Recognition of Sedentary Behavior by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living for Telemedical Assessment of Cardiovascular Risk

Predictive Data Analytics in Telecare and Telehealth: Systematic Scoping Review

BACKGROUND

Telecare and telehealth are important care-at-home services used to support individuals to live more independently at home. Historically, these technologies have reactively responded to issues. However, there has been a recent drive to make better use of the data from these services to facilitate more proactive and predictive care.

OBJECTIVE

This review seeks to explore the ways in which predictive data analytics techniques have been applied in telecare and telehealth in at-home settings.

METHODS

The PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) checklist was adhered to alongside Arksey and O'Malley's methodological framework. English language papers published in MEDLINE, Embase, and Social Science Premium Collection between 2012 and 2022 were considered and results were screened against inclusion or exclusion criteria.

RESULTS

In total, 86 papers were included in this review. The types of analytics featuring in this review can be categorized as anomaly detection (n=21), diagnosis (n=32), prediction (n=22), and activity recognition (n=11). The most common health conditions represented were Parkinson disease (n=12) and cardiovascular conditions (n=11). The main findings include: a lack of use of routinely collected data; a dominance of diagnostic tools; and barriers and opportunities that exist, such as including patient-reported outcomes, for future predictive analytics in telecare and telehealth.

CONCLUSIONS

All papers in this review were small-scale pilots and, as such, future research should seek to apply these predictive techniques into larger trials. Additionally, further integration of routinely collected care data and patient-reported outcomes into predictive models in telecare and telehealth offer significant opportunities to improve the analytics being performed and should be explored further. Data sets used must be of suitable size and diversity, ensuring that models are generalizable to a wider population and can be appropriately trained, validated, and tested.

On-Device Semi-Supervised Activity Detection: A New Privacy-Aware Personalized Health Monitoring Approach

This paper presents an on-device semi-supervised human activity detection system that can learn and predict human activity patterns in real time. The clinical objective is to monitor and detect the unhealthy sedentary lifestyle of a user. The proposed semi-supervised learning (SSL) framework uses sparsely labelled user activity events acquired from Inertial Measurement Unit sensors installed as wearable devices. The proposed cluster-based learning model in this approach is trained with data from the same target user, thus preserving data privacy while providing personalized activity detection services. Two different cluster labelling strategies, namely, population-based and distance-based strategies, are employed to achieve the desired classification performance. The proposed system is shown to be highly accurate and computationally efficient for different algorithmic parameters, which is relevant in the context of limited computing resources on typical wearable devices. Extensive experimentation and simulation study have been conducted on multi-user human activity data from the public domain in order to analyze the trade-off between classification accuracy and computation complexity of the proposed learning paradigm with different algorithmic hyper-parameters. With 4.17 h of training time for 8000 activity episodes, the proposed SSL approach consumes at most 20 KB of CPU memory space, while providing a maximum accuracy of 90% and 100% classification rates.

Artificial intelligence in preventive cardiology

Artificial intelligence (AI) is a field of study that strives to replicate aspects of human intelligence into machines. Preventive cardiology, a subspeciality of cardiovascular (CV) medicine, aims to target and mitigate known risk factors for CV disease (CVD). AI's integration into preventive cardiology may introduce novel treatment interventions and AI-centered clinician assistive tools to reduce the risk of CVD. AI's role in nutrition, weight loss, physical activity, sleep hygiene, blood pressure, dyslipidemia, smoking, alcohol, recreational drugs, and mental health has been investigated. AI has immense potential to be used for the screening, detection, and monitoring of the mentioned risk factors. However, the current literature must be supplemented with future clinical trials to evaluate the capabilities of AI interventions for preventive cardiology. This review discusses present examples, potentials, and limitations of AI's role for the primary and secondary prevention of CVD.

How Could Sensor-Based Measurement of Physical Activity Be Used in Cardiovascular Healthcare?

Physical activity and cardiovascular disease (CVD) are intimately linked. Low levels of physical activity increase the risk of CVDs, including myocardial infarction and stroke. Conversely, when CVD develops, it often reduces the ability to be physically active. Despite these largely understood relationships, the objective measurement of physical activity is rarely performed in routine healthcare. The ability to use sensor-based approaches to accurately measure aspects of physical activity has the potential to improve many aspects of cardiovascular healthcare across the spectrum of healthcare, from prediction, prevention, diagnosis, and treatment to disease monitoring. This review discusses the potential of sensor-based measurement of physical activity to augment current cardiovascular healthcare. We highlight many factors that should be considered to maximise the benefit and reduce the risks of such an approach. Because the widespread use of such devices in society is already a reality, it is important that scientists, clinicians, and healthcare providers are aware of these considerations.

