Search Results (3,195)

The growth of electronic word-of-mouth (eWOM) on digital platforms has heightened the need to distinguish authentic user-generated content from covert promotional material. This study proposes an integrated framework combining Natural Language Processing (NLP), machine learning, and Latent Dirichlet Allocation (LDA) to classify sentiment and detect advertising features in online game reviews. Reviews from the Steam platform were analyzed using Support Vector Machine (SVM), Decision Tree, and Naïve Bayes classifiers, with class imbalance addressed through SMOTE and SMOTE–Tomek techniques. The SMOTE-augmented SVM achieved the highest performance, with 98.18% overall accuracy and 97.52% negative sentiment detection. LDA and Quality Function Deployment (QFD) further uncovered latent promotional themes, providing insights into how advertising elements manifest in positive reviews and how negative feedback reflects genuine user concerns. The framework assists platform managers in enhancing eWOM credibility and supports marketers in designing data-driven advertising strategies. By bridging sentiment analysis with covert marketing detection, this research contributes a novel methodological approach for assessing review trustworthiness, improving transparency, and fostering consumer trust in digital information environments. Full article

Biomimetic olfactory and taste biosensors replicate human sensory functions by coupling selective biological recognition elements (such as receptors, binding proteins, or synthetic mimics) with highly sensitive transducers (including electrochemical, transistor, optical, and mechanical types). This review summarizes recent progress in olfactory and taste biosensors focusing on three key areas: (i) materials and device design, (ii) artificial intelligence (AI) and data fusion for real-time decision-making, and (iii) pathways for practical application, including hybrid platforms, Internet of Things (IoT) connectivity, and regulatory considerations. We provide a comparative analysis of smell and taste sensing methods, emphasizing cases where integrating both modalities enhances sensitivity, selectivity, detection limits, and reliability in complex environments like food, environmental monitoring, healthcare, and security. Ongoing challenges are addressed with emerging solutions such as antifouling/self-healing interfaces, modular cartridges, machine learning (ML)-assisted calibration, and manufacturing-friendly approaches using scalable microfabrication and sustainable materials. The review concludes with a practical roadmap advocating for the joint development of receptors, materials, and algorithms; establishment of open standards for long-term stability; implementation of explainable/edge AI with privacy-focused analytics; and proactive collaboration with regulatory bodies. Collectively, these strategies aim to advance biomimetic smell and taste biosensors from experimental prototypes to dependable, commercially viable tools for continuous chemical sensing in real-world applications. Full article

The pomegranate, a widely consumed fruit, produces large quantities of waste, mainly from its peel. Pomegranate peels (PPs) contain high amounts of antioxidant compounds, such as polyphenols, flavonoids, and anthocyanins, which can be isolated from them and used for the benefit of humans and the environment. In the present work, a study of recovery of these compounds by ultrasound-assisted extraction (UAE) was carried out, whose parameters were optimized. The optimal results were a total polyphenol content of 195.55 mg gallic acid equivalents/g, total flavonoid content of 74.78 mg rutin equivalents/g, total anthocyanin content of 992.87 μg cyanidin 3-O-glucoside equivalents/g, and ascorbic acid content of 15.68 mg/g, while the antioxidant activity determined through ferric-reducing antioxidant power and DPPH assays was 2366.89 and 1755.17 μmol ascorbic acid equivalents/g, respectively. In parallel, an artificial intelligence (AI)-based framework was developed to model and predict antioxidant and phytochemical responses from UAE parameters. Six machine learning models were implemented on the experimental dataset, with the Random Forest (RF) regressor consistently achieving the best predictive accuracy. Partial dependence analysis revealed ethanol concentration as the dominant factor influencing outcomes, while ultrasonic power and extraction time exerted comparatively minor effects. Although dataset size limited model generalizability, the RF model reproduced experimental outcomes within experimental variability, underscoring its suitability for predictive extraction optimization. These findings demonstrate the complementary role of machine learning in accelerating antioxidant compound recovery research and its potential to guide future industrial-scale applications of AI-assisted extraction. Full article

