ABSTRACT Voice‐based machine learning models for Parkinson's disease (PD) screening routinely exceed 95% accuracy on the UCI Oxford dysphonia benchmark, but its ∼6 recordings per participant mean a random split places the same speaker's recordings in both training and test sets, rewarding speaker recognition rather than disease detection. To quantify performance under a leakage‐free protocol, identify competitive classifiers, and test transfer to an independent cohort. A total of 9 classifiers were evaluated on 195 phonations from 32 subjects using repeated stratified group nested cross‐validation (10 × 5 × 3, 50 outer folds), subjects grouped in both loops, predictions aggregated per participant, and fold assignment made deterministic for exact reproducibility. Models were compared via paired effect sizes, bootstrap confidence intervals, and Holm‐adjusted values. External validation used 756 recordings from 252 participants (Sakar Istanbul cohort) under three separate threshold policies, with feature equivalence assessed via standardized mean differences among controls. Logistic regression and random forest were statistically indistinguishable at the top (AUC = 0.856 [0.832–0.880] and 0.850 [0.809–0.892]), both exceeding every gradient‐boosting method (CatBoost: 0.761; difference 0.095, ). A total of 12 of the 16 nominally shared features differed by 1 SD between cohorts among controls. Discrimination transferred only partially externally (AUC = 0.685–0.707), while calibration failed entirely: a threshold fixed from training labeled every external participant a patient under logistic regression (specificity = 0.000) and almost none under random forest (sensitivity = 0.096). Leakage‐free evaluation supports 0.86 AUC rather than the 0.95–0.99 accuracy widely reported, consistent with independent claims‐based prodromal studies. This is retrospective classification, not early detection; the reproducible protocol generalizes to other small repeated‐measures biomedical datasets.
ABSTRACT Continuous worker localization and identity‐consistent tracking at power grid construction sites is challenged by equipment occlusion, extreme scale variation and visually homogeneous protective equipment. Each defeats a different stage: a worker the detector never proposes is unrecoverable downstream; overlap‐based matching collapses once occlusion drives the predicted–observed intersection towards zero; and uniform equipment suppresses the chromatic cues reidentification depends on. Detection and tracking are also tuned in isolation, so gains need not compose. This paper presents a jointly optimized detection‐tracking framework, YOLOv8‐ES + DeepSORT‐GE, for real‐time worker monitoring. The YOLOv8‐ES detector adds a C2f‐DG module combining deformable convolution with dynamic multidimensional modulation, adapting sampling geometry, kernel weighting and channel–spatial saliency within one bottleneck rather than in successive stages, dual semantic enhancement paths via transposed convolution cascades for cross‐scale reinforcement, and a dedicated P2‐level small‐target detection head. The DeepSORT‐GE tracker adds MP‐ResNet for multiscale appearance discrimination and a DeIoU geometry‐aware matching strategy with center distance penalization, its box expansion scaled by detection confidence so that uncertain predictions are gated more permissively. On purpose‐constructed power grid worker datasets YOLOv8‐ES achieves 88.1% mAP, 4.6 points above the baseline, for 1.3 M added parameters, 2.1 GFLOPs and about 3 ms per frame. The integrated framework attains 72.5% MOTA, 81.5% MOTP, 73.6% IDF1 and 66.3% HOTA, gains of 9.4, 2.4, 1.8 and 1.9 points. The upgrades prove more than additive on identity: separately 0.5 and 0.3 IDF1 points, together 1.8, an interaction supplying 56 percent of the gain. A controlled 220 kV GIS substation simulation, stratifying performance against ground‐truth occlusion duration as the captured sequences cannot, yields 73.6% fewer identity switches and 55.2% lower reidentification latency; both are conditional on the simulated appearance model and complement rather than replace the measurements on real footage. Throughput of 28.6 fps exceeds the 25 fps acquisition rate.
