Machine Learning; Biometrics; Biomedical Signal Analysis
58
Scopus Publications
1444
Scholar Citations
22
Scholar h-index
34
Scholar i10-index
Scopus Publications
Transformer-based deep learning approach for obstructive sleep apnea detection using single-lead ECG Malak Abdullah Almarshad, Saad Al-Ahmadi, Saiful Islam, Adel Soudani, Ahmed S. BaHammam Frontiers in Artificial Intelligence, 2026 Obstructive sleep apnea (OSA) results from repeated collapses of the upper airway during sleep, which can lead to serious health complications. Although polysomnography (PSG) is the diagnostic gold standard, it is costly, labor-intensive, and associated with long waiting times. With the rapid evolution of automated scoring solutions and the emergence of machine learning (ML) and deep learning (DL) in many disciplines, there is a need for tools that use fewer signals and can provide accurate diagnoses. DL models can an process large amounts of data and often generalize effectively to new instances. This makes them a suitable choice for classifying continuous time series data. This study introduces a transformer-based deep learning approach using a single-lead electrocardiogram (ECG) for OSA detection. The proposed architecture, designed to handle raw signals with high sampling rates, preserves temporal continuity over unlimited durations. Without any preprocessing, the model tolerates high-noise raw data. The model is tested with different positional embedding techniques. Additionally, a novel positional encoding technique using an autoencoder is introduced. The proposed approach achieves a high F1 score, outperforming other published work by an average margin of more than 13%. In addition, the model classifies apnea episodes at one-second intervals, providing clinicians with nuanced insights.
Recent advances in the tools and techniques for AI-aided diagnosis of atrial fibrillation Saiful Islam, Md. Rashedul Islam, Sanjid-E-Elahi, Md. Anwarul Abedin, Tansel Dökeroğlu, Mahmudur Rahman Biophysics Reviews, 2025 Atrial fibrillation (AF) is recognized as a developing global epidemic responsible for a significant burden of morbidity and mortality. To counter this public health crisis, the advancement of artificial intelligence (AI)-aided tools and methodologies for the effective detection and monitoring of AF is becoming increasingly apparent. A unified strategy from the international research community is essential to develop effective intelligent tools and technologies to support the health professionals for effective surveillance and defense against AF. This review delves into the practical implications of AI-aided tools and techniques for AF detection across different clinical settings including screening, diagnosis, and ambulatory monitoring by reviewing the revolutionary research works. The key finding is that the advance in AI and its use for automatic detection of AF has achieved remarkable success, but collaboration between AI and human intelligence is required for trustworthy diagnostic of this life-threatening cardiac condition. Moreover, designing efficient and robust intelligent algorithms for onboard AF detection using portable and implementable computing devices with limited computation power and energy supply is a crucial research problem. As modern wearable devices are equipped with sophisticated embedded sensors, such as optical sensors and accelerometers, hence photoplethysmography and ballistocardiography signals could be explored as an affordable alternative to electrocardiography (ECG) signals for AF detection, particularly for the development of low-cost and miniature screening and monitoring devices.
Secure Watermarking Using Adaptive QIM with Local Coefficient Magnitudes in the Frequency Domain with PUF-based Encryption Nayeem Hasan, Saiful Islam, Tahmina Begum 2025 International Symposium on Networks Computers and Communications Isncc 2025, 2025 In this paper, we propose a robust and blind image watermarking scheme based on Quantization Index Modulation (QIM), utilizing Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT). The method adaptively adjusts the watermark bit strength with proper pixel value modification, embedding it into the middle-frequency band of DCT coefficients and selected DWT subbands. The embedding strength is dynamically tuned based on local coefficient magnitudes, ensuring minimal visual distortion while maintaining high resistance to common image processing attacks-particularly filtering, compression, and noise. To improve security and unpredictability-unlike traditional random bit generators with fixed seeds-our proposal uses a Physical Unclonable Function (PUF) device, which provides a hardware-rooted source of entropy that is extremely difficult for attackers to predict. This approach dynamically inserts watermark bits, satisfying all core properties of a robust watermarking benchmark. The proposed method is fully blind, and the experimental results show an outstanding Peak Signal-to-Noise Ratio (PSNR $\gt80 \mathrm{~dB}$), making our scheme a powerful method in terms of robustness and imperceptibility. Additionally, the Structural Similarity Index (SSIM) reaches near-perfect levels, and the Bit Correction Rate $(B C R=100 \%)$ confirms the method’s efficiency and visual fidelity.
