Activity-Aware Wearable System for Power-Efficient Prediction of Physiological Responses

Human Activity Recognition in a Free-Living Environment Using an Ear-Worn Motion Sensor

Human activity recognition (HAR) technology enables continuous behavior monitoring, which is particularly valuable in healthcare. This study investigates the viability of using an ear-worn motion sensor for classifying daily activities, including lying, sitting/standing, walking, ascending stairs, descending stairs, and running. Fifty healthy participants (between 20 and 47 years old) engaged in these activities while under monitoring. Various machine learning algorithms, ranging from interpretable shallow models to state-of-the-art deep learning approaches designed for HAR (i.e., DeepConvLSTM and ConvTransformer), were employed for classification. The results demonstrate the ear sensor's efficacy, with deep learning models achieving a 98% accuracy rate of classification. The obtained classification models are agnostic regarding which ear the sensor is worn and robust against moderate variations in sensor orientation (e.g., due to differences in auricle anatomy), meaning no initial calibration of the sensor orientation is required. The study underscores the ear's efficacy as a suitable site for monitoring human daily activity and suggests its potential for combining HAR with in-ear vital sign monitoring. This approach offers a practical method for comprehensive health monitoring by integrating sensors in a single anatomical location. This integration facilitates individualized health assessments, with potential applications in tele-monitoring, personalized health insights, and optimizing athletic training regimes.

Wireless Battery-free and Fully Implantable Organ Interfaces

Advances in soft materials, miniaturized electronics, sensors, stimulators, radios, and battery-free power supplies are resulting in a new generation of fully implantable organ interfaces that leverage volumetric reduction and soft mechanics by eliminating electrochemical power storage. This device class offers the ability to provide high-fidelity readouts of physiological processes, enables stimulation, and allows control over organs to realize new therapeutic and diagnostic paradigms. Driven by seamless integration with connected infrastructure, these devices enable personalized digital medicine. Key to advances are carefully designed material, electrophysical, electrochemical, and electromagnetic systems that form implantables with mechanical properties closely matched to the target organ to deliver functionality that supports high-fidelity sensors and stimulators. The elimination of electrochemical power supplies enables control over device operation, anywhere from acute, to lifetimes matching the target subject with physical dimensions that supports imperceptible operation. This review provides a comprehensive overview of the basic building blocks of battery-free organ interfaces and related topics such as implantation, delivery, sterilization, and user acceptance. State of the art examples categorized by organ system and an outlook of interconnection and advanced strategies for computation leveraging the consistent power influx to elevate functionality of this device class over current battery-powered strategies is highlighted.

Wearable devices for continuous monitoring of biosignals: Challenges and opportunities

The ability for wearable devices to collect high-fidelity biosignals continuously over weeks and months at a time has become an increasingly sought-after characteristic to provide advanced diagnostic and therapeutic capabilities. Wearable devices for this purpose face a multitude of challenges such as formfactors with long-term user acceptance and power supplies that enable continuous operation without requiring extensive user interaction. This review summarizes design considerations associated with these attributes and summarizes recent advances toward continuous operation with high-fidelity biosignal recording abilities. The review also provides insight into systematic barriers for these device archetypes and outlines most promising technological approaches to expand capabilities. We conclude with a summary of current developments of hardware and approaches for embedded artificial intelligence in this wearable device class, which is pivotal for next generation autonomous diagnostic, therapeutic, and assistive health tools.

Towards Human Stress and Activity Recognition: A Review and a First Approach Based on Low-Cost Wearables

Detecting stress when performing physical activities is an interesting field that has received relatively little research interest to date. In this paper, we took a first step towards redressing this, through a comprehensive review and the design of a low-cost body area network (BAN) made of a set of wearables that allow physiological signals and human movements to be captured simultaneously. We used four different wearables: OpenBCI and three other open-hardware custom-made designs that communicate via bluetooth low energy (BLE) to an external computer—following the edge-computingconcept—hosting applications for data synchronization and storage. We obtained a large number of physiological signals (electroencephalography (EEG), electrocardiography (ECG), breathing rate (BR), electrodermal activity (EDA), and skin temperature (ST)) with which we analyzed internal states in general, but with a focus on stress. The findings show the reliability and feasibility of the proposed body area network (BAN) according to battery lifetime (greater than 15 h), packet loss rate (0% for our custom-made designs), and signal quality (signal-noise ratio (SNR) of 9.8 dB for the ECG circuit, and 61.6 dB for the EDA). Moreover, we conducted a preliminary experiment to gauge the main ECG features for stress detection during rest.

An Optimization Approach to Multi-Sensor Operation for Multi-Context Recognition

Mobile devices and sensors have limited battery lifespans, limiting their feasibility for context recognition applications. As a result, there is a need to provide mechanisms for energy-efficient operation of sensors in settings where multiple contexts are monitored simultaneously. Past methods for efficient sensing operation have been hierarchical by first selecting the sensors with the least energy consumption, and then devising individual sensing schedules that trade-off energy and delays. The main limitation of the hierarchical approach is that it does not consider the combined impact of sensor scheduling and sensor selection. We aimed at addressing this limitation by considering the problem holistically and devising an optimization formulation that can simultaneously select the group of sensors while also considering the impact of their triggering schedule. The optimization solution is framed as a Viterbi algorithm that includes mathematical representations for multi-sensor reward functions and modeling of user behavior. Experiment results showed an average improvement of 31% compared to a hierarchical approach.

