ABSTRACT
Maintaining the adhesion strength of flexible pressure-sensitive adhesives (PSAs) is crucial for advanced applications, such as health monitoring. Sustainable mounting is critical for wearable sensor devices, especially under challenging surroundings such as low and high temperatures (e.g., polar regions or deserts), underwater and sweat environments (physical activity), and cyclical shear complex stresses. In this article, we consider the adhesive, mechanical, and optical properties of medical-grade double-sided PSAs by simulating extreme human-centric environments. Diverse temperature conditions, water and humidity exposures, and cyclical loads were selected and tested over long intervals, up to 28 days. We observed that high temperatures increased the shear adhesion strength due to the pore closing and expanding contact area between the adhesive layer and substrate. Conversely, low temperatures caused the adhesive layers to harden and reduce the adhesive strength. Immersion in salty and weakly acidic water and excessive humidity reduced adhesion as water interfered with the interfacial interactions. PSA films showed either adhesive or cohesive failure under extreme mechanical stresses and cyclical loading, which is also affected by the presence of various polar solvents. We demonstrated that the variable adhesive performance, mechanical properties, and optical transparency of pressure-sensitive materials can be directly related to changes in their morphologies, surface roughness, swelling state, and alternation of the mechanical contact area, helping to establish the broader rules of design for wearable human health monitoring sensors for the long-term application of wearable devices, sensors, and electrodes.
ABSTRACT
Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose a Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE), to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress-detection methodologies in terms of precision, recall, and interpretability. The results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.
Subject(s)
Algorithms , Deep Learning , Stress, Psychological , Wearable Electronic Devices , Humans , Stress, Psychological/diagnosis , Stress, Psychological/physiopathology , Neural Networks, Computer , Adult , Male , FemaleABSTRACT
This article demonstrates the integration of sensor fusion for pose estimation and data collection in tennis balls, aiming to create a smaller, less intrusive form factor for use in progressive learning during tennis practice. The study outlines the design and implementation of the Bosch BNO055 smart sensor, which features built-in managed sensor fusion capabilities. The article also discusses deriving additional data using various mathematical and simulation methods to present relevant orientation information from the sensor in Unity. Embedded within a Vermont practice foam tennis ball, the final prototype product communicates with Unity on a laptop via Bluetooth. The Unity interface effectively visualizes the ball's rotation, the resultant acceleration direction, rotations per minute (RPM), and the orientation relative to gravity. The system successfully demonstrates accurate RPM measurement, provides real-time visualization of ball spin and offers a pathway for innovative applications in tennis training technology.
ABSTRACT
Lower extremity fractures pose challenges due to prolonged healing times and limited assessment methods. Integrating wearable sensors with machine learning can help overcome these challenges by providing objective assessment and predicting fracture healing. In this retrospective study, data from a gait monitoring insole on 25 patients with closed lower extremity fractures were analyzed. Continuous underfoot loading data were processed to isolate steps, extract metrics, and feed them into three white-box machine learning models. Decision tree and Lasso regression aided feature selection, while a logistic regression classifier predicted days until fracture healing within a 30-day range. Evaluations via 10-fold cross-validation and leave-one-out validation yielded stable metrics, with the model achieving a mean accuracy, precision, recall, and F1-score of approximately 76%. Feature selection revealed the importance of underfoot loading distribution patterns, particularly on the medial surface. Our research facilitates data-driven decisions, enabling early complication detection, potentially shortening recovery times, and offering accurate rehabilitation timeline predictions.
Subject(s)
Lower Extremity , Machine Learning , Wearable Electronic Devices , Humans , Male , Female , Middle Aged , Lower Extremity/physiopathology , Fracture Healing/physiology , Retrospective Studies , Adult , Aged , Fractures, Bone , Gait/physiologyABSTRACT
PURPOSE: The objective of this study is to train and test machine-learning (ML) models to automatically classify shoulder rehabilitation exercises. METHODS: The cohort included both healthy and patients with rotator-cuff (RC) tears. All participants performed six shoulder rehabilitation exercises, following guidelines developed by the American Society of Shoulder and Elbow Therapists. Each exercise was repeated six times, while wearing a wearable system equipped with three magneto-inertial sensors. Six supervised machine-learning models (k-Nearest Neighbours, Support Vector Machine, Decision Tree, Random Forest (RF), Logistic Regression and Adaptive Boosting) were trained for the classification. The algorithms' ability to accurately classify exercise activities was evaluated using the nested cross-validation method, with different combinations of outer and inner folds. RESULTS: A total of 19 healthy subjects and 17 patients with complete RC tears were enroled in the study. The highest classification performances were achieved by the RF classifier, with an accuracy of 89.91% and an F1-score of 89.89%. CONCLUSION: The results of this study highlight the feasibility and effectiveness of using wearable sensors and ML algorithms to accurately classify shoulder rehabilitation exercises. These findings suggest promising prospects for implementing the proposed wearable system in remote home-based monitoring scenarios. The ease of setup and modularity of the system reduce user burden enabling patient-driven sensor positioning. LEVEL OF EVIDENCE: Level III.
