Search Results (7,207)

Machine Learning (ML) models effectively capture complex, nonlinear, multimodal, and time-dependent patterns in indoor environments. In thisstudy, the relationship between indoor CO₂ concentrations and environmental variables in different areas of a university hospital was investigated using ML methods. The dataset is a total of 114, including 80% train and 20% test. CO₂ concentration measured at 16:00 was defined as the target variable, while eight inputs (number of occupants, room volume, room floor area, average relative humidity, average temperature, average CO₂ concentration, the change in CO₂ concentration, room orientation) were selected as model inputs. Artificial Neural Network (ANN), Extreme Gradient Boosting (XGBoost), Random Forest (RF) and Linear Regression were applied to predict CO₂ concentration. Model performance was evaluated based on prediction accuracy criteria, such as Mean Absolute Percentage Error (MAPE), Coefficient of Determination (R²), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), so it enabled a comparative consideration of their effectiveness. When CO₂-related variables were included, RF achieved the best performance (R² = 0.804, MAPE = 8.34%, MAE = 70.65, RMSE = 104.24), followed by XGBoost (R² = 0.776, MAPE = 9.07%, MAE = 78.10, RMSE = 111.44). In contrast, ANN (R² = 0.250, MAPE = 19.62%, MAE = 159.81, RMSE = 203.72) and Linear Regression (R² = 0.175, MAPE = 19.44%, MAE = 169.37, RMSE = 213.77) showed comparatively lower predictive performance. Overall, the results indicate that tree-based ML models can provide promising predictive performance and practical insights for indoor air quality monitoring and management in healthcare facilities, while their applicability and generalizability could be further strengthened through future evaluations involving data from diverse healthcare environments. Full article

Globally, respiratory diseases such as asthma, chronic obstructive pulmonary disease (COPD) and pneumonia affect populations significantly, requiring early and accurate diagnosis for effective clinical management. Manual auscultation and expert interpretation are the common shortcomings in conventional diagnostic approaches, as they lead to time-consuming and inconsistent analysis. To address these limitations, an artificial intelligence-driven framework for respiratory disease classification using multi-spectral feature extraction and deep learning architectures is proposed to classify four different respiratory conditions: Asthma, COPD, Pneumonia and Healthy. The dataset is collected from Kaggle’s respiratory sound database and the COUGHVID V3 database, which together contain 322 Asthma signals, 746 COPD signals, 323 Pneumonia signals and 174 Healthy signals. Subsequently, the features are extracted using four different feature extraction techniques—Constant Q Transform (CQT), a Gammatone spectrogram, Mel-Frequency Cepstral Coefficients (MFCC) and Perceptual Linear Prediction (PLP)—and these extracted spectral representations are provided as inputs to various deep learning models such as a Deep Convolutional Neural Network (Deep CNN), a Temporal Attention Network (TAN) and an Autoencoder for automated feature learning and disease classification. The proposed framework is evaluated using several performance metrics, and the experimental results clearly indicate that the performance of the proposed classification framework strongly depends on the selection of spectral feature extraction techniques and deep learning models. Among all the evaluated combinations, it is evident that the Autoencoder model integrated with CQT features exhibited the best classification performance, with an accuracy of 98.72%, precision of 98.74%, recall of 98.72%, Matthews correlation coefficient (MCC) of 98.11%, Cohen’s kappa value of 98.10% and the least log loss of 0.025. The proposed artificial intelligence (AI)-enabled respiratory disease classification framework has demonstrated the ability to produce a reliable computer-aided diagnostic system which is suitable for smart healthcare applications and automated pulmonary disease screening. Full article

