Current Issue : October-December Volume : 2026 Issue Number : 4 Articles : 5 Articles
Mobile authentication is essential for protecting personal data and payment authorization, yet prevailing approaches face two fundamental limitations: the nonrevocability of physiological biometrics once compromised and the susceptibility of knowledgebased authentication to observation- and trace-based attacks. This study proposes a next-generation mobile authentication framework based on dynamic behavioral profiling, in which binary pressure sequences and grip-position patterns are jointly modeled. The hardware design measures fine spatiotemporal pressure distributions using symmetrically mounted fabric-based strip sensor arrays along the display bracket, and enhances localized pressure-transfer efficiency via an electrode-aligned protrusion film. Closely coupled to this sensing design, the algorithm employs a probability-based soft-stacking scheme that combines class-wise predictive probabilities from base learners to mitigate information loss induced by threshold-based discretization, increasing mean accuracy from 0.802 to 0.857 compared with fixed-threshold encoding. The proposed framework achieves an AUC of 0.9867 (EER = 0.049) for 16-class pressure-sequence authentication and an AUC of 0.9870 (EER = 0.0595) for 6-class grip-scenario classification. These results support the feasibility of using touch-pressure and grip interactions as re-enrollable behavioral authentication signals and provide preliminary participant-level validation of the framework. Further investigation involving larger and more diverse populations and real-world settings is needed to assess its potential for continuous authentication....
Background/Objectives: Accurate post-mortem interval (PMI) estimation becomes increasingly difficult when bodies decompose under extreme heat. Hyperthermal Mediterranean environments accelerate soft-tissue degradation, induce early mummification, and distort classical thanatological indicators, often resulting in substantial PMI overestimation. This study analyzes three forensic cases affected by climate-driven decomposition anomalies and presents a climate-adaptive, AI-assisted diagnostic framework applied uniformly across all cases to improve PMI interpretation. Methods: A retrospective case series analysis was conducted on three individuals recovered during summer heatwaves. Crime scene investigation, post-mortem computed tomography (PMCT), autopsy, and genetic identification were integrated with 5–15-year meteorological datasets. Classical PMI estimations were compared with circumstantial data. A multimodal AI model, incorporating environmental features, decomposition morphology, and microenvironmental modifiers, was operationalized for each case using a hybrid Random Forest–LSTM architecture. Engineered indices included Accumulated Degree Days (ADD), a Decomposition Index, and climate-stress metrics (Thermal Load Index, Desiccation Pressure Factor, Microenvironmental Distortion Coefficient). Quantile regression provided calibrated prediction intervals. Results: Morphological assessments overestimated PMI in every case, suggesting intervals of 1–6 months despite true PMIs of approximately 20 days (Cases 1–2) or 36–48 h (Case 3). The AI model yielded conceptual outputs more consistent with verified PMIs, ~21 days (Case 1), ~23 days (Case 2), and ~42 h (Case 3), each accompanied by 50% and 90% prediction intervals. Explainability analyses identified thermal load, desiccation pressure, and microenvironmental distortion, particularly insulation in Case 3, as dominant drivers. Conclusions: Extreme heat fundamentally alters decomposition trajectories, rendering classical PMI methods unreliable. Applying a climate-aware, AI-assisted diagnostic framework across all three cases improved interpretability, providing uncertainty-aware estimates aligned with true PMIs. The AI framework is presented as a conceptual, non-trained, proof-of-concept system, and reported outputs represent operational demonstrations rather than validated predictions, offering a promising foundation for next-generation PMI diagnostics in hyperthermal forensic settings....
Complex and even chaotic dynamics, though prevalent in many natural and engineered systems, have been largely avoided in the design of electromechanical systems due to concerns about wear and controlability. Here, we demonstrate that complex dynamics might be particularly advantageous in soft robotics, offering new functionalities beyond motion not easily achievable with traditional actuation methods. We designed and realized resilient magnetic soft actuators capable of operating in a tunable dynamic regime for tens of thousands of cycles without fatigue. We experimentally demonstrated the application of these actuators for true random number generation and stochastic computing. We validate soft robots as physical reservoirs capable of performing Mackey–Glass time series prediction. These findings show that exploring the complex dynamics in soft robotics would extend the application scenarios in soft computing, human–robot interaction and collaborative robots, as we demonstrate with biomimetic blinking and randomized voice modulation....
Colonoscopy polyp segmentation is important for colorectal cancer screening, yet it remains challenging because polyps exhibit large morphological variation, weak lesion–background contrast, blurred boundaries, and severe foreground–background imbalance. To address these issues, this paper presents MCM-UNet++, a hybrid U-Net++-based segmentation framework that combines three targeted enhancements. First, a Multi-Axis Transformer Block (MATransformerBlock) is incorporated into convolutional feature blocks to model long-range horizontal and vertical dependencies with lower complexity than dense global self-attention. Second, a Cross-Channel Mixing (CCM) module is used in nested skip fusion paths to recalibrate the channel and spatial responses and reduce redundant feature transmissions. Third, a Multi-Objective Adaptive Loss (MOALoss) combines focal, Dice, and boundary-aware terms with learnable weights to improve supervision for small regions and ambiguous boundaries. Experiments on four public polyp segmentation datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-Larib) show competitive performance against the selected baseline methods, with Dice/IoU scores of 0.9563/0.9278 on Kvasir-SEG and 0.8593/0.7896 on CVC-ColonDB. These results indicate that the proposed components can improve benchmark-level polyp segmentation performance, while broader validation is still required before clinical deployment....
Spaceborne neural processing units (NPUs) increasingly support real-time deep-learning inference, but their dense multiply-accumulate arrays are vulnerable to radiation-induced soft errors. Conventional radiation-hardening methods improve reliability through hardware redundancy, but they incur substantial area, performance and compiler-mapping overheads. This paper proposes tile-resilient algorithm-based fault tolerance (TR-ABFT), a softwarescheduled, detection-oriented scheme for quantized NPU inference. TR-ABFT generates checksum information at tile granularity and maps checking tasks onto the original processing element (PE) array without changing the hardware topology. To make ABFT compatible with INT8 datapaths, we design two checksum-coding strategies: checksum decomposition and modulo-239 checksum coding. The modulo-239 scheme removes structural missed detections for two-bit flips with bit-position spacings in (1, 31), while preserving compatibility with signed INT8 inputs. Evaluations on ResNet, YOLOv8, and RT-DETR show that, on a 16 × 16 array, TR-ABFT introduces only 6.37% to 24.61% additional computational overhead. By converting spatial redundancy into schedulable temporal redundancy, TR-ABFT preserves systolic-array regularity and provides a low-overhead reliability-enhancement mechanism for space-grade neural-network accelerators....
Loading....