ABSTRACT
BACKGROUND: Wearable physiological monitoring devices are promising tools for remote monitoring and early detection of potential health changes of interest. The widespread adoption of such an approach across communities and over long periods of time will require an automated data platform for collecting, processing, and analyzing relevant health information. OBJECTIVE: In this study, we explore prospective monitoring of individual health through an automated data collection, metrics extraction, and health anomaly analysis pipeline in free-living conditions over a continuous monitoring period of several months with a focus on viral respiratory infections, such as influenza or COVID-19. METHODS: A total of 59 participants provided smartwatch data and health symptom and illness reports daily over an 8-month window. Physiological and activity data from photoplethysmography sensors, including high-resolution interbeat interval (IBI) and step counts, were uploaded directly from Garmin Fenix 6 smartwatches and processed automatically in the cloud using a stand-alone, open-source analytical engine. Health risk scores were computed based on a deviation in heart rate and heart rate variability metrics from each individual's activity-matched baseline values, and scores exceeding a predefined threshold were checked for corresponding symptoms or illness reports. Conversely, reports of viral respiratory illnesses in health survey responses were also checked for corresponding changes in health risk scores to qualitatively assess the risk score as an indicator of acute respiratory health anomalies. RESULTS: The median average percentage of sensor data provided per day indicating smartwatch wear compliance was 70%, and survey responses indicating health reporting compliance was 46%. A total of 29 elevated health risk scores were detected, of which 12 (41%) had concurrent survey data and indicated a health symptom or illness. A total of 21 influenza or COVID-19 illnesses were reported by study participants; 9 (43%) of these reports had concurrent smartwatch data, of which 6 (67%) had an increase in health risk score. CONCLUSIONS: We demonstrate a protocol for data collection, extraction of heart rate and heart rate variability metrics, and prospective analysis that is compatible with near real-time health assessment using wearable sensors for continuous monitoring. The modular platform for data collection and analysis allows for a choice of different wearable sensors and algorithms. Here, we demonstrate its implementation in the collection of high-fidelity IBI data from Garmin Fenix 6 smartwatches worn by individuals in free-living conditions, and the prospective, near real-time analysis of the data, culminating in the calculation of health risk scores. To our knowledge, this study demonstrates for the first time the feasibility of measuring high-resolution heart IBI and step count using smartwatches in near real time for respiratory illness detection over a long-term monitoring period in free-living conditions.
ABSTRACT
BACKGROUND: Despite deleterious biomechanics associated with injury, particularly as it pertains to load carriage, there is limited research on the association between physical demands and variables captured with wearable sensors. While inertial measurement units (IMUs) can be used as surrogate measures of ground reaction force (GRF) variables, it is unclear if these data are sensitive to military-specific task demands. RESEARCH QUESTION: Can wearable sensors characterise physical load and demands placed on individuals in different load, speed and grade conditions? METHODS: Data were collected on 20 individuals who were self-reportedly free from current injury, recreationally active, and capable of donning 23â¯kg in the form of a weighted vest. Each participant walked and ran on flat, uphill (+6â¯%) and downhill (-6â¯%) without and with load (23â¯kg). Data were collected synchronously from optical motion capture (OMC) and IMUs placed on the distal limb and the pelvis. Data from an 8-second window was used to generate a participant-based mean of OMC and IMU variables of interest. Repeated Measures ANOVA was used to measure main and interaction effects of load, speed, and grade. Simple linear regression was used to elucidate a relationship between OMC measures and estimated metabolic cost (EMC) to IMU measures. RESULTS: Load reduces foot and pelvic accelerations (p<0.001) but elevate signal attenuation per step (p=0.044). Conversely, attenuation per kilometre is lowered with the addition of load (p=0.017). Uphill had the lowest attenuation per step (p=0.003) and kilometre (p≤0.033) in walking, while downhill had the greatest attenuation per step (p≤0.002) and per kilometre (p≤0.004). Attenuation measures are inconsistently moderately related to limb negative work (R≤0.57). EMC is moderately positively related to unloaded running (R≥0.39), and moderately negatively related to walking with and without load (R≤-0.52). SIGNIFICANCE: While load reduces peak accelerations at both the pelvis and foot. However, it may increase demand on the lower extremity to attenuate the signal between the two sensors with each step, while attenuation over time reduces with load.