Scoliosis is a complex three-dimensional spinal deformity that requires early detection, accurate radiological assessment, individualized treatment planning, and long-term monitoring. In recent years, artificial intelligence (AI) has emerged as a promising tool across multiple stages of scoliosis management, including screening, automated imaging analysis, deformity classification, prediction of progression, surgical planning, postoperative outcome assessment, and patient education. This narrative review summarizes current and emerging applications of AI in scoliosis, with particular emphasis on studies published after 2023. Deep learning algorithms, including convolutional neural networks, U-Net-based architectures, transformer models, and generative approaches, have demonstrated high accuracy in automated Cobb angle measurement, vertebral segmentation, coronal and sagittal parameter assessment, and radiation-free screening using surface topography or smartphone-based photographs. Machine learning models have also shown potential in predicting curve progression, treatment response, risk of postoperative complications, and patient-reported outcomes by integrating radiological, clinical, biomechanical, and, increasingly, multimodal data. In parallel, large language models and generative AI tools are being investigated for patient education, communication support, readability improvement, and research hypothesis generation. Despite these advances, important limitations remain, including limited external validation, dataset heterogeneity, potential algorithmic bias, insufficient interpretability, and incomplete integration into clinical workflows. Moreover, while AI systems show strong performance in automated measurement and screening tasks, their role in complex therapeutic decision-making, such as Lenke classification, fusion-level selection, and autonomous surgical planning, remains experimental. Overall, AI has the potential to improve the precision, efficiency, and personalization of scoliosis care; however, prospective multicentre studies, transparent reporting, explainable model design, and regulatory validation are essential before widespread clinical implementation. Full article

Background/Objectives: Accurate segmentation of histopathological images while preserving cellular morphology in computer-aided diagnostic systems is critically important for the diagnosis and staging of colon cancer. However, conventional metaheuristic algorithms performing multi-level thresholding on such complex tissues often suffer from premature convergence by becoming trapped in local optima as the search space increases. To address this limitation, this study proposes a new label-independent hybrid optimization algorithm focused on colon adenocarcinoma segmentation. Methods: The proposed algorithm hybridizes the global exploration capability of the Artificial Rabbit Optimization (ARO) algorithm with the local exploitation ability of the Ant Lion Optimization (ALO) algorithm through an optimized fixed transition ratio, thereby enabling efficient localization of cellular density valleys. Results: The principal findings obtained from the LC25000 colon cancer dataset demonstrate that the ARO-ALO algorithm achieves stable performance with high SSIM (0.8043) and FSIM (0.8595) scores while preserving the histopathological hierarchy. Furthermore, the preservation of diagnostic morphology after segmentation is statistically validated by the high Pearson (0.9870) and Spearman (0.9948) correlation coefficients. In addition, supplementary generalization experiments are conducted on the Oral Squamous Cell Carcinoma (OSCC) and pulmonary circulation vessels datasets to verify the tissue-agnostic nature of the algorithm. Conclusions: Consequently, the ARO-ALO algorithm emerges as an efficient alternative for clinical decision support systems. Full article

Stochastic metaheuristic feature selection (FS) may generate unstable feature subsets across repeated runs, undermining reproducibility in Internet of Things (IoT) intrusion detection systems (IDSs). This paper presents Head–Tail Population Initialization (HTPI), a feature-importance-guided initialization approach for enhancing the stability of Adaptive Hybrid Genetic Algorithm–Simulated Annealing (AHGA-SA)-based FS. HTPI uses feature-importance scores to split candidate features into Head and Tail groups and initializes candidate subsets by prioritizing Head features and sampling Tail features with importance-based weights. HTPI is integrated into AHGA-SA as an incremental extension, termed HTPI-AHGA-SA, and modifies only the initialization and reinitialization steps. Experiments on eight IoT-oriented IDS datasets using 50 runs per configuration, with seeds paired across methods, showed significantly higher Nogueira stability under HTPI-AHGA-SA on all datasets after Holm correction, with non-overlapping 95% leave-one-run-out jackknife confidence intervals in every case. These results characterize algorithmic cross-run stability under a fixed data partition. All absolute differences in dataset-level mean F1 Macro remained below $0.003$; formal equivalence at this margin was supported for six datasets, while dataset-specific security-metric trade-offs remained. On three representative datasets, post hoc explainable artificial intelligence (XAI) analyses indicated generally higher permutation importance (PI)-based cross-run consistency and measurable predictive utility in the selected Head and Tail portions under retraining. Full article

