Search Results (10,744)

Massive Internet of Things (IoT) and sensor-network services in 5G/6G systems increasingly rely on network slicing to support large-scale sensing, monitoring, and mission-critical applications. In such sliced infrastructures, Proportional Fair (PF) allocation assigns resources according to slice-reported demands. This reliance on trusted demand reporting makes coexisting slices, including mMTC-based IoT sensor slices, vulnerable to resource exhaustion attacks, where a malicious slice inflates its demand to monopolize shared resources and induce Service Level Agreement (SLA) violations. Existing unsupervised defenses mainly focus on anomaly detection, while the translation of detection results into resource-level mitigation remains insufficiently addressed. To bridge this gap, this paper proposes AutoGuard-Hybrid, an unsupervised detection-to-mitigation framework that combines complementary anomaly detectors with allocation-aware mitigation policies to preserve slice-level service availability. Unlike prior detection-only approaches, AutoGuard-Hybrid converts unsupervised anomaly evidence into allocation-aware demand purification before PF scheduling. Its key design is a closed-loop integration of Isolation Forest (IF) and Long Short-Term Memory Autoencoder (LSTM-AE) as spatial and temporal front-end detectors with Adaptive Clipping and a Safety Cap, which translate anomaly scores into demand purification actions. Experiments show that AutoGuard-Hybrid remains comparable to Isolation Forest under Continuous attacks and improves the mean system-wide SLA violation rate by 27.6% under Adaptive Probing attacks. Stage activation analysis further shows that LSTM-AE activations increase from 9.3 under Continuous attacks to 29.4 under Adaptive Probing attacks. Ablation results show that Adaptive Clipping alone reduces the system-wide SLA violation rate by 75.0%, while the full mitigation pipeline achieves an 84.6% total reduction. AutoGuard-Hybrid operates within the 1 ms Transmission Time Interval (TTI) constraint and provides a practical defense framework for next-generation network slicing-enabled IoT and sensor-network services. Full article

A virtual training environment offers clear advantages for agricultural robotics. It provides a safe setting in which perception, navigation, and control algorithms can be evaluated without risking damage to either the robot or the crop. It also supports efficient data generation: large volumes of training data can be collected under diverse environmental conditions that would be costly, slow, and often season-dependent in real-world deployments. This broader variability improves model adaptability, reduces the risk of overfitting, and leads to more robust operation. In this paper, we argue that digital twin technology should therefore be understood not merely as a passive mirror of a physical robot, but as an active training environment in which multiple sensor-related subprocesses can be developed, tested, validated, and refined jointly. This paper is based on our experiences with digital twin technology used in the development of a vineyard robot, including a self-driving rover, sensor simulation, procedural map generation, and agriculture-specific movement models. Our contribution is threefold: we reinterpret the digital twin as a training space, propose a layered framework for training agricultural robots in virtual environments, and explain why agriculture is a particularly strong use case, given variable field conditions, expensive real-world experimentation, and persistent labor scarcity. To validate this framework, we present the simulation-based evaluation of an autonomous reinforcement learning agent. The agent has been trained entirely in this virtual environment, which successfully navigated to 155 out of 161 target points in a simulated vineyard demonstration environment. Full article

Wearable inertial sensing has considerable potential for process-level analysis of upper-limb function, but further evidence is needed to understand how it can be applied within ecologically structured immersive virtual reality (VR) tasks. Most VR-based functional assessments rely primarily on outcome-level indicators, such as task completion time, success rate, or error count, which may not fully capture how a task is executed. This exploratory study investigated whether wearable IMU signals collected during an immersive VR sushi-making task could support binary detection of a core upper-limb manipulation phase and provide additional information about task execution beyond global performance outcomes. A total of 45 participants contributed usable motion recordings for this study, with five Xsens DOT sensors placed on the hands, forearms, and waist. Three signal modalities were analysed, including acceleration (ACC), gyroscope angular velocity (GYR), and Euler angles. The downstream recognition problem was formulated as a binary classification task (Placing vs. Non-Placing), and a self-supervised learning (SSL) pretrain–fine-tune strategy was evaluated against conventional machine learning and from-scratch deep learning baselines using five subject-wise validation splits. The strongest overall performance was achieved with hand-mounted accelerometer signals, with LeftHand–ACC achieving a Macro-F1 of $0.712\pm 0.128$ and RightHand–ACC achieving $0.679\pm 0.118$. Under both hand-ACC settings, SSL fine-tuning showed higher mean Macro-F1 than the Balanced Random Forest baseline and the same deep architecture trained from scratch. Recognition performance varied substantially across sensor locations, signal modalities, and task segments, with distal upper-limb sensors generally outperforming waist-based configurations. Cross-age analyses further showed that within-cohort and cross-cohort performance did not fully align, indicating sensitivity to age-related distribution shift. Beyond classification, Log Dimensionless Jerk (LDLJ) derived from the Placing action showed a significant positive association with Cognitron motor control time cost ($r=0.636$, $p<0.001$). These findings suggest that wearable IMU sensing can provide preliminary process-level information during immersive VR functional tasks, including task-phase detection, sensing-configuration comparison, cross-cohort generalisation assessment, and exploratory motion-quality analysis. The results should be interpreted as evidence of feasibility rather than as a mature biomechanical or clinical assessment model. Full article

