Wearable Sensor Devices Research Articles

Feasibility and Effect of a Wearable Motion Sensor Device in Facilitating In-Home Rehabilitation Program in Patients after Total Knee Arthroplasty: A Preliminary Study

Postoperative home-based rehabilitation programs are essential for facilitating functional recovery after total knee replacement (TKA). This study aimed to verify the feasibility of applying a wearable motion sensor device (MSD) to assist patients in performing home-based exercises after TKA. The interrater reliability of the measurement for knee mobility and the time spent completing the 5-times sit-to-stand test (5TSST) by two experienced physicians and using the MSD in 12 healthy participants was first assessed. A prospective control trial was then conducted, in which 12 patients following TKA were allocated to two groups: the home-based exercise group and the MSD-assisted rehabilitation group. Changes in knee range of motion, pain, functional score, performance, and exercise completion rates were compared between the groups over two months of follow-up. MSD-measured knee mobility and 5TSST exhibited excellent reliability compared with the physician measurements. Furthermore, patients in the MSD-assisted rehabilitation group reported higher training compliance than participants in the home-based exercise group, which led to better outcomes in the knee extension angle and maximal and average angular velocity in 5TSST. MSD-assisted home-based rehabilitation following TKA is a feasible treatment model for telerehabilitation because it enhances patients’ compliance to training, which improves functional recovery.

Effectiveness of the heartbeat interval error and compensation method on heart rate variability analysis.

The purpose of this study is to evaluate the effectiveness of heartbeat error and compensation methods on heart rate variability (HRV) with mobile and wearable sensor devices. The HRV analysis extracts multiple indices related to the heart and autonomic nervous system from beat‐to‐beat intervals. These HRV analysis indices are affected by the heartbeat interval mismatch, which is caused by sampling error from measurement hardware and inherent errors from the state of human body. Although the sampling rate reduction is a common method to reduce power consumption on wearable devices, it degrades the accuracy of the heartbeat interval. Furthermore, wearable devices often use photoplethysmography (PPG) instead of electrocardiogram (ECG) to measure heart rate. However, there are inherent errors between PPG and ECG, because the PPG is affected by blood pressure fluctuations, vascular stiffness, and body movements. This paper evaluates the impact of these errors on HRV analysis using dataset including both ECG and PPG from 28 subjects. The evaluation results showed that the error compensation method improved the accuracy of HRV analysis in time domain, frequency domain and non‐linear analysis. Furthermore, the error compensation by the algorithm was found to be effective for both PPG and ECG.

Crystallinity of Nanocellulose and its Application in Polymer Composites: A Short Review

There are various different types of nanocellulose such as nanofibrillated cellulose (NFC), nanocrystal cellulose (NCC), and nanocrystal sphere (NCS). Each nanocellulose contains ordered nanocrystallites and low-ordered nano domains (amorphous). Nanocellulose can be used in several different applications such as coating for a wearable sensor device, film for supercapacitors, flexible fire-resistant foams for architecture, manufactory, and aerospace. All of these were made, following some chemical and mechanical processes. Some nanocellulose has a highly crystalline structure that has the potential to improve mechanical properties for industrial applications. Therefore, the present review compiles the most recent information on nanocellulose crystallinity influence on the polymer composites. In this review, the crystallinity of nanocellulose from different sources is discussed. The preparation of several nanocrystals cellulose via chemical treatment, particularly cellulose hydrolysis are described. It can be concluded that , the cellulose crystalline structure as filler or reinforce was responsible for the improvement of polymer matrix properties.

A Printed Flexible Humidity Sensor with High Sensitivity and Fast Response Using a Cellulose Nanofiber/Carbon Black Composite

In the emerging Internet of Things (IoT) society, there is a significant need for low-cost, high-performance flexible humidity sensors in wearable devices. However, commercially available humidity sensors lack flexibility or require expensive and complex fabrication methods, limiting their application and widespread use. We report a high-performance printed flexible humidity sensor using a cellulose nanofiber/carbon black (CNF/CB) composite. The cellulose nanofiber enables excellent dispersion of carbon black, which facilitates the ink preparation and printing process. At the same time, its hydrophilic and porous nature provides high sensitivity and fast response to humidity. Significant resistance changes of 120% were observed in the sensor at humidity ranging from 30% RH to 90% RH, with a fast response time of 10 s and a recovery time of 6 s. Furthermore, the developed sensor also exhibited high-performance uniformity, response stability, and flexibility. A simple humidity detection device was fabricated and successfully applied to monitor human respiration and noncontact fingertip moisture as a proof-of-concept.

