Hybrid pedestrian positioning system using wearable inertial sensors and ultrasonic ranging

Pedestrian positioning system(PPS)using wearable inertial sensors has wide applications towards various emerging fields such as smart healthcare,emergency rescue,soldier positioning,etc.The performance of traditional PPS is limited by the cumulative error of inertial sensors,complex motion modes of pedestrians,and the low robustness of the multi-sensor collaboration structure.This paper presents a hybrid pedestrian positioning system using the combination of wearable inertial sensors and ultrasonic ranging(H-PPS).A robust two nodes integration structure is developed to adaptively combine the motion data acquired from the single waist-mounted and foot-mounted node,and enhanced by a novel ellipsoid constraint model.In addition,a deep-learning-based walking speed estimator is proposed by considering all the motion features provided by different nodes,which effectively reduces the cumulative error originating from inertial sensors.Finally,a comprehensive data and model dual-driven model is presented to effectively combine the motion data provided by different sensor nodes and walking speed estimator,and multi-level constraints are extracted to further improve the performance of the overall system.Experimental results indicate that the proposed H-PPS significantly improves the performance of the single PPS and outperforms existing algorithms in accuracy index under complex indoor scenarios.

A Novel Method for Cross-Subject Human Activity Recognition with Wearable Sensors

Human Activity Recognition (HAR) is an important way for lower limb exoskeleton robots to implement human-computer collaboration with users. Most of the existing methods in this field focus on a simple scenario recognizing activities for specific users, which does not consider the individual differences among users and cannot adapt to new users. In order to improve the generalization ability of HAR model, this paper proposes a novel method that combines the theories in transfer learning and active learning to mitigate the cross-subject issue, so that it can enable lower limb exoskeleton robots being used in more complex scenarios. First, a neural network based on convolutional neural networks (CNN) is designed, which can extract temporal and spatial features from sensor signals collected from different parts of human body. It can recognize human activities with high accuracy after trained by labeled data. Second, in order to improve the cross-subject adaptation ability of the pre-trained model, we design a cross-subject HAR algorithm based on sparse interrogation and label propagation. Through leave-one-subject-out validation on two widely-used public datasets with existing methods, our method achieves average accuracies of 91.77% on DSAD and 80.97% on PAMAP2, respectively. The experimental results demonstrate the potential of implementing cross-subject HAR for lower limb exoskeleton robots.

Functionalized Hydrogel-Based Wearable Gas and Humidity Sensors

Breathing is an inherent human activity;however,the composition of the air we inhale and gas exhale remains unknown to us.To address this,wearable vapor sensors can help people monitor air composition in real time to avoid underlying risks,and for the early detection and treatment of diseases for home healthcare.Hydrogels with three-dimensional polymer networks and large amounts of water molecules are naturally flexible and stretchable.Functionalized hydrogels are intrinsically conductive,self-healing,self-adhesive,biocompatible,and room-temperature sensitive.Compared with traditional rigid vapor sensors,hydrogel-based gas and humidity sensors can directly fit human skin or clothing,and are more suitable for real-time monitoring of personal health and safety.In this review,current studies on hydrogel-based vapor sensors are investigated.The required properties and optimization methods of wearable hydrogel-based sensors are introduced.Subsequently,existing reports on the response mechanisms of hydrogel-based gas and humidity sensors are summarized.Related works on hydrogel-based vapor sensors for their application in personal health and safety monitoring are presented.Moreover,the potential of hydrogels in the field of vapor sensing is elucidated.Finally,the current research status,challenges,and future trends of hydrogel gas/humidity sensing are discussed.

Wearable and stretchable conductive polymer composites for strain sensors:How to design a superior one?

Wearable and stretchable strain sensors have potential values in the fields of human motion and health monitoring,flexible electronics,and soft robotic skin.The wearable and stretchable strain sensors can be directly attached to human skin,providing visualized detection for human motions and personal healthcare.Conductive polymer composites(CPC)composed of conductive fillers and flexible polymers have the advantages of high stretchability,good flexibility,superior durability,which can be used to prepare flexible strain sensors with large working strain and outstanding sensitivity.This review has put forward a comprehensive summary on the fabrication methods,advanced mechanisms and strain sensing abilities of CPC strain sensors reported in recent years,especially the sensors with superior performance.Finally,the structural design,bionic function,integration technology and further application of CPC strain sensors are prospected.