Trimethylamine (TMA), a characteristic volatile biogenic amine generated during aquatic product spoilage, has a concentration that quantitatively reflects product freshness. Therefore, developing a rapid and accurate method for TMA detection is important for food safety control. Herein, this study synthesized high-performance hollow SnO₂ nanospheres via a hydrothermal method, aiming to develop a rapid, non-destructive gas sensor for TMA detection and evaluate its feasibility for assessing aquatic product freshness. The material exhibited a high response (Ra/Rg = 10.5@100 ppm), rapid response-recovery kinetics (10 s/20 s), and good selectivity. These properties were attributed to the high specific surface area, efficient gas diffusion channels, and abundant active sites provided by the hollow structure, which enhances the sensor’s response rate. Ultraviolet–visible diffuse reflectance spectroscopy further showed that the hollow structure narrows the bandgap of SnO₂, which may facilitate electron transfer and contribute to the enhanced response to TMA. In practical applications, a MEMS sensor based on SnO₂ hollow nanospheres successfully detected TMA concentration changes from sea bass during 0–8 days of refrigerated storage, demonstrating its potential reliability for rapid freshness assessment of aquatic products and providing a technological route for quality evaluation. Full article

The majority of currently available hand kinematic databases have been gathered using expensive marker-based systems or are restricted to a particular gesture-recognition task, failing to capture the dynamic nature of joints when the hand is engaged with an object. To address this gap, we introduce the RGB-based Hand Joint Kinematics (RGB-HJK) dataset, a publicly available collection of continuous, frame-level 3D joint angle trajectories, recorded while ten healthy adults (six male, four female; age $25.8\pm 3.2$ years; BMI $22.8\pm 2.0$ kg/m²) performed five standardized object interaction grasps: Power Grasp (cylindrical bottle), Tripod Grasp (pen), Static Power Hold (smartphone), Precision Pinch (thin paper), and Lateral Pinch (book). Data were collected using a standard RGB camera and the MediaPipe Hands markerless pipeline at $26.95\pm 0.29$ Hz, a rate that was stable across all subjects. Each participant completed five trials for each grasp type. After filtering using active hold, 28,111 validated frames remained, with a 100% detection rate for all 250 trials. Intra-subject repeatability was good (mean SD $\le 7.9°$ across all joint grasp combinations) and inter-subject variability was within the range expected based on normal anatomical diversity. Importantly, kinematic validation of the Index Proximal Interphalangeal (PIP) joint (61.8° ± 18.4°) showed values consistent with ranges reported in previous studies using instrumented gloves and depth sensors. Principal Component Analysis (PCA) confirmed clear linear separability among the five grasp configurations. Unlike existing datasets, the RGB-HJK method does not compromise the natural sense of touch and is free of hardware occlusions, thereby providing an easily accessible ecological baseline. Full article