Clinicians’ Perspectives on Wearable Sensor Technology as an Alternative Bedside Monitoring Tool in Two West African Countries

OBJECTIVE

Healthcare facilities in low- and middle-income countries (LMICs), especially in Africa, suffer from a lack of continuous bedside monitoring capability, adversely affecting timely detection of hemodynamic deterioration and the opportunity for life-saving intervention. Wearable device technologies can overcome many of the challenges of conventional bedside monitors and could be viable alternatives. We assessed clinicians' perspectives on the use of a novel experimental wearable device ("biosensor") to improve bedside monitoring of pediatric patients in two West African LMICs.

METHODS

Focus groups were conducted in 3 hospitals (2 in Ghana and 1 in Liberia), in both urban and rural settings and of variable size, to elucidate clinicians' attitudes about the biosensor and to identify potential implementation needs. The focus group sessions were coded using a constant comparative method. Deductive thematic analysis was applied to pair themes with Consolidated Framework for Implementation Research (CFIR) contextual factors and domains.

RESULTS

Four focus groups were conducted in October 2019, and included 9 physicians, 20 nurses, and 20 community health workers. Fifty-two codes in four thematic areas were linked to 3 CFIR contextual factors and 9 domains. Key themes were durability and cost of the biosensor, hospital setting, and staffing concerns, which were related to the "Inner Setting" and "Characteristics of the Intervention" CFIR contextual factors. Participants, who recognized the limitations of current vital sign monitoring systems, further identified 21 clinical settings in which a biosensor could potentially be useful and expressed willingness to implement the biosensor.

CONCLUSION

Clinicians who provide care to pediatric patients in two West African LMICs suggested multiple uses of a novel experimental wearable biosensor and expressed willingness to use it for continuous bedside vital sign monitoring. They identified device design (e.g., durability, cost), hospital setting (rural vs urban), and staffing as important factors to consider during further development and implementation.

Predicting Cardiovascular Rehabilitation of Patients with Coronary Artery Disease Using Transfer Feature Learning

Cardiovascular diseases represent the leading cause of death worldwide. Thus, cardiovascular rehabilitation programs are crucial to mitigate the deaths caused by this condition each year, mainly in patients with coronary artery disease. COVID-19 was not only a challenge in this area but also an opportunity to open remote or hybrid versions of these programs, potentially reducing the number of patients who leave rehabilitation programs due to geographical/time barriers. This paper presents a method for building a cardiovascular rehabilitation prediction model using retrospective and prospective data with different features using stacked machine learning, transfer feature learning, and the joint distribution adaptation tool to address this problem. We illustrate the method over a Chilean rehabilitation center, where the prediction performance results obtained for 10-fold cross-validation achieved error levels with an NMSE of 0.03±0.013 and an R2 of 63±19%, where the best-achieved performance was an error level with a normalized mean squared error of 0.008 and an R2 up to 92%. The results are encouraging for remote cardiovascular rehabilitation programs because these models could support the prioritization of remote patients needing more help to succeed in the current rehabilitation phase.

Effect of Equipment on the Accuracy of Accelerometer-Based Human Activity Recognition in Extreme Environments

A little explored area of human activity recognition (HAR) is in people operating in relation to extreme environments, e.g., mountaineers. In these contexts, the ability to accurately identify activities, alongside other data streams, has the potential to prevent death and serious negative health events to the operators. This study aimed to address this user group and investigate factors associated with the placement, number, and combination of accelerometer sensors. Eight participants (age = 25.0 ± 7 years) wore 17 accelerometers simultaneously during lab-based simulated mountaineering activities, under a range of equipment and loading conditions. Initially, a selection of machine learning techniques was tested. Secondly, a comprehensive analysis of all possible combinations of the 17 accelerometers was performed to identify the optimum number of sensors, and their respective body locations. Finally, the impact of activity-specific equipment on the classifier accuracy was explored. The results demonstrated that the support vector machine (SVM) provided the most accurate classifications of the five machine learning algorithms tested. It was found that two sensors provided the optimum balance between complexity, performance, and user compliance. Sensors located on the hip and right tibia produced the most accurate classification of the simulated activities (96.29%). A significant effect associated with the use of mountaineering boots and a 12 kg rucksack was established.

