Search Results (555)

Background: Obesity and its accompanying complications have an influence on diurnal rhythm, potentially causing cardiometabolic disease. This study explores how weight loss due to bariatric surgery affects circadian rhythm disruptions measurable through wearable heart rate monitors. Methods: A single-center observational study was performed, in which patients who had undergone primary bariatric surgery 3 years ago with telemonitoring of vital parameters using a wireless accelerometer were eligible to participate. A Wilcoxon signed-rank test was conducted to evaluate the delta of, or amount of change in, circadian patterns between the baseline (before) and post-weight-loss peak, nadir, and peak–nadir heart rates. Results: In this cohort of 69 patients, 70% were female, with a median total weight loss of 31.4% towards a median BMI of 28.4 kg/m². Analysis revealed significant changes in peak–nadir excursions post-weight loss. Peak, nadir, and peak–nadir differences showed a significant reduction in values in the post-weight-loss group. No significant correlations between other clinical endpoints and change in peak–nadir excursion were found in the multivariable regression models. Conclusions: In conclusion, this study reveals significant changes in circadian heart rate patterns before and after weight loss due to metabolic surgery. The results could add to the health benefits of bariatric surgery, as it could lower the incidence of diseases associated with changes in diurnal rhythm due to obesity. However, a clear clinical explanation is lacking, as no correlation with total weight loss nor other variables was substantiated. Full article

Parkinson’s disease (PD) alters both speech and movement, yet most automated assessments still treat these signals separately. We examined whether combining voice with head motion improves discrimination between patients and healthy controls (HC). Synchronous measurements of acoustic and inertial signals were collected using a HoloLens 2 headset. Data were obtained from 165 participants (72 PD/93 HC), following a standardized mixed-reality (MR) protocol. We benchmarked single-modality models against fusion strategies under 5-fold stratified cross-validation. Voice alone was robust (pooled AUC ≈ 0.865), while the inertial channel alone was near chance (AUC ≈ 0.497). Fusion provided a modest but repeatable improvement: gated early-fusion achieved the highest AUC (≈0.875), cross-attention fusion was comparable (≈0.873). Gains were task-dependent. While speech-dominated tasks were already well captured by audio, tasks that embed movement benefited from complementary inertial data. Proposed MR capture proved feasible within a single session and showed that motion acts as a conditional improvement factor rather than a sole predictor. The results outline a practical path to multimodal screening and monitoring for PD, preserving the reliability of acoustic biomarkers while integrating kinematic features when they matter. 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

Population aging has intensified the prevalence of falls among older adults, making automatic Fall Detection Systems (FDS) a key component of telemonitoring and remote care. Among wearable-based approaches, inertial sensors, particularly accelerometers, offer an effective and low-cost alternative for continuous monitoring. However, the impact of the selection of the sampling frequency on model performance remains insufficiently explored. This work seeks to determine the sampling rate that best balances accuracy, stability, and computational efficiency in wearable FDS. Five representative algorithms (CNN-LSTM, CNN, LSTM-BN, k-NN, and SVM) were trained and evaluated using the SisFall dataset at 10, 20, 50, and 100 Hz, followed by a multi-stage validation including the real-fall repositories FARSEEING and Free From Falls, as well as a seven-day continuous monitoring test under real-life conditions. The results show that deep learning architectures consistently outperform traditional classifiers, with the CNN-LSTM model at 20 Hz achieving the best balance of accuracy (98.9%), sensitivity (96.7%), and specificity (99.6%), while maintaining stable performance across all validations. The observed consistency indicates that intermediate frequencies, around 20 Hz and down to 10 Hz, provide sufficient temporal resolution to capture fall dynamics while reducing data volume, which translates into more efficient energy usage compared to higher sampling rates. Overall, these findings establish a solid empirical foundation for designing next-generation wearable fall-detection systems that are more autonomous, robust, and sustainable in long-term IoT-based monitoring environments. Full article

