Dr Haider Raza
-
Email
h.raza@essex.ac.uk -
Location
4B.528, Colchester Campus
-
Academic support hours
My Academic Support Hour is given as follows: 9:00 AM - 10:00 AM on Monday at my office 4B.528. 9:00 AM - 10:00 AM on Friday at my office 4B.528.
Profile
Biography
I am an India-born British computer scientist and currently working as a Senior Lecturer in Artificial Intelligence at the School of Computer Science and Electronic Engineering (CSEE), University of Essex (UoE). From Nov 2020 to Nov 2022, I worked as a Lecturer in CSEE, and from Nov 2017 to Nov 2022, I worked as a Post-doctoral Research Fellow at the Institute for Analytics and Data Science (IADS), UoE. Prior to joining UoE, I worked as a Post-Doctoral Research Officer in Machine Learning at The Farr Institute of Health Informatics Research, Swansea University, UK (July 2016 - Present). Before joining Swansea, I worked as a Post-Doctoral Research Assistant in Machine Learning for EEG-based Brain-Computer Interfacing at the Intelligent Systems Research Centre (ISRC), School of Computing and Intelligent Systems, Ulster University, UK (December 2015-June 2016). My doctoral (PhD) dissertation was under the supervision of Professor Girijesh Prasad and Dr Hubert Cecotti and looked at adaptive learning for modelling for non-stationary systems and its application to EEG-based brain-computer interfaces (October 2012-December 2015). I am deeply passionate about exploring the intersection of technology and healthcare. My research focuses on leveraging advanced algorithms and machine learning techniques to develop innovative solutions for diagnostic tools and treatment planning. Specifically, I lead Innovate UK-funded projects on creating algorithms that can analyze healthcare data, aiding in the early detection and monitoring of various health conditions such as developing state-of-the-art computer vision-based skin cancer detection models and forensics dentistry. One of my main interests lies in Brain-Computer Interfacing (BCI), where I apply machine learning to establish a direct communication pathway between the human brain and computers. This research has potential applications in assisting individuals with disabilities for neurorehabilitation purposes. Furthermore, I actively investigate how technology, particularly machine learning and explainable AI (xAI), can be utilized to improve decision-making processes in healthcare. I strive to make advancements in understanding non-stationary learning, crucial for adapting AI models to ever-changing real-world data, ultimately aiming to enhance healthcare practices. In essence, my research pursuits stand at the forefront of AI and technology, with a clear goal of revolutionizing healthcare to make it more efficient, accessible, and beneficial for all.
Qualifications
-
PhD University of Ulster, (2016)
-
Master of Technology Manav Rachna International University, (2011)
-
Bachelor of Technology Integral University, (2008)
Appointments
University of Essex
-
Lecturer, School of Computer Science and Electronics Engineering, University of Essex (15/11/2020 - present)
-
IADS Postdoctoral Research Fellow, School of Computer Science and Electronics Engineering, University of Essex (21/11/2017 - 14/11/2020)
Other academic
-
Post-Doctorate Research Officer, Medical School, Swansea University (1/7/2016 - 20/11/2017)
-
Research Assistant in Brain-Computer Interfacing, School of Computing and Intelligent Systems, University of Ulster (7/12/2015 - 30/6/2016)
-
Visiting Researcher, Center of Mechantronics, Indian Institute of Technology Kanpur (6/4/2015 - 16/7/2015)
-
Assistant Professor, School of Computer Science, Dilla University (3/10/2011 - 31/8/2012)
-
Lecturer, Department of Information Technology, Manav Rachna International University (1/7/2009 - 30/9/2011)
Research and professional activities
Research interests
Agentic AI
My interest in Agentic AI stems from its potential to move beyond static, task-specific models towards autonomous, goal-driven systems capable of reasoning, planning, and adaptive decision-making. Unlike traditional AI pipelines, agentic systems integrate perception, memory, tool use, and iterative feedback to operate in dynamic, real-world environments. I am particularly interested in designing scalable agent architectures that combine large language models with symbolic reasoning, reinforcement learning, and structured knowledge. Agentic AI offers transformative opportunities across healthcare, education, and enterprise automation. My focus is on developing robust, trustworthy, and deployable agentic systems that deliver measurable impact while ensuring transparency, safety, and human alignment.
