Search Results (1,291)

Smart safety helmets equipped with vision systems are emerging as powerful tools for industrial infrastructure inspection. This paper presents a comprehensive state-of-the-art review of such VSLAM-enabled (Visual Simultaneous Localization and Mapping) helmets. We surveyed the evolution from basic helmet cameras to intelligent, sensor-fused inspection platforms, highlighting how modern helmets leverage real-time visual SLAM algorithms to map environments and assist inspectors. A systematic literature search was conducted targeting high-impact journals, patents, and industry reports. We classify helmet-integrated camera systems into monocular, stereo, and omnidirectional types and compare their capabilities for infrastructure inspection. We examine core VSLAM algorithms (feature-based, direct, hybrid, and deep-learning-enhanced) and discuss their adaptation to wearable platforms. Multi-sensor fusion approaches integrating inertial, LiDAR, and GNSS data are reviewed, along with edge/cloud processing architectures enabling real-time performance. This paper compiles numerous industrial use cases, from bridges and tunnels to plants and power facilities, demonstrating significant improvements in inspection efficiency, data quality, and worker safety. Key challenges are analyzed, including technical hurdles (battery life, processing limits, and harsh environments), human factors (ergonomics, training, and cognitive load), and regulatory issues (safety certification and data privacy). We also identify emerging trends, such as semantic SLAM, AI-driven defect recognition, hardware miniaturization, and collaborative multi-helmet systems. This review finds that VSLAM-equipped smart helmets offer a transformative approach to infrastructure inspection, enabling real-time mapping, augmented awareness, and safer workflows. We conclude by highlighting current research gaps, notably in standardizing systems and integrating with asset management, and provide recommendations for industry adoption and future research directions. Full article

This project aimed to develop personal protective equipment (PPE) that provides full biological protection for the general public without the need for extensive training to use the equipment. With the proposal to develop a device guided by a smartphone monitoring application (to guide the user on the replacement of perishable components, ensuring their safety and biological protection in potentially contaminated places), the embedded electronics of this equipment were built, as well as their control system, including a smartphone app. Thus, a device was successfully developed to monitor and assist individuals in using an advanced PPE device. Full article

Background: Family caregivers are a vital yet often under-recognized part of the healthcare system. They provide essential emotional, physical, and logistical support to individuals with illness, disability, or frailty, and their contributions improve continuity of care and reduce system strain. However, many healthcare and social service providers are not equipped to meaningfully engage caregivers as partners. In Alberta, stakeholders validated the Caregiver-Centered Care Competency Framework and identified the need for a three-tiered education model—Foundational, Advanced, and Champion—to help providers recognize, include, and support family caregivers across care settings. This paper focuses on the development and early evaluation of the Advanced Caregiver-Centered Care Education modules, designed to enhance the knowledge and skills of providers with more experience working with family caregivers. The modules emphasize how partnering with caregivers benefits not only the person receiving care but also improves provider effectiveness and supports better system outcomes. Methods: The modules were co-designed with a 154-member interdisciplinary team and grounded in the competency framework. Evaluation used the first three levels of the Kirkpatrick–Barr health workforce education model. We analyzed pre- and post-surveys from the first 50 learners in each module using paired t-tests and examined qualitative feedback and SMART goals through inductive content analysis. Results: Learners reported a high level of satisfaction with the education delivery and the knowledge and skill acquisition. Statistically significant improvements were observed in 53 of 54 pre-post items. SMART goals reflected intended practice changes across all six competency domains, indicating learners saw value in engaging caregivers as partners. Conclusions: The Advanced Caregiver-Centered Care education improved providers’ confidence, knowledge, and skills to work in partnership with family caregivers. Future research will explore whether these improvements translate into real-world practice changes and better caregiver experiences in care planning, communication, and navigation. Full article