LSTM Based Mental Stress Level Detection using Wearable Sensor Devices

LSTM Based Mental Stress Level Detection using Wearable Sensor Devices

Detection of abnormal human behavior using deep learning

The complete human body or the various limb postures are involved in human action. These days,Abnormal Human Activity Recognition (Abnormal HAR) is highly well noticed and surveyed in manystudies. However, because of complicated difficulties such as sensor movement, positioning, and so on,as well as how individuals carry out their activities, it continues to be a difficult process. Identifyingparticular activities benefits human-centric applications such as postoperative trauma recovery, gesturedetection, exercise, fitness, and home care help. The HAR system has the ability to automate orsimplify most of the people’s everyday chores. HAR systems often use supervised or unsupervisedlearning as their foundation. Unsupervised systems operate according to a set of rules, whereassupervised systems need to be trained beforehand using specific datasets. This study conducts detailedliterature reviews on the development of various activity identification techniques currently being used.The three methods—wearable device-based, pose-based, and smartphone sensor—are examined in thisinquiry for identifying abnormal acts (AAD). The sensors in wearable devices collect data, whereas thegyroscopes and accelerometers in smartphones provide input to the sensors in wearable devices. Tocategorize activities, pose estimation uses a neural network. The Anomalous Action Detection Dataset(Ano-AAD) is created and improved using several methods. The study examines fresh datasets andinnovative models, including UCF-Crime. A new pattern in anomalous HAR systems has emerged,linking anomalous HAR tasks to computer vision applications including security, video surveillance,and home monitoring. In terms of issues and potential solutions, the survey looks at vision-based HAR.

Deep enriched salp swarm optimization based bidirectional -long short term memory model for healthcare monitoring system in big data

The rapid development of communication technologies and expert systems have resulted in a large volume of medical data. Big data such as clinical data, omics data, and electronic health data are difficult to manage in real-time due to noise, large size, different formats, missing values and large features. Hence, it is more difficult for the health monitoring system to extract the correct information. Low quality and noisy data can lead to unnecessary treatment. To overcome these issues, we proposed Enriched Salp Swarm Optimization based Bidirectional Long Short Term Memory (ESSOBiLSTM) to monitor health. This method consists of four layers, such as the data collection layer, data storage layer, data analytics, and presentation layer. The initial layer handles a variety of information from main sources: wearable sensor devices (WSD), social network data, and medical records (MR). The second layer stores all the collected data from WSD, MR, and social network data to the cloud server through the wireless network. The proposed framework for performing big data analytics steps like preprocessing, filtering, dimensionality reduction, and classification is performed in the third layer. In the final layer, the doctor analyzes the patient's condition based on the classification results of the enriched SSO-BiLSTM. Based on the evaluation report, the proposed ESSOBiLSTM gives an accuracy of 85%, precision of 80%, RMSE of 0.6, MAE of 0.58, recall of 85% and F-measure of 79%. As a result, ESSOBiLSTM has proven to be more effective in monitoring health in large datasets.

Advanced three-dimensional graphene-based piezoresistive sensors in wearable devices

The piezoresistive pressure sensor made with a three-dimensional (3D) structure as the core material is considered a potential precision sensor for wearable devices because of its unique advantages of simple preparation principle, low power consumption, stable performance and high signal acquisition efficiency. It has attracted the attention of many scientific researchers who are committed to realizing the high intelligence and informatization of personal devices. After the rapid development in the 21st century, this technology has made many breakthroughs and showed strong application potential in high-tech fields such as human motion detection, health monitoring and electronic skin. However, this technology is still a long way from full commercial mass production. This paper introduces the unique advantages of the 3D graphene-based piezoresistive sensor in intelligent wearable devices, summarizes several production methods and applications of this 3D graphene-based piezoresistive sensor, explores the future development trend and application prospect of this technology, and discusses the challenges and prospects of piezoresistive pressure sensor based on three-dimensional graphene.

