Search Results (282)

Sensor-based human activity recognition (HAR) plays a fundamental role in healthcare monitoring, sports analytics, and ambient-assisted living. Although deep learning has substantially advanced HAR performance, two practical issues still limit its real-world deployment: (i) the distribution shift caused by changes in users or sensor placements can degrade generalization, and (ii) the quadratic $\mathcal{O}\left(L^2\right)$ complexity of standard self-attention hinders efficient long-sequence modeling on resource-constrained wearable devices. To address these issues, we propose DSHformer, which is an accuracy-oriented HAR framework that combines compact channel–temporal encoding with locality-sensitive hashing (LSH)-based attention. Specifically, DSHformer (i) employs a low-parameter patch-based graph-attention encoder to jointly model latent relationships among sensor channel–temporal dynamics; (ii) introduces a trainable prototype pool together with a multi-layer decomposition network to improve intra-class compactness and inter-class separability via prototype alignment; and (iii) introduces a decomposition-stable LSH-based attention mechanism tailored for HAR, whose core design couples prototype-guided feature decomposition with locality-sensitive hashing to ensure that semantically related tokens remain consistently grouped in the same hash bucket even after decomposition-induced attenuation. The mechanism thereby operates at $\mathcal{O}(LlogL)$ attention complexity on longer sensor sequences. Extensive experiments on five public benchmarks (WISDM, UCI-HAR, PAMAP2, Opportunity, and UniMiB-SHAR) show that DSHformer achieves accuracies of 98.6%, 93.7%, 98.4%, 88.5%, and 96.6%, respectively, achieving competitive or superior performance compared with both Transformer variants and HAR-specific baselines under the adopted benchmark protocols. Ablation studies further confirm the complementary contribution of each component. Full article

Effective dementia care is often hindered by fragmented communication among patients, informal caregivers, and clinicians. To address this, we introduce an ambient assisted living (AAL) framework designed to establish a continuous, virtual, and unobtrusive connection between an elder’s home and external guardians or medical staff (virtual rounds). The system enables guardians to communicate directly within the home environment, without requiring the older adult to manually accept calls or activate the connection using wearable devices, buttons, or other interfaces. The elders can activate the connection verbally. The structural core of this system relies on three novel hardware configurations designed for zero-interface operation: a remote audio announcement device, a bidirectional intercom, and a “zero-interface mirror” enabling stream-only, real-time video co-presence between patients and guardians. Crucially, the system utilizes a privacy-preserving, staged edge-AI architecture to process data. By default, it operates without long-term persistent storage, selectively transmitting abstracted audio-based behavioral metrics to a secure dashboard. For advanced dementia stages, the system employs ephemeral data retention—specifically a highly restricted, 24 h rolling audio buffer—allowing authorized guardians to verify acute events without permanently exfiltrating raw data. We evaluate this infrastructure through a 10-month longitudinal, single-home feasibility deployment, augmented with historical verified fall data to rigorously test the detection of rare acute events. The study validates the framework’s technical viability, system uptime, and privacy-first architecture in continuously tracking long-term proxy behavioral indicators under real-world conditions. Rather than asserting generalized clinical efficacy, this work demonstrates the operational feasibility of a novel, affordable, technical blueprint for dignified, remote digital care coordination. Full article

Ambient Assisted Living (AAL) systems have become increasingly relevant as aging populations intensify the demand for technologies that promote autonomy, safety, and quality of life. However, the widespread adoption of audiovisual sensing in smart homes raises critical concerns regarding data protection, privacy, and user trust. Ensuring secure processing while maintaining accurate activity recognition remains a key challenge. This work introduces DistSense, a distributed Peer-to-Peer (P2P) system designed to enhance activity detection in domestic environments through collaborative inference among intelligent audiovisual sensors. DistSense prioritizes privacy by performing local processing, sharing only high-level events, and leveraging distributed ledger mechanisms to ensure data integrity and auditability and support cross-device validation. This collaborative strategy reduces false positives caused by occlusions, illumination variability, and acoustic noise. To assess the system, functional tests were conducted for each module, followed by two use cases evaluated in both simulated and real edge hardware environments. The trained models achieved 88% accuracy for audio and 80% for video, and the system demonstrated effective performance in detecting daily activities and domestic hazards under varying noise conditions. Results indicate that DistSense successfully balances security, user acceptance, and inference robustness, positioning it as a viable solution for privacy-preserving activity monitoring in smart home contexts. Full article