This paper presents a detailed analysis of signal data acquired from wearable sensors such as accelerometers and barometric altimeters for human activity recognition, with an emphasis on fall detection. This research addressed two types of activity recognition tasks: a binary classification problem between activities of daily living (ADLs) and simulated fall activities and a multiclass classification problem involving five different activities (running, walking, sitting down, jumping, and falling). By combining features derived from both sensors, traditional machine models such as random forest, support vector machine, XGBoost, logistic regression, and majority voter models were used for both classification problems. All of the aforementioned methods generally produced better results using combined features of both sensors compared to single-sensor models, highlighting the potential of sensor fusion approaches for fall detection. Full article

Human daily physical activity (PA), monitored via wearable devices, provides valuable information for real-time health assessment and disease prevention. However, analyzing time-domain PA data is challenging due to large data volumes and high inter- and intra-individual heterogeneity. Traditional PA analyses often rely on demographics, while advanced methods utilize time-domain summary statistics (e.g., L5, M10) or functional principal component analysis (FPCA). This study presents a data-efficient approach utilizing the Discrete Fourier Transform (DFT) to convert time-domain data into a compact set of frequency-domain variables. Our research suggests that adding these DFT variables can significantly enhance model performance. We demonstrate that incorporating DFT-derived variables substantially improves model performance. Specifically, (1) a small subset of DFT variables effectively captures major PA levels with effective dimensionality reduction; (2) these variables retain known associations with factors like age, sex, and weekday/weekend status; (3) they enhance the performance of classifiers. Mathematical and empirical analyses further confirm the reliability and interpretability of DFT-based features in dimension reduction. Across three mental health studies, these DFT-derived variables successfully capture key PA characteristics while retaining known associations and strengthening model performance. Overall, the proposed DFT-based framework offers a robust and scalable tool for analyzing accelerometer data, with broad applicability in health and behavioral research. Full article

In general, epilepsy is considered to be one of most prevalent neurological disorders and frequently appears as sudden seizures resulting in injuries, accidents, sudden unexpected death, etc. Also, it is reported that around 60 million people across the globe are experiencing various seizures due to epilepsy. So, there is demand for ambulatory seizure detection devices to prevent such accidents and to improve the quality of life for epilepsy patients. In this work, an intelligent Internet of Medical Things (IoMT)-based wearable device is designed and developed to monitor seizures in epilepsy patients. Due to the lack of an accelerometer dataset for epileptic seizures, the proposed device was developed, and a dataset mimicking seizure-like activities was generated. Further, the proposed device utilizes an MPU6500-based inertial measurement unit (IMU) which is integrated into an ESP32 microcontroller board. The ESP32 has a built-in wireless fidelity (WiFi) + Bluetooth (BLE) un that supports MicroPython v1.22.1 programming. Also, the machine learning algorithms such as Decision Trees (DT), Support Vector Machines (SVM), and Random Forest (RF) were programmed using MicroPython v1.22.1 programming and deployed on a tiny edge computing device to monitor the activity of the epileptic patients. All the adopted machine learning algorithms were compared in terms of performance metrics such as accuracy, precision, recall, false positive rate (FPR), etc., and the efficacy of the device was analysed. Results demonstrate that the proposed device is capable of identifying the activities of individuals, which is highly useful for epilepsy patients to monitor epileptic seizures. Furthermore, the proposed device was deployed with an RF algorithm since it exhibits an accuracy of 95% which is better compared to other machine learning algorithms. Also, the proposed device is simple and cost-effective and, in the event of a seizure event, can alert caretakers of epilepsy patients with an FPR of less than 4%. Full article

The present study evaluates the effectiveness of a non-invasive wearable sensor system, combining accelerometers, surface electromyography, and artificial intelligence, to objectively characterize swallowing in elderly individuals affected by Parkinson’s Disease, without clinically manifested dysphagia. A cohort of patients and healthy control subjects performed the same swallowing test protocol, including tasks with different viscosity boluses, positioning a commercial adhesive grid of High-Density surface Electromyography (HD-sEMG) electrodes on the submental muscle and a triaxial accelerometer over the thyroid cartilage. Relevant temporal and spectral features were extracted from electromyography data. Proper filtering and processing by machine learning and Principal Component Analysis allowed identification of two distinct clusters of subjects, one predominantly composed of controls with just a few patients, the other mostly crowded by patients. Excellent classification performances were achieved (accuracy = 83.3%, precision = 79.0%, recall = 90.7%, F1-score = 84.5%, Cohen’s kappa = 0.67), revealing consistent differences in muscle activation patterns among subjects, even in the absence of clinically diagnosed dysphagia. These results support the feasibility of wearable sensor-based assessment as a reliable and non-invasive tool for the early detection of subclinical swallowing dysfunction in Parkinson’s Disease. Full article