Deep Learning with Backtracking Search Optimization Based Skin Lesion Diagnosis Model

Nowadays, quality improvement and increased accessibility to patient data, at a reasonable cost, are highly challenging tasks in healthcare sector. Internet of Things (IoT) and Cloud Computing (CC) architectures are utilized in the development of smart healthcare systems. These entities can support real-time applications by exploiting massive volumes of data, produced by wearable sensor devices. The advent of evolutionary computation algorithms and Deep Learning (DL) models has gained significant attention in healthcare diagnosis, especially in decision making process. Skin cancer is the deadliest disease which affects people across the globe. Automatic skin lesion classification model has a highly important application due to its fine-grained variability in the presence of skin lesions. The current research article presents a new skin lesion diagnosis model i.e., Deep Learning with Evolutionary Algorithm based Image Segmentation (DL-EAIS) for IoT and cloud-based smart healthcare environments. Primarily, the dermoscopic images are captured using IoT devices, which are then transmitted to cloud servers for further diagnosis. Besides, Backtracking Search optimization Algorithm (BSA) with Entropy-Based Thresholding (EBT) i.e., BSA-EBT technique is applied in image segmentation. Followed by, Shallow Convolutional Neural Network (SCNN) model is utilized as a feature extractor. In addition, Deep-Kernel Extreme Learning Machine (D-KELM) model is employed as a classification model to determine the class labels of dermoscopic images. An extensive set of simulations was conducted to validate the performance of the presented method using benchmark dataset. The experimental outcome infers that the proposed model demonstrated optimal performance over the compared techniques under diverse measures.

FRAMEWORK FOR TOUCHLESS PATIENT MONITORING SYSTEM INTEGRATING ULTRA-WIDEBAND RADAR AND INTERNET OF THINGS FOR COVID-19 PATIENTS

Effective Health monitoring and patient monitoring system is an inevitable need for the present world with the rapid increase of affected people due to various chronic diseases. Monitoring various health parameters like body temperature, blood pressure, heart beat, oxygen level and sugar level is very important to be proactive against chronic and pandemic diseases. Internet of Things (IoT) has gained a great interest in the health care sector through different wearable sensor devices. Monitoring the patients is a great challenge during pandemic diseases since the doctors and other medical practitioners were exposed to risk. This paper presents a novel touchless health and patient monitoring system (THPMS) embedding ultra-wide band (UWB) and IoT technologies for effective monitoring of COVID-19 patients. The IoT module is specifically designed for health monitoring whereas as UWB radar is designated for effective touchless patient monitoring. The IoT module comprises of temperature sensor, heart beat sensor and pulse oximeter which senses and stores the information in internet cloud which can be accessed through mobile and web applications. The UWB radar is integrated with the system for touchless patient monitoring. The proposed system also embedded with heath assisting module where it allows the person to interact with the doctors after receiving their health parameters through the mobile bot application termed as IOT FITBOT. The proposed system offers health monitoring through IoT module, patient monitoring through UWB radar and health assisting through IOT FITBOT application. Mobile application and WEB based graphical user interface (GUI) is developed to receive the

Test-retest reliability and minimal detectable change for measures of wearable gait analysis system (G-Walk) in children with cerebral palsy.

