The severity of mobility deficits is one of the most critical parameters in the diagnosis and rehabilitation of Parkinson's disease (PD). The current approach for severity evaluation is clinical ...scaling that relies on a clinician's subjective observations and experience, and the observation in laboratories or clinics may not suffice to reflect the severity of motion deficits as compared to daily living activities. The paper presents an approach to modeling and quantifying the severity of mobility deficits from motion data by using nonintrusive wearable physio-biological sensors. The approach provides a user-specific metric that measures mobility deficits in terms of the quantities of motion primitives that are learned from motion tracking data. The proposed method achieved 99.84% prediction accuracy on laboratory data and 93.95% prediction accuracy on clinical data. This approach presents the potential to supplant traditional observation-based clinical scaling, providing an avenue for real-time feedback to fortify positive progression throughout the course of rehabilitation.
Display omitted
•Hydrogel possessed prominent mechanics, conductivity and freezing tolerance.•Multi-model hydrogel sensor can detect large-scale pressure and various defromation.•Hydrogel sensor ...exhibited superior sensitivity, cycling stability and durability.•The gel/aluminum sensor maintained superior sensing performance at low temperature.
Hydrogel sensors are peculiarly attractive in flexible wearable electronics due to the stretchability and strain-responsive ability. However, flexible sensors (e.g. electronic skin) in practice require to perceive both strain and pressure concurrently and repeatedly, which put forward an imperative demand for multi-model and durable hydrogel sensors. Additionally, freezing intolerance is also an urgent problem to be addressed for low-temperature applications of hydrogel sensors. Herein, we constructed a wearable multi-model hydrogel sensor featuring with sensitive and large-range strain and pressure detection capacity, together with long-term stability and wide operating temperature range, based on a resilient, anti-fatigue and freezing-tolerant chitosan-poly(hydroxyethyl acrylamide) double-network (CS-PHEAA DN) hydrogel, which was fabricated via post-crosslinking CS-PHEAA composite hydrogel into Na3Cit solution. The ions simultaneously furnished the hydrogel with superior mechanics (stretchability, supercompressibility, excellent resilience and remarkable fatigue resistance), prominent ionic conductivity and low temperature tolerance. Impressively, the assembled hydrogel sensor exhibited preeminent sensitivity and cycling stability on detecting multi-type and large-range deformation (elongation, compression and bend), pressure and various human motions even at low temperatures. Remarkably, the fabricated hydrogel/aluminum hybrid combination serving as a flexible sensor maintained mechanical advantages, sensitive sensing capacity and good durability within a wide temperature range. This work provides a feasible method to construct anti-freezing, durable and multi-mode hydrogel sensors with high sensitivity and large-range detection capacity and paves a way for versatile applications in electronic skin, human-motion detection and intelligence device.
The growing recent interest in wearable and mobile technologies has led to increased research efforts toward development of non-invasive glucose monitoring platforms. Continuous glucose monitoring ...addresses the limitations of finger-stick blood testing and provides the opportunity for optimal therapeutic interventions. This article reviews recent advances and challenges toward the development of non-invasive epidermal electrochemical glucose sensing systems. Recent reports claim success in glucose monitoring in human subjects using skin-worn electrochemical sensors. Such epidermal electrochemical biosensors obviate the disadvantages of minimally-invasive subcutaneous glucose biosensors and offer promise for improved glycemic control. The ability of such systems to monitor glucose non-invasively offers an attractive route toward advancing the management of diabetes and achieving improved glycemic control. However, realizing the potential diagnostic impact of these new epidermal sensing strategies would require extensive efforts toward addressing key technological challenges and establishing a reliable correlation to gold standard blood glucose meters.
Display omitted
•This paper reviews recent advances and challenges toward the development of non-invasive epidermal glucose sensing systems.•Non-invasive detection of glucose in sweat and interstitial fluid using wearable and flexible skin-worn sensors.•The wearable epidermal glucose sensors offer promise for advanced management of diabetes with improved glycemic control.
The effectiveness of knee rehabilitation systems in aiding patients with rehabilitation training has been well-documented. Presently, there is an increasing emphasis on the wearing comfort and user ...engagement of these systems. In this paper, a wearable knee rehabilitation system (WKRS) based on the graphene textile composite sensor (GTCS), which subjects perform rehabilitation training by controlling the ascent and descent of a bird in the visual feedback game utilized GTCS, is proposed and investigated. To obtain an accurate and smooth estimated knee joint angle, we propose an improved tree boosting regression algorithm based on extreme gradient boosting (XGBoost), called improved XGBoost (IXGB). Specifically, the estimated results are smoothed by two steps: curving the preliminary estimating results within the same interval and smoothing the preliminary estimating results using the weighted moving average method. An online experiment with ten subjects validates the effectiveness of the WKRS and IXGB. Results indicate that the IXGB significantly enhances the smoothness of estimated value while maintaining estimation accuracy compared to XGBoost, random forest regression (RFR) and support vector regression (SVR). IXGB achieves an average increase of 33.43 % in root mean square error, 23.83 % in R-squared, and a 62.63% decrease in smoothness.
Traditional methods of human activity recognition usually require a large amount of strictly labeled data for training classifiers. However, it is hard for one to keep a fixed activity when ...collecting desired activity data by wearable sensors, and the weakly labeled data inevitably occurs in the process of data collection. For now, human activity recognition methods have seldom been researched according to weakly labeled data, which deserves deep investigation. In this paper, we proposed a novel attention-based human activity recognition method to process the weakly labeled activity data. The traditional convolutional neural network (CNN)-based human activity recognition is modified by attention mechanism, which computes the compatibility between the global features extracted at the final fully connected layers and the local features extracted at a given convolutional layer. The attention-based CNN architecture can amplify the salient activity information and suppress the irrelevant and potentially confusing information by weighing up their compatibility. Our methods are compared with two state-of-the-art methods, CNN and DeepConvLSTM. The experimental results show that our model is comparably well on the traditional UCI HAR dataset and outperforms them on the weakly labeled dataset in accuracy. Our method can greatly facilitate the process of sensor data annotation and makes data collection easier.