Applying Artificial Intelligence to Wearable Sensor Data to Diagnose and Predict Cardiovascular Disease: A Review

Cardiovascular disease (CVD) is the world's leading cause of mortality. There is significant interest in using Artificial Intelligence (AI) to analyse data from novel sensors such as wearables to provide an earlier and more accurate prediction and diagnosis of heart disease. Digital health technologies that fuse AI and sensing devices may help disease prevention and reduce the substantial morbidity and mortality caused by CVD worldwide. In this review, we identify and describe recent developments in the application of digital health for CVD, focusing on AI approaches for CVD detection, diagnosis, and prediction through AI models driven by data collected from wearables. We summarise the literature on the use of wearables and AI in cardiovascular disease diagnosis, followed by a detailed description of the dominant AI approaches applied for modelling and prediction using data acquired from sensors such as wearables. We discuss the AI algorithms and models and clinical applications and find that AI and machine-learning-based approaches are superior to traditional or conventional statistical methods for predicting cardiovascular events. However, further studies evaluating the applicability of such algorithms in the real world are needed. In addition, improvements in wearable device data accuracy and better management of their application are required. Lastly, we discuss the challenges that the introduction of such technologies into routine healthcare may face.

Inertial Data-Based AI Approaches for ADL and Fall Recognition

The recognition of Activities of Daily Living (ADL) has been a widely debated topic, with applications in a vast range of fields. ADL recognition can be accomplished by processing data from wearable sensors, specially located at the lower trunk, which appears to be a suitable option in uncontrolled environments. Several authors have addressed ADL recognition using Artificial Intelligence (AI)-based algorithms, obtaining encouraging results. However, the number of ADL recognized by these algorithms is still limited, rarely focusing on transitional activities, and without addressing falls. Furthermore, the small amount of data used and the lack of information regarding validation processes are other drawbacks found in the literature. To overcome these drawbacks, a total of nine public and private datasets were merged in order to gather a large amount of data to improve the robustness of several ADL recognition algorithms. Furthermore, an AI-based framework was developed in this manuscript to perform a comparative analysis of several ADL Machine Learning (ML)-based classifiers. Feature selection algorithms were used to extract only the relevant features from the dataset’s lower trunk inertial data. For the recognition of 20 different ADL and falls, results have shown that the best performance was obtained with the K-NN classifier with the first 85 features ranked by Relief-F (98.22% accuracy). However, Ensemble Learning classifier with the first 65 features ranked by Principal Component Analysis (PCA) presented 96.53% overall accuracy while maintaining a lower classification time per window (0.039 ms), showing a higher potential for its usage in real-time scenarios in the future. Deep Learning algorithms were also tested. Despite its outcomes not being as good as in the prior procedure, their potential was also demonstrated (overall accuracy of 92.55% for Bidirectional Long Short-Term Memory (LSTM) Neural Network), indicating that they could be a valid option in the future.

Wearables and their applications for the rehabilitation of elderly people

Globally, there has been a change in the population pyramid with an accelerated aging process. This increase requires a greater challenge to maintain autonomy and independence. Currently, there are technologies developed with a focus on health. This is given by the development of wearables and their areas of applications. As a general context, this technology is characterized by the research field in energy generation, the development of external devices for human control and monitoring, clothing, smart textiles, and electronics. The latter are classified into three areas of application: monitoring and safety; fabrics, perception, and physical activity; and rehabilitation. A literature review is conducted to identify the state-of-the-art in these fields within the last years. The progress in monitoring systems and intelligent textiles is evidenced, being able to highlight remote feedback, materials, and wearability both at a commercial and user level. A discussion is included to address the main challenges and future trends in the application of wearables in elderly people.

Are Machine Learning Models on Wrist Accelerometry Robust against Differences in Physical Performance among Older Adults?

Sufficient physical activity (PA) reduces the risk of a myriad of diseases and preserves physical capabilities in later life. While there have been significant achievements in mapping accelerations to real-life movements using machine learning (ML), errors continue to be common, particularly for wrist-worn devices. It remains unknown whether ML models are robust for estimating age-related loss of physical function. In this study, we evaluated the performance of ML models (XGBoost and LASSO) to estimate the hallmark measures of PA in low physical performance (LPP) and high physical performance (HPP) groups. Our models were built to recognize PA types and intensities, identify each individual activity, and estimate energy expenditure (EE) using wrist-worn accelerometer data (33 activities per participant) from a large sample of participants (n = 247, 57% females, aged 60+ years). Results indicated that the ML models were accurate in recognizing PA by type and intensity while also estimating EE accurately. However, the models built to recognize individual activities were less robust. Across all tasks, XGBoost outperformed LASSO. XGBoost obtained F1-Scores for sedentary (0.932 ± 0.005), locomotion (0.946 ± 0.003), lifestyle (0.927 ± 0.006), and strength flexibility exercise (0.915 ± 0.017) activity type recognition tasks. The F1-Scores for recognizing low, light, and moderate activity intensity were (0.932 ± 0.005), (0.840 ± 0.004), and (0.869 ± 0.005), respectively. The root mean square error for EE estimation was 0.836 ± 0.059 METs. There was no evidence showing that splitting the participants into the LPP and HPP groups improved the models’ performance on estimating the hallmark measures of physical activities. In conclusion, using features derived from wrist-worn accelerometer data, machine learning models can accurately recognize PA types and intensities and estimate EE for older adults with high and low physical function.