ABSTRACT
The purpose of this study was to test whether a machine learning model can accurately predict VO2 across different exercise intensities by combining muscle oxygen (MO2) with heart rate (HR). Twenty young highly trained athletes performed the following tests: a ramp incremental exercise, three submaximal constant intensity exercises, and three severe intensity exhaustive exercises. A Machine Learning model was trained to predict VO2, with model inputs including heart rate, MO2 in the left (LM) and right legs (RM). All models demonstrated equivalent results, with the accuracy of predicting VO2 at different exercise intensities varying among different models. The LM+RM+HR model performed the best across all intensities, with low bias in predicted VO2 for all intensity exercises (0.08 ml/kg/min, 95% limits of agreement: -5.64 to 5.81), and a very strong correlation (r = 0.94, p < 0.001) with measured VO2. Furthermore, the accuracy of predicting VO2 using LM+HR or RM+HR was higher than using LM+RM, and higher than the accuracy of predicting VO2 using LM, RM, or HR alone. This study demonstrates the potential of a machine learning model combining MO2 and HR to predict VO2 with minimal bias, achieving accurate predictions of VO2 for different intensity levels of exercise.
Subject(s)
Bicycling , Heart Rate , Machine Learning , Muscle, Skeletal , Oxygen Consumption , Humans , Oxygen Consumption/physiology , Male , Heart Rate/physiology , Young Adult , Muscle, Skeletal/metabolism , Muscle, Skeletal/physiology , Bicycling/physiology , Exercise Test/methods , Oxygen/metabolism , Adolescent , FemaleABSTRACT
BACKGROUND: Fall detection is of great significance in safeguarding human health. By monitoring the motion data, a fall detection system (FDS) can detect a fall accident. Recently, wearable sensors-based FDSs have become the mainstream of research, which can be categorized into threshold-based FDSs using experience, machine learning-based FDSs using manual feature extraction, and deep learning (DL)-based FDSs using automatic feature extraction. However, most FDSs focus on the global information of sensor data, neglecting the fact that different segments of the data contribute variably to fall detection. This shortcoming makes it challenging for FDSs to accurately distinguish between similar human motion patterns of actual falls and fall-like actions, leading to a decrease in detection accuracy. OBJECTIVE: This study aims to develop and validate a DL framework to accurately detect falls using acceleration and gyroscope data from wearable sensors. We aim to explore the essential contributing features extracted from sensor data to distinguish falls from activities of daily life. The significance of this study lies in reforming the FDS by designing a weighted feature representation using DL methods to effectively differentiate between fall events and fall-like activities. METHODS: Based on the 3-axis acceleration and gyroscope data, we proposed a new DL architecture, the dual-stream convolutional neural network self-attention (DSCS) model. Unlike previous studies, the used architecture can extract global feature information from acceleration and gyroscope data. Additionally, we incorporated a self-attention module to assign different weights to the original feature vector, enabling the model to learn the contribution effect of the sensor data and enhance classification accuracy. The proposed model was trained and tested on 2 public data sets: SisFall and MobiFall. In addition, 10 participants were recruited to carry out practical validation of the DSCS model. A total of 1700 trials were performed to test the generalization ability of the model. RESULTS: The fall detection accuracy of the DSCS model was 99.32% (recall=99.15%; precision=98.58%) and 99.65% (recall=100%; precision=98.39%) on the test sets of SisFall and MobiFall, respectively. In the ablation experiment, we compared the DSCS model with state-of-the-art machine learning and DL models. On the SisFall data set, the DSCS model achieved the second-best accuracy; on the MobiFall data set, the DSCS model achieved the best accuracy, recall, and precision. In practical validation, the accuracy of the DSCS model was 96.41% (recall=95.12%; specificity=97.55%). CONCLUSIONS: This study demonstrates that the DSCS model can significantly improve the accuracy of fall detection on 2 publicly available data sets and performs robustly in practical validation.
