Search Results (11,563)

Human activity recognition (HAR) based on inertial measurement units (IMUs) embedded in wearable devices has gained increasing relevance in healthcare, wellness, and fitness monitoring. However, most existing classification methods assume a closed-set setting, where all activity classes need to be defined during training, which limits their applicability in real-world environments where unseen or unexpected activities are present. To overcome this limitation, we adopt an open-set recognition (OSR) framework that requires minimal changes to the HAR classifiers traditionally employed for this purpose. We also provide an extensive empirical evaluation based on a leave-one-activity-out validation protocol applied to two datasets with IMU signals acquired from smart eyewear: a proprietary dataset and the publicly available UCA-EHAR dataset. A lightweight one-dimensional convolutional neural network was trained to classify six-axis IMU data across common activities. We assess open-set HAR performance using several methods requiring limited computational overhead and operating in the logit space, including maximum logit, Gaussian Mixture Models, Kernel Density Estimation, OpenMax, and Nearest Neighbor Distance Ratio. Robust identification of unknown activities was achieved, with area under the ROC curve > 0.8. These findings highlight the potential of low-complexity open-set approaches for real-time HAR on resource-constrained wearable platforms, supporting the development of adaptive and reliable sensor-based recognition systems for real-world use. Full article

Predictive maintenance based on vibration monitoring can significantly improve gearbox reliability in heavy-industry environments. Although it is well established in vibration engineering that operating regimes influence vibration levels, the contribution of this work lies in providing an integrated, data-driven diagnostic linkage between continuously acquired IoT vibration indicators and key process/operational variables to identify and quantify the dominant drivers of vibration escalation. This study deployed wireless IoT sensors for continuous acquisition of RMS vibration and lubrication temperature in gearboxes operating in cement and mining plants and applied multivariate machine learning models to detect anomalies and identify root causes. We compared boosted multilayer feedforward neural networks, boosted trees, and k-nearest neighbors using RMS vibration and process variables including mill feed, lubrication pressures, and temperature. The boosted neural network delivered superior validation performance and isolated low or near-zero mill feed during operation as the primary driver of elevated RMS vibration, with lubrication instability acting as a secondary interacting factor. This shifts the diagnosis from a generic “high vibration during transients” statement to actionable operational mitigations—minimum feed set-points, controlled ramping logic, and lubrication pressure governance—supported by multivariate evidence. Our results motivate further validation with k-fold and out-of-time tests. Full article

Advancements in Industry 4.0 technologies, which combine big data analytics, robotics, and intelligent decision systems to enable new ways to increase automation in the industrial sector, have undergone significant transformations. In this research, a Hybrid Attention-Gated Recurrent Unit (At-GRU) model, combined with Sand Cat Optimization (SCO), is proposed to enhance fault identification and predictive maintenance capabilities. The model utilized multivariate sensor data from cyber-physical and IoT-enabled robotic platforms to learn operational patterns and predict failures with enhanced reliability. The At-GRU provides deeper temporal feature extraction, thereby improving classification performance. The robustness of the proposed model is validated through analysis of a benchmark dataset for industrial robots, and the results demonstrate that the proposed model exhibits impressive predictive capacity, surpassing other prediction methods and predictive maintenance approaches. Additionally, the performance evaluation indicates a lower computational cost due to the lightweight gating architecture of GRU, combined with attention. The robotic motion is further optimized by the SCO algorithm, which reduces energy usage, execution delay, and trajectory deviations while ensuring smooth operation. Overall, the proposed work offers an intelligent and scalable solution for next-generation industrial automation systems. Furthermore, the proposed model demonstrates the real-world applicability and significant benefits of incorporating hybrid artificial intelligence models into real-time robot control applications for smart manufacturing environments. Full article