Image sensors produce high-dimensional visual data for classification algorithms. Deep Neural Networks (DNNs) achieve high accuracy but require large labeled datasets and computational and energy resources, limiting their use in embedded systems. Active Learning (ALrn) can reduce labeling effort by selecting samples based on informativeness scores, but it remains computationally expensive, especially for high-dimensional images. This work presents a hardware-accelerated approach for the instance selection stage based on a query strategy in uncertainty-based ALrn for image classification using a novel in-line top-k selection algorithm that avoids conventional sorting and reduces memory and computational requirements. The algorithm is implemented on an Xilinx ZYNQ-7000 System on Chip (SoC) using a Field Programmable Gate Array (FPGA)-based accelerator operating at 110 MHz, interfacing with an embedded Advanced RISC Machine (ARM) processor for data acquisition and communication via the Python Productivity for Zynq (PYNQ) framework. Experiments on diverse multiclass datasets demonstrate correctness within an ALrn setting, showing negligible performance deviation in the learning curves compared to software baselines. The accelerator achieves speedup of 231.7× and 22.9× over software baseline and optimized software implementation of the proposed algorithm, respectively, in query-strategy computation while consuming only 0.473 W, substantially lower than conventional Central Processing Unit (CPU)- and Graphics Processing Unit (GPU)-based platforms. These results demonstrate the efficiency and extensibility of the proposed accelerator across alternative ALrn designs and hardware platforms, where the computational cost of instance selection scales with the size of the unlabeled pool. Full article

Autonomous driving systems face critical perception failures in dense fog, where conventional RGB cameras suffer from severe degradation due to atmospheric scattering and reduced visibility. This paper presents an adaptive multi-modal fusion framework that synergistically integrates gated imaging with 3D LiDAR point clouds to achieve robust obstacle detection under visibility conditions as low as 50 m. Unlike standard cameras that passively capture scattered ambient light, gated cameras employ time-synchronized active illumination to physically filter backscattered photons, preserving structural features even in low-visibility scenarios. We propose a novel Adaptive Feature-Weighting Network (AFW-Net) that dynamically adjusts sensor modality contributions based on real-time environmental degradation assessment. The framework incorporates three key innovations: (1) a cross-modal feature extraction module that exploits the complementary physical properties of gated imaging and LiDAR, (2) an attention-based adaptive fusion mechanism that quantifies per-modality reliability through uncertainty estimation, and (3) a degradation-aware training strategy using weather-specific augmentation. Extensive experiments on the Princeton Automated Driving Dataset demonstrate that our approach maintains detection average precision (AP) above 82% under dense fog conditions (50 m visibility), representing a 23.7% improvement over state-of-the-art RGB-LiDAR fusion methods that exhibit substantial performance degradation to 58.4% AP. Ablation studies validate the necessity of each component, and cross-dataset evaluation confirms the generalization capability of the proposed framework. The adaptive weighting mechanism proves particularly effective, dynamically rebalancing modality contributions across the gated imaging and LiDAR branches while maintaining LiDAR geometric constraints. This work establishes a robust perception paradigm for safety-critical autonomous systems operating in low-visibility environmental conditions. Full article

Pupil response may be a useful biomarker in Parkinson’s disease (PD) due to links with autonomic function and cognitive load. However, research has focused on static tasks, missing functional demands during real-world activities like walking. Methods: We recruited 38 people with PD and 16 healthy controls who walked for 2 min under single- and dual-task conditions while wearing mobile eye-tracking glasses (Tobii Pro Glasses 2, 100 Hz). Pupil response outcomes (velocity, size, difference between eyes) were extracted alongside gait characteristics from inertial sensors. Known groups validity compared PD and controls; convergent/divergent validity examined relationships with cognitive, visual, clinical, and gait measures. Results: People with PD had significantly altered pupil constriction/dilation velocity (p = 0.01), a larger difference between their left and right pupils (p = 0.04), and a larger mean and minimum pupil size (p ≤ 0.01) compared to controls during walking. Pupil response correlated with cognitive function (JLO, CLOX1, TMTB), visual acuity, disease severity (MDS-UPDRS-III), and gait characteristics in both groups. No dual-task effects were observed. Conclusions: Pupil response during walking demonstrates known groups and convergent validity, indicating potential as a clinical biomarker for PD. Following this initial study, more research is required to further validate pupil response in PD (e.g., analytical validation and testing within real-world ecologically valid environments). Full article

