Search Results (407)

This paper proposes a robust convolutional neural network (CNN) architecture for human activity recognition (HAR) using smartphone accelerometer data, evaluated on the WISDM dataset. We introduce two novel pooling mechanisms—Pooling A (Extrema Contrast Pooling (ECP)) and Pooling B (Center Minus Variation (CMV))—that enhance feature discrimination and noise robustness. ECP emphasizes sharp signal transitions through a nonlinear penalty based on the squared range between extrema, while CMV Pooling penalizes local variability by subtracting the standard deviation, improving resilience to noise. Input data are normalized to the [0, 1] range to ensure bounded and interpretable pooled outputs. The proposed framework is evaluated in two separate configurations: (1) a 1D CNN applied to raw tri-axial sensor streams with the proposed pooling layers, and (2) a histogram-based image encoding pipeline that transforms segment-level sensor redundancy into RGB representations for a 2D CNN with fully connected layers. Ablation studies show that histogram encoding provides the largest improvement, while the combination of ECP and CMV further enhances classification performance. Across six activity classes, the 2D CNN system achieves up to 96.84% weighted classification accuracy, outperforming baseline models and traditional average pooling. Under Gaussian, salt-and-pepper, and mixed noise conditions, the proposed pooling layers consistently reduce performance degradation, demonstrating improved stability in real-world sensing environments. These results highlight the benefits of redundancy-aware pooling and histogram-based representations for accurate and robust mobile HAR systems. Full article

Human Activity Recognition (HAR) has become crucial across various domains, including healthcare, smart homes, and security systems, owing to the proliferation of Internet of Things (IoT) devices. Several Machine Learning (ML) techniques, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), have been proposed for HAR. However, they are still deficient in addressing the challenges of noisy features and insufficient data. This paper introduces a novel approach to tackle these two challenges, employing a Deep Learning (DL) Ensemble-Based Stacking Neural Network (SNN) combined with Generative Adversarial Networks (GANs) for HAR based on ambient sensors. Our proposed deep learning ensemble-based approach outperforms traditional ML techniques and enables robust and reliable recognition of activities in real-world scenarios. Comprehensive experiments conducted on six benchmark datasets from the CASAS smart home project demonstrate that the proposed stacking framework achieves superior accuracy on five out of six datasets when compared to literature-reported state-of-the-art baselines, with improvements ranging from 3.36 to 39.21 percentage points and an average gain of 13.28 percentage points. Although the baseline marginally outperforms the proposed models on one dataset (Aruba) in terms of accuracy, this exception does not alter the overall trend of consistent performance gains across diverse environments. Statistical significance of these improvements is further confirmed using the Wilcoxon signed-rank test. Moreover, the ASGAN-augmented models consistently improve macro-F1 performance over the corresponding baselines on five out of six datasets, while achieving comparable performance on the Milan dataset. The proposed GAN-based method further improves the activity recognition accuracy by a maximum of 4.77 percentage points, and an average of 1.28 percentage points compared to baseline models. By combining ensemble-based DL with GAN-generated synthetic data, a more robust and effective solution for ambient HAR addressing both accuracy and data imbalance challenges in real-world smart home settings is achieved. Full article

Human Activity Recognition (HAR) using wearable sensors enables impactful applications in healthcare, fitness, and smart environments, but it also faces challenges related to data privacy, non-independent and identically distributed (non-IID) data, and limited computational resources on edge devices. This study proposes an efficient and personalized federated learning (PFL) framework for HAR that integrates federated training with model compression and per-client fine-tuning to address these challenges and support deployment on resource-constrained devices (RCDs). A convolutional neural network (CNN) is trained across multiple clients using FedAvg, followed by magnitude-based pruning and float16 quantization to reduce model size. While personalization and compression have previously been studied independently, their combined application for HAR remains underexplored in federated settings. Experimental results show that the global FedAvg model experiences performance degradation under non-IID conditions, which is further amplified after pruning, whereas per-client personalization substantially improves performance by adapting the model to individual user patterns. To ensure realistic evaluation, experiments are conducted using both random and temporal data splits, with the latter mitigating temporal leakage in time-series data. Personalization consistently improves performance under both settings, while quantization reduces the model footprint by approximately 50%, enabling deployment on wearable and IoT devices. Statistical analysis using paired significance tests confirms the robustness of the observed performance gains. Overall, this work demonstrates that combining lightweight model compression with personalization providing an effective and practical solution for federated HAR, balancing accuracy, efficiency, and deployment feasibility in real-world scenarios. Full article