Using Bio-Cryptographic Key Extracted from Heartprint Signal by a Deep Neural Network for Authentication Orkun Kocak, Saiful Islam, Onur Gumus, Gokce Nur Yilmaz Ichora 2025 2025 7th International Congress on Human Computer Interaction Optimization and Robotic Applications Proceedings, 2025 A cryptographic key extracted from a biometric sample could leverage the strength of both biometrics and cryptography simultaneously. However, the random nature of this bio-cryptographic key prevents it from being used in encryption directly. To address this problem, we present a novel authentication method employing bio-cryptographic key extracted from heartprint (ECG signal) by using a Siamese Neural Network (SNN). We have used a public dataset of heartprints obtained from the fingers of 199 users. The extracted keys have demonstrated excellent cryptographic and biometric characteristics. Experimental results show that bio-cryptographic keys with entropy ~1 achieve higher intra-similarity compared to inter-similarity. Cross-validation results show an average equal error rate (EER) of 0.02. These results underscore the robustness and feasibility of the bio-cryptographic key which can play a crucial role in preventing unauthorized access to digital content.
Person identification with arrhythmic ECG signals using deep convolution neural network Awabed Al-Jibreen, Saad Al-Ahmadi, Saiful Islam, Abdel Momin Artoli Scientific Reports, 2024 Over the past decade, the use of biometrics in security systems and other applications has grown in popularity. ECG signals in particular are attracting increased attention due to their characteristics, which are required for a trustworthy identification system. The majority of ECG-based person identification systems are evaluated without considering the health-state of the individuals. Few person identification systems consider person-by-person health-state annotation. This paper proposes a person identification system considering the health-state annotated ECG signals where each person’s beats overlap among variant arrhythmia classes. This overlapping between the normal class and other arrhythmia classes grants the ability to isolate normal beats in the train set from the Arrhythmic beats in the test set. Therefore, this paper investigates the effect of arrhythmic heartbeats on biometric recognition. An effective lightweight CNN based on depth-wise separable convolution (DWSC) is proposed to enhance the performance of person identification for several common arrhythmia types using the MITBIH dataset. The proposed methodology has been tested on nine arrhythmia types and presents how different types of arrhythmia affect ECG-based biometric systems differently. The experimental results show excellent recognition performance (99.28%) on normal heartbeats and (93.81%) on arrhythmic heartbeats, outperforming other models in terms of mean accuracy.
Biometrics-based Image Watermarking by Heartprint Signal Utku Oktay, Saiful Islam 2024 Innovations in Intelligent Systems and Applications Conference Asyu 2024, 2024 Biometries-based watermarking is getting attention in recent times to prevent unauthorized use of digital images. In this paper, we aim to examine the potential use of biometrics for the verification of ownership and authenticity of digital images by presenting a novel blind digital image watermarking technique. It utilizes a Siamese neural network for generating a binary key from heartprint biometrics followed by an embedding process of the bit sequence into the image in the frequency domain. The proposed method is evaluated for various attacks on the embedded image such as JPEG compression, filtering, and cropping to examine the robustness and reliability of the method. Experimental results showed that under different attacks on the watermarked image, the heartprint-based watermarking process achieved over 90% reliability while maintaining a reasonable PSNR value over 40 dB.
Measuring 3D Video Quality of Experience (QoE) Using A Hybrid Metric Based on Spatial Resolution and Depth Cues Sahin Coskun, Gokce Nur Yilmaz, Federica Battisti, Musaed Alhussein, Saiful Islam Journal of Imaging, 2023 A three-dimensional (3D) video is a special video representation with an artificial stereoscopic vision effect that increases the depth perception of the viewers. The quality of a 3D video is generally measured based on the similarity to stereoscopic vision obtained with the human vision system (HVS). The reason for the usage of these high-cost and time-consuming subjective tests is due to the lack of an objective video Quality of Experience (QoE) evaluation method that models the HVS. In this paper, we propose a hybrid 3D-video QoE evaluation method based on spatial resolution associated with depth cues (i.e., motion information, blurriness, retinal-image size, and convergence). The proposed method successfully models the HVS by considering the 3D video parameters that directly affect depth perception, which is the most important element of stereoscopic vision. Experimental results show that the measurement of the 3D-video QoE by the proposed hybrid method outperforms the widely used existing methods. It is also found that the proposed method has a high correlation with the HVS. Consequently, the results suggest that the proposed hybrid method can be conveniently utilized for the 3D-video QoE evaluation, especially in real-time applications.
Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea Malak Abdullah Almarshad, Saad Al-Ahmadi, Md Saiful Islam, Ahmed S. BaHammam, Adel Soudani Sensors, 2023 Scoring polysomnography for obstructive sleep apnea diagnosis is a laborious, long, and costly process. Machine learning approaches, such as deep neural networks, can reduce scoring time and costs. However, most methods require prior filtering and preprocessing of the raw signal. Our work presents a novel method for diagnosing obstructive sleep apnea using a transformer neural network with learnable positional encoding, which outperforms existing state-of-the-art solutions. This approach has the potential to improve the diagnostic performance of oximetry for obstructive sleep apnea and reduce the time and costs associated with traditional polysomnography. Contrary to existing approaches, our approach performs annotations at one-second granularity. Allowing physicians to interpret the model’s outcome. In addition, we tested different positional encoding designs as the first layer of the model, and the best results were achieved using a learnable positional encoding based on an autoencoder with structural novelty. In addition, we tried different temporal resolutions with various granularity levels from 1 to 360 s. All experiments were carried out on an independent test set from the public OSASUD dataset and showed that our approach outperforms current state-of-the-art solutions with a satisfactory AUC of 0.89, accuracy of 0.80, and F1-score of 0.79.
Deep Contrastive Learning-Based Model for ECG Biometrics Nassim Ammour, Rami M. Jomaa, Md Saiful Islam, Yakoub Bazi, Haikel Alhichri, Naif Alajlan Applied Sciences Switzerland, 2023 The electrocardiogram (ECG) signal is shown to be promising as a biometric. To this end, it has been demonstrated that the analysis of ECG signals can be considered as a good solution for increasing the biometric security levels. This can be mainly due to its inherent robustness against presentation attacks. In this work, we present a deep contrastive learning-based system for ECG biometric identification. The proposed system consists of three blocks: a feature extraction backbone based on short time Fourier transform (STFT), a contrastive learning network, and a classification network. We evaluated the proposed system on the Heartprint dataset, a new ECG biometrics multi-session dataset. The experimental analysis shows promising capabilities of the proposed method. In particular, it yields an average top1 accuracy of 98.02% on a new dataset built by gathering 1539 ECG records from 199 subjects collected in multiple sessions with an average interval between sessions of 47 days.
An evaluation of local image features for object class recognition Visapp 2010 Proceedings of the International Conference on Computer Vision Theory and Applications, 2010
A wireless sensor network for visual detection and classification of intrusions Wseas Transactions on Circuits and Systems, 2005
Towards invariant interest point detection of an object 13th International Conference in Central Europe on Computer Graphics Visualization and Computer Vision 2005 Wscg 2005 in Co Operation with Eurographics Full Papers, 2005
Detecting and matching interest points in relative scale Machine Graphics and Vision, 2005
RECENT SCHOLAR PUBLICATIONS
Transformer-based Deep Learning Approach for Obstructive Sleep Apnea Detection Using Single-lead ECG M Almarshad, S Al-Ahmadi, MS Islam, A Soudani, AS BaHammam Frontiers in Artificial Intelligence 9, 1727091 , 2026 2026
Secure Watermarking Using Adaptive QIM with Local Coefficient Magnitudes in the Frequency Domain with PUF-based Encryption N Hasan, S Islam, T Begum 2025 International Symposium on Networks, Computers and Communications … , 2025 2025