Brain-Computer Interface
My interest and contribution in Brain-Computer Interface (BCI) research centre on developing intelligent systems that translate neural signals into meaningful actions for communication, rehabilitation, and assistive technologies. I have worked on EEG/MEG-based signal processing, adaptive learning algorithms, and robust classification models to improve decoding accuracy in non-invasive BCI systems. My focus lies in enhancing real-time performance, reducing noise sensitivity, and integrating AI-driven adaptive mechanisms to create reliable, user-centred neurotechnology solutions.
Deep Learning, Generative AI, and Large Language Models (LLMs)
Deep Learning, Generative AI, and Large Language Models (LLMs) lies in advancing intelligent systems capable of learning rich representations, reasoning over complex data, and generating human-like outputs. I am particularly fascinated by transformer architectures, multimodal learning, and foundation models that can be adapted across domains. Beyond model performance, I focus on efficiency, robustness, and responsible deployment in real-world settings. Generative AI opens new possibilities in healthcare analytics, education, and enterprise automation, enabling creativity, simulation, and decision support at scale. My goal is to design scalable, trustworthy, and domain-adapted deep learning systems that bridge cutting-edge research with measurable societal and industrial impact.
Computer Vision and Domain Adaptation
Computer Vision and Domain Adaptation lies in building intelligent systems that remain reliable across diverse, real-world environments. While state-of-the-art vision models often perform well on benchmark datasets, their performance can degrade significantly when deployed in new domains with distribution shifts. I am particularly interested in developing robust, generalisable models that adapt across variations in lighting, devices, populations, and data quality. My focus includes transfer learning, self-supervised learning, and domain-invariant representation learning to improve performance in healthcare imaging and other safety-critical applications. By advancing domain adaptation techniques, I aim to bridge the gap between research prototypes and dependable, real-world computer vision deployment.
Non-Stationary Learning and Domain Adaptation
Non-Stationary Learning and Domain Adaptation focuses on developing intelligent systems that remain robust under evolving data distributions and real-world uncertainty. Many deployed AI models face performance degradation due to concept drift and distribution shift. I am particularly interested in adaptive learning algorithms, online learning strategies, and domain-invariant representation techniques that enable continual model refinement. My goal is to design resilient AI systems capable of sustained accuracy across dynamic, safety-critical environments.
Artificial Intelligence (AI) and eXplainable AI (XAI)
Artificial Intelligence (AI) and eXplainable AI (XAI) focuses on developing intelligent systems that are not only powerful but also transparent, trustworthy, and accountable. As AI increasingly influences high-stakes domains such as healthcare, finance, and public services, understanding how models reach their decisions becomes essential. I am particularly interested in interpretable machine learning, post-hoc explanation techniques, and inherently explainable model design. My work emphasises fairness, robustness, and regulatory compliance, ensuring that AI systems support responsible innovation. By integrating explainability into the model development lifecycle, I aim to build AI solutions that earn user trust and enable informed human oversight and decision-making.
EEG and MEG Signal Processing
AI in Decision Making for Healthcare
AI for Decision Making in Healthcare centres on developing intelligent systems that enhance clinical judgement, improve patient outcomes, and support safe, data-driven care pathways. Healthcare environments are complex, uncertain, and high-stakes, requiring models that are accurate, interpretable, and robust. I am particularly interested in combining machine learning with statistical modelling and causal reasoning to support diagnosis, risk stratification, and treatment optimisation. Ensuring fairness, transparency, and regulatory compliance is central to my approach. By integrating multimodal data such as imaging, physiological signals, and electronic health records, I aim to build trustworthy AI systems that meaningfully augment clinical decision-making rather than replace it.
