Shivayogi V. Hiremath

Wearable Internet of Things: Concept, architectural components and promises for person-centered healthcare

The proliferation of mobile devices, ubiquitous internet, and cloud computing has sparked a new era of Internet of Things (IoT), thus allowing researchers to create application-specific solutions based on the interconnection between physical objects and the internet. Recently, wearable devices are rapidly emerging and forming a new segment-“Wearable IoT (WIoT)” due to their capability of sensing, computing and communication. Future generations of WIoT promise to transform the healthcare sector, wherein individuals are seamlessly tracked by wearable sensors for personalized health and wellness information-body vital parameters, physical activity, behaviors, and other critical parameters impacting quality of daily life. This paper presents an effort to conceptualize WIoT in terms of their design, function, and applications. We discuss the building blocks of WIoT-including wearable sensors, internet-connected gateways and cloud and big data support-that are key to its future success in healthcare domain applications. We also present a new system science for WIoT that suggests future directions, encompassing operational and clinical aspects.

Evaluation of activity monitors in manual wheelchair users with paraplegia

Abstract Objective: The aim of this study was to evaluate the performance of SenseWear® (SW) and RT3 activity monitors (AMs) in estimating energy expenditure (EE) in manual wheelchair users (MWUs) with paraplegia for a variety of physical activities. Methods: Twenty-four subjects completed four activities including resting, wheelchair propulsion, arm-ergometry exercise, and deskwork. The criterion EE was measured by a K4b2 portable metabolic cart. The EE estimated by the SW and RT3 were compared with the criterion EE by the absolute differences and absolute percentage errors. Intraclass correlations and the Bland and Altman plots were also used to assess the agreements between the two AMs and the metabolic cart. Correlations between the criterion EE and the estimated EE and sensors data from the AMs were evaluated. Results: The EE estimation errors for the AMs varied from 24.4 to 125.8% for the SW and from 22.0 to 52.8% for the RT3. The intraclass correlation coefficients (ICCs) between the criterion EE and the EE estimated by the two AMs for each activity and all activities as a whole were considered poor with all the ICCs smaller than 0.75. Except for deskwork, the EE from the SW was more correlated to the criterion EE than the EE from the RT3. Conclusion: The results indicate that neither of the AMs is an appropriate tool for quantifying physical activity in MWUs with paraplegia. However, the accuracy of EE estimation could be potentially improved by building new regression models based on wheelchair-related activities.

Predicting Energy Expenditure of Manual Wheelchair Users With Spinal Cord Injury Using a Multisensor-Based Activity Monitor.

OBJECTIVE To develop and evaluate new energy expenditure (EE) prediction models for manual wheelchair users (MWUs) with spinal cord injury (SCI) based on a commercially available multisensor-based activity monitor. DESIGN Cross-sectional. SETTING Laboratory. PARTICIPANTS Volunteer sample of MWUs with SCI (N=45). INTERVENTION Subjects were asked to perform 4 activities including resting, wheelchair propulsion, arm-ergometer exercise, and deskwork. Criterion EE using a metabolic cart and raw sensor data from a multisensor activity monitor was collected during each of these activities. MAIN OUTCOME MEASURES Two new EE prediction models including a general model and an activity-specific model were developed using enhanced all-possible regressions on 36 MWUs and tested on the remaining 9 MWUs. RESULTS The activity-specific and general EE prediction models estimated the EE significantly better than the manufacturers model. The average EE estimation error using the manufacturers model and the new general and activity-specific models for all activities combined was -55.31% (overestimation), 2.30% (underestimation), and 4.85%, respectively. The average EE estimation error using the manufacturers model, the new general model, and activity-specific models for various activities varied from -19.10% to -89.85%, -18.13% to 25.13%, and -4.31% to 9.93%, respectively. CONCLUSIONS The predictors for the new models were based on accelerometer and demographic variables, indicating that movement and subject parameters were necessary in estimating the EE. The results indicate that the multisensor activity monitor with new prediction models can be used to estimate EE in MWUs with SCI during wheelchair-related activities mentioned in this study.