Smart Clothing Framework for Health Monitoring Applications

Wearable technologies are making a significant impact on people’s way of living thanks to the advancements in mobile communication, internet of things (IoT), big data and artificial intelligence. Conventional wearable technologies present many challenges for the continuous monitoring of human health conditions due to their lack of flexibility and bulkiness in size. Recent development in e-textiles and the smart integration of miniature electronic devices into textiles have led to the emergence of smart clothing systems for remote health monitoring. A novel comprehensive framework of smart clothing systems for health monitoring is proposed in this paper. This framework provides design specifications, suitable sensors and textile materials for smart clothing (e.g., leggings) development. In addition, the proposed framework identifies techniques for empowering the seamless integration of sensors into textiles and suggests a development strategy for health diagnosis and prognosis through data collection, data processing and decision making. The conceptual technical specification of smart clothing is also formulated and presented. The detailed development of this framework is presented in this paper with selected examples. The key challenges in popularizing smart clothing and opportunities of future development in diverse application areas such as healthcare, sports and athletics and fashion are discussed.

Context-Aware Probabilistic Models for Predicting Future Sedentary Behaviors of Smartphone Users

Sedentary behaviors are now prevalent as most modern jobs are done while seated. However, such sedentary behaviors have been found to increase the risk of several ailments including diabetes, cardiovascular disease, and all-cause mortality. Current interventions are mostly reactive and are triggered after the user has already been sedentary. Behavior change theory suggests that preventive sedentary interventions, which are triggered before a person becomes sedentary, are more likely to succeed. In this paper, we characterize user patterns of sedentary behaviors by analyzing smartphone-sensor data in a real-world dataset. Our work reveals location types (where), times of day/week (when), and smartphone contexts in which sedentary behaviors are most likely. Leveraging our findings, we then propose a set of context-aware probabilistic models that can predict sedentary behaviors in advance by analyzing smartphone sensor data. Our Context-Aware Predictive (CAP) models leverage smartphone-sensed contextual variables and the user's history of sedentary behaviors to predict their future sedentary behaviors. We rigorously analyze the performance of our models and discuss the implications of our work.

The Internet of Things in Geriatric Healthcare

There is a significant increase in the geriatric population across the globe. With the increase in the number of geriatric people and their associated health issues, the need for larger healthcare resources is inevitable. Because of this, healthcare service-providing industries are facing a severe challenge. However, technological advancement in recent years has enabled researchers to develop intelligent devices to deal with the scarcity of healthcare resources. In this regard, the Internet of things (IoT) technology has been a boon for healthcare services industries. It not only allows the monitoring of the health parameters of geriatric patients from a remote location but also lets them live an independent life in a cost-efficient way. The current paper provides up-to-date comprehensive knowledge of IoT-based technologies for geriatric healthcare applications. The study also discusses the current trends, issues, challenges, and future scope of research in the area of geriatric healthcare using IoT technology. Information provided in this paper will be helpful to develop futuristic solutions and provide efficient cost-effective healthcare services to the needy.

Age Differences in Estimating Physical Activity by Wrist Accelerometry Using Machine Learning

Accelerometer-based fitness trackers and smartwatches are proliferating with incessant attention towards health tracking. Despite their growing popularity, accurately measuring hallmark measures of physical activities has yet to be accomplished in adults of all ages. In this work, we evaluated the performance of four machine learning models: decision tree, random forest, extreme gradient boosting (XGBoost) and least absolute shrinkage and selection operator (LASSO), to estimate the hallmark measures of physical activities in young (20-50 years), middle-aged (50-70 years], and older adults (70-89 years]. Our models were built to recognize physical activity types, recognize physical activity intensities, estimate energy expenditure (EE) and recognize individual physical activities using wrist-worn tri-axial accelerometer data (33 activities per participant) from a large sample of participants (n = 253, 62% women, aged 20-89 years old). Results showed that the machine learning models were quite accurate at recognizing physical activity type and intensity and estimating energy expenditure. However, models performed less optimally when recognizing individual physical activities. F1-Scores derived from XGBoost's models were high for sedentary (0.955-0.973), locomotion (0.942-0.964) and lifestyle (0.913-0.949) activity types with no apparent difference across age groups. Low (0.919-0.947), light (0.813-0.828) and moderate (0.846-0.875) physical activity intensities were also recognized accurately. The root mean square error range for EE was approximately 1 equivalent of resting EE [0.835-1.009 METs]. Generally, random forest and XGBoost models outperformed other models. In conclusion, machine learning models to label physical activity types, activity intensity and energy expenditure are accurate and there are minimal differences in their performance across young, middle-aged and older adults.

