Search Results (6,837)

The deployment of artificial intelligence in safety-critical industrial systems is hindered by a core trust deficit, as models trained via empirical risk minimization often fail catastrophically in out-of-distribution (OOD) scenarios. We address this challenge by developing a physics-informed hybrid ensemble that achieves state-of-the-art accuracy and robustness for Permanent Magnet Synchronous Motor (PMSM) temperature forecasting. Our methodology first calibrates a Lumped-Parameter Thermal Network (LPTN) to serve as a physics engine for generating physically consistent data augmentations, which then pre-trains a Temporal Convolutional Network (TCN) encoder via self-supervision, with the final prediction assembled from the physics model’s baseline guess and a correction learned by an ensemble of gradient boosting models on a rich, multi-modal feature set. Evaluated against a suite of strong baselines, our hybrid ensemble achieves a state-of-the-art Root Mean Squared Error of 5.24 °C on a challenging OOD stress test composed of the most chaotic operational profiles. Most compellingly, our model’s performance improved by an unprecedented −10.68% under these extreme stress conditions where standard, purely data-driven models collapsed. This demonstrated robustness, combined with a statistically valid Coverage Under Shift (CUS) Gap of only 1.43%, provides a complete blueprint for building high-performance, trustworthy AI, enabling safer and more efficient control of critical cyber-physical systems and motivating future research into physics-guided pre-training for other industrial assets. Full article

While walking robots possess significantpotential for various real-world applications, the reliance on high-performance sensors and complex control architectures for precise gait control remains a significant barrier to commercialization and lightweight design. To overcome these engineering limitations and lay the groundwork for a sensing paradigm adaptable to complex terrains, this study proposes an AI-based sensorless feedback control framework that incorporates the biological principles of proprioception. To this end, a walking robot leveraging the morphological intelligence of the Klann linkage was developed. We constructed a time-series dataset by defining motor current signals as ‘interoceptive sensing’ information—analogous to biological muscle feedback—and synchronizing them with absolute angular data. This dataset was used to train an Attention-LSTM (A-LSTM) model, which predicts future motor states in real-time by decoding nonlinear physical information embedded within internal current data, independent of external environmental sensors. By integrating the proposed model into a PI controller, a stable biomimetic walking loop was successfully implemented without the need for additional position sensors. Full article

This study introduces and compares online rule-based and optimization-based energy management strategies for a mild hybrid electric vehicle, with their performance evaluated against an offline Dynamic Programming benchmark. A structured rule-based strategy is proposed to enforce engine operation along its optimal efficiency line, while the remaining power demand is balanced by the electric motor. To achieve charge-sustaining battery operation, a soft state of charge regulation mechanism is incorporated. An Equivalent Consumption Minimization Strategy (ECMS) is also developed using a precise formulation of battery equivalent fuel consumption computed from instantaneous engine and electric path efficiencies, instead of constant efficiencies used in the literature. DP, which provides a globally optimal solution over the entire driving cycle, is employed as a benchmark for assessing the rule-based and ECMS strategies. The control strategies are compared under charge-sustaining conditions, considering engine and motor operation characteristics, overall fuel consumption, and battery usage intensity. Furthermore, the influence of load shifting between the internal combustion engine and the electric motor on overall vehicle performance is analyzed. Fuel consumption decreases by 13.5% relative to the engine-only baseline with the proposed ECMS with precise equivalent fuel consumption, and DP yields an additional 1.6% benefit. Compared with the developed rule-based controller, ECMS nearly halves the battery usage intensity, and DP provides 3.1% further reduction relative to ECMS. Full article