Teaching and supervision
Current teaching responsibilities
-
Team Project Challenge (CE101)
-
Data Science and Decision Making (CE888)
Current supervision
Publications
Publications (1)
Raza, H., Ali, M., Singh, VK., Wahjuningrum, A., Sarig, R. and Chaurasia, A., (2024). Segmentation of Mental Foramen in Orthopantomographs: A Deep Learning Approach
Journal articles (22)
Islam, S., Wishart, GC., Walls, J., Hall, P., Seco de Herrera, AG., Gan, JQ. and Raza, H., (2026). Advancing Skin Cancer Detection through Deep Learning and Fusion of Patient Metadata and Skin Lesion Images. Scientific Reports. 16 (1), 1968-
Islam, S., Wishart, GC., Walls, J., Hall, P., Herrera, AGSD., Gan, JQ. and Raza, H., (2024). Leveraging AI and Patient Metadata to Develop a Novel Risk Score for Skin Cancer Detection. Scientific Reports. 14 (1), 20842-
Uroko, JB., Gu, D., Raza, H. and Hu, L., (2024). Enhancing gait parameter analysis for Cerebral Palsy using Attention modules. Gait & Posture. 113, 225-226
Roy, S., Gaur, V., Raza, H. and Jameel, S., (2023). CLEFT: Contextualised Unified Learning of User Engagement in Video Lectures with Feedback. IEEE Access. 11, 17707-17720
Singh, VK., Tripathi, G., Ojha, A., Bhardwaj, R. and Raza, H., (2023). Graph Laplacian for Heterogeneous Data Clustering in Sensor-Based Internet of Things. IETE Journal of Research. 70 (3), 2615-2627
Nara, S., Raza, H., Manuel, C. and Molinaro, N., (2023). Decoding Numeracy and Literacy in the Human Brain: Insights from MEG and MVPA. Scientific Reports. 13 (1), 10979-
Pandey, D., Raza, H. and Bhattacharyya, S., (2023). Development of explainable AI based predictive models for bubbling fluidised bed gasification process. Fuel. 351, 128971-128971
Singh, VK., Singh, C. and Raza, H., (2022). Event Classification and Intensity Discrimination for Forest Fire Inference With IoT. IEEE Sensors Journal. 22 (9), 8869-8880
Raza, H., Rathee, D., Roy, S. and Prasad, G., (2021). A magnetoencephalography dataset for motor and cognitive imagery-based brain–computer interface. Scientific Data. 8 (1), 120-
Bhattacharyya, S., Konar, A., Raza, H. and Khasnobish, A., (2021). Editorial: Brain-Computer Interfaces for Perception, Learning, and Motor Control. Frontiers in Neuroscience. 15, 758104-
Hemingway, H., Lyons, R., Li, Q., Buchan, I., Ainsworth, J., Pell, J. and Morris, A., (2020). national initiative in data science for health: an evaluation of the UK Farr Institute. International Journal of Population Data Science. 5 (1), 1128-
Raza, H., Rathee, D., Zhou, S-M., Cecotti, H. and Prasad, G., (2019). Covariate shift estimation based adaptive ensemble learning for handling non-stationarity in motor imagery related EEG-based brain-computer interface. Neurocomputing. 343, 154-166
Chowdhury, A., Raza, H., Meena, YK., Dutta, A. and Prasad, G., (2019). An EEG-EMG Correlation-based Brain-Computer Interface for Hand Orthosis Supported Neuro-Rehabilitation. Journal of Neuroscience Methods. 312, 1-11
Raza, H., Zhou, S., Todd, S., Christian, D., Merchant, E., Morgan, K., Khanom, A., Hill, R., Lynos, R. and Brophy, S., (2019). Predictors of Objectively Measured Physical Activity in 12 month-Old Infants: A Study of Linked Birth Cohort Data with Electronic Health Records. Pediatric Obesity. 14 (7), e12512-
Devi, SJ., Singh, B. and Raza, H., (2019). Link Prediction Evaluation Using Palette Weisfeiler-Lehman Graph Labelling Algorithm. International Journal of Knowledge and Systems Science. 10 (1), 1-20
Chowdhury, A., Raza, H., Meena, YK., Dutta, A. and Prasad, G., (2018). Online Covariate Shift Detection based Adaptive Brain-Computer Interface to Trigger Hand Exoskeleton Feedback for Neuro-Rehabilitation. IEEE Transactions on Cognitive and Developmental Systems. 10 (4), 1070-1080
Chowdhury, A., Meena, YK., Raza, H., Bhushan, B., Uttam, AK., Pandey, N., Hashmi, AA., Bajpai, A., Dutta, A. and Prasad, G., (2018). Active Physical Practice Followed by Mental Practice Using BCI-Driven Hand Exoskeleton: A Pilot Trial for Clinical Effectiveness and Usability. IEEE Journal of Biomedical and Health Informatics. 22 (6), 1786-1795