ABSTRACT Conditions affecting mental health, namely stress, anxiety, and depression, are on the rise in various populations, emphasizing the need for early evaluation and ongoing surveillance of these states. Mental health evaluation typically relies on subjective questionnaires and fails to assess underlying physiological mechanisms. This study describes an automated framework for multi‐class mental health classification and level of severity assessment using multimodal data. The model X‐DyFGate proposed in this paper uses Laser Doppler Flowmetry, Fluorescence Spectroscopy, and clinical factors. It is built using residual sensor encoders, cross‐attention fusion, transformer representation learning, dynamic feature gating, and a compact bottleneck layer. This pipeline moves beyond simple feature concatenation. Its novelty lies in its hierarchical, attention‐based fusion of low‐level (sensor) and high‐level (clinical) data, coupled with a dynamic gating mechanism that learns the importance of each modality for a specific individual's prediction. This personalizes the model, a key step toward precision psychiatry. The dataset used in this work consists of 1078 samples across six mental health categories with associated severity levels. The proposed model provided an accuracy of 99.38% multi‐class classification, while the one‐dimensional Convolution Neural Network model accuracy is 94.44%. For severity level classification, the proposed model provided 95.67% accuracy for stress, 95.67% for anxiety, and 97.53% for depression, whereas the one‐dimensional Convolution Neural Network model produced an accuracy of 67.28% for stress, 90.12% for anxiety, and 61.11% for depression. The proposed model is further validated on two more publicly available datasets, and it performed well on those two datasets. Despite promising performance, the proposed framework involves relatively high computational cost and has been validated on a limited, homogeneous dataset. Furthermore, comprehensive evaluation on diverse real‐world clinical data and deeper interpretability analysis remain areas for future investigation.
ABSTRACT Computational modeling provides a useful framework for investigating cancer‐immune dynamics and the interactions between tumor cells and immune components. In this study, a nonlinear fractional cancer‐immune model incorporating CD4+ T cells, CD8+ T cells, dendritic cells, IL‐2, IL‐12, and anti‐PD‐L1 inhibitors is investigated in the Caputo sense. The proposed system is solved using the He‐Laplace algorithm to obtain approximate series solutions for the seven coupled state variables. The accuracy of the obtained solutions is assessed through residual‐error analysis, and the corresponding results are presented in tabulated form. Two‐dimensional, three‐dimensional, and contour plots are further employed to examine the effects of the model parameters and fractional order on the system dynamics. The results indicate that the considered immune and therapeutic components produce noticeable changes in tumor and immune‐cell profiles, while variations in the fractional parameter influence the obtained solutions. The study provides a theoretical computational framework for analyzing complex fractional cancer‐immune dynamics and the interactions among the incorporated biological components.
ABSTRACT This paper introduces a lightweight yet highly secure image encryption framework that combines chaotic dynamics, HKDF‐S3‐based key expansion, and Möbius‐Affine transformations to achieve strong protection with minimal computational burden. The encryption process begins with the generation of chaotic ignition values derived from a highly sensitive nonlinear chaotic system. These initial values are then expanded using a hierarchical HKDF‐S3 mechanism, producing cryptographically strong and diversified round keys. The expanded keys are subsequently mapped to affine transformation parameters and to a carefully designed Maximum Distance Separable (MDS) diffusion matrix constructed over the finite ring ℤp. The proposed design enables per‐pixel Möbius transformations followed by chaotic masking and block‐wise diffusion. By employing an MDS matrix with maximal branch number, the framework achieves strong confusion and diffusion characteristics, ensuring that even slight variations in plaintext or key values propagate rapidly throughout the encrypted image. To further enhance sensitivity to both plaintext and key modifications, rotational key updates are applied at each encryption round. This dynamic updating mechanism significantly strengthens resistance against chosen‐plaintext and differential attacks. Comprehensive experimental analysis conducted on standard color images confirms the effectiveness of the proposed scheme.