This paper presents an evaluation methodology for multiphase Permanent Magnet Synchronous Motors (PMSMs) using winding function theory. The study extends a previously developed space harmonic model and focuses on deriving comparative indicators for making decisions on slot, pole, and phase number combinations. Thus, it contributes a unified framework that integrates diverse performance indicators for the early-stage evaluation of multiphase motors, complemented by an experimental validation that defines the accuracy limits of such analytical models. Key performance metrics such as cogging torque harmonic order, torque ripple harmonic order, winding factor, inductance value, and inductance balance among harmonic planes are analytically derived and applied to two motor configurations: a Three-Phase (TP) and a Dual Three-Phase (DTP) motor, both with 24 slots and 10 pole pairs. Theoretical analysis reveals that the DTP winding offers improved torque capability, higher fundamental inductance ratio, and lower torque ripple, contributing to enhanced torque production and reduced airgap harmonic content. Experimental validation confirms the analytical predictions, demonstrating a 3.5% increase in torque and a 4–5% reduction in inductance for the DTP configuration. Additionally, vibration and torque ripple measurements show lower harmonic content in the DTP motor. While minor discrepancies existed between the analytical and experimental data, they were deemed within acceptable limits for a tool designed for preliminary comparative analysis rather than exact performance prediction. However, the analytical model was unable to predict the inductance balance across the various harmonic planes; addressing this would require a more complex model, which was beyond the scope of the current study. These findings underscore the effectiveness of winding function theory as a rapid design tool for evaluating multiphase motor windings. Full article

Parkinson’s disease (PD) is a progressive neurodegenerative disorder in which early detection remains a major clinical challenge due to heterogeneous motor and non-motor manifestations and the lack of reliable biomarkers. In recent years, machine learning (ML) and deep learning (DL) methods have been increasingly investigated as decision-support tools for PD screening using diverse clinical and behavioral data. This review synthesizes PD detection studies published between 2017 and 2025, systematically analyzing 32 representative works across multiple modalities, including MRI, PET, EEG, REM sleep biomarkers, voice recordings, gait signals, handwriting/drawing tasks, and finger-tapping measurements. Across the reviewed literature, high classification performance is frequently reported, with CNN-based and hybrid DL architectures achieving particularly strong results in imaging and time-series settings, while classical ML approaches such as SVM and ensemble models remain competitive for engineered feature-based datasets. However, the review also reveals major barriers to reliable translation, including small datasets, inconsistent evaluation protocols, limited external validation, and the risk of performance inflation caused by non-subject-independent data splitting. Overall, this review provides a structured and modality-oriented reference of algorithms, datasets, and performance trends, while highlighting key methodological gaps and practical priorities for developing robust and clinically deployable PD detection systems. Full article

Spontaneous intracerebral hemorrhage (ICH) is associated with substantial mortality and morbidity. Current management paradigms rely heavily on the rapid interpretation of neuroimaging and clinical data, yet are frequently constrained by limitations in processing speed, diagnostic accuracy, and prognostic precision. Artificial intelligence (AI), specifically machine learning (ML) and deep learning (DL), offers transformative potential to circumvent these challenges across the entire continuum of ICH care. This comprehensive review synthesizes the rapidly evolving landscape of AI applications in ICH management. Through a systematic evaluation of recent literature, we examine studies focused on the development, validation, or critical appraisal of AI-driven technologies for ICH care. Our analysis encompasses automated neuroimaging, computer-assisted surgical navigation, brain–computer interfaces (BCIs), prognostic modeling, and fundamental research into disease mechanisms. AI has demonstrated performance comparable to that of clinical experts in automating hematoma segmentation, predicting complications such as hematoma expansion, and refining surgical planning via augmented reality. Furthermore, BCIs present innovative therapeutic avenues for motor rehabilitation. However, the translation of these technological advances into routine clinical practice is impeded by substantial challenges, including data heterogeneity, model opacity (“black-box” issues), workflow integration barriers, regulatory ambiguities, and ethical concerns surrounding accountability and algorithmic bias. The integration of AI into ICH care signifies a paradigm shift from standardized treatment protocols toward dynamic, precision medicine. Realizing this vision necessitates interdisciplinary collaboration to engineer robust, generalizable, and interpretable AI systems. Key priorities include the establishment of large-scale multimodal data repositories, the advancement of explainable AI (XAI) frameworks, the execution of rigorous prospective clinical trials to validate efficacy, and the implementation of adaptive regulatory and ethical guidelines. By systematically addressing these barriers, AI can evolve from a mere analytical tool into an indispensable clinical partner, ultimately optimizing patient outcomes. Full article