The rapid growth of the elderly population worldwide demands reliable activity recognition technologies to support independent living and continuous health supervision. However, conventional wearable sensor-based human activity recognition (HAR) techniques often fail to capture the complex temporal behaviour and subtle motion patterns characteristic of the elderly. To address these limitations, this study introduces a hybrid deep residual architecture—CNN-CBAM-BiGRU—that integrates convolutional neural networks (CNNs), the convolutional block attention module (CBAM), and bidirectional gated recurrent units (BiGRUs) to improve activity recognition using inertial measurement unit (IMU) data. In the proposed CNN-CBAM-BiGRU framework, CNN layers automatically derive representative features from raw sensor signals, CBAM applies adaptive channel and spatial attention to highlight informative patterns, and BiGRU captures long-range temporal relationships within activity sequences. The approach was evaluated on three benchmark datasets designed for elderly populations—HAR70+, HARTH, and SisFall—covering daily activities and fall events. The proposed model consistently outperforms existing methods across all datasets, achieving accuracies exceeding 96%, F1-scores above 93%, and a fall detection recall of 93.74%, confirming its robustness and suitability for safety-critical monitoring applications. Class-level evaluation indicates excellent recognition of static postures and consistent performance for dynamic actions. Convergence analysis further confirms efficient learning with limited overfitting across datasets. The proposed framework thus provides a robust and accurate solution for wearable-based elderly activity recognition, with strong potential for deployment in fall detection, health monitoring, and ambient assisted living systems. Full article

(1) Research Highlights: This study provides the first integrated assessment of Scots pine (Pinus sylvestris L.) growing in the urban forests of Karaganda, Kazakhstan, a city consistently ranked among the most air-polluted cities globally. We examined the adaptive phyto-chemical response of needles to extreme technogenic stress and evaluated their dual potential as biological filters and renewable sources of bioactive compounds. (2) Background and Objectives: Urban forests are critical for mitigating air pollution; however, the biochemical responses of trees in heavily industrialized environments remain poorly understood. Karaganda faces severe atmospheric pollution from mining, metallurgy, and energy sectors, with particulate matter (PM) levels exceeding permissible limits by up to 20-fold. This study aimed to evaluate the state of Pinus sylvestris, a key component of local protective plantations, by studying heavy metal accumulation, anatomical localization of secondary metabolites, and the phytochemical profile and biological activity of needle extracts obtained using different extraction techniques. (3) Materials and Methods: Needles were collected from 15 trees across three sites in Karaganda’s industrial green zones. Heavy metal content (Pb, Cd, As, and Hg) was determined using atomic absorption spectroscopy and voltammetry. Anatomical–histochemical analysis localizes major metabolite classes. Liquid extracts were prepared using four methods, percolation (PER), vortex-assisted (VAE), microwave-assisted (MAE), and ultrasound-assisted (UAE) extraction, and analyzed by GC-MS. Antimicrobial activity was tested against S. aureus, B. subtilis, E. coli, and C. albicans using the disk diffusion method. The antioxidant capacity (water- and fat-soluble) was measured amperometrically. Statistical analysis was performed using one-way ANOVA with Tukey’s HSD test (p < 0.05). Results: Despite extreme ambient pollution, heavy metal concentrations remained below pharmacopoeial limits (Pb < 0.1, Cd < 0.05, As < 0.01, Hg < 0.001 mg/kg), indicating effective biofiltration without toxic accumulation. Histochemistry confirmed the active synthesis of protective phenolics, flavonoids, and essential oils in the mesophyll, epidermis, and schizogenic cavities. GC-MS identified 72 compounds in the PER extract, 70 (the VAE), 72 in (MAE), and 46 in (UAE). The PER extract exhibited the highest relative abundance of bioactive terpenoids: α-cadinol (5.24%), α-muurolene (4.32%), and caryo-phyllene (2.20%). UAE extracts exhibited elevated 5-hydroxymethylfurfural (6.90%), indicating degradation. Antimicrobial testing revealed that PER produced the largest inhibition zone against S. aureus (15.0 ± 1.0 mm), significantly exceeding that of the other methods (p < 0.001). PER extract also demonstrated the highest water-soluble antioxidant capacity (3600 ± 0.40 mg quercetin equiv./dm³) and substantial fat-soluble activity (1633 ± 0.23 mg gallic acid equiv./dm³). (4) Conclusions: Pinus sylvestris in Karaganda exhibits remarkable adaptive resilience, maintaining safe heavy metal levels while accumulating a rich repertoire of stress-induced secondary metabolites. Classical percolation optimally preserves this native phytocomplex, yielding extracts with superior antimicrobial and antioxidant properties. These findings support a dual-use model wherein urban pine plantations simultaneously serve as living biofilters and renewable sources of standardized bioactive extracts, a concept with direct implications for circular bioeconomy strategies in industrial regions worldwide. This supports the strategic importance of coniferous plantations for bioremediation and sustainable resource use in industrial regions. Full article