Raza, H., Zhou, S., Hill, R., Lyons, RA. and Brophy, S., (2017). Identification of predictors of objectively measured physical activity in 12-month-old British infants: a machine learning driven study. The Lancet. 390, S74-S74
Rathee, D., Raza, H., Prasad, G. and Cecotti, H., (2017). Current Source Density Estimation Enhances the Performance of Motor-Imagery-Related Brain–Computer Interface. IEEE Transactions on Neural Systems and Rehabilitation Engineering. 25 (12), 2461-2471
Raza, H., Cecotti, H., Li, Y. and Prasad, G., (2016). Adaptive learning with covariate shift-detection for motor imagery-based brain–computer interface. Soft Computing. 20 (8), 3085-3096
Raza, H., Prasad, G. and Li, Y., (2015). EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments. Pattern Recognition. 48 (3), 659-669
Singh, B., Raza, H. and Ritu, M., (2010). GBG Approach for Connectivity and Coverage Control in Wireless Sensor Network. International Journal of Computer Applications. 16 (3), 13-18
Books (4)
Tanwar, P., Kumar, T., Kalaiselvi, K., Raza, H., Rawat, S. and Raza, H., (2024). Predictive data modelling for biomedical data and imaging. River Publishers. 9788770040778
Raza, H., Arvaneh, M., Tanaka, T., Nakanishi, M. and Ward, TE., (2023). Machine learning and signal processing for neurotechnologies and brain-computer interactions out of the lab. Frontiers in Neuroergonomics
Kalaiselvi, K., Anand, AJ., Tanwar, P. and Raza, H., (2023). Advanced Technologies for Smart Agriculture
Bhattacharyya, S., Konar, A., Raza, H. and Khasnobish, A., (2021). Brain-Computer Interfaces for Perception, Learning, and Motor Control. Frontiers Media SA. 2889718514. 9782889718511
Book chapters (2)
Liu, C., Raza, H. and Bhattacharyya, S., (2023). Deep learning methods for analysis of neural signals: From conventional neural network to graph neural network. In: Advanced Methods in Biomedical Signal Processing and Analysis. Elsevier. 205- 242. 9780323859554
Raza, H. and Rathee, D., (2018). Covariate shift detection-based nonstationary adaptation in motor-imagery-based brain–computer interface. In: Signal Processing and Machine Learning for Brain-Machine Interfaces. Editors: Tanaka, T. and Arvaneh, M., . Institution of Engineering and Technology. 125- 141. 9781785613982
Conferences (35)
Ali, M., Raza, H., Gan, J. and Khan, MH., FocusViT: Faithful Explanations for Vision Transformers via Gradient-Guided Layer-Skipping
Haider, MH., Raza, H., Filder, A., Koya, R. and Chaurasia, A., A Multi-Model Ensemble YOLO Framework for Automated Detection of Dental Pathologies in Low- Quality Panoramic Radiographs
Ali, M., Raza, H. and Gan, J., (2025). Optimising Vision Transformer Performance on Limited Datasets: A Multi-Gradient Approach
Heroza, RI., Raza, H. and Gan, J., (2025). FedCIAL: Federated Color-Invariant Adversarial Learning for Enhancing Fairness and Performance in Skin Lesion Classification
Shajimon, GM., Ufumaka, I. and Raza, H., (2024). An Improved Vision-Transformer Network for Skin Cancer Classification
Sarma, M., Bond, C., Nara, S. and Raza, H., (2024). MEGNet: A MEG-Based Deep Learning Model for Cognitive and Motor Imagery Classification
Ali, M., Hassan, M., Esra, K., Gan, J. and Raza, H., (2024). Enhancing Dental Diagnostics: Advanced Image Segmentation Models for Teeth Identification and Enumeration
Izwan Heroza, R., Gan, JQ. and Raza, H., (2024). Enhancing Skin Lesion Classification: A Self-Attention Fusion Approach with Vision Transformer
Raza, H., Rathee, D., Amorim, R. and Fasli, M., (2024). Optimizing Patient Care Pathways: Impact Analysis of an AI-Assisted Smart Referral System for Musculoskeletal Services
Islam, MS., Wishart, G., Walls, J., Hall, P., Garcia, A., Gan, J. and Raza, H., (2024). Unlocking the Potential of Patient Metadata for Skin Cancer Detection: An AI Framework
Ali, M., Raza, H. and Gan, JQ., (2024). Fortifying Deep Neural Networks for Industrial Applications: Feature Map Fusion for Adversarial Defense