Cardiovascular and Pre-Frailty Risk Assessment during Shelter-In-Place Measures Based on Multimodal Biomarkers Collected from Smart Telemedical Wearables

Wearable devices play a growing role in healthcare applications and disease prevention. We conducted a retrospective study to assess cardiovascular and pre-frailty risk during the Covid-19 shelter-in-place measures on human activity patterns based on multimodal biomarkers collected from smartwatch sensors. For methodology validation we enrolled five adult participants (age range: 32 to 84 years; mean 57 ± 22.38; BMI: 27.80 ± 2.95 kg/m²) categorized by age who were smartwatch users and self-isolating at home during the Covid-19 pandemic. Resting heart rate, daily steps, and minutes asleep were recorded using smartwatch sensors. Overall, we created a dataset of 464 days of continuous measurement that included 50 days of self-isolation at home during the Covid-19 pandemic. Student’s t-test was used to determine significant differences between the pre-Covid-19 and Covid-19 periods. Our findings suggest that there was a significant decrease in the number of daily steps (−57.21%; −4321; 95% CI, 3722 to 4920) and resting heart rate (−4.81%; −3.04; 95% CI, 2.59 to 3.51) during the period of self−isolation compared to the time before lockdown. We found that there was a significant decrease in the number of minutes asleep (−13.48%; −57.91; 95% CI, 16.33 to 99.49) among older adults. Finally, cardiovascular and pre-frailty risk scores were calculated based on biomarkers and evaluated from the clinical perspective.

Low-Cost and Device-Free Human Activity Recognition Based on Hierarchical Learning Model

Human activity recognition (HAR) has been a vital human–computer interaction service in smart homes. It is still a challenging task due to the diversity and similarity of human actions. In this paper, a novel hierarchical deep learning-based methodology equipped with low-cost sensors is proposed for high-accuracy device-free human activity recognition. ESP8266, as the sensing hardware, was utilized to deploy the WiFi sensor network and collect multi-dimensional received signal strength indicator (RSSI) records. The proposed learning model presents a coarse-to-fine hierarchical classification framework with two-level perception modules. In the coarse-level stage, twelve statistical features of time–frequency domains were extracted from the RSSI measurements filtered by a butterworth low-pass filter, and a support vector machine (SVM) model was employed to quickly recognize the basic human activities by classifying the signal statistical features. In the fine-level stage, the gated recurrent unit (GRU), a representative type of recurrent neural network (RNN), was applied to address issues of the confused recognition of similar activities. The GRU model can realize automatic multi-level feature extraction from the RSSI measurements and accurately discriminate the similar activities. The experimental results show that the proposed approach achieved recognition accuracies of 96.45% and 94.59% for six types of activities in two different environments and performed better compared the traditional pattern-based methods. The proposed hierarchical learning method provides a low-cost sensor-based HAR framework to enhance the recognition accuracy and modeling efficiency.

Wearable Sensor Clothing for Body Movement Measurement during Physical Activities in Healthcare

This paper presents a wearable wireless system for measuring human body activities, consisting of small inertial sensor nodes and the main hub for data transmission via Bluetooth for further analysis. Unlike optical and ultrasonic technologies, the proposed solution has no movement restrictions, such as the requirement to stay in the line of sight, and it provides information on the dynamics of the human body’s poses regardless of its location. The problem of the correct placement of sensors on the body is considered, a simplified architecture of the wearable clothing is described, an experimental set-up is developed and tests are performed. The system has been tested by performing several physical exercises and comparing the performance with the commercially available BTS Bioengineering SMART DX motion capture system. The results show that our solution is more suitable for complex exercises as the system based on digital cameras tends to lose some markers. The proposed wearable sensor clothing can be used as a multi-purpose data acquisition device for application-specific data analysis, thus providing an automated tool for scientists and doctors to measure patient’s body movements.

Directing and Orienting ICT Healthcare Solutions to Address the Needs of the Aging Population

BACKGROUND

With an aging population, it is essential to maintain good health and autonomy for as long as possible. Instead of hospitalisation or institutionalisation, older people with chronic conditions can be assisted in their own home with numerous "smart" devices that support them in their activities of daily living, manage their medical conditions, and prevent fall incidents. Information and Communication Technology (ICT) solutions facilitate the monitoring and management of older people's health to improve quality of life and physical activity with a decline in caregivers' burden.

METHOD

The aim of this paper was to conduct a systematic literature review to analyse the state of the art of ICT solutions for older people with chronic conditions, and the impact of these solutions on their quality of life from a biomedical perspective.

