The rapid growth of Internet of Things (IoT) technologies has significantly transformed smart healthcare systems by enabling continuous monitoring of physiological parameters through wearable devices. However, many existing healthcare monitoring systems rely heavily on cloud-based architectures, which lead to increased network latency, high energy consumption, and limited real-time decision support. This study proposes an IoT-enabled Smart Healthcare Decision-aid System (ISHDS) that integrates a wearable physical sensor node (WPSN), mobile-based Edge AI computing, and cloud-assisted data analysis for efficient real-time health monitoring. The proposed system is designed as a four-layer architecture consisting of a wearable sensing layer, mobile edge processing layer, communication layer, and cloud analytics layer. A prototype WPSN device is developed to continuously monitor multiple physiological parameters, including blood pressure, body temperature, heart rate, blood oxygen saturation ( S p O 2 ) and respiration rate. A pilot experimental study was conducted for 5 consecutive days involving 27 participants aged between 11 and 77 years with a combination of healthy and patients having chronic conditions to evaluate system performance. The primary outcomes included measurement accuracy, system latency, and real-time decision support capability. The collected data were processed using an on-device data fusion approach through a mobile application (Healthy App), which reduces network latency and communication overhead while improving system responsiveness. Experimental results suggest that the proposed framework achieves high accuracy (up to 99.96%) in physiological data analysis; however, this result is preliminary and requires further validation on larger and more diverse populations. These findings indicate that the proposed ISHDS framework offers an efficient and scalable solution for smart healthcare applications by combining wearable sensing, Edge AI-based data processing, and intelligent data fusion. The system shows strong potential for deployment in remote healthcare monitoring and real-time medical decision support environments.
Population ageing is accelerating globally, placing increasing pressure on local health and social care systems. Older people who remain living independently generally have better health outcomes and use fewer care resources. Moreover, many older people express a preference for living independently. Therefore, supporting independent living represents a cost-effective objective for health and care systems. One potential means for supporting such ageing in place is domestic sensor-based activity monitoring technologies; however, to date evidence on their effectiveness, usability, and real-world implementation has been inconclusive. A scoping review has been undertaken following PRISMA-ScR guidance to map the latest evidence on domestic passive sensor-based monitoring for older adults. Twenty-nine studies met the inclusion criteria; the evidence they provide suggests domestic sensors can support monitoring of activities of daily living, detect early functional or cognitive decline, and are generally acceptable to users. However, robust evidence for improved clinical outcomes, cost-effectiveness, and effective integration into health systems remains limited.
Forest fires are among the most destructive natural hazards, posing significant threats to ecosystems, infrastructure, and human life. In Mediterranean regions such as Algeria, the frequency and intensity of wildfires have increased due to climate change and human activities. This article proposes a cloud-centric hybrid Internet of Things (IoT) and machine learning (ML) framework for intelligent forest fire monitoring and prevention. The proposed system integrates distributed IoT sensor nodes equipped with temperature and humidity sensors that continuously collect environmental data and transmit them to a central gateway through NRF24L01 communication modules, while long-range communication with the cloud platform is achieved using a SIM808 cellular module. To enhance predictive capabilities, the framework combines real-time IoT sensing data with complementary meteorological variables, including wind speed and rainfall, obtained from external meteorological services during dataset construction. Six supervised ML models-logistic regression, decision tree, random forest, XGBoost, LightGBM, and CatBoost-were evaluated using historical Algerian wildfire data (2000-2003) together with a recent dataset collected in 2024. Experimental results show that XGBoost achieved the highest overall predictive performance with a test accuracy of 98.75% and an F1-score of 98.97%, while Random Forest and CatBoost also demonstrated robust and stable performance. Logistic Regression achieved competitive results with significantly lower computational cost, making it suitable for resource-constrained IoT environments. The proposed hybrid IoT-ML framework enables early wildfire risk assessment and supports proactive decision-making for forest management. These findings demonstrate the potential of integrating IoT sensing, meteorological information, and machine learning to support sustainable environmental monitoring within ambient intelligence systems.
By integrating technological advancements into home-based fitness environments, smart fitness applications have increasingly become an integral part of daily exercise routines. A key challenge in their design lies in presenting information that aligns with users' cognitive and perceptual needs, especially during self-directed exercise. This study explores how exercise experience and intensity influence users' attention to interface information in smart fitness applications. Using a within-subjects mixed factorial design (3 Levels of Exercise Intensity & times; 2 Levels of Exercise Experience), we conducted a 40-second wall sit experiment with 32 valid participants, employing eye-tracking technology to measure fixation duration as an indicator of visual attention. The results reveal that experienced users exhibit significantly greater attention to physical data, while inexperienced users focus more on atmosphere-related information. In low-intensity exercise, inexperienced users allocate more attention to achievement-related information, though no significant difference in attention to exercise information is observed between the two groups. Additionally, high-intensity exercise leads to increased attention to atmosphere-related information, particularly among inexperienced users. These findings provide empirical support for interface design strategies in smart fitness applications and contribute to the advancement of public health.
Urban mobility challenges have intensified with the rapid expansion of private vehicle fleets. To mitigate parking scarcity in central areas, municipalities often implement Metered Parking Zones to encourage vehicle turnover. These digitized systems generate historical data following the Arrive-Stay-Leave (ASL) pattern, enabling occupancy mapping and predictive analysis. This study introduces ParkMapSense, a computational model designed to generate occupancy maps and forecast parking availability. The model was validated using operational data from Novo Hamburgo, RS (Brazil), covering November 2022 to May 2024, comprising 1.4 million inspections and 1.3 million parking activations across 2,052 parking spaces. Occupancy was aggregated into 10-minute intervals, and prediction algorithms based on Global, 7-day, and 28-day moving averages were applied, segmented by weather conditions and day type. Rainfall data were integrated to analyze behavioral variations. Evaluation metrics showed scores of 0.86 for weekdays without rain, 0.74 with rain, and 0.81 on Saturdays in any weather, confirming the model's ability to capture temporal patterns. The main contribution of this study lies in the occupancy mapping algorithm, which transforms metered parking data into structured time-series occupancy maps, and in the weather-aware segmentation strategy, which serves as lightweight baselines within an extensible structure designed to support future integration of other prediction algorithms. ParkMapSense demonstrated low computational cost and operational feasibility for medium-sized cities, offering valuable insights for urban mobility planning and enforcement optimization.