Wildfires are environmental hazards with severe ecological, social, and economic impacts. Wildfires devastate ecosystems, communities, and economies worldwide, with rising frequency and intensity driven by climate change, human activity, and environmental shifts. Analyzing wildfire insights such as detection, predictive patterns, and risk assessment enables proactive response and long-term prevention. However, most of the existing approaches have been focused on isolated processing of data, making it challenging to orchestrate cross-modal reasoning and transparency. This study proposed a novel orchestrator-based multi-agent system (MAS), with the aim of transforming multimodal environmental data into actionable intelligence for decision making. We designed a framework to utilize Large Multimodal Models (LMMs) augmented by structured prompt engineering and specialized Retrieval-Augmented Generation (RAG) pipelines to enable transparent and context-aware reasoning, providing a cutting-edge Visual Question Answering (VQA) system. It ingests diverse inputs like satellite imagery, sensor readings, weather data, and ground footage and then answers user queries. Validated by several public datasets, the system achieved a precision of 0.797 and an F1-score of 0.736. Thus, powered by Agentic AI, the proposed, human-centric solution for wildfire management, empowers firefighters, governments, and researchers to mitigate threats effectively. Full article

The dairy sheep, vital to the Mediterranean economy, struggles to balance productivity, sustainability, and animal welfare, especially in extensive, small-scale systems. Precision livestock farming (PLF) technologies offer new opportunities by enabling continuous, non-invasive, and data-driven monitoring across diverse farming conditions. Despite rapid progress in sensors, computer vision, wearable devices, and artificial intelligence (AI), a comprehensive synthesis focused on dairy sheep remains limited. This review provides an updated overview of PLF applications in dairy sheep farming, based on a literature review. The 2018–2025 timeframe was chosen to capture recent advances in Internet of Things (IoT), AI, and sensor technologies that have achieved practical relevance only in recent years. The review identifies core technological domains such as automated weight and body condition monitoring, biometric identification, wearable and IoT-based sensors, localization systems, behavioral and thermal monitoring, virtual fencing, drone-assisted herding, and advanced decision-support tools. Innovations including lightweight deep-learning models, multimodal sensing frameworks, and digital twins highlight the growing potential for scalable, real-time applications. While technological progress is substantial, practical adoption is hindered by economic, technical, interoperability, and ethical barriers. This review consolidates current evidence and identifies future priorities to guide the development of integrated, welfare-focused PLF solutions for dairy sheep farming. Full article

Due to the rapid proliferation and evolution of the Internet of Things (IoT) in industrial and smart city applications, concerns over sensitive data security have become increasingly prominent. This is especially true in resource-constrained “cloud–terminal” centralized architectures, where ensuring privacy protection for downlink data and implementing fine-grained access control have become critical. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) serves as an effective solution due to its fine-grained access control capability. Nevertheless, conventional CP-ABE approaches face notable limitations when deployed in these practical settings, including the lack of an efficient and lightweight client-side revocation mechanism, excessive decryption overhead on terminal devices, and the practical difficulty in balancing security with performance. To address these issues, this paper proposes LOR-A2ABE, a Lightweight, Outsourced, and Revocable Anonymous Attribute-Based Encryption scheme. The scheme achieves lightweight client-side revocation through partial updates by embedding version numbers and timestamps into keys and ciphertexts via hash mapping. Furthermore, it employs outsourcing to offload the majority of computations to the cloud, allowing client-side decryption with only constant, low-complexity operations, thereby significantly reducing the computational burden on resource-constrained terminals. Considering the practical context where client devices are typically resource-limited sensors or microcontrollers and downlink data often require real-time processing, our scheme adopts a practical security model optimized for IoT constraints. This model prioritizes forward security and efficient revocation—the most critical requirements for operational IoT systems—while maintaining provable security under the Decisional Linear (DLIN) assumption within a bounded collusion model, achieving IND-CPA security and anonymity. Theoretical analysis and experimental simulations show that LOR-A2ABE incurs acceptable and controllable overhead in the key issuance and encryption phases, while outperforming most existing schemes in decryption and revocation efficiency, making it particularly suitable for “cloud–terminal” centralized IoT environments where terminal devices are resource-constrained and require frequent decryption operations. Full article