This study develops an interpretable machine learning framework for type 1 motor insurance renewal classification using 70,290 real-world Thai policies, providing essential insights for pricing, customer retention, and operational decision making. The dataset was partitioned into a 70% training set, utilizing 5-fold cross-validation for hyperparameter tuning and model selection, and a 30% hold-out testing set to evaluate final model performance. Five machine learning models including Binary Logistic Regression, K-Nearest Neighbors, Support Vector Machines, Random Forests, and XGB are systematically evaluated across multiple curated feature sets generated through statistical filtering, stepwise selection, and permutation-based importance. Non-parametric tests are employed to compare model performance across scenarios. Experimental results show that a reduced four-feature Random Forest model (car age, net premium, sum insured, and car group) achieves the highest predictive performance (AUC = 99.62%; F1 = 98.15%), outperforming full-feature models while maintaining superior computational efficiency. Consequently, H2OAutoML serves as an external validation tool to verify that this manually curated, interpretable pipeline remains highly competitive with fully automated systems. Integrating a SHAP-based explainability layer quantifies predictor influence, ensuring transparency and regulatory alignment. Prioritizing feature parsimony, this study provides integrable insights for dynamic pricing and risk-adjusted retention, enhancing decision support within evolving motor insurance markets through transparent systems. Full article

Recreational dance offers significant psychological well-being potential. However, traditional instruction emphasizes technique while limiting attention to nervous system development and embodied meaning-making. Despite empirical support for polyvagal theory, motor learning science, somatic education, and phenomenology, their systematic integration into unified structures is not clearly established in recreational dance contexts. This protocol integrates nervous system regulation, motor learning, and creative expression within structured Imperial Society of Teachers of Dancing (ISTD) modern dance syllabus for recreational adults. It presents a 12-week integrated dance-mindfulness intervention addressing this gap through a three-phase structure grounded in neuroscience and embodied pedagogy. The intervention comprises eight standardized components delivered weekly. The randomized controlled trial evaluates intervention effects using the Satisfaction With Life Scale (SWLS), Depression Anxiety Stress Scales-21 (DASS-21), the Mindful Attention Awareness Scale (MAAS), the Subjective Happiness Scale (SHS), and the Leisure Involvement Scale (LIS). Qualitative assessment via semi-structured phenomenological interviews (Weeks 8 and 12) and weekly journaling captures somatic awareness, nervous system resilience, technical confidence, creative expression, relational and social belonging, and embodied meaning-making. Intervention participants are expected to show significantly greater improvements compared to controls. Results will establish evidence-based practice standards for recreational dance and demonstrate neuroscience integration’s efficacy for psychological wellbeing and embodied meaning-making. Full article

The early detection and diagnosis of faults in induction motors is vital in today’s industry, since these are the motors used for the largest number of applications in the industrial environment and failure to detect a fault early can lead to significant losses. Bearing faults are the main problems detected in induction motors and several techniques have been developed to detect them. The use of the information contained in the motor vibrations is the main traditional source for its diagnosis, although there are also proposals that use the supply current, or the sound of the motor. Furthermore, these variables can be used in the time domain or in the frequency domain. The purpose of this work is to use explainable artificial intelligence (XAI) to determine which of these variables, and in which domain, contributes most to a correct diagnosis and how much can be gained in diagnosis by using multisensor data fusion. To carry out this comparison in the most objective way possible, a model selection procedure is proposed and boosting techniques are considered that prove to give a very precise diagnosis. The obtained diagnostic rules are then interpreted using SHAP values, a recent interpretation technique for complex classification procedures. Full article