Electromyography-based assistive and rehabilitation devices have shown potential for restoring mobility, especially for post-stroke patients. However, the variability of biological signals and the processing delays caused by signal acquisition and feature extraction influence myoelectric control systems’ real-time functionality and robustness. This study evaluates the classification performance of electromyographic (EMG) signals for six distinct hand gestures in healthy individuals and post-stroke patients. Different feature extraction methods and machine learning algorithms are employed to analyze the impact of acquisition time (0.5–4 s) and the number of channels (1–4) on model accuracy, robustness, and generalization. The best results are obtained using power spectral density and dimensionality reduction, reaching a classification accuracy of 94.79% with a 2 s signal and 95.31% for 4 s. Acquisition time has a greater effect on accuracy than the number of channels used with accuracy stabilizing at 2 s. We test for generalization using post-stroke patient data, evaluating two scenarios: intra-patient validation with 90% accuracy and cross-patient validation with 35–40% accuracy. This study contributes to developing effective real-time myoelectric control systems for neurorehabilitation. Full article

Background: Artificial intelligence (AI) has been proposed as a transformative tool in suicide prevention, yet most evidence remains observational. To provide a rigorous benchmark, we systematically reviewed randomized controlled trials (RCTs) evaluating AI-based interventions targeting suicidal thoughts, behaviours, or help-seeking. Methods: Following PRISMA 2020 guidelines, MEDLINE, Web of Science, and Scopus were searched to 31 May 2025. Eligible studies were RCTs in humans that incorporated AI or machine learning for risk prediction, automated intervention, or treatment allocation. Methodological quality was assessed with the PEDro scale and certainty of evidence with GRADE. Results: From 1101 screened records, six RCTs (n = 793) met all criteria. Three studies tested machine learning risk prediction, two evaluated fully automated interventions (a transformer-based recommender and a digital nudge), and one examined AI-assisted treatment allocation. Risk-prediction models stratified short-term suicidal outcomes with accuracies of up to 0.67 and AUC values around 0.70. Digital interventions reduced counsellor response latency or increased crisis-service uptake by 23%. Algorithm-guided allocation reduced the occurrence of suicidal events when randomisation aligned with model recommendations. Methodological quality was moderate to high (median PEDro = 8/10), but GRADE certainty was low due to small samples and imprecision. Conclusions: AI can enhance discrete processes in suicide prevention, including risk stratification, help-seeking, and personalized treatment. However, the current evidence is limited, and larger multisite RCTs with longer follow-up, CONSORT-AI compliance, and equity-focused design are urgently required. Full article

Anaerobic digestion (AD) is increasingly recognized as a key technology for renewable energy generation and sustainable waste management within the circular economy. However, its performance is highly sensitive to feedstock variability and environmental fluctuations, making stable operation and high methane yields difficult to sustain. Conventional monitoring and control systems, based on limited sensors and mechanistic models, often fail to anticipate disturbances or optimize process performance. This review discusses recent progress in electrochemical, optical, spectroscopic, microbial, and hybrid sensors, highlighting their advantages and limitations in artificial intelligence (AI)-assisted monitoring. The role of soft sensors, data preprocessing, feature engineering, and explainable AI is emphasized to enable predictive and adaptive process control. Various machine learning (ML) techniques, including neural networks, support vector machines, ensemble methods, and hybrid gray-box models, are evaluated for yield forecasting, anomaly detection, and operational optimization. Persistent challenges include sensor fouling, calibration drift, and the lack of standardized open datasets. Emerging strategies such as digital twins, data augmentation, and automated optimization frameworks are proposed to address these issues. Future progress will rely on more robust sensors, shared datasets, and interpretable AI tools to achieve predictive, transparent, and efficient biogas production supporting the energy transition. Full article

