IET Biometrics最新文献

{"title":"Towards Secure Biometric Solutions: A Multifactor Authentication Framework for Facial Recognition While Protecting User Data","authors":"José Silva,&nbsp;Ajnas Muhammed,&nbsp;Aniana Cruz,&nbsp;Bruno Sousa,&nbsp;Nuno Gonçalves","doi":"10.1049/bme2/7426169","DOIUrl":"https://doi.org/10.1049/bme2/7426169","url":null,"abstract":"<p>Storing raw facial images or face embeddings in an authentication database creates a persistent privacy liability. A single breach can permanently expose a person’s biometric identity. This paper presents a multifactor authentication (MFA) framework for facial recognition systems that removes this liability by never storing biometric data, in any form, on the server. Unlike conventional biometric template protection (BTP) techniques, which typically trade a fixed transformation of the image or the feature vector (e.g., PolyProtect, cancelable biometrics, and the fuzzy commitment scheme) for a reduction in recognition accuracy, the proposed method couples a decomposition-based feature-obfuscation step with time-based one-time passwords, AES-256 encryption, and SHA-512 hashing to generate a single-use, revocable authentication proof. This proof is designed to be irreversible, unlinkable, and revocable while leaving recognition accuracy effectively unchanged. Across six public benchmarks, namely, Labeled Faces in the Wild dataset (LFW), Age Database 30 (AgeDB-30), Cross-Age LFW (CALFW), Cross-Pose LFW (CPLFW), Racial Faces in the Wild (RFW), and Cross-Quality LFW (XQLFW), the proposed method attains 99.91% accuracy on LFW (area under the curve [AUC] 0.997) and is within 0.08–5.38 percentage above the published ArcFace and MagFace baselines on the benchmarks. A dedicated ablation with and without the protection layer, repeated under cosine, Euclidean, and Manhattan similarity, shows no measurable accuracy degradation attributable to the protection step itself. The principal novelty of the approach is architectural rather than purely cryptographic. The framework embeds feature-level BTP directly inside a MFA protocol, so that biometric-free storage, revocability, and MFA are obtained jointly instead of as separate, loosely coupled add-ons. Performance is comparatively weaker on cross-quality (XQLFW, 83.7%) and cross-age (CALFW) dataset, a limitation we analyze in this work.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/7426169","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149205480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Stability of EEG-Biometrics: The Role of Artifacts in Within vs. Cross Session Authentication","authors":"Yvonne Höller,&nbsp;Arne C. Bathke,&nbsp;Andreas Uhl","doi":"10.1049/bme2/5158377","DOIUrl":"https://doi.org/10.1049/bme2/5158377","url":null,"abstract":"<p>Artifacts in the electroencephalogram (EEG) have not been investigated systematically regarding their effect on EEG biometric performance. Since artifacts vary over time, they can be expected to lower EEG biometric performance in cross session cross-validation. However, because of their presumed uniqueness, they might increase within session cross-validation performance of an EEG biometric system. We examined the EEG biometric performance of 15 features within and across 6 sessions recorded over 3 days, including 3 different cognitive conditions, before and after artifact exclusion in a sample of up to 90 individuals. Our results revealed significant effects of artifact exclusion depending on the cross-validation scenario and the feature. Overall, within session cross-validation was not systematically affected differently by artifact exclusion as compared to cross session cross-validation, but depending on the feature and the type of cognitive task employed, artifact exclusion led to better or worse results, with some frequency-dependent features performing better when artifacts were excluded. Our results emphasize the overestimation of biometric performance in within session cross-validation (with equal error rates (EERs) down to 0) as compared to cross session cross-validation (with EERs for the same feature above 30) and the low reliability of results obtained when evaluating EEG biometric performance in small samples. We recommend that future developments of EEG biometrics must test their robustness against artifacts in the data.