To enable safe and effective human–robot collaboration (HRC) in smart manufacturing, it is critical to seamlessly integrate sensing, cognition, and prediction into the robot controller for real-time awareness, response, and communication inside a heterogeneous environment (robots, humans, and equipment). The proposed approach takes advantage of the prediction capabilities of nonlinear model predictive control (NMPC) to execute safe path planning based on feedback from a vision system. To satisfy the requirements of real-time path planning, an embedded solver based on a penalty method is applied. However, due to tight sampling times, NMPC solutions are approximate; therefore, the safety of the system cannot be guaranteed. To address this, we formulate a novel safety-critical paradigm that uses an exponential control barrier function (ECBF) as a safety filter. Several common human–robot assembly subtasks have been integrated into a real-life HRC assembly task to validate the performance of the proposed controller and to investigate whether integrating human pose prediction can help with safe and efficient collaboration. The robot uses OptiTrack cameras for perception and dynamically generates collision-free trajectories to the predicted target interactive position. Results for a number of different configurations confirm the efficiency of the proposed motion planning and execution framework, with a 23.2% reduction in execution time achieved for the HRC task compared to an implementation without human motion prediction. Full article

The results of this study highlight the effectiveness of the proposed semantic security detection framework, SSB, in identifying a wide range of vulnerabilities in smart contracts tailored for industrial control scenarios. Compared to existing tools like ZEUS, Securify, and VULTRON, SSB demonstrates superior logical coverage across various vulnerability types, as evidenced by its performance on smart contract samples. This suggests that semantic-based approaches, which integrate domain-specific invariants and runtime monitoring, can address the unique challenges of ICS, such as real-time constraints and semantic consistency between code and physical control logic. The framework’s ability to model industrial invariants—covering security, functionality, consistency, time-related, and resource consumption aspects—provides a robust mechanism to prevent critical errors like unauthorized access or premature equipment operation. However, the lack of real-world ICS validation due to confidentiality constraints limits the generalizability of these findings. Future research should focus on adapting SSB for real industrial deployments, exploring scalability across diverse ICS architectures, and integrating advanced AI techniques for dynamic invariant adjustment. Additionally, addressing cross-chain interoperability and privacy concerns could further enhance the framework’s applicability in complex industrial ecosystems. Full article

Background: Gold mining is a critical part of the industry of Central Asia, contributing significantly to regional economic growth. However, gold production management faces numerous challenges, including adopting innovative technologies such as AI, using improved logistical equipment, resolving supply chain inefficiencies and disruptions, and incorporating modernized waste management and advancements in gold bar processing technologies. This study explores how advanced technologies and improved logistical processes can enhance efficiency and sustainability. Method: This paper examines gold production processes in Kyrgyzstan, a gold-producing country in Central Asia. The case study approach combines qualitative interviews with industry stakeholders and a system dynamics (SD) simulation model to compare current operations with a technology-based scenario. Results: The simulation model shows improved outcomes when innovative technologies are applied to ore processing, waste refinement, and gold bar production. The results also indicate an approximate twenty-five percent reduction in transport time, a thirty percent decrease in equipment downtime, a thirty percent reduction in emissions, and a fifteen percent increase in gold extraction when using artificial intelligence, smart logistics, and regional smelting. Conclusions: The study concludes with recommendations to modernize equipment, localize processing, and invest in digital logistics to support sustainable mining and improve operational performance in Kyrgyzstan’s gold sector. Full article

This comprehensive review maps the fast-evolving landscape in which artificial intelligence (AI) and deep-learning (DL) techniques converge with the Internet of Things (IoT) to manage energy, comfort, and sustainability across smart environments. A PRISMA-guided search of four databases retrieved 1358 records; after applying inclusion criteria, 143 peer-reviewed studies published between January 2019 and April 2025 were analyzed. This review shows that AI-driven controllers—especially deep-reinforcement-learning agents—deliver median energy savings of 18–35% for HVAC and other major loads, consistently outperforming rule-based and model-predictive baselines. The evidence further reveals a rapid diversification of methods: graph-neural-network models now capture spatial interdependencies in dense sensor grids, federated-learning pilots address data-privacy constraints, and early integrations of large language models hint at natural-language analytics and control interfaces for heterogeneous IoT devices. Yet large-scale deployment remains hindered by fragmented and proprietary datasets, unresolved privacy and cybersecurity risks associated with continuous IoT telemetry, the growing carbon and compute footprints of ever-larger models, and poor interoperability among legacy equipment and modern edge nodes. The authors of researches therefore converges on several priorities: open, high-fidelity benchmarks that marry multivariate IoT sensor data with standardized metadata and occupant feedback; energy-aware, edge-optimized architectures that lower latency and power draw; privacy-centric learning frameworks that satisfy tightening regulations; hybrid physics-informed and explainable models that shorten commissioning time; and digital-twin platforms enriched by language-model reasoning to translate raw telemetry into actionable insights for facility managers and end users. Addressing these gaps will be pivotal to transforming isolated pilots into ubiquitous, trustworthy, and human-centered IoT ecosystems capable of delivering measurable gains in efficiency, resilience, and occupant wellbeing at scale. Full article