This work presents a novel method known as the Red Deer Algorithm-Based Artificial Neural Network (RDA-ANN) for managing real-time voltage and harmonic control in a cascade H-bridge multilevel inverter (CHB-MLI) that is fed by photovoltaic (PV) panels. The RDA-ANN technique proposed here computes the switching angles in real-time for selective harmonic elimination (SHE) on the output voltage of a multilevel inverter (MLI). In the proposed approach, a comprehensive lookup table containing 7776 permutations of switching angles was first generated offline using RDA optimization for a three-phase, 11-level CHB-MLI with five PV panels operating across a voltage range of 30 V to 35 V. This dataset was subsequently used to train a feed-forward ANN model capable of predicting optimal switching angles corresponding to any real-time voltage measurements from the panels. The SHE-PWM approach based on RDA-ANN targets the elimination of the 5th, 7th, 11th, and 13th order harmonics. This algorithm guarantees that the intended fundamental voltage is achieved, even during fluctuations in the voltages of the panels caused by varying irradiation and temperature conditions, while effectively removing the unwanted harmonics. The findings, validated under multiple environmental scenarios, illustrate that the RDA-ANN-based SHE-PWM technique successfully eliminates the selected harmonics from the load voltage with a fundamental voltage error not exceeding 0.18%, and results in a low total harmonic distortion (THD) value that complies with the IEEE 519-2022 standard across all tested conditions. Full article

This study investigated how detection distance affects spectral models for soluble solids content (SSC) and firmness evaluation in Korla fragrant pears and provides a reference for calibrating standardized indoor non-destructive detection equipment. Two hundred visually intact fruit samples at the early-ripening stage were collected from the Korla production area in Xinjiang. An FS-640 multispectral camera system equipped with a VS-SWR fixed-focus industrial lens (16 mm focal length, F1.8 maximum aperture, 1/2-inch sensor format) was used to acquire fruit reflectance spectra at seven vertical lens-to-fruit-surface distances of 90, 100, 110, 120, 130, 140, and 150 cm. A 625-pixel region of interest (ROI) was selected using ENVI at an undamaged equatorial or near-equatorial position of each fruit, and the regional mean spectrum was used as the spectral feature of one fruit sample. The sample-set partitioning based on joint X–Y distances (SPXY) algorithm was used to divide the calibration and prediction sets at a 3:1 ratio after outlier removal via a residual-threshold method. Four preprocessing methods, namely LOESS smoothing, standardization, vector normalization, and Savitzky–Golay (SG) smoothing, were compared. Competitive adaptive reweighted sampling (CARS) was performed with 50 Monte-Carlo sampling runs, a maximum of 30 principal components, and 10-fold cross-validation, yielding 99 characteristic wavelengths. Partial least squares regression (PLSR), support vector regression (SVR), random forest (RF), and artificial neural network (ANN) models were then established using identical input variables and sample partitions. Model performance was evaluated using the coefficient of determination for calibration ($R_c^2$), coefficient of determination for prediction ($R_P^2$), root-mean-square error of calibration (RMSEC), root-mean-square error of prediction (RMSEP), relative prediction deviation (RPD), and ratio of performance to interquartile distance (RPIQ). Under the static laboratory acquisition conditions in this work, the SSC model achieved the best prediction performance at 110 cm with SG smoothing ($R_P^2$) = 0.8949, RPD = 3.0633, RPIQ = 5.8661), whereas the firmness model obtained optimal prediction performance at 140 cm with standardization ($R_P^2$) = 0.7460, RPD = 1.9425, RPIQ = 3.2867). Changes in detection distance altered illumination uniformity, effective reflected signal, photon-scattering paths, and background-noise proportion. These effects may partially explain why the chemical-absorption-dominated SSC index and the tissue-scattering-dominated firmness index responded differently to detection distance. The results provide a reference for setting spectral detection parameters for Korla fragrant pears; however, samples were obtained from only a single producing region, harvest season, and maturity stage, and no independent external validation dataset was used. Therefore, the generalization ability of the developed models needs to be further verified using cross-season and cross-orchard sample sets. Full article