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/5158377","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148994072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MPAN-Entropy: Multi-Prototype Adaptive Network for Few-Shot EEG–Based Person Identification Using Entropy Features","authors":"Jianfeng Hu,&nbsp;Jing Gao,&nbsp;Ping Wang","doi":"10.1049/bme2/9303061","DOIUrl":"10.1049/bme2/9303061","url":null,"abstract":"<p>This paper proposes DPPN-Entropy, a dual-path prototypical pretraining network (DPPN) for few-shot EEG–based person identification using precomputed multiscale entropy features. Unlike existing approaches that rely on raw EEG signals, the proposed system operates on compact 180-dimensional entropy feature vectors (30 channels × 6 entropy types), enabling efficient template storage and fast matching in real-world biometric enrollment with limited data. The architecture introduces two key innovations: (1) a DPPN that leverages supervised contrastive learning and mutual distillation between parallel encoder branches to learn robust discriminative embeddings from scarce training data; and (2) a global–local prototype fusion (GLPF) module that adaptively combines class-level global prototypes with sample-level local prototypes via variance-based weighting, with a fallback to global-only prototypes when <i>K</i> = 1 to prevent variance-collapse failure. Under a strict subject-independent evaluation protocol with 16 subjects for meta-training and 10 unseen subjects for meta-testing, DPPN achieves 86.6% accuracy in the 5-way 5-shot setting, significantly outperforming ProtoNet (85.4%) and traditional classifiers (logistic regression 95.1%). Comprehensive downstream analyses—including channel selection, cognitive state comparison (eyes-open (EO) significantly higher than eyes-closed (EC)), N-way scalability, and biometric metrics (EER 21.2%, AUC 0.843)—establish practical benchmarks for few-shot EEG person identification. Although the framework is termed MPAN-entropy, ablation studies identify DPPN as the primary driver of performance; we thus adopt DPPN for all downstream analyses.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/9303061","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148849311","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence-Based OSAS Biomarker Screening and Prediction Algorithm","authors":"Ting Lu,&nbsp;Liang Wu","doi":"10.1049/bme2/1251077","DOIUrl":"https://doi.org/10.1049/bme2/1251077","url":null,"abstract":"<p>Traditional biomarker research has the problems of low manual screening efficiency, strong subjectivity, small sample size but high feature dimension, and difficulty in capturing complex relationships between variables, which limits its practical application in clinical practice. To solve the above problems, this article studies an obstructive sleep apnea syndrome (OSAS) biomarker screening and prediction algorithm based on artificial intelligence. LASSO (least absolute shrinkage and selection operator) regression and random forest feature importance ranking are used to automatically screen key biomarkers from high-dimensional features, effectively improving screening efficiency and reducing subjective intervention. Combining regularized modeling strategies with cross-validation techniques, the risk of overfitting can be suppressed, and the robustness of the model under small sample conditions can be improved. Gradient boosting trees and multilayer perceptron (MLP) models are also used to capture the nonlinear and interactive effects between variables, thereby building a more expressive prediction model. The experimental results show that the constructed model performs well in terms of accuracy, sensitivity, and computing performance, with a prediction accuracy (optimal parameter combination) of 0.86 and an inference time between 0.046 and 0.085 s, verifying the potential of artificial intelligence in OSAS biomarker mining and individualized risk prediction. This study provides adequate technical support for early screening and precision medicine of OSAS.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/1251077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148616840","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Multimodal Framework for Continuous Skin Hydration Monitoring Using Wearable Sensor","authors":"Arslan Amjad,&nbsp;Muhammad Farooq,&nbsp;Hasan Abbas,&nbsp;Agnieszka Szczęsna","doi":"10.1049/bme2/1400782","DOIUrl":"https://doi.org/10.1049/bme2/1400782","url":null,"abstract":"<p>The outermost layer of the skin, stratum corneum, functions as a critical barrier. Its hydration levels are being actively affected by sweat gland activity, which is a significant mechanism for thermoregulation during physical exertion. Despite the known relationship, a direct, noninvasive method for monitoring dynamic changes in skin hydration with common wearable devices has remained elusive. Prior studies rely on specialized biosensors or preinduced hydration states to formulate the problem as a supervised classification, which lacks generalizability for continuous, free-living assessment. Our study utilized the photoplethysmography (PPG)-DaLiA publicly available dataset to develop a mathematical model