Accurate recognition of lower limb activities is essential for wearable rehabilitation systems and assistive robotics like exoskeletons and prosthetics. This study introduces SDALLE, a custom hardware data acquisition system that integrates surface electromyography sensors (EMGs) and inertial measurement sensors (IMUs) into a wireless, portable platform for locomotor monitoring. Using this system, data were collected from nine healthy subjects performing four fundamental locomotor activities: walking, jogging, stair ascent, and stair descent. The recorded signals underwent an offline structured preprocessing pipeline consisting of time-series augmentation (jittering and scaling) to increase data diversity, followed by wavelet-based denoising to suppress high-frequency noise and enhance signal quality. A temporal one-dimensional convolutional neural network (1D-TCNN) with three convolutional blocks and fully connected layers was trained on the prepared dataset to classify the four activities. Classification using IMU sensors achieved the highest performance, with accuracies ranging from 0.81 to 0.95. The gyroscope X-axis of the left Rectus Femoris achieved the best performance (0.95), while accelerometer signals also performed strongly, reaching 0.93 for the Vastus Medialis in the Y direction. In contrast, electromyography channels showed lower discriminative capability. These results demonstrate that the combination of SDALLE hardware, appropriate data preprocessing, and a temporal CNN provides an effective offline sensing and activity classification pipeline for lower limb activity recognition and offers an open-source dataset that supports further research in human activity recognition, rehabilitation, and assistive robotics. Full article

Human Activity Recognition (HAR) using wearable sensor data plays a vital role in health monitoring, context-aware computing, and smart environments. Many existing deep learning models for HAR incorporate MaxPooling layers after convolutional operations to reduce dimensionality and computational load. While this approach is effective in image-based tasks, it is less suitable for the sensor signals used in HAR. MaxPooling introduces a form of temporal downsampling that can discard subtle yet crucial temporal information. Also, traditional CNNs often struggle to capture long-range dependencies within each window due to their limited receptive fields, and they lack effective mechanisms to aggregate information across multiple windows without stacking multiple layers, which increases computational cost. In this study, we introduce Retentive-HAR, a model designed to enhance feature learning by capturing dependencies both within and across sliding windows. The proposed model intentionally omits the MaxPooling layer, thereby preserving the full temporal resolution throughout the network. The model begins with parallel dilated convolutions, which capture long-range dependencies within each window. Feature outputs from these convolutional layers are then concatenated along the feature dimension and transposed, allowing the Retentive Module to analyze dependencies across both window and feature dimensions. Additional 1D-CNN layers are then applied to the transposed feature maps to capture complex interactions across concatenated window representations before including Bi-LSTM layers. Experiments on PAMAP2, HAPT, and WISDM datasets achieve a performance of 96.40%, 94.70%, and 96.16%, respectively, which outperforms the existing methods with minimal computational cost. Full article