Deafness poses significant challenges to effective communication, particularly in contexts where access to sign language interpreters is limited. Hand configuration recognition represents a fundamental component of sign language understanding, as configurations constitute a core cheremic element in many sign languages, including Italian Sign Language (LIS). In this work, we address configuration-level recognition as an independent classification task and propose a machine vision framework based on RGB-D sensing. The proposed approach combines MediaPipe-based hand landmark extraction with normalized three-dimensional geometric features and a Support Vector Machine classifier. The first contribution of this study is the formulation of LIS hand configuration recognition as a standalone, configuration-level problem, decoupled from temporal gesture modeling. The second contribution is the integration of sensor-acquired RGB-D depth measurements into the landmark-based feature representation, enabling a direct comparison with estimated depth obtained from monocular data. The third contribution consists of a systematic experimental evaluation on two LIS configuration sets (6 and 16 classes), demonstrating that the use of real depth significantly improves classification performance and class separability, particularly for geometrically similar configurations. The results highlight the critical role of depth quality in configuration-level recognition and provide insights into the design of robust vision-based systems for LIS analysis. Full article

Effective thermal runaway (TR) detection is critical for the safety of lithium-ion battery packs, particularly in electric vehicles. However, deploying laboratory-validated methods into resource-constrained battery management systems (BMS) presents significant engineering challenges. This review surveys the state of the art in on-board TR monitoring, with an emphasis on the practical constraints of automotive applications. We first examine available precursor signals, including thermal, electrical, gas, and acoustic emissions, and evaluate their trade-offs regarding response speed and integration complexity. Second, diagnostic algorithms, from threshold-based logic to deep learning, are assessed against key performance metrics such as computational latency, false alarm rates, and lead time. Furthermore, the review discusses essential deployment considerations, including model compression techniques, inference hardware architectures, and compliance with functional safety standards. Specifically, the review discusses the implementation challenges of multi-modal data fusion, with a particular focus on the constraints imposed by limited hardware resources and long-term sensor reliability. Future directions regarding data standardization and cloud-edge collaboration are also discussed. Full article

To address the tradeoff between environmental robustness and fine-grained accuracy in single-sensor human behavior recognition, this paper proposes a non-contact system fusing 77 GHz SIFT (mmWave) radar and a 40 kHz ultrasonic array. The system leverages radar’s long-range penetration and low-visibility adaptability, paired with ultrasound’s centimeter-level short-range precision and electromagnetic clutter immunity. A synchronized data acquisition platform ensures multi-modal signal consistency, while wavelet transform (for radar) and STFT (for ultrasound) extract complementary time–frequency features. The proposed Attention-CNN-BiLSTM architecture integrates local spatial feature extraction, bidirectional temporal dependency modeling, and salient cue enhancement. Experimental results on 1600 synchronized sequences (four behaviors: standing, sitting, walking, falling) show a 98.6% mean class accuracy with subject-wise generalization, outperforming single-sensor baselines and traditional deep learning models. As a privacy-preserving, lighting-agnostic solution, it offers promising applications in smart homes, healthcare monitoring, and intelligent surveillance, providing a robust technical foundation for contactless behavior recognition. Full article

Data loss caused by sensor malfunctions in bridge Structural Health Monitoring (SHM) systems poses a critical risk to structural safety assessment. Although deep learning has advanced data imputation, standard “black-box” models often fail to capture the underlying deterioration mechanisms governed by physical laws. To address this limitation, we propose SP-VMD-CNN-GRU, a prior-knowledge-guided framework that integrates environmental thermal mechanisms with deep representation learning for bridge crack data imputation. Deviating from empirical parameter selection, we utilize the Granger causality test to statistically validate temperature as the primary driver of crack evolution. Leveraging this prior knowledge, we introduce a Shared Periodic Variational Mode Decomposition (SP-VMD) method to isolate temperature-dominated annual and daily periodic components from noise. These physically validated components serve as inputs to a hybrid CNN-GRU network, designed to simultaneously capture spatial correlations across sensor arrays and long-term temporal dependencies. Validated on real-world monitoring data from the Luo’an River Grand Bridge, our framework achieves the highest coefficient of determination ($R^2$) of 0.9916 and the lowest Mean Absolute Percentage Error (MAPE) of 12.95%. Furthermore, statistical validation via Diebold–Mariano and Model Confidence Set tests proves that our physics-guided approach significantly surpasses standard baselines (TCN, LSTM), demonstrating the critical value of integrating prior knowledge into data-driven SHM. Full article