Subject(s)
Accidental Falls , Deep Learning , Accidental Falls/prevention & control , Humans , Wearable Electronic Devices , Neural Networks, Computer , MaleABSTRACT
Recent years have witnessed tremendous advances in machine learning techniques for wearable sensors and bioelectronics, which play an essential role in real-time sensing data analysis to provide clinical-grade information for personalized healthcare. To this end, supervised learning and unsupervised learning algorithms have emerged as powerful tools, allowing for the detection of complex patterns and relationships in large, high-dimensional data sets. In this Review, we aim to delineate the latest advancements in machine learning for wearable sensors, focusing on key developments in algorithmic techniques, applications, and the challenges intrinsic to this evolving landscape. Additionally, we highlight the potential of machine-learning approaches to enhance the accuracy, reliability, and interpretability of wearable sensor data and discuss the opportunities and limitations of this emerging field. Ultimately, our work aims to provide a roadmap for future research endeavors in this exciting and rapidly evolving area.
Subject(s)
Machine Learning , Wearable Electronic Devices , Humans , Biosensing Techniques/instrumentation , AlgorithmsABSTRACT
Gait analysis has proven to be a key process in the functional assessment of people involving many fields, such as diagnosis of diseases or rehabilitation, and has increased in relevance lately. Gait analysis often requires gathering data, although this can be very expensive and time consuming. One of the main solutions applied in fields when data acquisition is a problem is augmentation of datasets with artificial data. There are two main approaches for doing that: simulation and synthetic data generation. In this article, we propose a parametrizable generative system of synthetic walking simplified human skeletons. For achieving that, a data gathering experiment with up to 26 individuals was conducted. The system consists of two artificial neural networks: a recurrent neural network for the generation of the movement and a multilayer perceptron for determining the size of the segments of the skeletons. The system has been evaluated through four processes: (i) an observational appraisal by researchers in gait analysis, (ii) a visual representation of the distribution of the generated data, (iii) a numerical analysis using the normalized cross-correlation coefficient, and (iv) an angular evaluation to check the kinematic validity of the data. The evaluation concluded that the system is able to generate realistic and accurate gait data. These results reveal a promising path for this research field, which can be further improved through increasing the variety of movements and the user sample.
Subject(s)
Neural Networks, Computer , Humans , Gait/physiology , Models, Biological , Biomechanical Phenomena/physiology , Male , Walking/physiology , FemaleABSTRACT
Physical therapy is often essential for complete recovery after injury. However, a significant population of patients fail to adhere to prescribed exercise regimens. Lack of motivation and inconsistent in-person visits to physical therapy are major contributing factors to suboptimal exercise adherence, slowing the recovery process. With the advancement of virtual reality (VR), researchers have developed remote virtual rehabilitation systems with sensors such as inertial measurement units. A functional garment with an integrated wearable sensor can also be used for real-time sensory feedback in VR-based therapeutic exercise and offers affordable remote rehabilitation to patients. Sensors integrated into wearable garments offer the potential for a quantitative range of motion measurements during VR rehabilitation. In this research, we developed and validated a carbon nanocomposite-coated knit fabric-based sensor worn on a compression sleeve that can be integrated with upper-extremity virtual rehabilitation systems. The sensor was created by coating a commercially available weft knitted fabric consisting of polyester, nylon, and elastane fibers. A thin carbon nanotube composite coating applied to the fibers makes the fabric electrically conductive and functions as a piezoresistive sensor. The nanocomposite sensor, which is soft to the touch and breathable, demonstrated high sensitivity to stretching deformations, with an average gauge factor of ~35 in the warp direction of the fabric sensor. Multiple tests are performed with a Kinarm end point robot to validate the sensor for repeatable response with a change in elbow joint angle. A task was also created in a VR environment and replicated by the Kinarm. The wearable sensor can measure the change in elbow angle with more than 90% accuracy while performing these tasks, and the sensor shows a proportional resistance change with varying joint angles while performing different exercises. The potential use of wearable sensors in at-home virtual therapy/exercise was demonstrated using a Meta Quest 2 VR system with a virtual exercise program to show the potential for at-home measurements.