Falls represent a major health risk for older adults living independently, motivating the development of unobtrusive and privacy-preserving monitoring solutions. This study investigates whether Bluetooth Low Energy (BLE) 6.0 Channel Sounding (CS) can support device-free fall detection using low-complexity signal representations suitable for residential deployment. The proposed system employs two BLE nodes performing periodic channel sounding, from which only scalar distance estimates are extracted. Time-domain and temporal-dynamic features are computed from sliding windows of the distance signal and used for supervised classification. Three widely used classifiers—Support Vector Machine with radial basis function kernel, Random Forest, and gradient-boosted decision trees (XGBoost)—are evaluated under both a default operating point and a sensitivity-first regime achieved through validation-based decision threshold adjustment, reflecting the higher cost of missed fall detections in assisted living scenarios. Experiments conducted in a furnished indoor environment with six participants performing realistic fall and non-fall scenarios demonstrate strong window-level sensitivity under subject-independent evaluation, with XGBoost providing the most favorable sensitivity–specificity balance. Under sensitivity-first operation, very high recall is achieved at the expense of increased false alarms. Given the limited dataset and single-environment setting, the reported results should be interpreted as a proof-of-concept demonstration of feasibility rather than definitive large-scale performance. The findings suggest that BLE CS captures motion-relevant signal variations that may support practical fall detection while maintaining low deployment complexity and privacy preservation. Full article

This article presents a scalable IoT-based architecture for continuous and passive monitoring of human behavior in home environments, designed as a technical foundation for future dementia risk assessment systems. The architecture addresses three fundamental challenges: achieving room-level spatial localization without privacy-invasive methods, balancing temporal resolution with bandwidth efficiency in continuous data streams, and enabling multi-institutional model development under GDPR constraints. The system integrates (1) wearable BLE sensors with infrared room-level localization; (2) edge computing gateways with local preprocessing and machine learning; (3) a three-channel data architecture that simultaneously achieves full 1 s temporal resolution for machine learning training, low-latency real-time visualization, and 41.2% network bandwidth reduction; and (4) a federated learning framework enabling collaborative model development without data sharing between institutions. Technical validation in two apartments (three participants, 7 days) demonstrated: 97.6% room-level localization accuracy using infrared beacons; less than 7 s end-to-end latency for 99.5% of critical events; and 98.5% deduplication accuracy in multi-gateway configurations. Federated learning simulation demonstrates algorithmic convergence (84.3% IID, 79.8% non-IID) and workflow feasibility, establishing a foundation for future production deployment. Cost analysis shows approximately €490 for initial implementation and approximately €55 monthly operation, representing substantially lower costs than existing research systems. The work establishes architectural and technical feasibility, as well as system-level economic viability, of continuous home monitoring for behavioral analysis within the evaluated residential scenarios. Clinical validation of diagnostic capabilities through longitudinal studies with validated cognitive assessments and patients with mild cognitive impairment remains to be studied in future work. Full article

To support ambient assisted living for the elderly living alone, we investigate a method for recognizing daily activities from household sounds. To reduce the cost of building an activity-recognition model, we adopt an unsupervised learning approach based on a Dirichlet multinomial mixture model. The model represents the generative process of neural audio codec codes conditioned on latent activities. We further extend the model to handle multiple streams of codes corresponding to different sound directions. This extension enables the formation of more accurate activity clusters, partly because code occurrence patterns exhibit burstiness. The proposed approach is expected to serve as a key component for constructing an activity recognition system that requires minimal labeled data and a small number of user inquiries. Full article