The integration of heterogeneous spatio-temporal datasets presents a critical challenge in geospatial data science, particularly when combining large-scale, passively collected “big” data with precise but sparse “small” data. In this study, we propose a novel framework—Multi-Channel Spatio-Temporal Data Fusion (MCST-DF)—that leverages transformer-based deep learning to fuse these data sources for accurate network flow estimation. Our approach introduces a Residual Spatio-Temporal Transformer Network (RSTTNet), equipped with a layered attention mechanism and multi-scale embedding architecture to capture both local and global dependencies across space and time. We evaluate the framework using real-world mobile sensing and loop detector data from the London road network, demonstrating over 89% prediction accuracy and outperforming several benchmark deep learning models. This work provides a generalisable solution for spatio-temporal fusion of diverse geospatial data sources and has direct relevance to smart mobility, urban infrastructure monitoring, and the development of spatially informed AI systems. Full article

In precision cotton seeding, the toothed-disk precision seeder often experiences issues with missed seeding and multiple seeding. To promptly detect and address these abnormal seeding conditions, this study develops a modular photoelectric sensing monitoring system. Initially, the monitoring time window is divided using the capacitance sensing signal between two seed drop ports. Concurrently, a photoelectric monitoring circuit is designed to convert the time when seeds block the sensor into a level signal. Subsequently, threshold segmentation is performed on the time when seeds block the photoelectric path under different seeding states. The proposed spatiotemporal joint counting algorithm identifies, in real time, the threshold type of the photoelectric sensor’s output signal within the current monitoring time window, enabling the differentiation of seeding states and the recording of data. Additionally, an STM32 micro-controller serves as the core of the signal acquisition circuit, sending collected data to the PC terminal via serial port communication. The graphical display interface, designed with LVGL (Light and Versatile Graphics Library), updates the seeding monitoring information in real time. Compared to photoelectric monitoring algorithms that detect seed pickup at the seed metering disc, the monitoring node in this study is positioned posteriorly within the seed guide chamber. Consequently, the differentiation between single seeding and multiple seeding is achieved with greater accuracy by the spatiotemporal joint counting algorithm, thereby enhancing the monitoring precision of the system. Field test results indicate that the system’s average accuracy for single-seeding monitoring is 97.30%, for missed-seeding monitoring is 96.48%, and for multiple-seeding monitoring is 96.47%. The average probability of system misjudgment is 3.25%. These outcomes suggest that the proposed modular photoelectric sensing monitoring system can meet the monitoring requirements of precision cotton seeding at various seeding speeds. Full article

A novel approach to managing domestic heating systems through IoT technologies is introduced in this paper. The system optimizes energy consumption by dynamically adapting to electricity and fuel price fluctuations while maintaining user comfort. Integrating smart devices significantly reduce energy costs and offer a favorable payback period, positioning the solution as both sustainable and economically viable. Efficient heating management is increasingly critical amid growing energy and environmental concerns. This strategy uses IoT devices to collect real-time data on prices, consumption, and user preferences. Based on this data, the system adjusts heating settings intelligently to balance comfort and cost savings. IoT connectivity manages continuous monitoring and dynamic optimization in response to changing conditions. This study includes a real-case comparison between a conventional central heating system and an IoT-managed electric radiator setup. By applying automation rules linked to energy pricing and user habits, the system enhances energy efficiency, especially in cold climates. The economic evaluation shows that using low-cost IoT devices yields meaningful savings and achieves equipment payback within approximately three years. The results demonstrate the system’s effectiveness, demonstrating that smart, adaptive heating solutions can cut energy expenses without sacrificing comfort, while offering environmental and financial benefits. Full article