The increasing depth and complexity of underground metal mining has raised ventilation energy demands and safety risks, driving the need for intelligent and more adaptive ventilation systems. Ventilation on Demand (VOD) systems dynamically adjust airflow using real-time operational and environmental data to improve energy efficiency while maintaining safety. Although VOD has been applied for over a decade, deeper and more extreme mining environments associated with critical minerals extraction introduce new challenges and opportunities. VOD systems rely on the tight integration of hardware, sensing, optimization-based control, and flexible infrastructure as mining operations evolve. The application of Artificial Intelligence (AI) introduces significant opportunities to further enhance and adapt VOD systems to these emerging challenges. This work presents a comprehensive review of the state of the art in AI integration within VOD technologies, covering sensing and prediction models, control strategies, and optimization frameworks aimed at improving energy efficiency, safety, and overall system performance. Findings show an increasing use of hybrid deep learning architectures, such as CNN-LSTM and Bi-LSTM, for forecasting, as well as AI-enabled optimization methods for sensor and actuator placement. Key research gaps include a reliance on narrow AI models, limited long-term predictive capabilities for maintenance and strategic planning, and a predominance of simulation-based validation over real-world field deployment. Future research directions include the integration of generative and generalized AI approaches, along with human–cyber–physical system (Human-CPS) designs, to enhance robustness and reliability under the uncertain and dynamic conditions characteristic of deep underground mining environments. Full article

Increased global energy consumption contributes to higher operational costs in the energy sector and results in environmental deterioration. This study evaluates the effectiveness of integrating Internet of Things (IoT) sensors and machine learning techniques to predict adaptive thermostat setpoints to support behavior-aware Heating, Ventilation, and Air Conditioning (HVAC) operation in residential buildings. The dataset was collected over two years from 2080 IoT devices installed in 370 zones in two buildings in Halifax, Canada. Specific categories of real-time information, including indoor and outdoor temperature, humidity, thermostat setpoints, and window/door status, shaped the dataset of the study. Data preprocessing included retrieving data from the MySQL database and converting the data into an analytical format suitable for visualization and processing. In the machine learning phase, deep learning (DL) was employed to predict adaptive threshold settings (“from” and “to”) for the thermostats, and a gradient boosted trees (GBT) approach was used to predict heating and cooling thresholds. Standard metrics (RMSE, MAE, and R²) were used to evaluate effective prediction for adaptive thermostat setpoints. A comparative analysis between GBT ”from” and “to” models and the deep learning (DL) model was performed to assess the accuracy of prediction. Deep learning achieved the highest performance, reducing the MAE value by about 9% in comparison to the strongest GBT model (1.12 vs. 1.23) and reaching an R² value of up to 0.60, indicating improved predictive accuracy under real-world building conditions. The results indicate that IoT-driven setpoint prediction provides a practical foundation for behavior-aware thermostat modeling and future adaptive HVAC control strategies in smart buildings. This study focuses on setpoint prediction under real operational conditions and does not evaluate automated HVAC control or assess actual energy savings. Full article