RESULTS

By analysing the literature on the available ICT proposals, it is shown that different approaches have been deployed by noticing that the more cross-interventions are merged then the better the results are, but there is still no evidence of the effects of ICT solutions on older people's health outcomes. Furthermore, there are still unresolved ethical and legal issues.

CONCLUSION

While there has been much research and development in healthcare ICT solutions for the aging population, ICT solutions still need significant development in order to be user-oriented, affordable, and to manage chronic conditions in the aging wider population.

Smart Textiles and Sensorized Garments for Physiological Monitoring: A Review of Available Solutions and Techniques

Several wearable devices for physiological and activity monitoring are found on the market, but most of them only allow spot measurements. However, the continuous detection of physiological parameters without any constriction in time or space would be useful in several fields such as healthcare, fitness, and work. This can be achieved with the application of textile technologies for sensorized garments, where the sensors are completely embedded in the fabric. The complete integration of sensors in the fabric leads to several manufacturing techniques that allow dealing with both the technological challenges entailed by the physiological parameters under investigation, and the basic requirements of a garment such as perspiration, washability, and comfort. This review is intended to provide a detailed description of the textile technologies in terms of materials and manufacturing processes employed in the production of sensorized fabrics. The focus is pointed at the technical challenges and the advanced solutions introduced with respect to conventional sensors for recording different physiological parameters, and some interesting textile implementations for the acquisition of biopotentials, respiratory parameters, temperature and sweat are proposed. In the last section, an overview of the main garments on the market is depicted, also exploring some relevant projects under development.

Patient Monitoring by Abnormal Human Activity Recognition Based on CNN Architecture

Human action recognition has emerged as a challenging research domain for video understanding and analysis. Subsequently, extensive research has been conducted to achieve the improved performance for recognition of human actions. Human activity recognition has various real time applications, such as patient monitoring in which patients are being monitored among a group of normal people and then identified based on their abnormal activities. Our goal is to render a multi class abnormal action detection in individuals as well as in groups from video sequences to differentiate multiple abnormal human actions. In this paper, You Look only Once (YOLO) network is utilized as a backbone CNN model. For training the CNN model, we constructed a large dataset of patient videos by labeling each frame with a set of patient actions and the patient’s positions. We retrained the back-bone CNN model with 23,040 labeled images of patient’s actions for 32 epochs. Across each frame, the proposed model allocated a unique confidence score and action label for video sequences by finding the recurrent action label. The present study shows that the accuracy of abnormal action recognition is 96.8%. Our proposed approach differentiated abnormal actions with improved F1-Score of 89.2% which is higher than state-of-the-art techniques. The results indicate that the proposed framework can be beneficial to hospitals and elder care homes for patient monitoring.

A Kinematic Model of a Humanoid Lower Limb Exoskeleton with Hydraulic Actuators

Although it is well-established that exoskeletons as robots attached to the extremities of the human body increase their strength, limited studies presented a computer and mathematical model of a human leg hydraulic exoskeleton based on anthropometric data. This study aimed to examine lower limb joint angles during walking and running by using Inertial Measurement Units. The geometry and kinematic parameters were calculated. Twenty-six healthy adults participated in walking and running experiments. The geometric model of a human leg hydraulic exoskeleton was presented. Joint angle data acquired during experiments were used in the mathematical model. The position and velocity of exoskeleton actuators in each phase of movement were calculated using the MATLAB package (Matlab_R2017b, The MathWorks Company, Novi, MI, USA). The highest velocity of the knee actuator during walking and running was in the swing phase, 0.3 and 0.4 m/s, respectively. For the ankle and hip joints, the highest velocity of actuators occurred during the push-off phase. The results with 26 healthy subjects demonstrated that the system's compliance can be effectively adjusted while guiding the subjects walking in predefined trajectories. The developed mathematical model makes it possible to determine the position of lower limb segments and exoskeleton elements. The proposed model allows for calculating the position of the human leg and actuators' characteristic points.

Patterns of Use and Key Predictors for the Use of Wearable Health Care Devices by US Adults: Insights from a National Survey

BACKGROUND

Despite the growing popularity of wearable health care devices (from fitness trackes such as Fitbit to smartwatches such as Apple Watch and more sophisticated devices that can collect information on metrics such as blood pressure, glucose levels, and oxygen levels), we have a limited understanding about the actual use and key factors affecting the use of these devices by US adults.

OBJECTIVE

The main objective of this study was to examine the use of wearable health care devices and the key predictors of wearable use by US adults.

METHODS

Using a national survey of 4551 respondents, we examined the usage patterns of wearable health care devices (use of wearables, frequency of their use, and willingness to share health data from a wearable with a provider) and a set of predictors that pertain to personal demographics (age, gender, race, education, marital status, and household income), individual health (general health, presence of chronic conditions, weight perceptions, frequency of provider visits, and attitude towards exercise), and technology self-efficacy using logistic regression analysis.