Deep Pyramidal Residual Network for Indoor-Outdoor Activity Recognition Based on Wearable Sensor

Recognition of human activity is one of the most exciting aspects of time-series classification,with substantial practical and theoretical impli-cations.Recent evidence indicates that activity recognition from wearable sensors is an effective technique for tracking elderly adults and children in indoor and outdoor environments.Consequently,researchers have demon-strated considerable passion for developing cutting-edge deep learning sys-tems capable of exploiting unprocessed sensor data from wearable devices and generating practical decision assistance in many contexts.This study provides a deep learning-based approach for recognizing indoor and outdoor movement utilizing an enhanced deep pyramidal residual model called Sen-PyramidNet and motion information from wearable sensors(accelerometer and gyroscope).The suggested technique develops a residual unit based on a deep pyramidal residual network and introduces the concept of a pyramidal residual unit to increase detection capability.The proposed deep learning-based model was assessed using the publicly available 19Nonsens dataset,which gathered motion signals from various indoor and outdoor activities,including practicing various body parts.The experimental findings demon-strate that the proposed approach can efficiently reuse characteristics and has achieved an identification accuracy of 96.37%for indoor and 97.25%for outdoor activity.Moreover,comparison experiments demonstrate that the SenPyramidNet surpasses other cutting-edge deep learning models in terms of accuracy and F1-score.Furthermore,this study explores the influence of several wearable sensors on indoor and outdoor action recognition ability.

Automatic Recognition of Construction Worker Activities Using Deep Learning Approaches and Wearable Inertial Sensors

The automated evaluation and analysis of employee behavior in an Industry 4.0-compliant manufacturingfirm are vital for the rapid and accurate diagnosis of work performance,particularly during the training of a new worker.Various techniques for identifying and detecting worker performance in industrial applications are based on computer vision techniques.Despite widespread com-puter vision-based approaches,it is challenging to develop technologies that assist the automated monitoring of worker actions at external working sites where cam-era deployment is problematic.Through the use of wearable inertial sensors,we propose a deep learning method for automatically recognizing the activities of construction workers.The suggested method incorporates a convolutional neural network,residual connection blocks,and multi-branch aggregate transformation modules for high-performance recognition of complicated activities such as con-struction worker tasks.The proposed approach has been evaluated using standard performance measures,such as precision,F1-score,and AUC,using a publicly available benchmark dataset known as VTT-ConIoT,which contains genuine con-struction work activities.In addition,standard deep learning models(CNNs,RNNs,and hybrid models)were developed in different empirical circumstances to compare them to the proposed model.With an average accuracy of 99.71%and an average F1-score of 99.71%,the experimentalfindings revealed that the suggested model could accurately recognize the actions of construction workers.Furthermore,we examined the impact of window size and sensor position on the identification efficiency of the proposed method.

On-body propagation characterization based on FDTD method for 2.4/5.2/5.7 GHz wearable body sensor networks

The on-body path loss and time delay of radio propagation in 2. 4/5.2/5.7 GHz wearable body sensor networks （W-BSN） are studied using Remcom XFDTD, a simulation tool based on the finite-difference time- domain method. The simulation is performed in the environment of free space with a simplified three- dimensional human body model. Results show that the path loss at a higher radio frequency is significantly smaller. Given that the transmitter and the receiver are located on the body trunk, the path loss relevant to the proposed minimum equivalent surface distance follows a log-fitting parametric model, and the path loss exponents are 4. 7, 4. 1 and 4. 0 at frequencies of 2. 4, 5.2, 5.7 GHz, respectively. On the other hand, the first- arrival delays are less than 2 ns at all receivers, and the maximum time delay spread is about 10 ns. As suggested by the maximum time delay spread, transmission rates of W-BSN must be less than 10^8 symbol/s to avoid intersymbol interference from multiple-path delay.

Functionalized Fiber-Based Strain Sensors:Pathway to Next-Generation Wearable Electronics

Wearable strain sensors are arousing increasing research interests in recent years on account of their potentials in motion detection,personal and public healthcare,future entertainment,man-machine interaction,artificial intelligence,and so forth.Much research has focused on fiber-based sensors due to the appealing performance of fibers,including processing flexibility,wearing comfortability,outstanding lifetime and serviceability,low-cost and large-scale capacity.Herein,we review the latest advances in functionalization and device fabrication of fiber materials toward applications in fiber-based wearable strain sensors.We describe the approaches for preparing conductive fibers such as spinning,surface modification,and structural transformation.We also introduce the fabrication and sensing mechanisms of state-of-the-art sensors and analyze their merits and demerits.The applications toward motion detection,healthcare,man-machine interaction,future entertainment,and multifunctional sensing are summarized with typical examples.We finally critically analyze tough challenges and future remarks of fiber-based strain sensors,aiming to implement them in real applications.