Parkinson’s disease (PD) and associated synucleinopathies are preceded by a prolonged prodromal phase during which neurodegenerative processes evolve years before the onset of motor or cognitive symptoms. Identifying biologically specific and accessible biomarkers during this window is critical for early diagnosis, risk stratification, and the development of disease-modifying therapies. Increasing evidence supports the skin as a key peripheral tissue involved in synucleinopathy, offering a minimally invasive source for in vivo detection of pathological α-synuclein. This review summarizes current evidence on skin-derived biomarkers across the prodromal continuum of PD, with particular emphasis on skin biopsy-based detection of phosphorylated α-synuclein and α-synuclein seed amplification assays (SAAs). Findings in high-risk prodromal phenotypes, including idiopathic REM sleep behavior disorder (iRBD) and pure autonomic failure (PAF), are critically reviewed. Emerging data suggest that cutaneous α-synuclein pathology may precede nigrostriatal dopaminergic degeneration and may predict phenoconversion to overt synucleinopathies. Important knowledge gaps are highlighted, including the lack of data in other prodromal phenotypes such as hyposmia. Overall, skin-based biomarkers appear to represent promising, scalable tools for biological diagnosis, prognostication, and enrichment of prodromal PD cohorts in clinical trials. Full article

In recent years, primary school physical education and sports have been acknowledged as crucial for children’s comprehensive development and skill enhancement. Consequently, there is a demand for validated instruments to evaluate both intervention outcomes and their educational quality and inclusivity. This study aimed to create and validate EIP-Move (Educational and Inclusive Potential of Motor Programmes), a standardized instrument designed to assess the pedagogical, inclusive, relational, and equitable potential of physical education and sports initiatives. The research employed a longitudinal framework comprising multiple phases (theoretical construction, pilot study, psychometric validation, and longitudinal validation), founded on a conceptual model with four dimensions: pedagogical quality, inclusion and participation, relational climate and safety, and equity and valorization of differences. Psychometric analyses validated the robustness of the four-factor model, demonstrating strong reliability, validity, and measurement invariance across gender, context, and the presence of special educational needs, along with sensitivity to change and predictive validity with respect to subsequent programme-level outcomes, including students’ active participation, relational climate quality, psychological safety, and programme continuity over time, assessed across a 12-month longitudinal framework. In summary, EIP-Move emerges as a valid and reliable instrument, beneficial for both research and professional application, thereby significantly aiding the formative evaluation of motor programmes and fostering a culture of quality and inclusion in primary education. Full article

The use of photovoltaic (PV) water pumping technology offers a viable and sustainable alternative to conventional diesel-driven pumping systems. In PV-based pumping installations, the elimination of bulky transformers significantly reduces the overall system size and weight, which is particularly advantageous for rural and remote irrigation applications. However, removing the transformer can result in high common-mode voltage (CMV) when the induction motor is controlled using a direct torque control (DTC) scheme. This elevated CMV induces leakage currents that may damage the motor, compromise system reliability, and pose potential safety hazards. To ensure a more compact and safer PV pumping system, this paper introduces an improved DTC-based control strategy for induction motors driven by transformerless multilevel PV inverters. The proposed approach effectively suppresses leakage current by mitigating its main source, CMV, while maintaining the simple structure and dynamic performance inherent to conventional DTC. Two new look-up tables (LUTs) are developed to control the stator flux and electromagnetic torque while simultaneously eliminating leakage current. The first method, termed zero-medium vector DTC (ZMV-DTC), employs both zero and medium voltage vectors from the space vector diagram. The second, referred to as medium vector DTC (MV-DTC), utilizes only medium vectors. Numerical simulation results validate the feasibility and superior performance of the proposed algorithms in terms of leakage current suppression. Compared with a conventional DTC (C-DTC) scheme that is designed to limit the CMV, the proposed DTC algorithms achieve a much stronger reduction in the CMV, confining its amplitude to only a few volts, instead of the levels ±V_dc/6 typically produced by the C-DTC. As a result, the leakage current is effectively eliminated, ensuring safer and more reliable operation of the system. Full article