RESULTS

About 30% (1266/4551) of US adults use wearable health care devices. Among the users, nearly half (47.33%) use the devices every day, with a majority (82.38% weighted) willing to share the health data from wearables with their care providers. Women (16.25%), White individuals (19.74%), adults aged 18-50 years (19.52%), those with some level of college education or college graduates (25.60%), and those with annual household incomes greater than US $75,000 (17.66%) were most likely to report using wearable health care devices. We found that the use of wearables declines with age: Adults aged >50 years were less likely to use wearables compared to those aged 18-34 years (odds ratios [OR] 0.46-0.57). Women (OR 1.26, 95% CI 0.96-1.65), White individuals (OR 1.65, 95% CI 0.97-2.79), college graduates (OR 1.05, 95% CI 0.31-3.51), and those with annual household incomes greater than US $75,000 (OR 2.6, 95% CI 1.39-4.86) were more likely to use wearables. US adults who reported feeling healthier (OR 1.17, 95% CI 0.98-1.39), were overweight (OR 1.16, 95% CI 1.06-1.27), enjoyed exercise (OR 1.23, 95% CI 1.06-1.43), and reported higher levels of technology self-efficacy (OR 1.33, 95% CI 1.21-1.46) were more likely to adopt and use wearables for tracking or monitoring their health.

CONCLUSIONS

The potential of wearable health care devices is under-realized, with less than one-third of US adults actively using these devices. With only younger, healthier, wealthier, more educated, technoliterate adults using wearables, other groups have been left behind. More concentrated efforts by clinicians, device makers, and health care policy makers are needed to bridge this divide and improve the use of wearable devices among larger sections of American society.

What Features and Functions Are Desired in Telemedical Services Targeted at Polish Older Adults Delivered by Wearable Medical Devices?-Pre-COVID-19 Flashback

The emerging wearable medical devices open up new opportunities for the provision of health services and promise to accelerate the development of novel telemedical services. The main objective of this study was to investigate the desirable features and applications of telemedical services for the Polish older adults delivered by wearable medical devices. The questionnaire study was conducted among 146 adult volunteers in two cohorts (C.1: <65 years vs. C.2: ≥65 years). The analysis was based on qualitative research and descriptive statistics. Comparisons were performed by Pearson’s chi-squared test. The questionnaire, which was divided into three parts (1-socio-demographic data, needs, and behaviors; 2-health status; 3-telemedicine service awareness and device concept study), consisted of 37 open, semi-open, or closed questions. Two cohorts were analyzed (C.1: n = 77; mean age = 32 vs. C.2: n = 69; mean age = 74). The performed survey showed that the majority of respondents were unaware of the telemedical services (56.8%). A total of 62.3% of C.1 and 34.8% of C.2 declared their understanding of telemedical services. The 10.3% of correct explanations regarding telemedical service were found among all study participants. The most desirable feature was the detection of life-threatening and health-threatening situations (65.2% vs. 66.2%). The findings suggest a lack of awareness of telemedical services and the opportunities offered by wearable telemedical devices.

EMG-Centered Multisensory Based Technologies for Pattern Recognition in Rehabilitation: State of the Art and Challenges

In the field of rehabilitation, the electromyography (EMG) signal plays an important role in interpreting patients' intentions and physical conditions. Nevertheless, utilizing merely the EMG signal suffers from difficulty in recognizing slight body movements, and the detection accuracy is strongly influenced by environmental factors. To address the above issues, multisensory integration-based EMG pattern recognition (PR) techniques have been developed in recent years, and fruitful results have been demonstrated in diverse rehabilitation scenarios, such as achieving high locomotion detection and prosthesis control accuracy. Owing to the importance and rapid development of the EMG centered multisensory fusion technologies in rehabilitation, this paper reviews both theories and applications in this emerging field. The principle of EMG signal generation and the current pattern recognition process are explained in detail, including signal preprocessing, feature extraction, classification algorithms, etc. Mechanisms of collaborations between two important multisensory fusion strategies (kinetic and kinematics) and EMG information are thoroughly explained; corresponding applications are studied, and the pros and cons are discussed. Finally, the main challenges in EMG centered multisensory pattern recognition are discussed, and a future research direction of this area is prospected.