The scope of this paper is the development of a cost-effective wireless torque measurement system for vehicle drivetrain shafts. The prototype integrates strain gauges, an HX711 conditioner, a Wemos D1 Mini ESP8266, and a rechargeable battery directly on the rotating shaft, forming a self-contained sensor node. Calibration against a certified dynamometric wrench confirmed an operating span of ±5–50 N·m. Within this range, the device achieved a mean absolute error of 0.559 N·m. It also maintained precision better than ±2.5 N·m at 95% confidence, while real-time data were transmitted via Wi-Fi. The total component cost is below EUR 30 based on current prices. The novelty of this proof-of-concept implementation demonstrates that reliable, IoT-enabled torque sensing can be realized with low-cost, readily available parts. The paper details assembly, calibration, and deployment procedures, providing a transparent pathway for replication. By aligning with Industry 4.0 requirements for smart, connected equipment, the proposed torque measurement system offers an affordable solution for process monitoring and predictive maintenance in automotive and industrial settings. Full article

Smart glasses are promising alternatives for the continuous, unobtrusive monitoring of heart rate (HR). This study validates HR estimates obtained with the “Essilor Connected Glasses” (SmartEW) during sedentary activities. Thirty participants wore the SmartEW, equipped with an IMU sensor for HR estimation, a commercial smartwatch (Garmin Venu 3), and an ECG device (Movesense Flash). The protocol included six static tasks performed under controlled laboratory conditions. The SmartEW algorithm analyzed 22.5 s signal windows using spectral analysis to estimate HR and provide a quality index (QI). Statistical analyses assessed agreement with ECG and the impact of QI on HR accuracy. SmartEW showed high agreement with ECG, especially with QI threshold equal to 70, as a trade-off between accuracy, low error, and acceptable data coverage (80%). Correlation for QI ≥ 70 was high across all the experimental phases (r² up to 0.96), and the accuracy within ±5 bpm reached 95%. QI ≥ 70 also allowed biases to decrease (e.g., from −1.83 to −0.19 bpm while standing), with narrower limits of agreement, compared to ECG. SmartEW showed promising HR accuracy across sedentary activities, yielding high correlation and strong agreement with ECG and Garmin. SmartEW appears suitable for HR monitoring in static conditions, particularly when data quality is ensured. Full article

Winter wheat yield prediction is critical for optimizing field management plans and guiding agricultural production. To address the limitations of conventional manual yield estimation methods, including low efficiency and poor interpretability, this study innovatively proposes an intelligent yield estimation method based on a convolutional neural network (CNN). A comprehensive two-factor (fertilization × irrigation) controlled field experiment was designed to thoroughly validate the applicability and effectiveness of this method. The experimental design comprised two irrigation treatments, sufficient irrigation (C) at 750 m³ ha⁻¹ and deficit irrigation (M) at 450 m³ ha⁻¹, along with five fertilization treatments (at a rate of 180 kg N ha⁻¹): (1) organic fertilizer alone, (2) organic–inorganic fertilizer blend at a 7:3 ratio, (3) organic–inorganic fertilizer blend at a 3:7 ratio, (4) inorganic fertilizer alone, and (5) no fertilizer control. The experimental protocol employed a DJI M300 RTK unmanned aerial vehicle (UAV) equipped with a multispectral sensor to systematically acquire high-resolution growth imagery of winter wheat across critical phenological stages, from heading to maturity. The acquired multispectral imagery was meticulously annotated using the Labelme professional annotation tool to construct a comprehensive experimental dataset comprising over 2000 labeled images. These annotated data were subsequently employed to train an enhanced CNN model based on ResNet50 architecture, which achieved automated generation of panicle density maps and precise panicle counting, thereby realizing yield prediction. Field experimental results demonstrated significant yield variations among fertilization treatments under sufficient irrigation, with the 3:7 organic–inorganic blend achieving the highest actual yield (9363.38 ± 468.17 kg ha⁻¹) significantly outperforming other treatments (p < 0.05), confirming the synergistic effects of optimized nitrogen and water management. The enhanced CNN model exhibited superior performance, with an average accuracy of 89.0–92.1%, representing a 3.0% improvement over YOLOv8. Notably, model accuracy showed significant correlation with yield levels (p < 0.05), suggesting more distinct panicle morphological features in high-yield plots that facilitated model identification. The CNN’s yield predictions demonstrated strong agreement with the measured values, maintaining mean relative errors below 10%. Particularly outstanding performance was observed for the organic fertilizer with full irrigation (5.5% error) and the 7:3 organic-inorganic blend with sufficient irrigation (8.0% error), indicating that the CNN network is more suitable for these management regimes. These findings provide a robust technical foundation for precision farming applications in winter wheat production. Future research will focus on integrating this technology into smart agricultural management systems to enable real-time, data-driven decision making at the farm scale. Full article