Using Bio-Cryptographic Key Extracted from Heartprint Signal by a Deep Neural Network for Authentication O Kocak, S Islam, O Gumus, GN Yilmaz 2025 7th International Congress on Human-Computer Interaction, Optimization … , 2025 2025
Recent advances in the tools and techniques for AI-aided diagnosis of atrial fibrillation S Islam, MR Islam, MA Abedin, T Dökeroğlu, M Rahman Biophysics Reviews 6 (1) , 2025 2025 Citations: 5
Biometrics-Based Image Watermarking by Heartprint Signal U Oktay, S Islam 2024 Innovations in Intelligent Systems and Applications Conference (ASYU), 1-6 , 2024 2024 Citations: 1
Person identification with arrhythmic ECG signals using deep convolution neural network A Al-Jibreen, S Al-Ahmadi, S Islam, AM Artoli Scientific Reports 14 (1), 4431 , 2024 2024 Citations: 25
Polysomnography Raw Data Extraction, Exploration, and Preprocessing MA Almarshad, S Islam, S Bahammam, S Al-Ahmadi, AS BaHammam Handbook of AI and Data Sciences for Sleep Disorders, 45 , 2024 2024 Citations: 2
Measuring 3D Video Quality of Experience (QoE) Using A Hybrid Metric Based on Spatial Resolution and Depth Cues S Coskun, G Nur Yilmaz, F Battisti, M Alhussein, S Islam Journal of Imaging 9 (12), 281 , 2023 2023 Citations: 6
Deep Contrastive Learning-Based Model for ECG Biometrics N Ammour, RM Jomaa, MS Islam, Y Bazi, H Alhichri, N Alajlan Applied Sciences 13 (5), 3070 , 2023 2023 Citations: 21
Adoption of Transformer Neural Network to Improve the Diagnostic Performance of Oximetry for Obstructive Sleep Apnea MA Almarshad, S Al-Ahmadi, MS Islam, AS BaHammam, A Soudani Sensors 23 (18), 7924 , 2023 2023 Citations: 23
Heartprint: A Dataset of Multisession ECG Signal with Long Interval Captured from Fingers for Biometric Recognition MS Islam, H Alhichri, Y Bazi, N Ammour, N Alajlan, RM Jomaa Data 7 (10), 141 , 2022 2022 Citations: 26
Multiscale Encoding of Electrocardiogram Signals with a Residual Network for the Detection of Atrial Fibrillation MN Alsaleem, MS Islam, S Al-Ahmadi, A Soudani Bioengineering 9 (9), 480 , 2022 2022 Citations: 8
Using ECG signal as an entropy source for efficient generation of long random bit sequences MS Islam Journal of King Saud University-Computer and Information Sciences 34 (8 … , 2022 2022 Citations: 15
A multilayer system to boost the robustness of fingerprint authentication against presentation attacks by fusion with heart-signal RM Jomaa, MS Islam, H Mathkour, S Al-Ahmadi Journal of King Saud University-Computer and Information Sciences 34 (8 … , 2022 2022 Citations: 22
HGSORF: Henry Gas Solubility Optimization-based Random Forest for C-Section prediction and XAI-based cause analysis MS Islam, MA Awal, JN Laboni, FT Pinki, S Karmokar, KM Mumenin, ... Computers in Biology and Medicine 147, 105671 , 2022 2022 Citations: 50
Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review MA Almarshad, MS Islam, S Al-Ahmadi, AS BaHammam Healthcare 10 (3), 547 , 2022 2022 Citations: 248
An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP K Debjit, MS Islam, MA Rahman, FT Pinki, RD Nath, S Al-Ahmadi, ... Diagnostics 12 (5) , 2022 2022 Citations: 58
Automatic labeling of twitter data for developing COVID-19 sentiment dataset KMA Hasan, SD Shovon, NH Joy, MS Islam 5th International Conference on Electrical Information and Communication … , 2021 2021 Citations: 8
Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition DA AlDuwaile, MS Islam Entropy 23 (6), 733 , 2021 2021 Citations: 93
Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains N Hasan, MS Islam, W Chen, MA Kabir, S Al-Ahmadi Sensors 21 (16), 5540 , 2021 2021 Citations: 50
MOST CITED SCHOLAR PUBLICATIONS
Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review MA Almarshad, MS Islam, S Al-Ahmadi, AS BaHammam Healthcare 10 (3), 547 , 2022 2022 Citations: 248