Subject(s)
Elbow Joint , Nanocomposites , Virtual Reality , Wearable Electronic Devices , Humans , Nanocomposites/chemistry , Elbow Joint/physiology , Robotics/instrumentation , Nanotubes, Carbon/chemistry , Biosensing Techniques/instrumentation , Biosensing Techniques/methods , Range of Motion, Articular/physiology , Carbon/chemistryABSTRACT
Quantitative mobility analysis using wearable sensors, while promising as a diagnostic tool for Parkinson's disease (PD), is not commonly applied in clinical settings. Major obstacles include uncertainty regarding the best protocol for instrumented mobility testing and subsequent data processing, as well as the added workload and complexity of this multi-step process. To simplify sensor-based mobility testing in diagnosing PD, we analyzed data from 262 PD participants and 50 controls performing several motor tasks wearing a sensor on their lower back containing a triaxial accelerometer and a triaxial gyroscope. Using ensembles of heterogeneous machine learning models incorporating a range of classifiers trained on a set of sensor features, we show that our models effectively differentiate between participants with PD and controls, both for mixed-stage PD (92.6% accuracy) and a group selected for mild PD only (89.4% accuracy). Omitting algorithmic segmentation of complex mobility tasks decreased the diagnostic accuracy of our models, as did the inclusion of kinesiological features. Feature importance analysis revealed that Timed Up and Go (TUG) tasks to contribute the highest-yield predictive features, with only minor decreases in accuracy for models based on cognitive TUG as a single mobility task. Our machine learning approach facilitates major simplification of instrumented mobility testing without compromising predictive performance.
Subject(s)
Accelerometry , Machine Learning , Parkinson Disease , Wearable Electronic Devices , Humans , Parkinson Disease/diagnosis , Parkinson Disease/physiopathology , Male , Female , Aged , Middle Aged , Accelerometry/instrumentation , Accelerometry/methods , AlgorithmsABSTRACT
Sleep quality (SQ) is a crucial aspect of overall health. Poor sleep quality may cause cognitive impairment, mood disturbances, and an increased risk of chronic diseases. Therefore, assessing sleep quality helps identify individuals at risk and develop effective interventions. SQ has been demonstrated to affect heart rate variability (HRV) and skin temperature even during wakefulness. In this perspective, using wearables and contactless technologies to continuously monitor HR and skin temperature is highly suited for assessing objective SQ. However, studies modeling the relationship linking HRV and skin temperature metrics evaluated during wakefulness to predict SQ are lacking. This study aims to develop machine learning models based on HRV and skin temperature that estimate SQ as assessed by the Pittsburgh Sleep Quality Index (PSQI). HRV was measured with a wearable sensor, and facial skin temperature was measured by infrared thermal imaging. Classification models based on unimodal and multimodal HRV and skin temperature were developed. A Support Vector Machine applied to multimodal HRV and skin temperature delivered the best classification accuracy, 83.4%. This study can pave the way for the employment of wearable and contactless technologies to monitor SQ for ergonomic applications. The proposed method significantly advances the field by achieving a higher classification accuracy than existing state-of-the-art methods. Our multimodal approach leverages the synergistic effects of HRV and skin temperature metrics, thus providing a more comprehensive assessment of SQ. Quantitative performance indicators, such as the 83.4% classification accuracy, underscore the robustness and potential of our method in accurately predicting sleep quality using non-intrusive measurements taken during wakefulness.
ABSTRACT
STUDY OBJECTIVES: Discerning the differential contribution of sleep behavior and sleep physiology to the subsequent development of posttraumatic-stress-disorder (PTSD) symptoms following military operational service among combat soldiers. METHODS: Longitudinal design with three measurement time points: during basic training week (T1), during intensive stressed training week (T2), and following military operational service (T3). Participating soldiers were all from the same unit, ensuring equivalent training schedules and stress exposures. During measurement weeks soldiers completed the Depression Anxiety and Stress Scale (DASS) and the PTSD Checklist for DSM-5 (PCL-5). Sleep physiology (sleep heart-rate) and sleep behavior (duration, efficiency) were monitored continuously in natural settings during T1 and T2 weeks using wearable sensors. RESULTS: Repeated measures ANOVA revealed a progressive increase in PCL-5 scores from T1 and T2 to T3, suggesting an escalation in PTSD symptom severity following operational service. Hierarchical linear regression analysis uncovered a significant relation between the change in DASS stress scores from T1 to T2 and subsequent PCL-5 scores at T3. Incorporating participants' sleep heart-rate markedly enhanced the predictive accuracy of the model, with increased sleep heart-rate from T1 to T2 emerging as a significant predictor of elevated PTSD symptoms at T3, above and beyond the contribution of DASS stress scores. Sleep behavior did not add to the accuracy of the model. CONCLUSION: Findings underscore the critical role of sleep physiology, specifically elevated sleep heart-rate following stressful military training, in indicating subsequent PTSD risk following operational service among combat soldiers. These findings may contribute to PTSD prediction and prevention efforts.