Islam, S., Walls, J., Hall, P., Raza, H., Gan, J., Garcia, A. and Wishart, G., (2024). P028 The importance of clinical metadata when triaging patients for face-to-face assessment and possible biopsy in a teledermatology pathway
Islam, S., Walls, J., Hall, P., Raza, H., Gan, J., Garcia, A. and Wishart, G., (2024). BT13 (P028) The importance of clinical metadata when triaging patients for face-to-face assessment and possible biopsy in a teledermatology pathway
Ali, M., Raza, H., Gan, JQ. and Haris, M., (2024). Integrating Spatial Information into Global Context: Summary Vision Transformer (S-ViT)
Islam, MS., Walls, J., Hall, P., Raza, H., Gan, J., Garcia, A. and Wishart, G., (2024). AI model for accurate skin lesion classification during telemedicine triage of suspicious skin lesions
Islam, MS., Walls, J., Hall, P., Raza, H., Gan, J., Garcia, A. and Wishart, G., (2024). Machine learning techniques to develop a new risk score for urgent referral of all skin cancer subtypes
Izwan Heroza, R., Raza, H. and Gan, J., (2023). SIA-SMOTE: A SMOTE-based Oversampling Method with Better Interpolation on High-Dimensional Data by Using a Siamese Network
Barry, E., Jameel, S. and Raza, H., (2022). Emojional: Emoji Embeddings
Raza, H., Chowdhury, A., Bhattacharyya, S. and Samothrakis, S., (2020). Single-Trial EEG Classification with EEGNet and Neural Structured Learning for Improving BCI Performance
Raza, H., Chowdhury, A. and Bhattacharyya, S., (2020). Deep Learning based Prediction of EEG Motor Imagery of Stroke Patients' for Neuro-Rehabilitation Application
Raza, H. and Samothrakis, S., (2019). Bagging Adversarial Neural Networks for Domain Adaptation in Non-Stationary EEG
Chowdhury, A., Raza, H., Dutta, A. and Prasad, G., (2017). EEG-EMG based Hybrid Brain Computer Interface for Triggering Hand Exoskeleton for Neuro-Rehabilitation
Raza, H., Cecotti, H. and Prasad, G., (2016). A combination of transductive and inductive learning for handling non-stationarities in motor imagery classification
Raza, H., Chowdhury, A., Dutta, A. and Prasad, G., (2015). Cortico-Muscular-Coupling and Covariate Shift Adaptation based BCI for Personalized Neuro- Rehabilitation of Stroke Patients
Raza, H., Cecotti, H., Li, Y. and Prasad, G., (2015). Learning with Covariate Shift-Detection and Adaptation in Non-Stationary Environments : Application to Brain-Computer Interface
Raza, H., Cecotti, H. and Prasad, G., (2015). Optimising Frequency Band Selection with Forward-Addition and Backward-Elimination Algorithms in EEG-based Brain-Computer Interfaces
Chowdhury, A., Raza, H., Dutta, A., Nishad, SS., Saxena, A. and Prasad, G., (2015). A Study on Cortico-muscular Coupling in Finger Motions for Exoskeleton Assisted Neuro-Rehabilitation
Raza, H., Prasad, G., Li, Y. and Cecotti, H., (2014). Covariate shift-adaptation using a transductive learning model for handling non-stationarity in EEG based brain-computer interfaces
Raza, H., Prasad, G., Li, Y. and Cecotti, H., (2014). Toward Transductive Learning Classifiers for Non-Stationary EEG
Raza, H., Prasad, G. and Li, Y., (2014). Adaptive Learning with Covariate Shift- Detection for Non-Stationary Environments
O Doherty, D., Meena, YK., Raza, H., Cecotti, H. and Prasad, G., (2014). Exploring gaze-motor imagery hybrid brain-computer interface design
Raza, H., Prasad, G. and Li, Y., (2014). Adaptive Learning with Covariate Shift-Detection for Non-Stationary Environments
Raza, H., Prasad, G. and Li, Y., (2013). Dataset shift detection in non-stationary environments using EWMA charts
Raza, H., Prasad, G. and Li, Y., (2013). EWMA based two-stage dataset shift-detection in non-stationary environments
Raza, H., Nandal, P. and Makker, S., (2010). Selection of cluster-head using PSO in CGSR protocol
Patents (1)
Raza, H., Islam, S., Wishart, G. and Gan, J., A METHOD FOR CLASSIFYING SKIN LESIONS
Grants and funding
2026
Cybersecurity Audit & Framework for Ginger Nut Media Ltd
University of Essex
2025
The University of Essex and Unisurge International Limited KTP 24_25 R5: 'To revolutionise the medical supply industry by developing a demand prediction model for surgical procedure packs'.