Smart Shirts for Monitoring Physiological Parameters: Scoping Review

BACKGROUND

The recent trends of technological innovation and widescale digitization as potential solutions to challenges in health care, sports, and emergency service operations have led to the conception of smart textile technology. In health care, these smart textile systems present the potential to aid preventative medicine and early diagnosis through continuous, noninvasive tracking of physical and mental health while promoting proactive involvement of patients in their medical management. In areas such as sports and emergency response, the potential to provide comprehensive and simultaneous physiological insights across multiple body systems is promising. However, it is currently unclear what type of evidence exists surrounding the use of smart textiles for the monitoring of physiological outcome measures across different settings.

OBJECTIVE

This scoping review aimed to systematically survey the existing body of scientific literature surrounding smart textiles in their most prevalent form, the smart shirt, for monitoring physiological outcome measures.

METHODS

A total of 5 electronic bibliographic databases were systematically searched (Ovid Medical Literature Analysis and Retrieval System Online, Excerpta Medica database, Scopus, Cumulative Index to Nursing and Allied Health Literature, and SPORTDiscus). Publications from the inception of the database to June 24, 2019 were reviewed. Nonindexed literature relevant to this review was also systematically searched. The results were then collated, summarized, and reported.

RESULTS

Following the removal of duplicates, 7871 citations were identified. On the basis of title and abstract screening, 7632 citations were excluded, whereas 239 were retrieved and assessed for eligibility. Of these, 101 citations were included in the final analysis. Included studies were categorized into four themes: (1) prototype design, (2) validation, (3) observational, and (4) reviews. Among the 101 analyzed studies, prototype design was the most prevalent theme (50/101, 49.5%), followed by validation (29/101, 28.7%), observational studies (21/101, 20.8%), and reviews (1/101, 0.1%). Presented prototype designs ranged from those capable of monitoring one physiological metric to those capable of monitoring several simultaneously. In 29 validation studies, 16 distinct smart shirts were validated against reference technology under various conditions and work rates, including rest, submaximal exercise, and maximal exercise. The identified observational studies used smart shirts in clinical, healthy, and occupational populations for aims such as early diagnosis and stress detection. One scoping review was identified, investigating the use of smart shirts for electrocardiograph signal monitoring in cardiac patients.

CONCLUSIONS

Although smart shirts have been found to be valid and reliable in the monitoring of specific physiological metrics, results were variable for others, demonstrating the need for further systematic validation. Analysis of the results has also demonstrated gaps in knowledge, such as a considerable lag of validation and observational studies in comparison with prototype design and limited investigation using smart shirts in pediatric, elite sports, and emergency service populations.

Signal Processing and Analysis of Electrical Circuit

The analysis of electrical circuits is an essential task in the evaluation of electrical systems [...]

Towards The Internet-of-Smart-Clothing: A Review on IoT Wearables and Garments for Creating Intelligent Connected E-Textiles

Technology has become ubiquitous, it is all around us and is becoming part of us. Together with the rise of the Internet-of-Things (IoT) paradigm and enabling technologies (e.g., Augmented Reality (AR), Cyber-Physical Systems, Artificial Intelligence (AI), blockchain or edge computing), smart wearables and IoT-based garments can potentially have a lot of influence by harmonizing functionality and the delight created by fashion. Thus, smart clothes look for a balance among fashion, engineering, interaction, user experience, cybersecurity, design and science to reinvent technologies that can anticipate needs and desires. Nowadays, the rapid convergence of textile and electronics is enabling the seamless and massive integration of sensors into textiles and the development of conductive yarn. The potential of smart fabrics, which can communicate with smartphones to process biometric information such as heart rate, temperature, breathing, stress, movement, acceleration, or even hormone levels, promises a new era for retail. This article reviews the main requirements for developing smart IoT-enabled garments and shows smart clothing potential impact on business models in the medium-term. Specifically, a global IoT architecture is proposed, the main types and components of smart IoT wearables and garments are presented, their main requirements are analyzed and some of the most recent smart clothing applications are studied. In this way, this article reviews the past and present of smart garments in order to provide guidelines for the future developers of a network where garments will be connected like other IoT objects: the Internet-of-Smart-Clothing.

A Survey of the Techniques for The Identification and Classification of Human Actions from Visual Data

Recognition of human actions form videos has been an active area of research because it has applications in various domains. The results of work in this field are used in video surveillance, automatic video labeling and human-computer interaction, among others. Any advancements in this field are tied to advances in the interrelated fields of object recognition, spatio- temporal video analysis and semantic segmentation. Activity recognition is a challenging task since it faces many problems such as occlusion, view point variation, background differences and clutter and illumination variations. Scientific achievements in the field have been numerous and rapid as the applications are far reaching. In this survey, we cover the growth of the field from the earliest solutions, where handcrafted features were used, to later deep learning approaches that use millions of images and videos to learn features automatically. By this discussion, we intend to highlight the major breakthroughs and the directions the future research might take while benefiting from the state-of-the-art methods.