The application of advanced imaging techniques, particularly computed tomography (CT), photogrammetric scanning, and three-dimensional reconstructions of body surfaces and skeletal remains, is becoming a crucial component of Forensic Anthropology. These tools enable a non-invasive and highly standardized analysis of both intact cadavers and human remains recovered from terrestrial or aquatic environments, providing reliable support in identification processes, traumatological reconstruction, and the assessment of taphonomic processes. In the context of estimating the Post-Mortem Interval (PMI) and the Post-Mortem Submersion Interval (PMSI), digital imaging allows for the objective and reproducible documentation of morphological changes associated with decomposition, saponification, skeletonization, and taphonomic patterns specific to the recovery environment. Specifically, CT enables the precise assessment of gas accumulation, transformations in residual soft tissues, and structural bone modifications, while photogrammetry and 3D reconstructions facilitate the longitudinal monitoring of transformative processes in both terrestrial and underwater contexts. These observations enhance the reliability of PMI/PMSI estimates through integrated models that combine morphometric, taphonomic, and environmental data. Beyond PMI/PMSI estimation, imaging techniques play a central role in anthropological bioprofiling, facilitating the estimation of age, sex, and stature, the analysis of dental characteristics, and the evaluation of antemortem or perimortem trauma, including damage caused by terrestrial or fauna. Three-dimensional documentation also provides a permanent, shareable archive suitable for comparative analyses, ensuring transparency and reproducibility in investigations. Although not a complete substitute for traditional autopsy or anthropological examination, imaging serves as an essential complement, particularly in cases where the integrity of remains must be preserved or where environmental conditions hinder the direct handling of osteological material. Future directions include the development of AI-based predictive models for PMI/PMSI estimation using automated analysis of post-mortem changes, greater standardization of imaging protocols for aquatic remains, and the use of digital sensors and multimodal techniques to characterize microstructural alterations not detectable by the naked eye. The integration of high-resolution imaging and advanced analytical algorithms promises to further enhance the reconstructive accuracy and interpretative capacity of Forensic Anthropology. Full article

Structural health monitoring (SHM) has evolved into an indispensable component for ensuring the safety, durability, and life-cycle efficiency of civil infrastructure. Over the past five years, significant technological advancements have been made in innovative sensing systems, facilitating real-time assessment of structural performance and the early detection of deterioration. This comprehensive review presents recent developments in smart sensor-based SHM, with particular emphasis on the convergence of the Internet of Things (IoT), artificial intelligence (AI), and digital twin (DT) frameworks. Our review critically examines advances in fiber-optic, piezoelectric, MEMS-based, vision-based, acoustic, and environmental sensors, as well as emerging multi-sensor fusion architectures. In addition, bibliometric insights highlight the significant rise in global research activity and influential thematic clusters in SHM between 2020 and 2025. The discussion underscores how AI-integrated data analytics, IoT-enabled wireless networks, and DT-driven virtual replicas enable intelligent, autonomous, and predictive monitoring of bridges, buildings, tunnels, and other large-scale civil infrastructure. Field deployments and case studies are analyzed to bridge the gap between laboratory-scale demonstrations and real-world implementation. Finally, key scientific and practical challenges—including the durability of embedded sensors, the interoperability of heterogeneous data, cybersecurity in connected systems, and the explainability of AI models—are outlined to guide future research. Overall, this review positions contemporary SHM as a transition from traditional damage detection to comprehensive life-cycle management of infrastructure through self-diagnosing, data-centric, and sustainability-driven monitoring ecosystems. Full article

This paper explores the application of predictive maintenance (PdM) to address paraffin deposition in sucker rod pump systems used for oil production. System maintenance has become critical for enhancing efficiency and reducing costs, while PdM, supported by advanced analytics and sensors, enables downtime prediction and maintenance optimization. Paraffin deposition is a significant problem in the oil industry, as it diminishes production capacity and increases expenses. This paper presents the use of the SCADA system, which enables the collection and analysis of data in real time. Furthermore, it proposes diagnostic methods for early detection of paraffin deposition using predictive maintenance, offering timely warnings to prevent production delays. While the proposed framework relies on interpretable statistical and physics-informed predictive models, the results indicate that further improvements could be achieved by integrating advanced artificial intelligence techniques to enhance adaptability, automation, and decision support in predictive maintenance systems. Full article