Recent advances in numerical modelling, remote sensing, and artificial intelligence are bringing a transformation in our ability to assess sediment transport. Nevertheless, climate change is fundamentally altering sediment production, transport, and deposition through intensifying hydrological extremes, sea-level rise, changing storm regimes, cryosphere degradation, and increasing human modification of sediment pathways. These interacting drivers challenge conventional sediment transport assessment, which has largely evolved within separate fluvial, estuarine, coastal, and marine disciplines and often lacks an integrated perspective capable of representing source-to-sink sediment connectivity under non-stationary environmental conditions. Although significant advances have been made in process-based numerical modelling, Earth observation, and artificial intelligence (AI), these approaches are commonly reviewed independently, limiting their collective application to regional climate-responsive sediment assessment. This review examines state-of-the-art process-based numerical models, observational tools, and machine-learning approaches for sediment transport from source-to-sink. A transparent benchmarking scheme is used to compare leading modelling systems (e.g., AdH, SRH-2D, FLO-2D, HEC-RAS, TELEMAC, Delft3D, EFDC, SCHISM, XBeach, ROMS), highlighting differences in dimensionality, sediment-process representation, computational demands, and climate-scenario readiness. Remote sensing (optical, SAR, LiDAR, UAV) and AI/ML/DL methods (e.g., random forests) are reviewed as complementary tools that enhance model parametrization, improve validation, and address uncertainty in data-limited regions. A reproducible bibliometric synthesis based on Dimensions.ai records (2000–2026) reveals accelerating growth in sediment-transport research, with strong recent expansion in coastal, estuarine, and data-driven modelling applications. Major challenges include cohesive sediment physics, cross-environment coupling, limited long-term validation datasets, and the need for scalable workflows compatible with climate-model forcing. In this manuscript, we analyse and propose a future roadmap for near-term integration of satellite–field data streams, medium-term development of hybrid physics–AI models, and long-term coupling of sediment modules within Earth-system and regional climate frameworks. Collectively, this review provides a foundation for next-generation, climate-responsive sediment transport assessment supporting sustainable river basin and coastal management. Full article

Cancer is increasingly recognized as an emerging concern in wildlife health and biodiversity conservation in the Anthropocene. Although traditionally viewed as an individual disease associated primarily with aging, wildlife cancer is shaped by complex interactions among environmental changes, species-specific evolutionary adaptations, and ecological processes. This review synthesizes current knowledge on the ecological and evolutionary drivers of wildlife cancer by integrating evidence from comparative oncology, environmental toxicology, wildlife pathology, and conservation biology. We examine how anthropogenic stressors, including pollution, habitat degradation, climate change, and infectious agents, influence cancer susceptibility in wild populations, and summarize intrinsic mechanisms underlying interspecific variation in cancer vulnerability, including Peto’s paradox, enhanced tumor suppression, and adaptive immune surveillance. We further highlight major methodological challenges, including limited surveillance capacity, fragmented datasets, taxonomic biases, and insufficient integration between cancer biology and conservation science. Finally, we discuss emerging interdisciplinary approaches, such as standardized monitoring frameworks, multi-omics technologies, artificial intelligence-assisted diagnosis, and One Health-based strategies, to advance wildlife cancer research and management. Collectively, this review positions wildlife cancer as an important ecological and evolutionary phenomenon and provides perspectives for incorporating cancer surveillance into biodiversity conservation and ecosystem health assessment. Full article