Cerebral Palsy (CP) is the most frequent cause of physical disability in childhood. CP causes primary deficits such as impairments in muscle tone, muscle weakness, problems in selective motor control and secondary deficits such as contractures and deformities. These deficits lead to motor disorders during movement causing limitations in gait. Sixty percent of children with CP can walk independently despite these problems, however, they present with various gait abnormalities. Gait analysis is used in the quantitative assessment of gait disturbances providing functional diagnosis, assessment for treatment, planning, and monitoring of progress. G-Walk is a wearable sensor device which provides quantitative gait analysis via spatiotemporal parameters and pelvic girdle angles. In literature, there is no study investigating the reliability of the G-Walk in children with CP. The purpose of this study was to confirm the test-retest reliability of a commercially available body-worn sensor 'BTS G-WALK sensor system' for spatiotemporal gait parameters in children with CP. Fifty-four children with CP (mean age: 9.19 ± 3.49 years), Gross Motor Function Classification System (GMFCS) level I-II completed the test-retest protocol with 5 days between tests. The test-retest reliability was calculated using intra-class correlation coefficients (ICC). Minimal detectable changes were calculated using standard error measurements. According to the analysis, ICC varied from 0.799 to 0.977 in all of the gait parameters. The statistical analysis showed that all G-Walk parameters' measurements were found to have almost perfect test-retest reliability. The G-Walk was found to be reliable in gait parameters for children with CP between ages 5 and 15, in GMFCS level I-II. A gait analysis carried out with the G-Walk system is a reliable method to assess gait in children with CP in a clinical setting.

Wearable Medical Sensor Devices, Machine and Deep Learning Algorithms, and Internet of Things-based Healthcare Systems in COVID-19 Patient Screening, Diagnosis, Monitoring, and Treatment

Wearable Medical Sensor Devices, Machine and Deep Learning Algorithms, and Internet of Things-based Healthcare Systems in COVID-19 Patient Screening, Diagnosis, Monitoring, and Treatment

Activity Detection for the Wellbeing of Dogs Using Wearable Sensors Based on Deep Learning

Among pets, dogs are very famous in the whole world. The owners of dogs are very cautious about the well-being of dogs. The well-being of dogs can be ensured by continuous monitoring of their activities. Studies related to activity detection have gained much popularity due to the significant progress in sensor technology during the last few years. Automatic monitoring of pet applications includes real-time monitoring systems and surveillance which detect the pets with high accuracy using the latest pet activity classification techniques. The revolution in the domain of technology has allowed us to obtain better results using conventional techniques. Convolutional neural networks (CNNs) 1D recently become a cutting-edge approach for signal processing-based systems such as patient-individual ECG categorization, sensor-based health monitoring systems, and anomaly identification in manufacturing areas. Adaptive and compact 1D models have several advantages over their conventional 2D counterparts. A limited dataset is sufficient to train a 1D CNN efficiently while 2D CNNs require a plethora of data for training. Its architecture is not very complicated, so it is suitable for real-time detection of activities. The main goal of this study is to develop a state-of-the-art system that can detect and classify the activities based on sensors’ data (accelerometer, and gyroscope. We proposed a 1D CNN-based system for pet activity detection. The objective of this study was to recognize ten pet activities such as walking, sitting, down, staying, eating, sideway, jumping, running, shaking, and nose work respectively, using wearable sensor devices based on deep learning technique. The data collection procedure for this study was conducted with 10 dogs of different breeds, sex (male=7, female = 3), age (age = 4±3), and sizes (small, medium, large) in a healthy environment. After collecting the data, the following steps, namely data synchronization, and data preprocessing were considered to remove the irrelevant data from the dataset. To overcome imbalanced problems in the dataset we used the class-weight technique. Subsequently, we applied 1D CNN algorithm using the class-weight technique. The model with the class-weight technique showed 99.70% training accuracy and 96.85% validation accuracy. The 1D CNN approach will be helpful for real-time monitoring of activities and for tracing the behavior of dogs.

Human Activity Recognition Based on Multichannel Convolutional Neural Network With Data Augmentation

In view of the excellent portability and privacy protection of wearable sensor devices, human activity recognition (HAR) of wearable devices has increased applications in human-computer interaction, health care, etc. Therefore, it is necessary to recognize various human activities accurately and efficiently. In this paper, we propose a multi-channel convolutional neural network with data augmentation for HAR, denoted AMC-CNN. First, the sliding windows in time series are used to construct the feature window, and then the feature window is augmented by data transformation and data addition. Through the horizontal connection of the augmented feature windows, the reconstructed feature samples are obtained. Second, a relatively lightweight multi-channel convolutional neural network is designed. In order to mine deep correlations between sensor data more efficiently, we use reasonable convolution kernel settings to compute multi-channel convolutions and extract parallel multi-scale features, and then train the model to recognize human activities. Finally, experiments are carried out on WISDM and MHEALTH datasets to verify the effectiveness of the data augmentation. Moreover, the other three models are adopted for comparative experiments. The evaluation indexes show that the method proposed in this paper has a better recognition effect, which verifies that the AMC-CNN model is effective in both single-sensor and multi-sensor HAR.