Silk Fibroin-Based Hydrogel for Multifunctional Wearable Sensors

The flexible wearable sensors with excellent stretchability,high sensitivity and good biocompatibility are significantly required for continuously physical condition tracking in health management and rehabilitation monitoring.Herein,we present a high-performance wearable sensor.The sensor is prepared with nanocomposite hydrogel by using silk fibroin(SF),polyacrylamide(PAM),polydopamine(PDA)and graphene oxide(GO).It can be used to monitor body motions(including large-scale and small-scale motions)as well as human electrophysiological(ECG)signals with high sensitivity,wide sensing range,and fast response time.Therefore,the proposed sensor is promising in the fields of rehabilitation,motion monitoring and disease diagnosis.

Laser direct writing of Ga_(2)O_(3)/liquid metal-based flexible humidity sensors

Flexible and wearable humidity sensors play a vital role in daily point-of-care diagnosis and noncontact human-machine interactions.However,achieving a facile and high-speed fabrication approach to realizing flexible humidity sensors remains a challenge.In this work,a wearable capacitive-type Ga_(2)O_(3)/liquid metal-based humidity sensor is demonstrated by a one-step laser direct writing technique.Owing to the photothermal effect of laser,the Ga_(2)O_(3)-wrapped liquid metal particles can be selectively sintered and converted from insulative to conductive traces with a resistivity of 0.19Ω·cm,while the untreated regions serve as active sensing layers in response to moisture changes.Under 95%relative humidity,the humidity sensor displays a highly stable performance along with rapid response and recover time.Utilizing these superior properties,the Ga_(2)O_(3)/liquid metal-based humidity sensor is able to monitor human respiration rate,as well as skin moisture of the palm under different physiological states for healthcare monitoring.

Advances in self-powered sports monitoring sensors based on triboelectric nanogenerators

The new era of the internet of things brings great opportunities to the field of intelligent sports.The collection and analysis of sports data are becoming more intelligent driven by the widely-distributed sensing network system.Triboelectric nanogenerators(TENGs)can collect and convert energy as selfpowered sensors,overcoming the limitations of external power supply,frequent power replacement and high-cost maintenance.Herein,we introduce the working modes and principles of TENGs,and then summarize the recent advances in self-powered sports monitoring sensors driven by TENGs in sports equipment facilities,wearable equipment and competitive sports specialities.We discuss the existing issues,i.e.,device stability,material sustainability,device design rationality,textile TENG cleanability,sports sensors safety,kinds and manufacturing of sports sensors,and data collection comprehensiveness,and finally,propose the countermeasures.This work has practical significance to the current TENG applications in sports monitoring,and TENG-based sensing technology will have a broad prospect in the field of intelligent sports in the future.

Engineering Smart Composite Hydrogels for Wearable Health Monitoring

Growing health awareness triggers the public's concern about health problems. People want a timely and comprehensive picture of their condition without frequent trips to the hospital for costly and cumbersome general check-ups. The wearable technique provides a continuous measurement method for health monitoring by tracking a person's physiological data and analyzing it locally or remotely.During the health monitoring process,different kinds of sensors convert physiological signals into electrical or optical signals that can be recorded and transmitted, consequently playing a crucial role in wearable techniques. Wearable application scenarios usually require sensors to possess excellent flexibility and stretchability. Thus, designing flexible and stretchable sensors with reliable performance is the key to wearable technology. Smart composite hydrogels, which have tunable electrical properties, mechanical properties, biocompatibility, and multi-stimulus sensitivity, are one of the best sensitive materials for wearable health monitoring. This review summarizes the common synthetic and performance optimization strategies of smart composite hydrogels and focuses on the current application of smart composite hydrogels in the field of wearable health monitoring.

Ultra-Wideband Systems with Energy Harvesting Units for Sensors, 5G, IoT and Medical Systems