Evaluation of activity monitors to estimate energy expenditure in manual wheelchair users

In an effort to make activity monitors usable by manual wheelchair users with Spinal Cord Injury (SCI), our study examines the validity of SenseWear® Armband (SenseWear) and RT3 in assessing energy expenditure (EE) during wheelchair related activities. This paper presents the data obtained from six subjects (n=6) with SCI performing three activities, including wheelchair propulsion, armergometer exercise and deskwork. The analysis presented here compares the EE estimated from the SenseWear and the RT3 with respect to the EE measured from a portable metabolic cart. It was found that the SenseWear overestimated EE for resting (+5.78%), wheelchair propulsion (+88.20%, +46.20%, and +138.21% for the three trials at different intensities, respectively), arm-ergometer exercise (+55.05%, +26.91%, and +39.17% for the three trials at different intensities, respectively) and deskwork (+13.11%). The results also indicate that RT3 underestimated EE for resting (-3.06%), wheelchair propulsion (−24.23%, −19.42%, and −9.98% for the three trials at different intensities, respectively), arm-ergometer exercise (−49.06%, −53.69% and −52.08 for the three trials at different intensities, respectively) and measured EE relatively accurate for deskwork. Good and moderate Intraclass correlations were found between EE measured by metabolic cart and EE estimated by SenseWear (0.787, p<0.0001) and RT3 (0.705, p<0.0001). Weka, machine learning software, was used to select attributes and model EE equations for the SenseWear and the RT3. Excellent and good Intraclass correlations were found between the EE measured by the metabolic cart and the estimated EE based on the models for SenseWear (0.944, p<0.0001) and RT3 (0.821, p<0.0001). Future work will test more subjects to refine the model and provide manual wheelchair users with a valid tool to gauge their daily physical activity and EE.

Brain computer interface learning for systems based on electrocorticography and intracortical microelectrode arrays

A brain-computer interface (BCI) system transforms neural activity into control signals for external devices in real time. A BCI user needs to learn to generate specific cortical activity patterns to control external devices effectively. We call this process BCI learning, and it often requires significant effort and time. Therefore, it is important to study this process and develop novel and efficient approaches to accelerate BCI learning. This article reviews major approaches that have been used for BCI learning, including computer-assisted learning, co-adaptive learning, operant conditioning, and sensory feedback. We focus on BCIs based on electrocorticography and intracortical microelectrode arrays for restoring motor function. This article also explores the possibility of brain modulation techniques in promoting BCI learning, such as electrical cortical stimulation, transcranial magnetic stimulation, and optogenetics. Furthermore, as proposed by recent BCI studies, we suggest that BCI learning is in many ways analogous to motor and cognitive skill learning, and therefore skill learning should be a useful metaphor to model BCI learning.

Physical activity classification utilizing SenseWear activity monitor in manual wheelchair users with spinal cord injury

Study design:Validation.Objectives:The primary aim of this study was to develop and evaluate activity classification algorithms for a multisensor-based SenseWear (SW) activity monitor that can recognize wheelchair-related activities performed by manual wheelchair users (MWUs) with spinal cord injury (SCI). The secondary aim was to evaluate how the accuracy in activity classification affects the estimation of energy expenditure (EE) in MWUs with SCI.Setting:University-based laboratory.Methods:Forty-five MWUs with SCI wore a SW on their upper arm and participated in resting, wheelchair propulsion, arm-ergometery and deskwork activities. The investigators annotated the start and end of each activity trial while the SW collected multisensor data and a portable metabolic cart collected criterion EE. Three methods including linear discriminant analysis, quadratic discriminant analysis (QDA), and Naïve Bayes (NB) were used to develop classification algorithms for four activities based on the training data set from 36 subjects.Results:The classification accuracy was 96.3% for QDA and 94.8% for NB when the classification algorithms were tested on the validation data set from nine subjects. The average EE estimation errors using the activity-specific EE prediction model were 5.3±21.5% and 4.6±22.8% when the QDA and NB classification algorithms were applied, respectively, as opposed to 4.9±20.7% when 100% classification accuracy was assumed.Conclusion:The high classification accuracy and low EE estimation errors suggest that the SW can be used by researchers and clinicians to classify and estimate the EE for the four activities tested in this study among MWUs with SCI.