The progressive integration of Whole Slide Imaging (WSI) technology and Artificial Intelligence (AI) architectures is driving a structural transformation in pathology and precision oncology. This structured critical review analyzes and systematizes the impact of this technological transition along two fundamental operational dimensions of the modern biopharmaceutical industry: pre-registration Clinical Research and post-launch strategies governed by Medical Affairs. The first section explores how computational pathology is improving efficiency and reducing risk in drug development. Replacing analog visual assessment—intrinsically subject to inter-observer and intra-observer variability—with quantitative algorithms for cellular classification and segmentation enables optimization of patient recruitment in clinical trials, reducing screening failure rates. This review also examines the emerging role of Spatial Biology in extracting complex topological metrics from the Tumor Microenvironment (TME) and the use of AI for the objective and auditable quantification of critical surrogate endpoints, such as Pathological Complete Response (pCR), while acknowledging that algorithmic precision remains sensitive to pre-analytical variables and dataset biases. In the second section, the study investigates the strategic evolution of Medical Affairs, acting as a vital scientific communication and translational bridge between the complexity of Data Science and clinical hospital practice. Challenges related to AI adoption by clinicians are examined, emphasizing the importance of educational programs based on Explainable AI (XAI) to overcome the cognitive limitations of the black-box paradigm and the complex regulatory validation pathway for Software as a Medical Device (SaMD) under the stringent European IVDR framework—supported by an analysis of historical regulatory benchmarks such as the Paige Prostate case. The paper also explores the potential of AI in the large-scale generation of Real-World Evidence (RWE), applied to the creation of synthetic control arms in pharmacoeconomic settings. In conclusion, the study highlights that the diagnostic algorithm has ceased to be merely a laboratory support tool and has become a strategic asset and an integral adjunct to therapeutic decision-making. Overcoming current challenges related to data privacy through Federated Learning architectures, together with the imminent transition toward Foundation Models, foreshadows a fully data-driven healthcare ecosystem, making continuous skills development (digital upskilling) an essential requirement for professionals in the biopharmaceutical sector. Full article

Purpose: Marking the one hundredth anniversary of quantum mechanics in 2025, quantum science has become foundational for the development of contemporary technologies, enabling advances in sensing, imaging, computing, and materials engineering. Cancer radiotherapy, although traditionally developed within the scope of classical dosimetric models and phenomenological biological frameworks, is fundamentally initiated by quantum-mechanical radiation-matter interactions. Radiation-induced DNA damage, which ultimately determines therapeutic effectiveness, originates from primary quantum-mechanical processes involving particle transport, electronic excitation and ionisation, followed by successive physicochemical and chemical stages including water radiolysis and radical formation. As scientific disciplines undergo a rapid “quantum transition,” radiation cancer treatment is increasingly positioned to benefit from deeper integration of quantum principles and emerging quantum technologies. Methods: This review examines how quantum mechanics governs the primary radiation-matter interactions that initiate the physical, physicochemical, chemical, and ultimately biological stages of radiation action at the (sub)cellular level, with particular emphasis on track structure, water radiolysis, DNA damage induction, and multiscale biological response. Contemporary approaches to DNA damage modeling are discussed, including track-structure Monte Carlo methods, nanodosimetric frameworks, and multi-scale simulation approaches that connect microscopic interaction events with biological outcomes. Key quantum concepts relevant to radiation therapy are outlined, together with emerging quantum technologies such as nanoscale quantum sensing, quantum lasers, quantum dots, and quantum computing, which are evaluated for their potential roles in dosimetry, imaging, treatment planning, and radiation transport simulations. In this context, artificial intelligence (AI) is considered a complementary tool to accelerate computation and integrate quantum-informed data across multiple scales. Results: The review highlights that quantum-informed modeling enables a more consistent description of radiation-induced processes across spatial and temporal scales, linking microscopic interaction mechanisms to DNA damage formation and macroscopic biological outcomes. Recent advances in track-structure and radiobiological modeling provide new opportunities for improving predictions of radiation effects and treatment response. Emerging quantum technologies show potential to enhance measurement sensitivity, improve simulation efficiency, and enable more precise control of radiation delivery. Furthermore, AI-assisted approaches facilitate the extraction of predictive patterns from complex datasets, supporting faster and more accurate estimation of biological endpoints such as DNA damage and cell survival. Conclusions: The quantum aspects of advanced treatment modalities, including proton and heavy-ion therapy, ultrafast radiation delivery, and the FLASH effect, as well as future concepts such as laser-plasma-driven and coherence-informed radiotherapy systems, indicate a promising direction for next-generation cancer treatment. By critically assessing both opportunities and limitations, this work provides a coherent framework for integrating DNA damage modeling, quantum principles, quantum-inspired techniques, emerging quantum technologies, and advanced computational tools to guide future developments in radiation oncology. Full article