Existing vision-based action recognition is susceptible to occlusion and appearance variations, while wearable sensors can alleviate these challenges by capturing human motion with one-dimensional ...time-series signals (e.g. acceleration, gyroscope, and orientation). For the same action, the knowledge learned from vision sensors (videos or images) and wearable sensors, may be related and complementary. However, there exists a significantly large modality difference between action data captured by wearable-sensor and vision-sensor in data dimension, data distribution, and inherent information content. In this paper, we propose a novel framework, named Semantics-aware Adaptive Knowledge Distillation Networks (SAKDN), to enhance action recognition in vision-sensor modality (videos) by adaptively transferring and distilling the knowledge from multiple wearable sensors. The SAKDN uses multiple wearable-sensors as teacher modalities and uses RGB videos as student modalities. To preserve the local temporal relationship and facilitate employing visual deep learning models, we transform one-dimensional time-series signals of wearable sensors to two-dimensional images by designing a gramian angular field based virtual image generation model. Then, we introduce a novel Similarity-Preserving Adaptive Multi-modal Fusion Module (SPAMFM) to adaptively fuse intermediate representation knowledge from different teacher networks. Finally, to fully exploit and transfer the knowledge of multiple well-trained teacher networks to the student network, we propose a novel Graph-guided Semantically Discriminative Mapping (GSDM) module, which utilizes graph-guided ablation analysis to produce a good visual explanation to highlight the important regions across modalities and concurrently preserve the interrelations of original data. Experimental results on Berkeley-MHAD, UTD-MHAD, and MMAct datasets well demonstrate the effectiveness of our proposed SAKDN for adaptive knowledge transfer from wearable-sensors modalities to vision-sensors modalities. The code is publicly available at https://github.com/YangLiu9208/SAKDN .
The essential human gait parameters are briefly reviewed, followed by a detailed review of the state of the art in deep learning for the human gait analysis. The modalities for capturing the gait ...data are grouped according to the sensing technology: video sequences, wearable sensors, and floor sensors, as well as the publicly available datasets. The established artificial neural network architectures for deep learning are reviewed for each group, and their performance are compared with particular emphasis on the spatiotemporal character of gait data and the motivation for multi-sensor, multi-modality fusion. It is shown that by most of the essential metrics, deep learning convolutional neural networks typically outperform shallow learning models. In the light of the discussed character of gait data, this is attributed to the possibility to extract the gait features automatically in deep learning as opposed to the shallow learning from the handcrafted gait features.
Food safety affects everyone worldwide and will remain a global challenge to human health in the foreseeable future requiring the rapid, sensitive, efficient and inexpensive detection of food ...contaminants. Biosensors have long been investigated to be part of a solution. In fact, current research trends of nanoscale science and technology, efforts of miniaturization and connectivity enabled through the internet of things boost biosensors’ capabilities to a degree that they surely will play a major part of the answer to this global challenge. Surprisingly though, the adaption of such biosensors to function along the entire food value chain and hence also include important aspects of sustainable agriculture and food fraud has been neglected so far. In this review, the latest developments of biosensors addressing these issues are presented for the years 2015–2019 and point toward important new strategies needed to truly ensure safe food in a sustainable global market.
•The most current biosensors for food safety and food fraud are reviewed.•Biosensors supporting sustainable agriculture and livestock are highlighted.•The future role of biosensors for improving food safety is discussed.
Display omitted
The preparation of hydrogel-based wearable sensors for underwater application with high mechanical properties and electrical conductivity is an urgent challenge. Here, a ...supramolecular hydrogel based on polyionic liquids was designed and prepared for underwater sensing. The introduction of functional ionic liquid structures effectively increased the supramolecular interaction in the hydrogel network, which made the hydrogel successfully resist the interference of external water molecules. Depending on the effect of charge and hydrophobic interactions, this supramolecular hydrogel sensor exhibited high tensile (759 %), high tensile strength (0.23 MPa), high sensitivity (GF = 10.76) and extensive antibacterial properties, even in seawater environment. The obtained hydrogel sensor successfully monitored the swimming posture, which was helpful to digitally reflect the limb movement of athletes during underwater sports. This work made progress in the field of underwater wearable sensors based on hydrogels, and this design of multifunctional hydrogel provided a new idea for the development of functional sensors.
Wearable sweat sensors demonstrate outstanding performance in non-invasive, real-time monitoring of vital biomarkers in sweat, which offer an opportunity for individuals to achieve dynamic monitoring ...their own physiology in molecular-level. As a key step in sweat analysis that impact the accuracy of results, frequently-used sweat sampling methods are introduced in this review, and the emphasis is sweat sampling in wearable sensors including absorbent materials, superhydrophobic/superhydrophilic surface, sweat guidance and epidermal microfluidic systems. In the end, we also propose the remaining challenges in the practical, large-scale application of wearable sweat sensors and provide personal prospects on the future development.
Display omitted
•This paper summarized frequently-used sampling methods in emerging wearable sweat sensors.•The basic procedure, advantages and disadvantages of each sampling method have been introduced in details.•Non-invasive wearable sweat devices are promising for better personalized and predictive healthcare after overcoming several remaining challenges.