Energy-efficient IoT based improved health monitoring system for sports persons

Nowadays, wearable technology and the Internet of Things (IoT) are transforming the healthcare sector by refining the way how devices, applications, and people connect and interact with each other. IoT applications in sports are tremendously useful to monitor health and reduce the risk factor. The battery life of wearable and accurate monitoring has been considered a significant challenge in sports medicine. Hence, in this paper, Energy Efficient IoT based Improved Health Monitoring system (EEIoT-IHMS) has been proposed for accurate and continuous sports person’s health monitoring system. This paper determines the optimal set of clusters based on sensor features, in which power usage has been minimized by duty cycling with optimized prediction accuracy. The experimental results demonstrate that the proposed (EEIoT-IHMS) enhances accuracy ratio, improves battery life, and reduces energy consumption compared to other popular methods.

Integrated non-invasive biochemical and biophysical sensing systems for health and performance monitoring: A systems perspective

Advances in materials, bio-recognition elements, transducers, and microfabrication techniques, as well as progress in electronics, signal processing, and wireless communication have generated a new class of skin-interfaced wearable health monitoring systems for applications in personalized medicine and digital health. In comparison to conventional medical devices, these wearable systems are at the cusp of initiating a new era of longitudinal and noninvasive sensing for the prevention, detection, diagnosis, and treatment of diseases at the molecular level. Herein, we provide a review of recent developments in wearable biochemical and biophysical systems. We survey the sweat sampling and collection methods for biochemical systems, followed by an assessment of biochemical and biophysical sensors deployed in current wearable systems with an emphasis on their hardware specifications. Specifically, we address how sweat collection and sample handling platforms may be a rate limiting technology to realizing the clinical translation of wearable health monitoring systems; moreover, we highlight the importance of achieving both longitudinal sensing and assessment of intrapersonal variation in sweat-blood correlations to have the greatest clinical impact. Lastly, we assess a snapshot of integrated wireless wearable systems with multimodal sensing capabilities, and we conclude with our perspective on the state-of-the-art and the required developments to achieve the next-generation of integrated wearable health and performance monitoring systems.

Deep Support Vector Machines for the Identification of Stress Condition from Electrodermal Activity

Early detection of stress condition is beneficial to prevent long-term mental illness like depression and anxiety. This paper introduces an accurate identification of stress/calm condition from electrodermal activity (EDA) signals. The acquisition of EDA signals from a commercial wearable as well as their storage and processing are presented. Several time-domain, frequency-domain and morphological features are extracted over the skin conductance response of the EDA signals. Afterwards, a classification is undergone by using several classical support vector machines (SVMs) and deep support vector machines (D-SVMs). In addition, several binary classifiers are also compared with SVMs in the stress/calm identification task. Moreover, a series of video clips evoking calm and stress conditions have been viewed by 147 volunteers in order to validate the classification results. The highest F1-score obtained for SVMs and D-SVMs are 83% and 92%, respectively. These results demonstrate that not only classical SVMs are appropriate for classification of biomarker signals, but D-SVMs are very competitive in comparison to other classification techniques. In addition, the results have enabled drawing useful considerations for the future use of SVMs and D-SVMs in the specific case of stress/calm identification.

A Pipeline for Adaptive Filtering and Transformation of Noisy Left-Arm ECG to Its Surrogate Chest Signal

The performance of a low-power single-lead armband in generating electrocardiogram (ECG) signals from the chest and left arm was validated against a BIOPAC MP160 benchtop system in real-time. The filtering performance of three adaptive filtering algorithms, namely least mean squares (LMS), recursive least squares (RLS), and extended kernel RLS (EKRLS) in removing white (W), power line interference (PLI), electrode movement (EM), muscle artifact (MA), and baseline wandering (BLW) noises from the chest and left-arm ECG was evaluated with respect to the mean squared error (MSE). Filter parameters of the used algorithms were adjusted to ensure optimal filtering performance. LMS was found to be the most effective adaptive filtering algorithm in removing all noises with minimum MSE. However, for removing PLI with a maximal signal-to-noise ratio (SNR), RLS showed lower MSE values than LMS when the step size was set to 1 × 10−5. We proposed a transformation framework to convert the denoised left-arm and chest ECG signals to their low-MSE and high-SNR surrogate chest signals. With wide applications in wearable technologies, the proposed pipeline was found to be capable of establishing a baseline for comparing left-arm signals with original chest signals, getting one step closer to making use of the left-arm ECG in clinical cardiac evaluations.

Feasibility of a Wearable Reflectometric System for Sensing Skin Hydration

One of the major goals of Health 4.0 is to offer personalized care to patients, also through real-time, remote monitoring of their biomedical parameters. In this regard, wearable monitoring systems are crucial to deliver continuous appropriate care. For some biomedical parameters, there are a number of well established systems that offer adequate solutions for real-time, continuous patient monitoring. On the other hand, monitoring skin hydration still remains a challenging task. The continuous monitoring of this physiological parameter is extremely important in several contexts, for example for athletes, sick people, workers in hostile environments or for the elderly. State-of-the-art systems, however, exhibit some limitations, especially related with the possibility of continuous, real-time monitoring. Starting from these considerations, in this work, the feasibility of an innovative time-domain reflectometry (TDR)-based wearable, skin hydration sensing system for real-time, continuous monitoring of skin hydration level was investigated. The applicability of the proposed system was demonstrated, first, through experimental tests on reference substances, then, directly on human skin. The obtained results demonstrate the TDR technique and the proposed system holds unexplored potential for the aforementioned purposes.