ABSTRACT
Triboelectric nanogenerators (TENG) are promising alternatives for clean energy harvesting. However, the material utilization in the development of TENG relies majorly on polymers derived from non-renewable resources. Therefore, minimizing the carbon footprint associated with such TENG development demands a shift toward usage of sustainable materials. This study pioneers using natural rubber (NR) as a sustainable alternative in TENG development. Infusing graphene in NR, its dielectric constant and tribonegativity are optimized, yielding a remarkable enhancement. The optimized sample exhibits a dielectric constant of 411 (at 103 Hz) and a contact potential difference (CPD) value of 1.85 V. In contrast, the pristine NR sample showed values of 6 and 3.06 V for the dielectric constant and CPD. Simulation and experimental studies fine-tune the TENG's performance, demonstrating excellent agreement between theoretical predictions and practical studies. Sensors developed via stencil printing technique possess a remarkably low layer thickness of 270 µm, and boast a power density of 420 mW m-2, a staggering 250% increase over conventional NR. Moreover, the material is pressure sensitive, enabling precise real-time human motion detection, including finger contact, finger bending, neck bending, and arm bending. This versatile sensor offers wireless monitoring, empowering healthcare monitoring based on the Internet of Things.
ABSTRACT
The development of wearable electronic devices for human health monitoring requires materials with high mechanical performance and sensitivity. In this study, we present a novel transparent tissue-like ionogel-based wearable sensor based on silver nanowire-reinforced ionogel nanocomposites, P(AAm-co-AA) ionogel-Ag NWs composite. The composite exhibits a high stretchability of 605% strain and a moderate fracture stress of about 377 kPa. The sensor also demonstrates a sensitive response to temperature changes and electrostatic adsorption. By encapsulating the nanocomposite in a polyurethane transparent film dressing, we address issues such as skin irritation and enable multidirectional stretching. Measuring resistive changes of the ionogel nanocomposite in response to corresponding strain changes enables its utility as a highly stretchable wearable sensor with excellent performance in sensitivity, stability, and repeatability. The fabricated pressure sensor array exhibits great proficiency in stress distribution, capacitance sensing, and discernment of fluctuations in both external electric fields and stress. Our findings suggest that this material holds promise for applications in wearable and flexible strain sensors, temperature sensors, pressure sensors, and actuators.
ABSTRACT
In the context in which severe visual impairment significantly affects human life, this article emphasizes the potential of Artificial Intelligence (AI) and Visible Light Communications (VLC) in developing future assistive technologies. Toward this path, the article summarizes the features of some commercial assistance solutions, and debates the characteristics of VLC and AI, emphasizing their compatibility with blind individuals' needs. Additionally, this work highlights the AI potential in the efficient early detection of eye diseases. This article also reviews the existing work oriented toward VLC integration in blind persons' assistive applications, showing the existing progress and emphasizing the high potential associated with VLC use. In the end, this work provides a roadmap toward the development of an integrated AI-based VLC assistance solution for visually impaired people, pointing out the high potential and some of the steps to follow. As far as we know, this is the first comprehensive work which focuses on the integration of AI and VLC technologies in visually impaired persons' assistance domain.
Subject(s)
Artificial Intelligence , Self-Help Devices , Visually Impaired Persons , Humans , Visually Impaired Persons/rehabilitation , Light , Lighting , Surveys and QuestionnairesABSTRACT
The proliferation of wearable technology enables the generation of vast amounts of sensor data, offering significant opportunities for advancements in health monitoring, activity recognition, and personalized medicine. However, the complexity and volume of these data present substantial challenges in data modeling and analysis, which have been addressed with approaches spanning time series modeling to deep learning techniques. The latest frontier in this domain is the adoption of large language models (LLMs), such as GPT-4 and Llama, for data analysis, modeling, understanding, and human behavior monitoring through the lens of wearable sensor data. This survey explores the current trends and challenges in applying LLMs for sensor-based human activity recognition and behavior modeling. We discuss the nature of wearable sensor data, the capabilities and limitations of LLMs in modeling them, and their integration with traditional machine learning techniques. We also identify key challenges, including data quality, computational requirements, interpretability, and privacy concerns. By examining case studies and successful applications, we highlight the potential of LLMs in enhancing the analysis and interpretation of wearable sensor data. Finally, we propose future directions for research, emphasizing the need for improved preprocessing techniques, more efficient and scalable models, and interdisciplinary collaboration. This survey aims to provide a comprehensive overview of the intersection between wearable sensor data and LLMs, offering insights into the current state and future prospects of this emerging field.