The high tech industrial revolution in the last fifty years depleted and ruined the planet natural resources. Energy harvesting is the main challenge in the research in green technologies. Compact wideband efficient antennas are crucial for energy harvesting portable sensors and systems. Small antennas have low efficiency. The efficiency of 5G, IoT communication and energy harvesting systems may be improved by using wideband efficient passive and active antennas. The system dynamic range may be improved by connecting amplifiers to the small antenna feed line. Ultra-wideband portable harvesting systems are presented in this paper. This paper presents new Ultra-Wideband energy harvesting system and antennas in frequencies ranging from 0.15 GHz to 18 GHz. Three wideband antennas cover the frequency range from 0.15 GHz to 18 GHz. A wideband metamaterial antenna with metallic strips covers the frequency range from 0.15 GHz to 0.42 GHz. The antenna bandwidth is around 75% for VSWR better than 2.3:1. A wideband slot antenna covers the frequency range from 0.4 GHz to 6.4 GHz. A wideband fractal notch antenna covers the frequency range from 6 GHz to 18 GHz. Printed passive and active notch and slot antennas are compact, low cost and have low volume. The active antennas may be employed in energy harvesting portable systems. The antennas and the harvesting system components may be assembled on the same, printed board. The printed notch and slot antennas bandwidth are from 75% to 100% for VSWR better than 3:1. The slot and notch antenna gain is around 3 dBi with efficiency higher than 90%. The antennas electrical parameters were computed in free space and near the human body. There is a good agreement between computed and measured results.

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

Falls are the contributing factor to both fatal and nonfatal injuries in the elderly.Therefore,pre-impact fall detection,which identifies a fall before the body collides with the floor,would be essential.Recently,researchers have turned their attention from post-impact fall detection to pre-impact fall detection.Pre-impact fall detection solutions typically use either a threshold-based or machine learning-based approach,although the threshold value would be difficult to accu-rately determine in threshold-based methods.Moreover,while additional features could sometimes assist in categorizing falls and non-falls more precisely,the esti-mated determination of the significant features would be too time-intensive,thus using a significant portion of the algorithm’s operating time.In this work,we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial sensors.The proposed network was introduced to address the limitations of fea-ture extraction,threshold definition,and algorithm complexity.After training on a large-scale motion dataset,the KFall dataset,and straightforward evaluation with standard metrics,the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%,respectively.In addition,we have inves-tigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network(CNN),a long short-term memory neural network(LSTM),and a hybrid model(CNN-LSTM).The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models(CNN,LSTM,and CNN-LSTM)with significant improvements.

Driving Activity Classification Using Deep Residual Networks Based on Smart Glasses Sensors

Accidents are still an issue in an intelligent transportation system,despite developments in self-driving technology(ITS).Drivers who engage in risky behavior account for more than half of all road accidents.As a result,reckless driving behaviour can cause congestion and delays.Computer vision and multimodal sensors have been used to study driving behaviour categorization to lessen this problem.Previous research has also collected and analyzed a wide range of data,including electroencephalography(EEG),electrooculography(EOG),and photographs of the driver’s face.On the other hand,driving a car is a complicated action that requires a wide range of body move-ments.In this work,we proposed a ResNet-SE model,an efficient deep learning classifier for driving activity clas-sification based on signal data obtained in real-world traffic conditions using smart glasses.End-to-end learning can be achieved by combining residual networks and channel attention approaches into a single learning model.Sensor data from 3-point EOG electrodes,tri-axial accelerometer,and tri-axial gyroscope from the Smart Glasses dataset was utilized in this study.We performed various experiments and compared the proposed model to base-line deep learning algorithms(CNNs and LSTMs)to demonstrate its performance.According to the research results,the proposed model outperforms the previous deep learning models in this domain with an accuracy of 99.17%and an F1-score of 98.96%.

Finger-actuated wireless-charging wearable multifunctional sweatsensing system for levodopa and vitamin C

Efficient portable wearable sweat sensors allow the long-term monitoring of changes in the status of biomarkers in sweat,which can be useful in diagnosis,medication,and nutritional assessment.In this study,we designed and tested a wireless,battery-free,flexible,self-pumping sweat-sensing system that simultaneously tracks levodopa and vitamin C levels in human sweat and detects body temperature.The system includes a microfluidic chip with a self-driven pump and anti-reflux valve,a flexible wireless circuit board,and a purpose-designed smartphone app.The microfluidic chip is used for the efficient collection of sweat and the drainage of excess sweat.The dual electrochemical sensing electrodes in the chip are modified with functional materials and appropriate enzymatic reagents,achieving excellent selectivity and stability.The sensitivities of the levodopa sensor and the vitamin C sensor are 0.0073 and 0.0018μA·μM^(-1),respectively,and the detection correlation coefficients of both exceed 0.99.Both sensors have a wide linear detection range of 0–100 and 0–1000μM,respectively,and low detection limits of 0.28 and 17.9μM,respectively.The flexible wireless circuit board is equipped with the functions of wireless charging,electrical signal capture and processing,and wireless transmission.The data recorded from each sensor are displayed on a smartphone via a self-developed app.A series of experimental results confirmed the reliability of the sweat-sensing system in noninvasively monitoring important biomarkers in the human body and its potential utility in the comprehensive assessment of biological health.