Human activity recognition (HAR) based on wearable sensors is a key technology in the fields of smart sensing and health monitoring. With the rapid development of deep learning, its powerful feature extraction capabilities have significantly enhanced recognition performance and reduced reliance on traditional handcrafted feature engineering. However, current deep learning models still face challenges in effectively capturing complex temporal dependencies in long-term time-series sensor data and addressing information redundancy, which affect model recognition accuracy and generalization ability. To address these issues, this paper proposes an innovative CNN-BiGRU–Transformer hybrid deep learning model aimed at improving the accuracy and robustness of human activity recognition. The proposed model integrates a multi-branch Convolutional Neural Network (CNN) to effectively extract multi-scale local spatial features, and combines a Bidirectional Gated Recurrent Unit (BiGRU) with a Transformer hybrid module for modeling temporal dependencies and extracting temporal features in long-term time-series data. Additionally, an attention mechanism is incorporated to dynamically allocate weights, suppress redundant information, and enhance key features, further improving recognition performance. To demonstrate the capability of the proposed model, evaluations are performed on three public datasets: WISDM, PAMAP2, and UCI-HAR. The model achieved recognition accuracies of 98.41%, 95.62%, and 96.74% on the three datasets, respectively, outperforming several state-of-the-art methods. These results confirm that the proposed approach effectively addresses feature extraction and redundancy challenges in long-term sensor time-series data and provides a robust solution for wearable sensor-based human activity recognition. 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

Human Activity Recognition (HAR) using wearable sensors has shown great potential for personalized health management and ubiquitous computing. However, existing deep learning-based HAR models often suffer from poor user-level generalization, which limits their deployment in real-world scenarios. In this work, we propose a novel multi-task contrastive learning framework that jointly optimizes activity classification and supervised contrastive objectives to enhance generalization across unseen users. By leveraging both activity and user labels to construct semantically meaningful contrastive pairs, our method improves representation learning while maintaining user-agnostic inference at test time. We evaluate the proposed framework on three public HAR datasets using cross-user splits, achieving comparable results to both supervised and self-supervised baselines. Extensive ablation studies further confirm the effectiveness of our design choices, including multi-task training and the integration of user-aware contrastive supervision. These results highlight the potential of our approach for building more generalizable and scalable HAR systems. Full article

Prehabilitation programs for abdominal pre-operative patients are increasingly recognized for improving surgical outcomes, reducing post-operative complications, and enhancing recovery. Internet of Things (IoT)-enabled human movement monitoring systems offer promising support in mixed-mode settings that combine clinical supervision with home-based independence. These systems enhance accessibility, reduce pressure on healthcare infrastructure, and address geographical isolation. However, current implementations often lack personalized movement analysis, adaptive intervention mechanisms, and real-time clinical integration, frequently requiring manual oversight and limiting functional outcomes. This review-based paper proposes a conceptual framework informed by the existing literature, integrating Digital Twin (DT) technology, and machine learning/Artificial Intelligence (ML/AI) to enhance IoT-based mixed-mode prehabilitation programs. The framework employs inertial sensors embedded in wearable devices and smartphones to continuously collect movement data during prehabilitation exercises for pre-operative patients. These data are processed at the edge or in the cloud. Advanced ML/AI algorithms classify activity types and intensities with high precision, overcoming limitations of traditional Fast Fourier Transform (FFT)-based recognition methods, such as frequency overlap and amplitude distortion. The Digital Twin continuously monitors IoT behavior and provides timely interventions to fine-tune personalized patient monitoring. It simulates patient-specific movement profiles and supports dynamic, automated adjustments based on real-time analysis. This facilitates adaptive interventions and fosters bidirectional communication between patients and clinicians, enabling dynamic and remote supervision. By combining IoT, Digital Twin, and ML/AI technologies, the proposed framework offers a novel, scalable approach to personalized pre-operative care, addressing current limitations and enhancing outcomes. Full article

Heavy metal ions (HMIs) threaten ecosystems and human health due to their carcinogenicity, bioaccumulativity, and persistence, demanding highly sensitive, low-cost real-time detection. Electrochemical sensing technology has gained significant attention owing to its rapid response, high sensitivity, and low cost. Molybdenum disulfide (MoS₂), with its layered structure, tunable bandgap, and abundant edge active sites, demonstrates significant potential in the electrochemical detection of heavy metals. This review systematically summarizes the crystal structure characteristics of MoS₂, various preparation strategies, and their mechanisms for regulating electrochemical sensing performance. It particularly explores the cooperative effects of MoS₂ composites with other materials, which effectively enhance the sensitivity, selectivity, and detection limits of electrochemical sensors. Although MoS₂-based materials have made significant progress in theoretical and applied research, practical challenges remain, including fabrication process optimization, interference from complex-matrix ions, slow trace-metal enrichment kinetics, and stability issues in flexible devices. Future work should focus on developing efficient, low-cost synthesis methods, enhancing interference resistance through microfluidic and biomimetic recognition technologies, optimizing composite designs, resolving interfacial reaction dynamics via in situ characterization, and establishing structure–property relationship models using machine learning, ultimately promoting practical applications in environmental monitoring, food safety, and biomedical fields. Full article

