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.
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 K = 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.
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.
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.
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.