Parkinson’s disease (PD) is the second most prevalent neurodegenerative disorder, yet its pathogenic mechanisms remain incompletely understood, highlighting the need for reliable experimental models. We previously developed a murine model based on inhalation of a manganese mixture (MnCl₂ and Mn(OAc)₃), which reproduces dopaminergic neuron loss in the substantia nigra pars compacta (SNc) and motor impairment. However, its capacity to mimic mitochondrial dysfunction, a key mechanism in PD, had not been explored. This study evaluated mitochondrial ultrastructure, fission and fusion proteins, and the activity of electron transport chain complexes I and IV, alongside fine motor performance. Forty male CD1 mice were divided into control (deionized water) and manganese-exposed groups (0.04 M MnCl₂ + 0.02 M Mn(OAc)₃), inhaled for 1 h twice weekly over five months. Manganese inhalation induced significant fine motor deficits, increased mitochondrial number with reduced area and circularity, and disorganized cristae. Drp1 and Fis1 levels were elevated, accompanied by decreased activity of complexes I and IV, predominantly in the SNc. These findings demonstrate that this progressive, bilateral model reproduces mitochondrial and motor alterations resembling those observed in PD, supporting its utility for testing mitochondria-targeted therapeutic strategies. Full article

Background: Approximately half of patients with diabetes mellitus (DM) develop diabetic distal symmetric sensorimotor polyneuropathy (DM-DSPN), yet no reliable biomarkers for its early detection exist. This study assesses cystatin C (CysC), a naturally occurring protein, in diabetic persons with and without large-fiber DM-DSPN. Methods: This study involved persons with diabetes (HbA1c > 6.5%) visiting specialized diabetic clinics at King Saud University Medical City (KSUMC) in Riyadh, Saudi Arabia. Clinical features, laboratory data, nerve conduction findings, and serum CysC levels were assessed. DM-DSPN was diagnosed if signs of large nerve fiber impairment were present in the lower extremity in a symmetric and length-dependent pattern. Participants were designated as diabetic with or without large-fiber DSPN (+DM/+DSPN and +DM/−DSPN, respectively) based on validated composite scores of nerve conduction attributes. Results: A total of 52 persons with diabetes were included for analysis (24 with +DM/+DSPN and 28 with +DM/−DSPN). One participant had type 1 DM; all remaining participants had type 2 DM. In multivariate regression, serum CysC ≥ 0.88 mg/L was significantly associated with DM-DSPN. Serum CysC was significantly associated with peroneal and ulnar compound muscle action potential amplitudes (p-value = 0.003 and p-value = 0.03, respectively) and peroneal and tibial motor nerve conduction velocities (p-value = 0.009 and p-value = 0.0003, respectively). Conclusions: Serum CysC levels > 0.9 mg/L are associated with DM-DSPN (86% sensitivity and 81% specificity), independently of HbA1c or GFR. Serum CysC is also associated with peroneal and ulnar compound muscle action potential amplitudes and peroneal and tibial motor nerve conduction velocities. Larger studies are needed to determine the role of CysC as a potential biomarker of DM-DSPN. Full article

Background: Amyotrophic lateral sclerosis (ALS) is a devastating neurodegenerative disease that primarily affects the motor neurons. T cell intracellular antigen 1 (TIA1) is a risk gene for ALS pathogenesis. To elucidate TIA1-mediated disease mechanisms, a mouse model recapitulating clinical and pathological features of ALS is needed. TIA1 mutations are rare in human ALS, and mutations are heterozygous, while this study uses a homozygous TIA1 mutant mouse model to amplify pathogenic effects for experimental tractability. Methods: To explore the mechanisms by which mutant TIA1 causes ALS neurodegeneration, we generated a TIA1 mutant mouse by introducing ALS-causing mutations into the endogenous animal via cytosine base editors. Next, behavioral experiments (open-field and rotarod tests) assessed motor function and analyzed pathologies using morphological assessments. Results: Our TIA1Δ mouse model phenocopies select pivotal features of ALS, including TAR DNA-binding protein 43 (TDP-43) accumulation, motor neuron loss, neuroinflammation in the lumbar spinal cord, and muscle atrophy. Notably, this homozygous mutation design with reduced TIA1 expression differs from human heterozygous TIA1 mutations. Conclusions: This work provides a foundation for understanding the TIA1-ALS relationship and for developing strategies to treat this intractable neurodegenerative disorder. Caution is warranted extrapolating findings to human ALS pathogenesis due to model design differences. Full article