Rab Nawaz

Dr. Rab Nawaz

Computer Science and Electronic Engineering, University of Essex, Colchester, Essex, UK

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2020 in Biocybernetics and Biomedical Engineering
Verified
Journal Article
Closed access
Rab NawazRab Nawaz
Rab Nawaz
KCKit Hwa Cheah
Kit Hwa Cheah
Humaira NisarHumaira Nisar
Humaira Nisar
VYVooi Voon Yap
Vooi Voon Yap

20 July 2018 in IEEE Access
Verified
Journal Article
Open access
Rab NawazRab Nawaz
Rab Nawaz
Humaira NisarHumaira Nisar
Humaira Nisar
YVYap Vooi Voon
Yap Vooi Voon
The aim of this paper is to investigate the effect of music stimuli on human brain using electroencephalogram (EEG). The study comprises of two experiments, a short term and a long term experiment referred to as experiment 1 and experiment 2, respectively. Two types of music stimuli; favorite music (preferred music of the subjects) and relaxing music (composed of alpha binaural beats) are used in experiment 1. Experiment 2 is conducted using relaxing music. Assessment of soothing effects of the music on human brain is done by analyzing different features; absolute power in alpha band, approximate entropy, sample entropy, and frontal asymmetry using EEG recordings. The ANOVA measures for the extracted features indicated no significant change in experiment 1. In experiment 2, the features are evaluated for the music listening group and control group separately. From ANOVA results, no significant change is observed in the control group after both conditions (1 st week and 2 nd week) with respect to the baseline. On the other hand, significant change was observed in the music listening group, for all features investigated; (a) absolute alpha power: condition (baseline and 1 st week) F = 4.59, P <; 0.05, condition (baseline and 2 nd week) F = 18.87, P <; 0.05 (b) approximate entropy: condition (baseline and 2 nd week) F = 30.62, P <; 0.05 (c) sample entropy: condition (baseline and 1 st week) F = 4.75, P <; 0.05, condition (baseline and 2 nd week) F = 38.37, P <; 0.05. For inter-hemispheric alpha asymmetry index measured from the frontal region of the brain; no significant change is observed in both experiments. Hence, the main contribution of this study is to investigate the EEG dynamics under different music stimuli. The results indicate that relaxing music has better soothing effects as compared to the favorite music. It is also observed that the effect of relaxation is significant when the relaxing music is listened for a longer period of time (2 weeks).

29 March 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
Rab NawazRab Nawaz
Rab Nawaz
Humaira NisarHumaira Nisar
Humaira Nisar
VYVooi Voon Yap
Vooi Voon Yap
Chi-Yi TsaiChi-Yi Tsai
Chi-Yi Tsai
This study investigates the effect of long-term alpha neurofeedback training (NFT) in healthy adults using music stimuli. The optimal protocol for future research is presented in this study. The data from 40 healthy participants, divided into two groups (NFT group and Control group), were analyzed in the current study. We found a significantly enhanced alpha rhythm after training in the NFT group which was not observed in the control group. The immediate subsequent effects were greater in more than 80% of the sessions from the initial recordings. Stroop task and behavioral questionnaires, mini-mental state exam (MMSE), and perceived stress scale (PSS) did not reveal any training-specific changes. Within-training session effects were significant from the baseline and were more pronounced at the beginning of the session as compared to the end of the session. It is also observed that a shorter session length with multiple sessions may be more effective than a long and continuous run of a single session.