Microfinance institutions (MFIs) are vital in promoting financial inclusion for underserved populations. However, these institutions face growing security threats, including sophisticated burglary tactics like underground tunneling. In the Philippines, notable incidents, such as the “Termite Gang” heist in Marikina City and a mall robbery in Ozamiz, highlight the limitations of conventional security systems in addressing subterranean intrusions. This study addresses the gap in existing security technologies by developing a real-time detection system that integrates a vibration sensor, a Global System for Mobile Communications (GSM) module for sending real-time SMS alerts, an audible alarm, and a solar-powered backup system for continuous operation. The system was simulated in the electrical technology laboratory to enhance classroom learning. The system’s core is an Arduino Uno microcontroller that processes inputs from the SW-420 vibration sensor, activating alarms and triggering SMS notifications via the SIM900A module when it detects unusual vibrations. Simulations A, B, and C were conducted to evaluate the system’s response time, with results showing a progressive reduction in detection time from five seconds to one second, indicating improved calibration and system efficiency. These findings also support the existing literature on user interaction with vibration alerts, demonstrating high accuracy in interpreting haptic notifications and the cognitive trade-offs involved. The proposed solution offers a proactive, energy-resilient, and cost-effective security system specifically designed to address underground burglary attempts. It applies to MFIs, pawnshops, and other high-risk financial environments. Future research should explore the application of machine learning for adaptive threat detection, expand the system’s scalability, and integrate mobile applications to enable user customization and enhance alert management. Full article

Rooftop farms are urban green infrastructure integrating food production, ecological regulation, and public services, and their management increasingly relies on data-driven approaches. However, open built environments, microclimatic heterogeneity, and limited sensor deployment challenge continuous monitoring and short-term prediction of rooftop plant growth. This study proposes and validates a virtual sensor-driven digital twin system using a rooftop tomato case in Xiamen, China. The system adopts a five-layer architecture comprising data acquisition, transmission, modeling, processing, and application service layers. By coupling a Long Short-Term Memory (LSTM) weather prediction model with the Decision Support System for Agrotechnology Transfer (DSSAT) crop growth model, a predictive virtual sensor module was developed to forecast leaf area index (LAI), aboveground biomass, phenology, and yield for seven days. Results show that the system links environmental data acquisition, LSTM–DSSAT prediction, database storage, and three-dimensional visualization, transforming rooftop plant growth into an updatable, predictable, and visualized digital twin object. The coupled model showed high predictive accuracy, with R² values of 0.9814 for LAI and 0.9966 for aboveground biomass, while supporting phenology and yield prediction. The system supports irrigation optimization, landscape management, and activity planning in sensor-constrained rooftop farms. Full article

Poor indoor air quality, inadequate ventilation, and unnoticed local disturbances can reduce occupant well-being and compromise practical safety in smart-home and small-building environments. Although low-cost Internet-of-Things (IoT) sensing technologies are widely available, many monitoring systems remain focused on single-modality sensing and do not jointly evaluate environmental conditions, vibration activity, communication reliability, and gateway-side interpretation within one framework. This study presents the design, implementation, and proof-of-concept evaluation of a low-cost, privacy-conscious, non-imaging IoT-based indoor environment and safety-awareness monitoring framework built with ESP32/Arduino sensor nodes and a Raspberry Pi gateway. The system integrates carbon dioxide, temperature, humidity, gas-resistance/VOC-trend indication, and vibration sensing with MQTT-based communication and edge-side analytics. Controlled subsystem experiments showed that CO₂ concentration differentiated ventilation conditions, increasing from 395.47 ppm in the valid empty/open-door baseline to 1083.16 ppm in the closed occupied condition. Vibration states were distinguished using root-mean-square acceleration features across calm, surface-disturbance, footstep, play, and jump conditions. MQTT evaluation using 1000-message batches showed no observed message loss or duplicates across the tested QoS/network combinations, although latency and throughput varied by network configuration and QoS level. QoS 1 provided a practical balance between low latency and protocol-level delivery assurance in the tested local/Wi-Fi setting. A final integrated validation run further demonstrated synchronized acquisition from indoor environmental, vibration, and outdoor CO₂ reference publishers through the same Raspberry Pi gateway, with zero missing or duplicate sequence flags across the three streams. Overall, the findings indicate that lightweight open-source IoT hardware can support a reproducible building-level sensing and edge-analytics prototype for indoor environment and safety-awareness monitoring. Broader deployment in standard-sized rooms, multi-room buildings, and smart-city infrastructure remains future work. Full article