Background/Objectives: Artificial intelligence (AI) has been increasingly used to support radiological assessment in dentistry. We benchmarked machine learning (ML), deep learning (DL), and a hybrid optimization-assisted approach for the automatic five-class image-level classification of dental restorations (filling, implant, root canal treatment, fixed partial denture/bridge, crown) on panoramic radiographs. Methods: We analyzed 353 anonymized panoramic images comprising 2137 labeled restorations, acquired on the same device. Images were cropped and enhanced (histogram equalization and CLAHE), and texture features were extracted with GLCM. A three-stage pipeline was evaluated: (i) GLCM-based features classified by conventional ML and a baseline DL model; (ii) Hybrid Grey Wolf–Particle Swarm Optimization (HGWO-PSO) for feature selection followed by SVM; and (iii) a CNN trained end-to-end on raw images. Performance was assessed with an 80/20 per-patient split and 5-fold cross-validation on the training set. While each panoramic radiograph may contain multiple restorations, in this study we modeled the task as single-label, image-level classification (dominant restoration type) due to pipeline constraints; this choice is discussed as a limitation and motivates multi-label, localization-based approaches in future work. The CNN baseline was implemented in TensorFlow 2.12 (CUDA 11.8/cuDNN 8.9) and trained with Adam (learning rate 1 × 10⁻⁴), with a batch size 32 and up to 50 epochs with early stopping (patience 5); data augmentation included horizontal flips, ±10° rotations, and ±15% brightness variation. A post hoc power analysis (G*Power 3.1; α = 0.05, β = 0.2) confirmed sufficient sample size (n = 353, power > 0.84). Results: The HGWO-PSO + SVM configuration achieved the highest accuracy (73.15%), with macro-precision/recall/F1 = 0.728, outperforming the CNN (68.52% accuracy) and traditional ML models (SVM 67.89%; DT 59.09%; RF 58.33%; K-NN 53.70%). Conclusions: On this single-center dataset, the hybrid optimization-assisted classifier moderately improved detection performance over the baseline CNN and conventional ML. Given the dataset size and class imbalance, the proposed system should be interpreted as a decision-supportive tool to assist dentists rather than a stand-alone diagnostic system. Future work will target larger, multi-center datasets and stronger DL baselines to enhance generalizability and clinical utility. Full article

Brain–Computer Interface (BCI) technology facilitates direct communication between the human brain and external devices by interpreting brain wave patterns associated with specific motor imagery tasks, which are derived from EEG signals. Although BCIs allow applications such as robotic arm control and smart assistive environments, they face major challenges, mainly due to the large variation in EEG characteristics between and within individuals. This variability is caused by low signal-to-noise ratio (SNR) due to both physiological and non-physiological artifacts, which severely affect the detection rate (IDR) in BCIs. Advanced multi-stage signal processing pipelines, including efficient filtering and decomposition techniques, have been developed to address these problems. Additionally, numerous feature engineering techniques have been developed to identify highly discriminative features, mainly to enhance IDRs in BCIs. In this review, several pre-processing techniques, including feature extraction algorithms, are critically evaluated using deep learning techniques. The review comparatively discusses methods such as wavelet-based thresholding and independent component analysis (ICA), including empirical mode decomposition (EMD) and its more sophisticated variants, such as Self-Adaptive Multivariate EMD (SA-MEMD) and Ensemble EMD (EEMD). These methods are examined based on machine learning models using SVM, LDA, and deep learning techniques such as CNNs and PCNNs, highlighting key limitations and findings, including different performance metrics. The paper concludes by outlining future directions. Full article

Understanding and accurately estimating cognitive workload is crucial for the development of adaptive, user-centered interactive systems across a variety of domains including augmented reality, automotive driving assistance, and intelligent tutoring systems. Cognitive workload assessment enables dynamic system adaptation to improve user experience and safety. In this work, we introduce a novel framework that leverages smooth pursuit eye movements as a non-invasive and temporally precise indicator of mental effort. A key innovation of our approach is the development of trajectory-independent algorithms that address a significant limitation of existing methods, which generally rely on a predefined or known stimulus trajectory. Our framework leverages two solutions to provide accurate cognitive load estimation, without requiring knowledge of the exact target path, based on Kalman filter and B-spline heuristic classifiers. This enables the application of our methods in more naturalistic and unconstrained environments where stimulus trajectories may be unknown. We evaluated these algorithms against classical supervised machine learning models on a publicly available benchmark dataset featuring diverse pursuit trajectories and varying cognitive workload conditions. The results demonstrate competitive performance along with robustness across different task complexities and trajectory types. Moreover, our framework supports real-time inference, making it viable for continuous cognitive workload monitoring. To further enhance deployment feasibility, we propose a federated learning architecture, allowing privacy-preserving adaptation of models across heterogeneous devices without the need to share raw gaze data. This scalable approach mitigates privacy concerns and facilitates collaborative model improvement in distributed real-world scenarios. Experimental findings confirm that metrics derived from smooth pursuit eye movements reliably reflect fluctuations in cognitive states induced by working memory load tasks, substantiating their use for real-time, continuous workload estimation. By integrating trajectory independence, robust classification techniques, and federated privacy-aware learning, our work advances the state of the art in adaptive human–computer interaction. This framework offers a scientifically grounded, privacy-conscious, and practically deployable solution for cognitive workload estimation that can be adapted to diverse application contexts. Full article