This study focuses on human awareness, a critical component in human–robot interaction, particularly within agricultural environments where interactions are enriched by complex contextual information. The main objective is identifying human activities occurring during collaborative harvesting tasks involving humans and robots. To achieve this, we propose a novel and lightweight deep learning model, named 1D-ResNeXt, designed explicitly for recognizing activities in agriculture-related human–robot collaboration. The model is built as an end-to-end architecture incorporating feature fusion and a multi-kernel convolutional block strategy. It utilizes residual connections and a split–transform–merge mechanism to mitigate performance degradation and reduce model complexity by limiting the number of trainable parameters. Sensor data were collected from twenty individuals with five wearable devices placed on different body parts. Each sensor was embedded with tri-axial accelerometers, gyroscopes, and magnetometers. Under real field conditions, the participants performed several sub-tasks commonly associated with agricultural labor, such as lifting and carrying loads. Before classification, the raw sensor signals were pre-processed to eliminate noise. The cleaned time-series data were then input into the proposed deep learning network for sequential pattern recognition. Experimental results showed that the chest-mounted sensor achieved the highest F1-score of 99.86%, outperforming other sensor placements and combinations. An analysis of temporal window sizes (0.5, 1.0, 1.5, and 2.0 s) demonstrated that the 0.5 s window provided the best recognition performance, indicating that key activity features in agriculture can be captured over short intervals. Moreover, a comprehensive evaluation of sensor modalities revealed that multimodal fusion of accelerometer, gyroscope, and magnetometer data yielded the best accuracy at 99.92%. The combination of accelerometer and gyroscope data offered an optimal compromise, achieving 99.49% accuracy while maintaining lower system complexity. These findings highlight the importance of strategic sensor placement and data fusion in enhancing activity recognition performance while reducing the need for extensive data and computational resources. This work contributes to developing intelligent, efficient, and adaptive collaborative systems, offering promising applications in agriculture and beyond, with improved safety, cost-efficiency, and real-time operational capability. Full article

This study addresses mental fatigue as a critical state arising from prolonged human activity and positions its detection as a valuable task within the broader scope of human activity recognition using deep learning. This work compares two models for mental fatigue detection: a model that uses eye-tracking data for fatigue predictions and a vision-based model that relies on vital signs and human activity indicators from facial video using deep learning and computer vision techniques. The eye-tracking model (based on TabNet architecture) achieved 82% accuracy, while the vision-based model (features were estimated using deep learning and computer vision) based on Random Forest architecture reached 78% accuracy. A correlation analysis revealed strong alignment between both models’ predictions, with 21 out of 27 sessions showing significant positive correlations on the collected dataset. Further comparison with an earlier-developed vision-based model trained on another dataset supported the generalizability of the vision-based model using physiological indicators extracted from a facial video for fatigue estimation. These findings highlight the potential of the vision-based model as a practical alternative to sensor and special-devices-based systems, especially in settings where non-intrusiveness and scalability are critical. Full article