Integration of Fog Computing for Health Record Management Using Blockchain Technology

Internet of Medical Things (IoMT) is a breakthrough technology in the transfer of medical data via a communication system. Wearable sensor devices collect patient data and transfer them through mobile internet, that is, the IoMT. Recently, the shift in paradigm from manual data storage to electronic health recording on fog, edge, and cloud computing has been noted. These advanced computing technologies have facilitated medical services with minimum cost and available conditions. However, the IoMT raises a high concern on network security and patient data privacy in the health care system. The main issue is the transmission of health data with high security in the fog computing model. In today's market, the best solution is blockchain technology. This technology provides high-end security and authentication in storing and transferring data. In this research, a blockchain-based fog computing model is proposed for the IoMT. The proposed technique embeds a block chain with the yet another consensus (YAC) protocol building security infrastructure into fog computing for storing and transferring IoMT data in the network. YAC is a consensus protocol that authenticates the input data in the block chain. In this scenario, the patients and their family members are allowed to access the data. The empirical outcome of the proposed technique indicates high reliability and security against dangerous threats. The major advantages of using the blockchain model are high transparency, good traceability, and high processing speed. The technique also exhibits high reliability and efficiency in accessing data with secure transmission. The proposed technique achieves 95% reliability in transferring a large number of files up to 10,000.

RFMonitor: Monitoring smoking behavior of minors using COTS RFID devices

The protection laws of minors in various countries have clearly banned minors from smoking. However, due to various social factors and the psychological conditions of minors, smoking among minors cannot be effectively controlled. A typical example is that many countries ban smoking in public places, and many places have special smoking areas. Previous work designed wearable sensor devices or used wireless signals (e.g., WIFI and Bluetooth etc.) to identify smoking activities. System deployment and implementation are rarely considered in existing system application scenarios. Here, we show that we can use the backscatter signal of the passive RFID tag, combined with the improved radio frequency chromatographic imaging technology, to analyze the RSSI signal of the human smoking action. Therefore, the system is specially designed for application scenarios and can realize the height detection of minors and the recognition of smoking behavior. In the end, related comparative experiments were also carried out to verify the effectiveness and real-time performance of the system. Aiming at the classification problem of different age groups, this paper proposed to distinguish population categories and identify smoking behaviors by analyzing RSSI signals extracted from commercial readers. Finally, the validity and real-time performance of the system are verified by comparative experiments.

Feature Fusion of a Deep-Learning Algorithm into Wearable Sensor Devices for Human Activity Recognition.

This paper presents a wearable device, fitted on the waist of a participant that recognizes six activities of daily living (walking, walking upstairs, walking downstairs, sitting, standing, and laying) through a deep-learning algorithm, human activity recognition (HAR). The wearable device comprises a single-board computer (SBC) and six-axis sensors. The deep-learning algorithm employs three parallel convolutional neural networks for local feature extraction and for subsequent concatenation to establish feature fusion models of varying kernel size. By using kernels of different sizes, relevant local features of varying lengths were identified, thereby increasing the accuracy of human activity recognition. Regarding experimental data, the database of University of California, Irvine (UCI) and self-recorded data were used separately. The self-recorded data were obtained by having 21 participants wear the device on their waist and perform six common activities in the laboratory. These data were used to verify the proposed deep-learning algorithm on the performance of the wearable device. The accuracy of these six activities in the UCI dataset and in the self-recorded data were 97.49% and 96.27%, respectively. The accuracies in tenfold cross-validation were 99.56% and 97.46%, respectively. The experimental results have successfully verified the proposed convolutional neural network (CNN) architecture, which can be used in rehabilitation assessment for people unable to exercise vigorously.