In the last few decades, several wearable devices have been designed to monitor respiration rate to capture pulmonary signals with a higher accuracy and reduce patients’ discomfort during use. In this article, we present the design and implementation of a device for the real-time monitoring of respiratory system movements. When breathing, the circumference of the abdomen and thorax changes; therefore, we used a Force-Sensing Resistor (FSR) attached to a Printed Circuit Board (PCB) to measure this variation as the patient inhales and exhales. The mechanical strain this causes changes the FSR electrical resistance accordingly. Also, for streaming this variable resistance on an Internet of Things (IoT) platform, Bluetooth Low Energy (BLE) 5 is utilized due to its adequate throughput, high accessibility, and the possibility of power consumption reduction. In addition to the sensing mechanism, the device includes a compact, energy-efficient micro-controller and a three-axis accelerometer that captures body movement. Power is supplied by a rechargeable Lithium-ion Polymer (LiPo) battery, and energy usage is optimized using a buck converter. For comfort and usability, the enclosure was 3D printed using Stereolithography (SLA) technology to ensure a smooth, ergonomic shape. This setup allows the device to operate reliably over long periods without disturbing the user. Altogether, the design supports continuous respiratory tracking in both clinical and home settings, offering a practical, low-power, and portable solution. Full article

Cardiovascular exercise strengthens the heart and improves circulation, but most people struggle to fit regular workouts into their day. Short bursts of vigorous activity, sometimes called exercise snacks, can raise the heart rate and deliver meaningful health benefits. Accurate, real-time monitoring of cardio-exercises is essential to ensure that these workouts meet recommended intensity and rest guidelines. This paper proposes a Tiny Machine Learning (TinyML) wearable system that tracks the duration and type of common cardio-exercises in real time. A compact device containing a six-axis inertial measurement unit (IMU) is worn on the arm. The device streams accelerometer data to an on-device neural network model, which classifies exercises such as jumping jacks, squat jumps and jogging in place and resting states. The TinyML model is trained with labelled motion data and deployed on a microcontroller using quantization to meet memory and latency constraints. Preliminary tests with ten participants show that the system correctly recognizes the targeted exercises with around 95% accuracy and an average F1 score of 0.93 while maintaining inference latency below 100 ms and a memory footprint under 60 KB. By prompting users to alternate 30–60 s of high-intensity exercise with rest periods, the device can structure effective interval routines. This work demonstrates how TinyML can enable low-cost, low-power wearables for personalized cardiovascular exercise monitoring. Full article

Background: Respiratory exercises play a key role in rehabilitation programs, especially for older adults and individuals with chronic pulmonary conditions. Despite growing interest in wearable sensors for home-based care, structured reference metrics to quantitatively characterize respiratory exercises are still limited. This study aimed to provide a quantitative characterization of respiratory exercises and evaluate the level of agreement between a low-cost prototypical sensor and a commercial one. Methods: Eleven older adults (9 females; age = 72.6 ± 5.0 years; height = 1.66 ± 0.09 m; mass = 68 ± 10 kg) performed a structured respiratory exercises protocol. Algorithms were developed to identify respiratory cycles, their execution time, and parameters related to respiratory capacity, using accelerometer signals from the two wearable sensors placed on the rib cage. Results: The average respiratory cycle duration ranged from 2.8 to 4.3 s, with normalized inspiratory and expiratory peaks. Tidal volume variability was minimal, confirming consistency in breathing patterns across exercises. User comfort was high (mean VAS = 8.7). Sensor comparison confirmed strong agreement between the two sensors in detecting respiratory cycles, though some variability was observed in timing and tidal volume estimation. Conclusions: These findings suggest that even simple accelerometers can reliably capture key respiratory parameters, supporting the feasibility of using wearable sensors to monitor structured respiratory exercises performed in home-based settings. Full article