With the widespread application of wearable sensors in health monitoring and human–computer interaction, deep learning-based human activity recognition (HAR) research faces challenges such as the effective extraction of multi-scale temporal features and the enhancement of robustness against noise in multi-source data. This study proposes the TGA-HAR (TCN-GRU-Attention-HAR) model. The TGA-HAR model integrates Temporal Convolutional Neural Networks and Recurrent Neural Networks by constructing a hierarchical feature abstraction architecture through cascading Temporal Convolutional Network (TCN) and Bidirectional Gated Recurrent Unit (BiGRU) layers for complex activity recognition. This study utilizes TCN layers with dilated convolution kernels to extract multi-order temporal features. This study utilizes BiGRU layers to capture bidirectional temporal contextual correlation information. To further optimize feature representation, the TGA-HAR model introduces residual connections to enhance the stability of gradient propagation and employs an adaptive weighted attention mechanism to strengthen feature representation. The experimental results of this study demonstrate that the model achieved test accuracies of 99.37% on the WISDM dataset, 95.36% on the USC-HAD dataset, and 96.96% on the PAMAP2 dataset. Furthermore, we conducted tests on datasets collected in real-world scenarios. This method provides a highly robust solution for complex human activity recognition tasks. Full article

Background: Artificial Intelligence (AI) techniques have been extensively deployed in sensor-based Human Activity Recognition (HAR) systems. Recent advances in deep learning, especially Convolutional Neural Networks (CNNs), have advanced HAR by enabling automatic feature extraction from raw sensor data. However, these models often struggle to capture multiscale patterns in human activity, limiting recognition accuracy. Additionally, traditional centralized learning approaches raise data privacy concerns, as personal sensor data must be transmitted to a central server, increasing the risk of privacy breaches. Methods: To address these challenges, this paper introduces Conv-ScaleNet, a CNN-based model designed for multiscale feature learning and compatibility with federated learning (FL) environments. Conv-ScaleNet integrates a Pyramid Pooling Module to extract both fine-grained and coarse-grained features and employs sequential Global Average Pooling layers to progressively capture abstract global representations from inertial sensor data. The model supports federated learning by training locally on user devices, sharing only model updates rather than raw data, thus preserving user privacy. Results: Experimental results demonstrate that the proposed Conv-ScaleNet achieves approximately 98% and 96% F1-scores on the WISDM and UCI-HAR datasets, respectively, confirming its competitiveness in FL environments for activity recognition. Conclusions: The proposed Conv-ScaleNet model addresses key limitations of existing HAR systems by combining multiscale feature learning with privacy-preserving training. Its strong performance, data protection capability, and adaptability to decentralized environments make it a robust and scalable solution for real-world HAR applications. Full article

Human activity recognition (HAR) is an automated technique for identifying human activities using images and sensor data. Although numerous studies exist, most of the models proposed are highly complex and rely on deep learning. This research utilized two novel frameworks based on the Extreme Gradient Boosting (XGB) classifier, also known as the XGBoost classifier, enhanced with metaheuristic algorithms: Golden Jackal Optimization (GJO) and War Strategy Optimization (WARSO). This study utilized the KU-HAR dataset, which was collected from smartphone accelerometer and gyroscope sensors. We extracted 48 mathematical features to convey the HAR information. GJO-XGB achieved a mean accuracy in 10-fold cross-validation of 93.55% using only 23 out of 48 features. However, WARSO-XGB outperformed GJO-XGB and other traditional classifiers, achieving a mean accuracy, F-score, precision, and recall of 94.04%, 92.88%, 93.47%, and 92.40%, respectively. GJO-XGB has shown lower standard deviations on the test set (accuracy: 0.200; F-score: 0.285; precision: 0.388; recall: 0.336) compared to WARSO-XGB, indicating a more stable performance. WARSO-XGB exhibited lower time complexity, with average training and testing times of 30.84 s and 0.51 s, compared to 39.40 s and 0.81 s for GJO-XGB. After performing 10-fold cross-validation using various external random seeds, GJO-XGB and WARSO-XGB achieved accuracies of 93.80% and 94.19%, respectively, with a random seed = 20. SHAP identified that range_gyro_x, max_acc_z, mean_gyro_x, and some other features are the most informative features for HAR. The SHAP analysis also involved a discussion of the individual predictions, including the misclassifications. Full article