A physiological signal compression approach using optimized Spindle Convolutional Auto-encoder in mHealth applications

Background and ObjectivesThe COVID-19 pandemic manifested the need of developing robust digital platforms for facilitating healthcare services such as consultancy, clinical therapies, real time remote monitoring, early diagnosis and future predictions. Innovations made using technologies such as Internet of Things (IoT), edge computing, cloud computing and artificial intelligence are helping address this crisis. The urge for remote monitoring, symptom analysis and early detection of diseases lead to tremendous increase in the deployment of wearable sensor devices. They facilitate seamless gathering of physiological data such as electrocardiogram (ECG) signals, respiration traces (RESP), galvanic skin response (GSR), pulse rate, body temperature, photoplethysmograms (PPG), oxygen saturation (SpO2) etc. For diagnosis and analysis purpose, the gathered data needs to be stored. Wearable devices operate on batteries and have a memory constraint. In mHealth application architectures, this gathered data is hence stored on cloud based servers. While transmitting data from wearable devices to cloud servers via edge devices, a lot of energy is consumed. This paper proposes a deep learning based compression model SCAElite that reduces the data volume, enabling energy efficient transmission. ResultsStress Recognition in Automobile Drivers dataset and MIT-BIH dataset from PhysioNet are used for validation of algorithm performance. The model achieves a compression ratio of up to 300 fold with reconstruction errors within 8% over the stress recognition dataset and 106.34-fold with reconstruction errors within 8% over the MIT-BIH dataset. The computational complexity of SCAElite is 51.65% less compared to state-of-the-art deep compressive model. ConclusionIt is experimentally validated that SCAElite guarantees a high compression ratio with good quality restoration capabilities for physiological signal compression in mHealth applications. It has a compact architecture and is computationally more efficient compared to state-of-the-art deep compressive model.

Measurement of various intensities of physical activities and categorization of \u201cLocomotive\u201d and \u201cHousehold\u201d activities provide a subject-specific detailed assessment

This study aimed to compare the physical activity (PA) measured by a wearable sensor device (WSD) and the step count measurement, and to investigate the association between PAs and lifestyle. Data of 301 participants were collected from March 2019 to March 2021. Step counts, sedentary behavior, performance time of light/moderate/vigorous PA, METs × hour of “Locomotive” and “Household” categorized activities, and energy expenditure (EE) were measured by the WSD, respectively. Furthermore, the participants were classified into student, standing worker, and sitting worker groups. Data were analyzed using the Steel–Dwass and Pearson correlation coefficient tests. The correlation between the performance time of each PA and step count was weak, except for moderate PA. “Household” EE and step count also had a weak correlation. In the comparison of lifestyle, there was a significant difference in the mean performance time of each type of PA between the groups. Additionally, the standing worker and sitting worker groups had a significant difference in METs × hour of "Household" activities, indicating that the difference between the occupations is reflected in “Household” activities. The WSD measurement can be used to evaluate detailed individual PA, whereas the step count measurement showed weakness in the PA estimation.

A Comparative Study of Arousal and Valence Dimensional Variations for Emotion Recognition Using Peripheral Physiological Signals Acquired from Wearable Sensors.

Wearable sensors have made an impact on healthcare and medicine by enabling out-of-clinic health monitoring and prediction of pathological events. Further advancements made in the analysis of multimodal signals have been in emotion recognition which utilizes peripheral physiological signals captured by sensors in wearable devices. There is no universally accepted emotion model, though multidimensional methods are often used, the most popular of which is the two-dimensional Russell's model based on arousal and valence. Arousal and valence values are discrete, usually being either binary with low and high labels along each dimension creating four quadrants or 3-valued with low, neutral, and high labels. In day-to-day life, the neutral emotion class is the most dominant leaving emotion datasets with the inherent problem of class imbalance. In this study, we show how the choice of values in the two-dimensional model affects the emotion recognition using multiple machine learning algorithms. Binary classification resulted in an accuracy of 87.2% for arousal and up to 89.5% for valence. Maximal 3-class classification accuracy was 80.9% for arousal and 81.1% for valence. For the joined classification of arousal and valence, the four-quadrant model reached 87.8%, while the nine-class model had an accuracy of 75.8%. This study can be used as a basis for further research into feature extraction for better overall classification performance.