that computes a continuous, relative skin hydration proxy by integrating electrodermal activity (EDA) and skin temperature signals from a common multimodal wrist-worn device (Empatica E4). Despite the lack of direct hydration ground truth, the model’s output was validated by its physiological responses across various activities, exhibiting stable and interpretable trends. This study has significant practical implications, as it demonstrates a feasible approach to adapting affordable, consumer-grade wristbands into effective tools for daily hydration monitoring, utilizing their current multimodal sensors without necessitating specialized hardware or incurring additional costs, thus fostering proactive personal health management.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/1400782","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148467228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sensory Interference Recognition Based on NRBO-CNN-SE-LSTM","authors":"Jianyu Liu,&nbsp;Qin Wei,&nbsp;Yuzhuo Cheng,&nbsp;Mingjing Zhong,&nbsp;Chaoping Qin,&nbsp;Yi Han","doi":"10.1049/bme2/6263258","DOIUrl":"https://doi.org/10.1049/bme2/6263258","url":null,"abstract":"<p>Human walking balance relies on proprioception, vision, and the vestibular sense. Dysfunction in any of these systems can lead to unstable gait. Accurately identifying sensory disturbances is key to understanding the causes of sensory dysfunction. Most existing studies focus on disturbances in a single sensory system and lack methods to identify multiple disturbance types. This paper proposes a recognition method based on Newton–Raphson–based optimizer (NRBO)-convolutional neural network (CNN)-squeeze-and-excitation (SE)-long short-term memory (LSTM). The original feature set is filtered through multiple rounds of hybrid filtering-wrapping feature selection algorithm (HLOA-HFWA) to obtain a feature subset. The union of these features forms an integrated feature (IF) set. This set is used as input to a CNN-SE-LSTM model designed for multiclassification. The Newton–Raphson method (NRBO) is then used to optimize key hyperparameters, including learning rate (LR), LSTM hidden node number, and L2 regularization (L2R) coefficient. This improves the network’s feature extraction and pattern recognition capabilities. Experiments on public IF sets and gait-IF sets show that NRBO-CNN-SE-LSTM outperforms other models in both sensory disturbance recognition and overall performance.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/6263258","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148466958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Persian Speaker Identification Using a Lightweight Attention-Based CNN With Spectral Augmentation","authors":"Atefe Pakzad,&nbsp;Samira Hourali,&nbsp;Vahid Kiani","doi":"10.1049/bme2/5420687","DOIUrl":"https://doi.org/10.1049/bme2/5420687","url":null,"abstract":"<p>Accurate speaker identification is critical for forensic investigations and biometric authentication. This study introduces Lightweight squeeze-and-excitation network (LSE-Net), a compact, robust deep learning architecture specifically tailored for speaker identification in challenging, noisy environments. Our approach integrates four core design principles: RMS-energy-based voice activity detection (VAD) for signal refinement, standardized Log-Mel spectrogram extraction, noise-aware regularization with spectral data augmentation to enhance generalization, and channel-wise squeeze-excitation (SE) blocks that dynamically recalibrate feature maps to emphasize speaker-discriminative information. Finally, an utterance-level probability aggregation strategy ensures robust classification of entire audio recordings. We evaluated LSE-Net on two datasets: the newly constructed PERSID33 (933 formal Persian news-style utterances from 33 speakers) and the benchmark TIMIT dataset (6300 utterances from 630 speakers). Experiments were conducted across diverse conditions, including clean audio and various real-world and synthetic noise scenarios at multiple signal-to-noise ratios. LSE-Net achieved 100% accuracy on PERSID33 and 95.07% on TIMIT under noise-free conditions, consistently outperforming baseline methods. In noisy settings, LSE-Net maintained near-perfect accuracy on the PERSID33 dataset and demonstrated superior robustness on the larger TIMIT dataset compared to state-of-the-art (SOTA) approaches. Ablation studies confirmed that spectral augmentation and SE attention are pivotal in preserving identification accuracy under acoustic stress. These results demonstrate that LSE-Net is a highly efficient, forensic-grade solution for speaker identification, particularly suitable for constrained or noisy investigative contexts.