Innovate UK (formerly Technology Strategy Board)
To research public discourse on farming and nature, to ensure better understanding of evidence-based narratives, using different technologies.
Innovate UK (formerly Technology Strategy Board)
To transform business operations and processes by leveraging AI and data insights.
Storm Technologies Limited
AI for Oral Health: Exploring Mobile-Based Artificial Intelligence for Early Screening of Oral Pre-Cancer and Cancer
The Royal Society
To develop an AI-enabled biomarker discovery engine, using multi-modal data, to address growing demand in the precision medicine market for disease risk prediction services.
Innovate UK (formerly Technology Strategy Board)
2024
Check4Cancer BBSRC IAA Enhancing Skin Cancer Detection: AI Model Performance Across Diverse Skin Types
University of Essex (BBSRC IAA)
2023
Advanced Innovation Insights Ltd - IUK funded part of project. The project will develop a minimum viable product delivering the core functionality needed to provide the insights and recommendations based on both the patent and company data analysis
Advanced Innovation Insights Ltd
Advanced Innovation Insights Ltd - IV funded part of project. The project will develop a minimum viable product delivering the core functionality needed to provide the insights and recommendations based on both the patent and company data analysis
Advanced Innovation Insights Ltd
To develop the next generation of an existing software package into a highlyinnovative, AI-enabled platform suitable for a first widescale commercialisation.
Innovate UK (formerly Technology Strategy Board)
Eastern Region Advanced Data Sharing Project: MHCLG Local Data Accelerator Fund for Children and Families application (Hertfordshire) v2
Ministry of Housing, Communities and Local Government
To design and incorporate machine learning capabilities and robotic process automation tools into the administrative workflow of a traditionally-structured manufacturing and supply organisation.
Innovate UK (formerly Technology Strategy Board)
2022
Check4Cancer KTP Application (February 2022 submission).
Innovate UK (formerly Technology Strategy Board)
Brightstar Financial KTP Application - 2021 Submission
Innovate UK (formerly Technology Strategy Board)
2020
Unravelling the Forest Fires in Lower Himalayan Forests: A Comprehensive Study of Indian Forest Regions of Uttarakhand using IoT technology
University of Essex (GCRF)
Two-Way Visiting Fellowship with Indian colleague
University of Essex (GCRF)
Check4Cancer skin cancer AI model
Check4Cancer
Mersea Homes KTP application
Innovate UK (formerly Technology Strategy Board)
Check4Cancer skin cancer AI model
Check4Cancer
2019
The development of a new CPD tracker using AI and embedded machine learning to track and enhance performance of all staff.
Innovate UK (formerly Technology Strategy Board)
AI-Assisted Decision-Making System for Cancer Pathways of the Colchester Hospital
East Suffolk and North Essex NHS Foundation Trust
Maji - AI powered chatbot
Maji Financial Wellbeing Ltd
2018
Business and Local Government Data Research Centre (BLG DRC)
Economic and Social Research Council
Provide KTP 2018
Innovate UK (formerly Technology Strategy Board)
Business and Local Government Data Research Centre (BLG DRC)
Economic and Social Research Council
Provide KTP 2018
Innovate UK (formerly Technology Strategy Board)
Contact
Academic support hours:
My Academic Support Hour is given as follows: 9:00 AM - 10:00 AM on Monday at my office 4B.528. 9:00 AM - 10:00 AM on Friday at my office 4B.528.