Background: Falls are a leading cause of morbidity and mortality among older adults, creating a need for technologies that can automatically detect falls and summon timely assistance. The rapid evolution of sensor technologies and artificial intelligence has led to a proliferation of fall detection systems (FDS). This systematic review synthesizes the recent literature to provide a comprehensive overview of the current technological landscape. Objective: The objective of this review is to systematically analyze and synthesize the evidence from the academic literature on fall detection technologies. The review focuses on three primary areas: the sensor modalities used for data acquisition, the computational models employed for fall classification, and the emerging trend of shifting from reactive detection to proactive fall risk prediction. Methods: A systematic search of electronic databases was conducted for studies published between 2008 and 2025. Following the PRISMA guidelines, 130 studies met the inclusion criteria and were selected for analysis. Information regarding sensor technology, algorithm type, validation methods, and key performance outcomes was extracted and thematically synthesized. Results: The analysis identified three dominant categories of sensor technologies: wearable systems (primarily Inertial Measurement Units), ambient systems (including vision-based, radar, WiFi, and LiDAR), and hybrid systems that fuse multiple data sources. Computationally, the field has shown a progression from threshold-based algorithms to classical machine learning and is now dominated by deep learning architectures, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers. Many studies report high performance, with accuracy, sensitivity, and specificity often exceeding 95%. An important trend is the expansion of research from post-fall detection to proactive fall risk assessment and pre-impact fall prediction, which aim to prevent falls before they cause injury. Conclusions: The technological capabilities for fall detection are well-developed, with deep learning models and a variety of sensor modalities demonstrating high accuracy in controlled settings. However, a critical gap remains; our analysis reveals that 98.5% of studies rely on simulated falls, with only two studies validating against real-world, unanticipated falls in the target demographic. Future research should prioritize real-world validation, address practical implementation challenges such as energy efficiency and user acceptance, and advance the development of integrated, multi-modal systems for effective fall risk management. Full article

Monitoring muscle fatigue is essential to ensure safety and support activity in populations such as the elderly. This study introduces a novel deep learning framework for classifying muscle fatigue levels using data from wireless surface electromyographic sensors, with the long-term goal of supporting applications in Ambient Assisted Living. A new dataset was collected from healthy elderly and non-elderly adults performing dynamic tasks under controlled conditions, with muscle fatigue levels labelled through self-assessment. The proposed method employs a pipeline that transforms one-dimensional electromyographic signals into two-dimensional time–frequency images (scalograms) using the Continuous Wavelet Transform, which are then classified by a fine-tuned, pre-trained Convolutional Neural Network. These images are then classified by pretrained Convolutional Neural Networks on large-scale image datasets. The classification pipeline includes an initial binary discrimination between non-fatigued and fatigued conditions, followed by a refined three-level classification into No Fatigue, Moderate Fatigue, and Hard Fatigue. The system achieved an accuracy of 98.6% in the binary task and 95.6% in the multiclass setting. This integrated transfer learning pipeline outperformed traditional Machine Learning methods based on manually extracted features, which reached a maximum of 92% accuracy. These findings highlight the robustness and generalizability of the proposed approach, supporting its potential as a real-time, non-invasive muscle fatigue monitoring solution tailored to Ambient Assisted Living scenarios. Full article

The global increase in dementia cases, which is predicted to exceed 152 million by 2050, poses substantial challenges to healthcare systems and caregiving structures. Concurrently, the expansion of mobile health (mHealth) technologies offers scalable, cost-effective opportunities for dementia care. This study systematically reviews 100 publicly available dementia-related mobile applications on the Apple App Store (iOS) and the Google Play Store (Android), categorised using the Mobile App Rating Scale (MARS), as well as the targeted end-users, Internet of Things (IoT) integration, data protection, and cost burden. Applications were evaluated for their utility in cognitive training, memory support, carer education, clinical decision-making, and emotional well-being. Findings indicate a predominance of carer resources and support tools, while clinically integrated platforms, cognitive assessments, and adaptive memory aids remain underrepresented. Most apps lack empirical validation, inclusive design, and integration with electronic health records, raising ethical concerns around data privacy, transparency, and informed consent. In parallel, the study identifies promising pathways for energy-optimised IoT systems, Artificial Intelligence (AI), and Ambient Assisted Living (AAL) technologies in fostering dementia-friendly, sustainable environments. Key gaps include limited use of low-power wearables, energy-efficient sensors, and smart infrastructure tailored to therapeutic needs. Application domains such as cognitive training (19 apps) and carer resources (28 apps) show early potential, while emerging innovations in neuroadaptive architecture and emotional computing remain underexplored. The findings emphasize the need for co-designed, evidence-based digital solutions that align with the evolving needs of people with dementia, carers, and clinicians. Future innovations must integrate sustainability principles, promote interoperability, and support global aging populations through ecologically responsible, person-centred dementia care ecosystems. Full article