Wearable pressure sensors based on antibacterial and porous chitosan hydrogels for full-range human motion detection

Wearable pressure sensors made from conductive hydrogels hold significant potential in health monitoring.However,limited pressure range(Pa to hundreds of kPa)and inadequate antibacterial properties restrict their practical applications in diagnostic and health evaluation.Herein,a wearable high-performance pressure sensor was assembled using a facilely prepared porous chitosan-based hydrogel,which was constructed from commercial phenolphthalein particles as a sacrificial template.The relationship between the porosity of hydrogels and sensing performance of sensors was systematically explored.Herein,the wearable pressure sensor,featuring an optimized porosity of hydrogels,exhibits an ultrawide sensing capacity from 4.83 Pa to 250 k Pa(range-to-limit ratio of 51,760)and high sensitivity throughout high pressure ranges(0.7 kPa~(-1),120–250 kPa).The presence of chitosan endows these hydrogels with outstanding antibacterial performance against E.coli and S.aureus,making them ideal candidates for use in wearable electronics.These features allow for a practical approach to monitor full-range human motion using a single device with a simple structure.

A data and physical model dual-driven based trajectory estimator for long-term navigation

Long-term navigation ability based on consumer-level wearable inertial sensors plays an essential role towards various emerging fields, for instance, smart healthcare, emergency rescue, soldier positioning et al. The performance of existing long-term navigation algorithm is limited by the cumulative error of inertial sensors, disturbed local magnetic field, and complex motion modes of the pedestrian. This paper develops a robust data and physical model dual-driven based trajectory estimation(DPDD-TE) framework, which can be applied for long-term navigation tasks. A Bi-directional Long Short-Term Memory(Bi-LSTM) based quasi-static magnetic field(QSMF) detection algorithm is developed for extracting useful magnetic observation for heading calibration, and another Bi-LSTM is adopted for walking speed estimation by considering hybrid human motion information under a specific time period. In addition, a data and physical model dual-driven based multi-source fusion model is proposed to integrate basic INS mechanization and multi-level constraint and observations for maintaining accuracy under long-term navigation tasks, and enhanced by the magnetic and trajectory features assisted loop detection algorithm. Real-world experiments indicate that the proposed DPDD-TE outperforms than existing algorithms, and final estimated heading and positioning accuracy indexes reaches 5° and less than 2 m under the time period of 30 min, respectively.

Flexible wearable sensors:An emerging platform for monitoring of bacterial infection in skin wounds

Persistent inflammatory responses often occur when bacteria and other microorganisms frequently invade and colonize open wounds and eventually result in the formation of chronic wounds.Therefore,achieving real-time detection of invasive bacteria accurately and promptly is essential for efficient wound management and accelerat-ing the healing process.Recently,flexible wearable sensors have garnered significant attention,especially those designed for monitoring real-time biophysical or biochemical signals in wound sites in a minimally invasive manner.They provide more precise and continuous monitoring data,making them as emerging tools for clinical diagnostics.In this review,we first discuss the species and community distribution of different types of bacteria in chronic wounds.Next,we introduce currently developed techniques for detecting bacteria at wound sites.Fol-lowing that,we discuss the recent progress and unresolved issues of various flexible wearable sensors in detecting bacteria at wound sites.We believe that this review can provide meaningful guidance for the development of flexible wearable sensors for bacteria detection.

用于高风险环境安全监测和可调热管理的具有分层核壳结构的耐化学品纱线

Chemical resistant textiles are vital for safeguarding humans against chemical hazards in various settings.such as industrialproduction,chemicalaccidents,laboratory activities,and road transportation.However,the ideal integration of chemical resistance,thermal and moisture management,and wearer condition monitoring in conventional chemically protective textiles remains challenging.Herein,the design,manufacturing,and use of stretchable hierarchical core-shell yarns(HCSYs)for integrated chemical resistance,moisture regulation,and smart sensing textiles are demonstrated.These yarns con-tain helically elastic spandex,wrapped silver-plated nylon,and surface-structuredpolytetrafluo-roethylene(PTFE)yarns and are designed and manufactured based on a scalable fabrication process.In addition to their ideal chemical resistance performance,HCSYs can function as multifunctional stretch-able electronics for real-time human motion monitoring and as the basic element of intelligent textiles.Furthermore,a desirable dynamic thermoregulation function is achieved by exploiting the fabric structure with stretching modulation.Our HCSYs may provide prospective opportunities for the future development of smart protective textiles with high durability,flexibility,and scalability.