Wearable biosensors generate continuous physiological data in smart Internet of Disease (IoD) environments. These data can support early disease detection and remote patient monitoring. However, wearable data are often noisy, sensitive, and distributed across different devices. This paper proposes a multimodal neuro-symbolic model to overcome these limitations and incorporates it into a secure Edge–Fog–Cloud framework for anomaly detection in smart healthcare applications. The proposed system integrates the semantic analysis of clinical text using Bio-ClinicalBERT with temporal numerical data using an LSTM-based model, creating a unified neuro-symbolic artificial intelligence (AI) pipeline. Initial data processing is performed at the Edge, whereas inference is carried out at distributed Fog nodes for low-latency anomaly detection. Model training is handled in the Cloud, and privacy-preserving federated learning (FL) is supported through Homomorphic Encryption (HomEnc) to facilitate collaborative model training without sharing raw patient data. A sharded Tangle ledger is also used, with transactions broadcast by the Fog nodes and validated in the Cloud to create tamper-evident transaction logs. Furthermore, Honey Encryption (HoneyEnc) is integrated into the Fog layer to enhance security against brute-force attacks. Experimental results show that the proposed framework achieved 99.22% accuracy and a 99.31% F1-score on the held-out test set, with bootstrap 95% confidence intervals of 98.96–99.47% for accuracy and 99.08–99.53% for the F1-score. It also reduced detection latency from 185 ms in the baseline setting to approximately 50 ms in the Fog-inference setting. The blockchain layer achieved approximately 500 Transactions Per Second (TPS), while higher throughput was observed under increased transaction load and shard parallelism. Because the evaluation is based on synthetic multimodal EHR-like data and controlled simulations, the reported findings should be interpreted as proof-of-concept internal validation rather than evidence of deployment-ready clinical generalizability; external validation using real wearable biosensor data, hospital IoMT streams, or public clinical datasets such as MIMIC-III/MIMIC-IV is required before clinical deployment. These results highlight the potential of the proposed system for secure data processing and trustworthy anomaly detection in smart healthcare environments. Full article

The Internet of Medical Things (IoMT) is transforming healthcare through continuous patient monitoring, telemedicine, cloud–edge services, and Healthcare 5.0. However, the rapid growth of interconnected medical devices has expanded the healthcare cyberattack surface, making intelligent intrusion detection essential for protecting sensitive medical data and ensuring resilient clinical operations. Existing reviews examine specific aspects of AI-powered intrusion detection but rarely provide a deployment-oriented synthesis linking technical performance with operational and clinical requirements. This review critically examines Artificial Intelligence (AI)-powered Intrusion Detection Systems (IDSs) for IoMT across six analytical dimensions: detection performance, explainability, privacy preservation, computational efficiency, benchmarking practices, and cross-dataset generalization. This structured narrative review adopted the PRISMA 2020 framework to ensure transparent record identification, screening, and reporting, with evidence synthesized qualitatively rather than through quantitative meta-analysis. A total of 5127 records published between 2021 and 2026 were screened, resulting in 24 primary studies supported by 115 complementary studies. The findings show that machine learning, deep learning, hybrid AI, Explainable Artificial Intelligence (XAI), Federated Learning (FL), blockchain-assisted security, and edge intelligence have significantly advanced IoMT intrusion detection. However, despite benchmark accuracies often exceeding 95%, deployment remains constrained by dataset dependency, weak cross-dataset generalization, computational overhead, limited explainability, fragmented benchmarking, and insufficient operational validation. This review identifies deployment readiness, rather than predictive accuracy alone, as the principal challenge for next-generation healthcare cybersecurity and provides a practical framework for developing trustworthy, interoperable, privacy-preserving, and deployment-ready IoMT cybersecurity architectures supported by standardized evaluation protocols. Full article

