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.

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.

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.

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.

Instrumenting the six-minute walk test (6MWT) adds information about gait quality and insight into fall risk. Being physically active and preserving multi-directional stepping abilities are also important for fall risk reduction. This analysis investigated the relationship of gait quality during the 6MWT with physical functioning and physical activity. Twenty-one veterans (62.2 ± 6.4 years) completed the four square step test (FSST) multi-directional stepping assessment, a gait speed assessment, health questionnaires, and the accelerometer-instrumented 6MWT. An activity monitor worn at home captured free-living physical activity. Gait measures were not significantly different between minutes of the 6MWT. However, participants with greater increases in stride time (ρ = -0.594, p < 0.01) and stance time (ρ = -0.679, p < 0.01) during the 6MWT reported lower physical functioning. Neither physical activity nor sedentary time were related to 6MWT gait quality. Participants exploring a larger range in stride time variability (ρ = 0.614, p < 0.01) and stance time variability (ρ = 0.498, p < 0.05) during the 6MWT required more time to complete the FSST. Participants needing at least 15 s to complete the FSST meaningfully differed from those completing the FSST more quickly on all gait measures studied. Instrumenting the 6MWT helps detect ranges of gait performance and provides insight into functional limitations missed with uninstrumented administration. Established FSST cut points identify aging adults with poorer gait quality.

Non-invasive monitoring of pulmonary health may be useful for tracking several conditions such as COVID-19 recovery and the progression of pulmonary edema. Some proposed methods use impedance-based technologies to non-invasively measure the thorax impedance as a function of respiration but face challenges that limit the feasibility, accuracy, and practicality of tracking daily changes. In our prior work, we demonstrated a novel approach to monitor respiration by measuring changes in impedance from the back of the thigh. We reported the concept of using thigh-thigh bioimpedance measurements for measuring the respiration rate and demonstrated a linear relationship between the thigh-thigh bioimpedance and lung tidal volume. Here, we investigate the variability in thigh-thigh impedance measurements to further understand the feasibility of the technique for detecting a change in the respiratory status due to disease onset or recovery if used for long-term in-home monitoring. Multiple within-session and day-to-day impedance measurements were collected at 80 kHz using dry electrodes (thigh) and wet electrodes (thorax) across the five healthy subjects, along with simultaneous gold standard spirometer measurements for three consecutive days. The peak-peak bioimpedance measurements were found to be highly correlated (0.94 ± 0.03 for dry electrodes across thigh; 0.92 ± 0.07 for wet electrodes across thorax) with the peak-peak spirometer tidal volume. The data across five subjects indicate that the day-to-day variability in the relationship between impedance and volume for thigh-thigh measurements is smaller (average of 14%) than for the thorax (40%). However, it is affected by food and water and might limit the accuracy of the respiratory tidal volume.

Wearable sensors for psychophysiological monitoring are becoming increasingly mainstream in safety critical contexts. They offer a novel solution to capturing sub-optimal states and can help identify when workers in safety critical environments are suffering from states such as fatigue and stress. However, sensors can differ widely in their application, design, usability, and measurement and there is a lack of guidance on what should be prioritized or considered when selecting a sensor. The paper aims to highlight which concepts are important when creating or selecting a device regarding the optimization of both measurement and usability. Additionally, the paper discusses how design choices can enhance both the usability and measurement capabilities of wearable sensors. The hopes are that this paper will provide researchers and practitioners in human factors and related fields with a framework to help guide them in building and selecting wearable sensors that are well suited for deployment in safety critical contexts.

The characterization of human behavior in real-world contexts is critical for developing a comprehensive model of human health. Recent technological advancements have enabled wearables and sensors to passively and unobtrusively record and presumably quantify human behavior. Better understanding human activities in unobtrusive and passive ways is an indispensable tool in understanding the relationship between behavioral determinants of health and diseases. Adult individuals (N = 60) emulated the behaviors of smoking, exercising, eating, and medication (pill) taking in a laboratory setting while equipped with smartwatches that captured accelerometer data. The collected data underwent expert annotation and was used to train a deep neural network integrating convolutional and long short-term memory architectures to effectively segment time series into discrete activities. An average macro-F1 score of at least 85.1 resulted from a rigorous leave-one-subject-out cross-validation procedure conducted across participants. The score indicates the method\'s high performance and potential for real-world applications, such as identifying health behaviors and informing strategies to influence health. Collectively, we demonstrated the potential of AI and its contributing role to healthcare during the early phases of diagnosis, prognosis, and/or intervention. From predictive analytics to personalized treatment plans, AI has the potential to assist healthcare professionals in making informed decisions, leading to more efficient and tailored patient care.

BACKGROUND: While low back pain (LBP) is the leading cause of disability worldwide, its clinical objective assessment is currently limited. Part of this syndrome arises from the abnormal sensorimotor control of back muscles, involving increased muscle fatigability (i.e., assessed with the Biering-Sorensen test) and abnormal muscle activation patterns (i.e., the flexion-extension test). Surface electromyography (sEMG) provides objective measures of muscle fatigue development (median frequency drop, MDF) and activation patterns (RMS amplitude change). This study therefore assessed the sensitivity and validity of a novel and flexible sEMG system (NSS) based on PEVA electrodes and potentially embeddable in textiles, as a tool for objective clinical LBP assessment.
METHODS: Twelve participants wearing NSS and a commercial laboratory sEMG system (CSS) performed two clinical tests used in LBP assessment (Biering-Sorensen and flexion-extension). Erector spinae muscle activity was recorded at T12-L1 and L4-L5.
RESULTS: NSS showed sensitivity to sEMG changes associated with fatigue development and muscle activations during flexion-extension movements (p < 0.05) that were similar to CSS (p > 0.05). Raw signals showed moderate cross-correlations (MDF: 0.60-0.68; RMS: 0.53-0.62). Adding conductive gel to the PEVA electrodes did not influence sEMG signal interpretation (p > 0.05).
CONCLUSIONS: This novel sEMG system is promising for assessing electrophysiological indicators of LBP during clinical tests.

暂无摘要。