In Korea, the Public Health Center Mobile Healthcare Project was implemented in 2016. This project utilizes Information and Communication Technology (ICT) and big data to establish a health-related service foundation and a healthcare service operation system. Equipment and methods: This study recruited 1261 adolescents (660 males (13.40 ± 1.14 years, 156.12 ± 10.59 cm) and 601 females (13.51 ± 1.23 years, 154.45 ± 7.48 cm)) from 22 public health centers nationwide. Smart bands were provided, and the ‘Future Health’ application (APP) was installed on personal smartphones to assess body composition, physical fitness, and physical activity. Results: A paired sample t-test revealed height, 20 m shuttle run, grip strength, and long jump scores significantly differed after 24 weeks in males. Females exhibited significant height, 20 m shuttle run, grip strength, sit-ups, and long jump differences. Moderate physical activity (MPA, p < 0.001), vigorous physical activity (VPA, p < 0.001), and moderate-to-vigorous physical activity (MVPA, p < 0.001) were significantly different after 24 weeks in adolescents. These results establish that an ICT-based health promotion service can provide adolescent students with individual information from a centralized organization to monitor health behaviors and receive feedback regardless of location in South Korea. Full article

In this study, we comprehensively analyzed material consumption (fuel, hydraulic oil, lubricants, and AdBlue fluid) and estimated carbon dioxide emissions during logging operations. This study was carried out in the northeastern part of Poland. Four harvesters and four forwarders representing two manufacturers (John Deere-Deere & Co., Moline, USA, and Komatsu Forest AB, Umeå, Sweden) were analyzed to compare their operational efficiency and constructional influences on overall operating costs. Due to differences in engine emission standards, approximate greenhouse gas emissions were estimated. The results indicate that harvesters equipped with Stage V engines have lower fuel consumption, while large forwarders use more consumables than small ones per hour and cubic meter of harvested and extracted timber. A strong positive correlation was observed between total machine time and fuel consumption (r = 0.81), as well as between machine time and total volume of timber harvested (r = 0.72). Older and larger machines showed about 40% higher combustion per unit of wood processed. Newer machines meeting higher emission standards (Stage V) generally achieved lower CO₂ and other GHG emissions compared to older models. Machines with Stage V engines emitted about 2.07 kg CO₂ per processing of 1 m³ of wood, while machines with older engine types emitted as much as 4.35 kg CO₂ per 1 m³—roughly half as much. These differences are even more pronounced in the context of nitrogen oxide (NO_x) emissions: the estimated NO_x emissions for the older engine types were as high as ~85 g per m³, while those for Stage V engines were only about 5 g per m³ of harvested wood. Continuing the study would need to expand the number of machines analyzed, as well as acquire more detailed performance data on individual operators. A tool that could make this possible would be fleet monitoring services offered by the manufacturers of the surveyed harvesters and forwards, such as Smart Forestry or Timber Manager. Full article