This paper deals with a privacy-preserving human tracking system that uses multi-property infrared sensor arrays. In the growing field of intelligent elderly care, there is a critical need for monitoring systems that ensure safety without compromising personal privacy. While traditional camera-based systems offer detailed activity recognition, privacy-related concerns often limit their practical application and user acceptance. Consequently, approaches that protect privacy at the sensor level have gained increasing attention. The privacy-preserving human tracking system proposed in this paper protects privacy at the sensor level by fusing data from an ultra-low-resolution $8\times 8$ (64-pixel) passive thermal infrared (IR) sensor array and a similarly low-resolution $8\times 8$ active Time-of-Flight (ToF) sensor. The thermal sensor identifies human presence based on heat signature, while the ToF sensor provides a depth map of the environment. By integrating these complementary modalities through a convolutional neural network (CNN) enhanced with a cross-attention mechanism, our system achieves real-time three-dimensional human tracking. Compared to previous methods using ultra-low-resolution IR sensors, which mostly only obtained two-dimensional coordinates, the acquisition of the Z coordinate enables the system to analyze changes in a person’s vertical position. This allows for the detection and differentiation of critical events such as falls, sitting, and lying down, which are ambiguous to 2D systems. With a demonstrated mean absolute error (MAE) of 0.172 m in indoor tracking, our system provides the data required for privacy-preserving Ambient Assisted Living (AAL) applications. Full article

Smart furniture represents a growing field that integrates Internet of Things (IoT), embedded systems and assistive technologies, yet lacks a comprehensive synthesis of its components and applications. This PRISMA-guided systematic review analysed 35 studies published between 2014 and 2024, sourced from PubMed, Web of Science and Scopus. The included studies presented prototypes of smart furniture that used IoT, sensors or automation. The focus was on extracting data related to technological configurations, functional uses, validation methods, maturity levels and commercialisation. Three technological pillars emerged, data collection (n = 31 studies), transmission/processing (n = 30), and actuation (n = 22), often combined into multifunctional systems (n = 14). Health monitoring was the dominant application (n = 15), followed by environmental control (n = 8) and assistive functions for older adults (n = 8). Validation methods varied; 37% relied solely on laboratory testing, while 20% only involved end-users. Only one solution surpassed Technology Readiness Level (TRL) 7 and is currently on the market. Current research remains pre-commercial, with gaps in AI integration, long-term validation, and participatory design. Smart furniture shows promise for healthcare and independent living, but requires standardised evaluation, ethical data practices, and co-creation to achieve market readiness. Full article

Fall detection systems in ambient assisted living (AAL) and smart homes are essential for the comfort, safety, and autonomy of elderly people. The aim of this study was to investigate the performance of these systems considering categories of sensors and methods used. A systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Seven open databases were screened without a date limit: PubMed/MedLine, Google Scholar, ScienceDirect, Science.gov, Academia, IEEE Xplore, and Mendeley. The article selection and data extraction were performed by two authors independently. Among the 473 unique records, 80 studies were selected. Five fall detection performance parameters (accuracy, precision, sensitivity, specificity, F1-score) and two computation speed parameters (training and testing time) were extracted and classified according to three sensor categories (wearable, non-wearable, and hybrid solutions), and four methods (deep learning, machine learning, threshold, and all others). The ANOVA results showed that wearable sensors performed the worst in fall detection. Deep learning methods produced the best results for the five parameters. Identifying the advantages of different solutions is a major challenge for researchers, practitioners, and policymakers in the design and implementation of more effective fall detection systems. Full article

This work presents the design and prototyping of two reconfigurable BLE-based devices developed to overcome the limitations of commercial platforms in terms of configurability, data transparency, and energy efficiency. The first is a wearable smart wristband integrating inertial and biometric sensors, while the second is a configurable beacon (ASIA Beacon) able to dynamically adjust key transmission parameters such as channel selection and power level. Both devices were engineered with energy-aware components, OTA update support, and flexible 3D-printed enclosures optimized for residential environments. The firmware, developed under Zephyr RTOS, exposes data through standardized interfaces (GATT, MQTT), facilitating their integration into IoT architectures and research-oriented testbeds. Initial experiments carried out in an anechoic chamber demonstrated improved RSSI stability, extended autonomy (up to 4 months for beacons and 3 weeks for the wristband), and reliable real-time data exchange. These results highlight the feasibility and potential of the proposed devices for future deployment in ambient assisted living environments, while the focus of this work remains on the hardware and software development process and its validation. Full article