1 October 2024 in Neural Networks
Verified
Journal Article
Open access
FAFarhatullah
Farhatullah
XCXin Chen
Xin Chen
DZDeze Zeng
Deze Zeng
Rahmat UllahRahmat Ullah
Rahmat Ullah
Rab NawazRab Nawaz
Rab Nawaz
TATughrul Arslan
Tughrul Arslan
Over 50 million people globally suffer from Alzheimer’s disease (AD), emphasizing the need for efficient, early diagnostic tools. Traditional methods like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) scans are expensive, bulky, and slow. Microwave-based techniques offer a cost-effective, non-invasive, and portable solution, diverging from conventional neuroimaging practices. This article introduces a deep learning approach for monitoring AD , using realistic numerical brain phantoms to simulate scattered signals via the CST Studio Suite. The obtained data is preprocessed using normalization, standardization, and outlier removal to ensure data integrity. Furthermore, we propose a novel data augmentation technique to enrich the dataset across various AD stages. Our deep learning approach combines Recursive Feature Elimination (RFE) with Principal Component Analysis (PCA) and Autoencoders (AE) for optimal feature selection. Convolution Neural Network (CNN) is combined with Gated Recurrent Unit (GRU), Bidirectional Long Short Term Memory (Bidirectional-LSTM), and Long Short-Term Memory (LSTM) to improve classification performance. The integration of RFE-PCA-AE significantly elevates performance, with the CNN+GRU model achieving an 87% accuracy rate, thus outperforming existing studies.

28 July 2020 in IEEE Access
Verified
Journal Article
Open access
Rab NawazRab Nawaz
Rab Nawaz
Humaira NisarHumaira Nisar
Humaira Nisar
YVYap Vooi Voon
Yap Vooi Voon
Neurofeedback training (NFT) teaches self-control of brain activity to the subjects by measuring brain waves and providing a feedback signal in real time. NFT is considered to be a promising tool for healthy people to enhance cognition, however its specific effects on response-conflict are unknown. This study employed 50 healthy participants into two groups (NFT group = 25, control group = 25), in order to explore the NFT effects towards response-conflict resolution phenomenon. Changes in Absolute power and functional connectivity in different bands of response-conflict EEG, were investigated. The EEG of each participant was recorded while performing a response-conflict task before and after NFT. The results show an increase in theta and alpha band powers and functional connectivity. No training specific modulation is observed in beta band functional connectivity. A significant improvement in theta and alpha band functional connectivity is observed in the NFT group that is not present in the control group. These findings provide a strong rationale for the use of NFT in the resolution of response-conflict phenomenon in healthy human beings.

3 December 2025 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
IAIjaz Ahmad
Ijaz Ahmad
SASarra Ayouni
Sarra Ayouni
FAFaizan Ahmad
Faizan Ahmad
HLHaiying Li
Haiying Li
SASunday Timothy Aboyeji
Sunday Timothy Aboyeji
BLBaiying Lei
Baiying Lei
Epilepsy is a chronic neurological disorder that significantly affects the quality of life (QoL), often causing irreversible brain damage and physical impairment. Electroencephalography (EEG) signal analysis is crucial for monitoring epilepsy, enabling early seizure detection and timely intervention. Effective seizure detection requires the identification of interpretable features from the EEG signal to improve clinical outcomes. This study proposes a novel interpretable multi-view feature learning approach (IMV-FL), in which the time-domain signals and Discrete Fourier Transform (DFT) are applied to convert the time-domain EEG signal into frequency-domain representations. To develop initial multiview feature extraction and compression, spatial and temporal morphological features are extracted from optimal layers of ResNet and Long Short-Term Memory (LSTM) models, with feature compression performed using a Deep Neural Network (DNN). To construct an interpretable multi-view feature fusion, linear and nonlinear properties are calculated for the feature and with fusion strategies. The selected features are processed using the Mutual Information-Based Feature (MIBF) selection algorithm, and a Stacking Ensemble Classifier (SAEC) is adopted for unified view classification. To enhance clinical interpretability, SHapley Additive exPlanations (SHAP) is applied. The proposed framework outperforms single-view feature learning methods by 3% on average and state-of-the-art techniques by 2% in classification accuracy, sensitivity, specificity, and F1-score using the CHB-MIT Scalp and Bonn EEG datasets. This approach offers an effective tool for EEG-based seizure detection (ESD) in clinical and healthcare settings.