Multiomics Analysis Reveals that GLS and GLS2 Differentially Modulate the Clinical Outcomes of Cancer SK Saha, SMR Islam, M Abdullah-AL-Wadud, S Islam, F Ali, K Sik Park Journal of Clinical Medicine 8 (3) , 2019 2019 Citations: 112
Using Convolutional Neural Network and a Single Heartbeat for ECG Biometric Recognition DA AlDuwaile, MS Islam Entropy 23 (6), 733 , 2021 2021 Citations: 93
HBS: a novel biometric feature based on heartbeat morphology MS Islam, N Alajlan, Y Bazi, HS Hichri IEEE Transactions on Information Technology in Biomedicine 16 (3), 445-453 , 2012 2012 Citations: 59
An Improved Machine-Learning Approach for COVID-19 Prediction Using Harris Hawks Optimization and Feature Analysis Using SHAP K Debjit, MS Islam, MA Rahman, FT Pinki, RD Nath, S Al-Ahmadi, ... Diagnostics 12 (5) , 2022 2022 Citations: 58
End-to-End Deep Learning Fusion of Fingerprint and Electrocardiogram Signals for Presentation Attack Detection RM Jomaa, H Mathkour, Y Bazi, MS Islam Sensors 20 (7), 2085 , 2020 2020 Citations: 55
Biometric template extraction from a heartbeat signal captured from fingers MS Islam, N Alajlan Multimedia Tools and Applications 76 (10), 12709–12733 , 2017 2017 Citations: 54
Rhythm-based heartbeat duration normalization for atrial fibrillation detection MS Islam, N Ammour, N Alajlan, H Aboalsamh Computers in Biology and Medicine , 2016 2016 Citations: 53
HGSORF: Henry Gas Solubility Optimization-based Random Forest for C-Section prediction and XAI-based cause analysis MS Islam, MA Awal, JN Laboni, FT Pinki, S Karmokar, KM Mumenin, ... Computers in Biology and Medicine 147, 105671 , 2022 2022 Citations: 50
Encryption Based Image Watermarking Algorithm in 2DWT-DCT Domains N Hasan, MS Islam, W Chen, MA Kabir, S Al-Ahmadi Sensors 21 (16), 5540 , 2021 2021 Citations: 50
Self-Adaptive Scheduling of Base Transceiver Stations in Green 5G Networks UK Dutta, MA Razzaque, M Abdullah Al-Wadud, MS Islam, MS Hossain, ... IEEE Access 6 , 2018 2018 Citations: 46
A morphology alignment method for resampled heartbeat signals MS Islam, N Alajlan Biomedical Signal Processing and Control 8 (3), 315–324 , 2013 2013 Citations: 30
Single Heartbeat ECG Biometric Recognition using Convolutional Neural Network D Alduwaile, MS Islam 2020 International Conference on Advanced Science and Engineering (ICOASE … , 2020 2020 Citations: 27
Selection of Heart-Biometric Templates for Fusion MS Islam, N Ammour, N Alajlan, M Abdullah-Al-Wadud IEEE Access , 2017 2017 Citations: 27
Heartprint: A Dataset of Multisession ECG Signal with Long Interval Captured from Fingers for Biometric Recognition MS Islam, H Alhichri, Y Bazi, N Ammour, N Alajlan, RM Jomaa Data 7 (10), 141 , 2022 2022 Citations: 26
Heartbeat Biometrics for Remote Authentication using Sensor Embedded Computing Devices MS Islam International Journal of Distributed Sensor Networks 2015 , 2015 2015 Citations: 26
Fusion of fingerprint and heartbeat biometrics using fuzzy adaptive genetic algorithm N Alajlan, MS Islam, N Ammour World Congress on Internet Security (WorldCIS-2013), 76-81 , 2013 2013 Citations: 26
Person identification with arrhythmic ECG signals using deep convolution neural network A Al-Jibreen, S Al-Ahmadi, S Islam, AM Artoli Scientific Reports 14 (1), 4431 , 2024 2024 Citations: 25
An efficient QRS detection method for ECG signal captured from fingers MS Islam, N Alajlan 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 1-5 , 2013 2013 Citations: 25
Retinal blood vessel segmentation from fundus image using an efficient multiscale directional representation technique Bendlets R Kushol, MH Kabir, M Abdullah-Al-Wadud, MS Islam Mathematical Biosciences and Engineering 17 (6), 7751–7771 , 2020 2020 Citations: 24
