G and 5G Applications," 20th International Bhurban Conference on Applied Sciences and Technology (IBCAST), Pakistan, pp. 385-392, 2023.
S. Khalid et al., "Design of miniaturized single and dual-band bandpass filters using diamond-shaped coupled line resonator for next-generation wireless systems," International Journal of Microwave and Wireless Technologies, 2022.
S. Khalid et al., "Design of a novel compact highly selective wideband bandstop RF filter using dual path lossy resonator for next generation applications," PLoS ONE, 17(10), 2022.
S. Khalid et al., "Design of a Compact Novel Stub Loaded Pentaband Bandpass Filter for Next Generation Wireless RF Front Ends," IEEE Access, vol. 10, pp. 109919-109924, 2022.
S. Khalid et al., "Multi-band bandpass filter using novel topology for next-generation IOT wireless systems," Computers, Materials and Continua, vol. 73, no.3, pp. 4819–4832, 2022.
S. Khalid et al., "Non-Invasive Early Diagnosis of Obstructive Lung Diseases Leveraging Machine Learning Algorithms,” Computers, Materials and Continua, 2022.
S. Khalid et al., “Leveraging Training Strategies of Artificial Neural Network for Classification of Multiday Electromyography Signals,” ETECTE, Lahore, Pakistan, 2022.
S. Khalid et al., "Synthesis and Design of Highly Selective Multi-Mode Dual-Band Bandstop Filter,” IEEE Access, 2021.
S. Khalid et al., "Future Forecasting of COVID-19: A Supervised Learning Approach,” MDPI Sensors, 2021.
S. Khalid et al., "Dynamic Substitution and Confusion-Diffusion Based Noise-resistive Image Encryption Using Multiple Chaotic Maps,” IEEE Access, 2021.
S. Khalid et al., "The Extended Model Predictive-Sliding Mode Control of Three-Level AC/DC Power Converters with Output Voltage and Load Resistance Variations,” Systems Science and Control Engineering, Taylor and Francis, 2021.
S. Khalid et al., “Design of Highly Selective Dual Band Band Stop Filter using Dual-Path Step Impedance Resonator,” 3rd Asia Pacific International Conference on Emerging Engineering, Karachi, Pakistan, 2021.
S. Khalid et al., "Polarization insensitive penta bandstop frequency selective surface for closely placed bands,” Microwave and Optical Technology Letters, Aug 2020.
S. Khalid et al., "A Novel Technique to Diagnose Sleep Apnea in Suspected Patients using their ECG Data,” IEEE Access, 2019.
S. Khalid et al., "Design of tri-band bandpass filter using symmetrical open stub loaded step impedance resonator,” Electronics Letter, 2018.
S. Khalid et al., "Exact synthesis design theory of analogue broadband bandpass filter,” Microelectronics Journal, 64, pp. 53-59, 2017.
S. Khalid et al., “Design of highly selective ultra-wideband (UWB) bandpass filter using step impedance resonator and parallel coupled lines,” IEEE Symposium on Recent Advances in Electrical Engineering (RAEE), Islamabad, Pakistan, 2015.
S. Khalid et al., "Optimum filter synthesis procedure for ultra-wideband bandpass filter using step-impedance resonator,” Journal of Electromagnetic Waves and Applications, 28.8, pp. 943-955, 2014.
S. Khalid et al., "Synthesis design of UWB bandpass filter using multiple resonances resonator (MRR),” Electronics Letters, 50.24, pp. 1851-1853, 2014.
S. Khalid et al., "A novel synthesis procedure for ultra wideband (UWB) bandpass filters,” Progress in Electromagnetic Research (PIER), vol. 141, pp. 249-266, 2013.
S. Khalid et al., “Highly selective, compact ultra-wideband bandpass filter using a novel multiple resonances resonator (MRR),” International Microwave Symposium Digest (IMS), Seattle, USA, 2013.
S. Khalid et al., “Design of Highly Selective Ultra-Wideband Bandpass Filter Using Multiple Resonance Resonator,” IEEE RFM conference, Penang, Malaysia, 2013.
S. Khalid et al., “Synthesis and design of four pole Ultra-Wide Band (UWB) bandpass filter (BPF) employing multi-mode resonators (MMR)”, International Microwave Symposium Digest (IMS), Montreal, Canada, 2012.
S. Khalid et al., “A novel design technique for ultra-wideband (UWB) bandpass filter using step Impedance resonators (SIR)”, IEEE Asia-Pacific Conference on Applied Electromagnetic (APACE), Melaka, Malaysia, 2012.
S. Khalid et al., “Sleep apnea detection from heart rate variability data using a DWPT based technique”, 4th International Conference on Intelligent and Advanced Systems (ICIAS), Malaysia, 2012.
S. Khalid et al., “Analysis of ultra-wide bandpass filter,” National Postgraduate Conference (NPC), Malaysia, 2011.