Multi-field coupled numerical analysis and strain monitoring experiments were conducted for the curing process of a ring-shaped CFRP component. The curing kinetics and mechanical properties of LD-2184 epoxy resin were characterized using non-isothermal DSC, tensile testing, and CTE measurements. The curing reaction follows a single-stage autocatalytic mechanism with an activation energy of 54.73 kJ·mol⁻¹. A piecewise curing kinetics equation was established. The elastic modulus of the fully cured resin is 2.810 GPa, and the coefficient of thermal expansion is 6.060 × 10⁻⁵ K⁻¹. Composite ring specimens were fabricated using a wet winding process. FBG sensors were embedded to monitor axial strain during curing. A coupled numerical model was developed that includes heat conduction, curing kinetics, and curing deformation. ABAQUS was used to simulate the curing process of the composite ring. The results show a temperature gradient within the filament-wound layer. Thermo-chemical strain is similar between inner and outer regions. Total strain varies along the thickness due to mold constraint. Residual stress is governed by resin chemical shrinkage and thermal contraction during cooling. The difference between measured and simulated strain is 7.15%, which supports the validity of the multi-field coupled curing model. Full article

Physical activity is a key lifestyle factor for mental health prevention, yet the influence of accelerometer placement on mood prediction remains unclear. We merged high-resolution acceleration data and Ecological Momentary Assessment (EMA) mood reports from 259 healthy participants across three ambulatory studies (SedMood, 24 hrCog, HO). Additionally, 15 min pre-assessment movement windows consisting of raw triaxial acceleration (64 Hz) from hip, thigh, chest, and wrist sensors were paired with six-item mood EMA queries. Features (e.g., mean, entropy, spectral power) were extracted and fed into gradient-boosted decision tree models (XGBoost), trained separately for energetic arousal, valence, and calmness. Performance was measured using the metrics MAE, RMSE and R². Within individual studies, chest and hip sensors achieved the highest performance, followed by wrist and thigh. In the combined dataset, hip sensors again outperformed thigh (R² 0.38 vs. 0.20). Multi-sensor models rarely surpassed the best single-sensor configuration and sometimes reduced accuracy. These results suggest that sensor location modestly impacts mood-prediction performance, with hip and chest offering the most reliable signals, while adding sensors does not reliably enhance predictive power. Future work should explore larger, homogenous datasets and location-specific feature engineering to refine wearable-based mental health monitoring. Full article

With the development of Internet of Things (IoT) technology, fire detection systems based on multi-sensor fusion have become critical infrastructure to ensure public safety. Due to environmental noise and sensor heterogeneity, these systems often suffer from high rates of false alarms and missed detections. Although existing machine learning approaches have partially improved classification accuracy, their overall performance remains limited. Inspired by the cognitive mechanisms of the human brain, we developed an improved mind-linked continuous-coupled neural network (ML-CCNN) based on the existing continuous-coupled neural network (CCNN). We propose a parameter adaptation mechanism that modulates neural activations through a global threshold. We utilized the synthetic minority oversampling technique (SMOTE) to mitigate data imbalance and transformed sample feature vectors into matrices for training. Our model achieved an accuracy of 99.96% on our own dataset and 99.97% on the public Smoke Detection Dataset (SDD), which highlights ML-CCNN’s potential for fire detection. Full article

This study systematically evaluates the impact of sensor configuration, body location, classification granularity, and model choice on inertial-based human activity recognition in a laboratory dataset aligned with the Spanish IMPaCT cohort design. Data were collected from 85 participants instrumented with thigh-, wrist-, and hip-mounted inertial measurement units over a structured protocol of 13 semi-structured daily activities, a resting phase and a structured activity. After manual correction of timestamp drift, signals were segmented into overlapping 10-s windows and analyzed using convolutional neural networks, Random Forest, and XGBoost classifiers.Two classification targets were defined: fine-grained recognition of 15 laboratory-controlled activities and coarse-grained classification into four MET-based intensity levels. Results showed that classification granularity is the primary determinant of performance ($F=224.85$, p-value = $2.304\times {10}^{-13}$ through the analysis of variance of the F1-score), with intensity-level classification substantially outperforming fine-grained activity recognition. Sensor configuration, model type, and body location also significantly influenced classification outcomes. Wrist-mounted sensors achieved the highest overall F1-scores. Incorporating gyroscope-derived features consistently improved performance across configurations, and feature importance analysis confirmed their substantial contribution. These findings, derived from models developed under controlled laboratory conditions, provide practical guidance for the design of wearable sensing protocols and modeling strategies in large-scale population-based studies, and support their extension to everyday physical activity, laying the foundation for future real-world applications. Full article