Development and evaluation of a gyroscope-based wheel rotation monitor for manual wheelchair users

Abstract Objective To develop and evaluate a wireless gyroscope-based wheel rotation monitor (G-WRM) that can estimate speeds and distances traveled by wheelchair users during regular wheelchair propulsion as well as wheelchair sports such as handcycling, and provide users with real-time feedback through a smartphone application. Methods The speeds and the distances estimated by the G-WRM were compared with the criterion measures by calculating absolute difference, mean difference, and percentage errors during a series of laboratory-based tests. Intraclass correlations (ICC) and the Bland–Altman plots were also used to assess the agreements between the G-WRM and the criterion measures. In addition, battery life and wireless data transmission tests under a number of usage conditions were performed. Results The percentage errors for the angular velocities, speeds, and distances obtained from three prototype G-WRMs were less than 3% for all the test trials. The high ICC values (ICC (3,1) > 0.94) and the Bland–Altman plots indicate excellent agreement between the estimated speeds and distances by the G-WRMs and the criterion measures. The battery life tests showed that the device could last for 35 hours in wireless mode and 139 hours in secure digital card mode. The wireless data transmission tests indicated less than 0.3% of data loss. Conclusion The results indicate that the G-WRM is an appropriate tool for tracking a spectrum of wheelchair-related activities from regular wheelchair propulsion to wheelchair sports such as handcycling. The real-time feedback provided by the G-WRM can help wheelchair users self-monitor their everyday activities.

Physical activity monitoring and sharing platform for manual wheelchair users

Unlike able-bodied ambulatory population, wheelchair users do not have adequate access to technologies that monitor and motivate physical activity (PA). We developed a physical activity monitoring and sharing platform (PAMS) especially suited for capturing PA that are part of the lifestyle in wheelchair users and motivating them to be physically active via social networking based applications. This paper describes the general infrastructure and components of the prototype PAMS. The monitoring unit is designed to capture the activity type, amount, and associated energy expenditure of wheelchair users. The sharing unit consists of a web-based application and an Android-based mobile application built on top of Facebook platform and allows wheelchair users to self-monitor and share their PA information with their community of interest. The prototype PAMS is being evaluated for its reliability in capturing PA, validity in measuring PA parameters, and usability of the sharing applications among wheelchair users. We expect the PAMS will enable wheelchair users to track their own PA participation and become more physically active, leading to better overall health, greater community participation, and higher quality of life.

Detection of wheelchair user activities using wearable sensors

Wearable sensors are increasingly used to monitor and quantify physical activity types and levels in a real-life environment. In this project we studied the activity classification in manual wheelchair users using wearable sensors. Twenty-seven subjects performed a series of representative activities of daily living in a semi-structured setting with a wheelchair propulsion monitoring device (WPMD) attached to their upper limb and their wheelchair. The WPMD included a wheel rotation datalogger that collected wheelchair movements and an eWatch that collected tri-axial acceleration on the wrist. Features were extracted from the sensors and fed into four machine learning algorithms to classify the activities into three and four categories. The results indicated that these algorithms were able to classify these activities into three categories including self propulsion, external pushing, and sedentary activity with an accuracy of 89.4-91.9%.

Regression equations for RT3 activity monitors to estimate energy expenditure in manual wheelchair users

Activity monitors (AMs) can assist persons with Spinal Cord Injury (SCI) who use manual wheelchairs to self-assess regular physical activity to move towards healthier lifestyles. In this study we evaluated the validity of an accelerometer-based RT3 AM in predicting energy expenditure (EE) of manual wheelchair users with SCI. Twenty-four subjects performed four types of physical activities including wheelchair propulsion, arm-ergometry exercise, deskwork, and resting in a laboratory setting. Subjects wore two RT3 AMs: an RT3 around the waist (RT3W) per the manufacturers instruction and an RT3 on the upper arm (RT3A). Criterion EE was collected by a portable metabolic system. The absolute EE estimation error for the RT3W varied from 21.3%-55.2% for different activities. Two EE prediction equations (general and activity-specific) were developed from 19 randomly selected subjects and validated on the remaining 4 subjects for the RT3A, RT3W, and RT3 AMs combined. The results showed that the general and activity-specific regression equations for the RT3A performed better than the RT3W and similar to the RT3 AMs combined. The general EE equation for RT3A consisted of both the demographic variable weight and accelerometer variables showing it is sensitive to subject parameters and upper extremity movement. The activity-specific EE equations for RT3A showed demographic variable weight to be a significant predictor during resting and deskwork and accelerometer variables along with weight to be significant predictors during propulsion and arm-ergometry. The validation results from the activity-specific equations for the RT3A showed that the absolute EE estimation error varied from 12.2%-38.1%. Future work will recruit more subjects and refine the prediction equations for the RT3 AM to quantify physical activity in MWUs with SCI