Assistance dogs have shown promise in alerting to epileptic seizures in their owners, but current approaches often lack consistency, standardisation, and objective validation. This proof-of-concept study presents the development and initial validation of a wearable behaviour-alert detection collar developed for trained assistance dogs. It demonstrates the technical feasibility for automated detection of trained signalling behaviours. The collar integrates an inertial sensor and machine learning pipeline to detect a specific, trained alert behaviour of two rapid clockwise spins used by dogs to signal a seizure event. Data were collected from six trained dogs, resulting in 135 labelled spin alerts. Although the dataset size is limited compared to other machine learning applications, this reflects the real-world constraint that it is not practical for assistance dogs to perform excessive spin signalling during their training. Four supervised machine learning models (Random Forest, Logistic Regression, Naïve Bayes, and SVM) were evaluated on segmented accelerometer and gyroscope data. Random Forest achieved the highest performance (F1-score = 0.65; accuracy = 92%) under a Leave-One-DOG-Out (LODO) protocol. The system represents a novel step toward combining intentional canine behaviours with wearable technology, aligning with trends on the Internet of Medical Things. This proof-of-concept demonstrates technical feasibility and provides a foundation for future development of real-time seizure-alerting systems, representing an important first step toward scalable animal-assisted healthcare innovation. 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

Accidental opioid overdose and Sudden Unexpected Death in Epilepsy (SUDEP) represent major forms of preventable mortality, often involving sudden-onset catastrophic events that could be survivable with rapid detection and intervention. The current physiological monitoring technologies are potentially applicable, but face challenges, including complex setups, poor patient compliance, high costs, and uncertainty about community-based use. Paradoxically, simple clinical observation in supervised injection facilities has proven highly effective, suggesting observable changes in central body motion may be sufficient to detect life-threatening events. We describe a novel wearable biosensor for continuous central body motion monitoring, offering a potential early warning system for life-threatening events. The biosensor incorporates a low-power, triaxial MEMS accelerometer within a discreet, chest-worn device, enabling long-term monitoring with minimal user burden. Two system architectures are described: stored data for retrospective analysis/research, and an in-development system for real-time overdose detection and response. Early user research highlights the importance of accuracy, discretion, and trust for adoption among people who use opioids. The initial clinical data collection, including the OD-SEEN study, demonstrates feasibility for capturing motion data during real-world opioid use. This technology represents a promising advancement in non-invasive monitoring, with potential to improve the outcomes for at-risk populations with multiple health conditions. Full article

Over the years, researchers have developed several speed estimation techniques using wearable inertial measurement units (IMUs). In this paper, we introduce a medium-scale dataset, containing measurements of walking/running at speeds ranging from 4.0 km/h (1.11 m/s) to 9.5 km/h (2.64 m/s) in increments of 0.5 km/h (0.14 m/s) from 33 healthy subjects wearing IMUs. We name it the “Speed” dataset. In summary, we present accelerometer and gyroscope data from 12 speeds and 22 subject-independent sets with the full range of 12 speeds. The data in each set consists of overlapping sections of 250 time samples (corresponding to 2.5 s, sampled at 100 Hz), and six dimensions (corresponding to the three axes of the accelerometer and three axes of the gyroscope). Each speed set contains 1775 examples. We benchmark the existing approaches used in the literature for the purpose of speed estimation on this dataset. These include support vector regression, Gaussian Process Regression, and shallow neural networks. We then design a deep Convolutional Neural Network (CNN), SpeedNet, for baseline results. The proposed SpeedNet yields an average Root Mean Square Error (RMSE) of 0.4819 km/h (0.13 m/s), following a subject-independent approach. Then, the SpeedNet obtained from the subject-independent approach are adapted using a portion of subject-specific data. The average RMSE for the remainder of the data for all subjects then drops down to 0.1747 km/h (0.05 m/s). The suggested SpeedNet yields a lower RMSE in comparison to the other approaches. In addition, we also compare the proposed method to others in terms of the average testing time, to give an idea of computational complexity. The proposed SpeedNet, despite being more accurate, yields real-time performance. Full article