Background/Objectives: Human gait analysis is essential for identifying biomechanical alterations associated with pathological conditions. However, conventional laboratory systems that combine optical motion capture and force plates remain costly, space-demanding, and difficult to implement in routine or accessible settings. This study proposes a dual-model artificial intelligence framework designed to bridge kinematics and dynamics and subsequently support gait health-status classification from motion data. Methods: The first model was developed to estimate ground reaction forces (GRF) and center of pressure (CoP) signals from kinematic inputs. Public datasets containing synchronized kinematics and dynamics were used to train and evaluate long short-term memory (LSTM) and one-dimensional convolutional neural network (CNN1D) architectures. A robustness stage further adapted the dynamic prediction model to markerless-like kinematic inputs through domain-adaptation training. The second model was implemented as a multichannel convolutional classifier using normalized GRF/CoP signals and metadata. Three variants were compared: signals only, signals with minimal metadata, and signals with rich metadata. Finally, a bridge block connected both models, and a proof-of-concept deployment was performed using markerless kinematics obtained with Move AI and Blender. Results: The final dynamic prediction model achieved an overall RMSE of 0.0676, with reconstructed-signal RMSE of 0.0500 and reconstructed contact accuracy of 0.9736. The best classification variant achieved a balanced accuracy of 0.9608, while the minimal-metadata variant was selected for pipeline integration due to its compatibility with accessible data acquisition. In the full pipeline evaluation, the predicted dynamics correctly classified the healthy-control samples. In the Move AI/Blender proof-of-concept, all five healthy participants were classified as healthy controls, with a mean non-pathological classification probability consistent with this outcome. Conclusions: The proposed dual-model framework demonstrates the operational feasibility of linking kinematic acquisition, dynamic prediction, and gait classification within a single artificial intelligence pipeline. The Move AI/Blender stage represents a preliminary proof of concept rather than clinical validation, and further evaluation with pathological participants and synchronized force-plate measurements is required. Full article

Advances in artificial intelligence have made hand gesture recognition an important human–computer interaction modality. Graph convolutional networks (GCNs) are widely used for skeleton-based hand gesture recognition, yet their performance can be limited by weak semantic topology modeling, underused feature channels, and shallow spatio-temporal fusion. We propose a Multi-scale Attention Graph Convolutional Network (MA-GCN) that combines three components within one skeleton framework: a hybrid topology that augments physiological connections with semantic priors; a Gaussian Multi-Scale Channel Attention (GMCA) module for coordinate denoising and adaptive channel weighting; and a Local-Global Fusion Module (LGFM) that combines local convolutional features with channel-wise global attention. Ablation studies quantify the independent and joint contributions of these components. MA-GCN obtains Top-1 accuracies of 97.50%/95.95% on SHREC’17 Track and 94.29%/92.86% on DHG14/28 for the 14-/28-class settings. In a SHREC’17 Track-to-FPHA pre-train-then-fine-tune evaluation, it reaches 94.09% Top-1 accuracy, providing preliminary evidence that the proposed framework maintains effectiveness under cross-dataset transfer. Full article