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.6,"publicationDate":"2026-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/5420687","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148324375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multiscale Convolutional–Bidirectional LSTM Fusion of Spatiotemporal Attention for Human Activity Recognition","authors":"Yuyang Zhang,&nbsp;Changcheng Xiang,&nbsp;Yinrui Zhang","doi":"10.1049/bme2/8129974","DOIUrl":"https://doi.org/10.1049/bme2/8129974","url":null,"abstract":"<p>Human activity recognition (HAR) is a core technology in fields such as smart healthcare and human–computer interaction, which aims to classify daily activities (e.g., walking and running) based on sensor data automatically. While existing approaches achieve high accuracy in controlled laboratory settings, they often perform poorly in real-world applications due to limited multiscale feature extraction and poor modeling of interchannel sensor correlations. These shortcomings lead to high sensitivity to noise and irrelevant time segments. An innovative model integrating multiscale convolution, bidirectional long short-term memory (BiLSTM), and a spatiotemporal attention mechanism is proposed to address these issues in this research. The model employs a multiscale parallel convolutional structure with filter sizes of 3, 5, 7, and 9 that enable it to capture both short-term local dependencies and long-term global patterns simultaneously. The introduction of a spatial–temporal dual attention mechanism dynamically focuses on key sensor channels and time segments, significantly improving the accuracy of feature selection. In addition, the Swish activation function is used to optimize the feature extraction process. Its smooth characteristics and self-gating mechanism avoid the gradient vanishing problem of the traditional ReLU effectively. The experimental results show that the model achieves an accuracy of 95.39% on the UCI–HAR public dataset and an excellent performance of 99.58% on the custom dataset.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/8129974","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148079782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"","authors":"","doi":"","DOIUrl":"","url":null,"abstract":"","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148080376","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Internet of Medical Things-Driven Deep Learning Approach for Automated Heart Sound Classification","authors":"Muhammad Sajid,&nbsp;Ghulam Gilanie,&nbsp;Syeda Naila Batool,&nbsp;Salil Bharany,&nbsp;Rania M. Ghoniem,&nbsp;Amna Ikram,&nbsp;Shefali Gupta,&nbsp;Belayneh Matebie Taye","doi":"10.1049/bme2/3212328","DOIUrl":"https://doi.org/10.1049/bme2/3212328","url":null,"abstract":"<p>The Internet of Medical Things (IoMT) has emerged as a transformative force in healthcare, enabling the development of innovative and noninvasive diagnostic tools that leverage connected technologies. This research focuses on the application of IoMT in conjunction with deep learning techniques to detect and classify heart diseases through the analysis of heart sounds, a method that promises to enhance the accuracy and accessibility of diagnostics. We proposed frameworks that utilize advanced signal processing algorithms to capture and analyze heart sound data, that is, phonocardiograms (PCGs) collected from District Headquarters Hospital, Bahawalnagar, Pakistan. Deep learning models, specifically convolutional neural networks (CNN) and long short-term memory (LSTM), and a combination of these are employed to identify patterns associated with various cardiac conditions. This study involves a comprehensive dataset comprising annotated heart sounds from diverse demographics, ensuring the robustness and generalizability of the proposed models. The proposed methodology involves using three models: one-dimensional CNN (1D-CNN), LSTM, and a combination of 1D-CNN + LSTM to classify heart sounds into normal, murmur, extra-systole, and artifact categories. Results demonstrate high accuracy in the classification of common heart diseases, including normal, murmur, extra-systole, and artifact, surpassing traditional diagnostic methods. The model achieved the highest accuracy for normal cases as of 95%, for murmur cases as of 94%, for extra-systole cases as of 95%, and for artifact cases as of 96%. This approach holds significant potential for improving patient outcomes through timely and accurate diagnostics, thus exemplifying the power of digital health innovations in modern medicine.</p>","PeriodicalId":48821,"journal":{"name":"IET Biometrics","volume":"2026 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/bme2/3212328","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148076184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}