Population aging and rising rehabilitation demands highlight the need for advanced assistive devices to improve mobility in individuals with motor impairments. Existing back-support lifting nursing beds often lack adequate human–machine adaptability, safety, and emotional consideration. This study presents a human-centered, data-driven optimization pipeline that integrates behavior–emotion dual recognition, simulation verification, and parameter optimization with user demand mining, biomechanical simulation, and sustainable practices. The design utilizes GreenAI, focusing on low-power algorithms and eco-friendly materials, ensuring energy-efficient AI models and reducing the environmental footprint. A dual-channel data fusion method was developed, combining movement parameters from sit-to-lie transitions with emotional needs extracted from e-commerce reviews using the Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA) models. The fuzzy Kano model prioritized design objectives, identifying multi-position adjustment, joint protection, armrest optimization, and interaction comfort as key targets. An AnyBody-based human–device model quantified muscle (erector spinae, rectus abdominis, trapezius) and hip joint loads during posture changes. Simulations verified the design’s ability to improve load distribution, reduce joint stress, and enhance comfort. The optimized nursing bed demonstrated improved adaptability across user profiles while maintaining functional reliability. This framework offers a scalable paradigm for intelligent rehabilitation equipment design, with potential extension toward AI-driven adaptive control and clinical validation. This sustainable methodology ensures that the device not only meets rehabilitation goals but also contributes to a more environmentally responsible healthcare solution, aligning with global sustainability efforts. Full article

Recent breakthroughs in machine learning, artificial intelligence, and the emergence of large datasets have made the integration of eye tracking increasingly feasible not only in computing but also in many other disciplines to accelerate innovation and scientific discovery. These transformative changes often depend on intelligently analyzing and interpreting gaze data, which demand a substantial technical background. Overcoming these technical barriers has remained an obstacle to the broader adoption of eye tracking technologies in certain communities. In an effort to increase accessibility that potentially empowers a broader community of researchers and practitioners to leverage eye tracking, this paper presents an open-source software platform: Beach Environment for the Analytics of Human Gaze (BEACH-Gaze), designed to offer comprehensive descriptive and predictive analytical support. Firstly, BEACH-Gaze provides sequential gaze analytics through window segmentation in its data processing and analysis pipeline, which can be used to achieve simulations of real-time gaze-based systems. Secondly, it integrates a range of established machine learning models, allowing researchers from diverse disciplines to generate gaze-enabled predictions without advanced technical expertise. The overall goal is to simplify technical details and to aid the broader community interested in eye tracking research and applications in data interpretation, and to leverage knowledge gained from eye gaze in the development of machine intelligence. As such, we further demonstrate three use cases that apply descriptive and predictive gaze analytics to support individuals with autism spectrum disorder during technology-assisted exercises, to dynamically tailor visual cues for an individual user via physiologically adaptive visualizations, and to predict pilots’ performance in flight maneuvers to enhance aviation safety. Full article

This study presents a Digital Image Correlation (DIC)-based experimental framework for the calibration of the Hosford-Coulomb (HC) and Modified-Mohr Coulomb (MMC) damage initiation criteria in an Advanced High Strength Steel (AHSS) DP1000. Three characteristic loading conditions in sheet metal forming—pure shear, uniaxial tension, and plane strain tension—were reproduced using flat specimens in a universal tensile testing machine, thus eliminating the need for costly and time-consuming tooling systems. An additional notch tension specimen was employed to validate the stress-state sensitivity of the proposed calibration approach. By integrating full-field strain data from DIC with tensile test results, stress–strain relationships were directly obtained without finite element modeling. The results confirm the effectiveness of dogbone, mini shear, and plane strain tension specimens in achieving proportional loading path histories up to fracture initiation, with constant stress state evolution during deformation. Comparison of the HC and MMC damage criteria reveals similar fracture loci, with the HC model exhibiting slightly higher resistance between shear and uniaxial tension conditions. This study discusses the suitability of a fully experimental DIC-based methodology for the calibration of stress-state-dependent damage initiation criteria. The results highlight the ability of the proposed methodology as a simplified and lower time-consuming alternative to traditional numerical assisted frameworks. Full article

Sensor sampling errors and inverter dead-time effects introduce significant nonlinear disturbances into dual three-phase permanent magnet synchronous machine (DTP-PMSM) drive systems with sinusoidal excitation, leading to pronounced alternating current (AC) and direct current (DC) disturbances. These disturbances severely compromise the stability and reliability of the current control loop, ultimately degrading the overall driving accuracy of the system. To effectively address this issue, this paper proposes a novel interference suppression strategy based on bi-subspace predictive current control. Specifically, the proposed approach optimizes modulation through two-step virtual-vector-based predictive current control (VVPCC) operation to achieve disturbance decoupling. Building upon this foundation, a model-assisted discrete extended state observer (DESO) is incorporated into the fundamental subspace, whereas a discrete vector resonant controller (DVRC) with pre-distorted Tustin discretization is applied to the secondary subspace. Modeling analysis and experimental results demonstrate that, compared with the classical VVPCC method, the proposed bi-subspace VVPCC method has good steady-state performance and enhanced robustness in the presence of disturbances. Full article

The rapid increase in retired lithium-ion batteries (LIBs) from electric vehicles (EVs) highlights the urgent need for accurate and automated end-of-life (EOL) assessment. This study proposes an AI-integrated smart grading system that combines hardware diagnostics and deep learning-based evaluation to classify the residual usability of retired batteries. The system incorporates a bidirectional charger/discharger, a CAN-enabled battery management system (BMS), and a GUI-based human–machine interface (HMI) for synchronized real-time data acquisition and control. Four diagnostic indicators—State of Health (SOH), Direct Current Internal Resistance (DCIR), temperature deviation, and voltage deviation—are processed through a deep neural network (DNN) that outputs categorical grades (A: reusable, B: repurposable, C: recyclable). Experimental validation shows that the proposed AI-assisted model improves grading accuracy by 18% and reduces total testing time by 30% compared to rule-based methods. The integration of adaptive correction models further enhances robustness under varying thermal and aging conditions. Overall, this system provides a scalable framework for automated, explainable, and sustainable battery reuse and recycling, contributing to the circular economy of energy storage. Full article

Efficient operation of robotic manipulators in constrained workspaces requires careful coordination of robot placement, motion planning, and posture optimization. This paper presents a hierarchical optimization framework that addresses these challenges for robot placement, motion planning, and posture determination for multi-target manipulation tasks. Initially, the workspace layout is optimized using an adaptive genetic algorithm to determine robot placement that maximizes reachability and task efficiency. Subsequently, a surrogate-assisted rapidly-exploring random tree (SA-RRT) algorithm generates collision-free paths from the start to target configurations, leveraging machine learning models to reduce computational cost while preserving path quality. Finally, the robot’s posture is optimized via a second genetic algorithm to achieve a single configuration that allows rapid access to all target positions. The effectiveness of the proposed framework was evaluated through extensive simulations in a Unity-based environment, comparing SA-RRT against the conventional target-biased nearest neighbor (TNN-RRT) algorithm. In particular, the proposed SA-RRT algorithm reduces path planning computation time by 76.17% compared to TNN-RRT and also yields lower path cost, demonstrating both efficiency and path quality improvement. Overall, the framework provides a unified methodology for integrating layout planning, motion planning, and posture optimization, facilitating more effective deployment of robotic manipulators in industrial environments. Full article