Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299382
Brianne Y. Williams, Brandon Allen, Hanna True, N. Fell, D. Levine, Mina Sartipi
With the growing population of the elderly, the need for mobile health solutions is also increasing. We propose a system which allows patients to perform basic stroke rehabilitation tests from their own homes. This drastically cuts down on patient/therapist visits, freeing up therapists for more pressing work. This paper will focus on the Timed Up and Go Test (TUG) portion of our system. Our system requires very little setup, is relatively low cost, and is able to provide immediate feedback to the user. Our results show that the timing portion of the system is on par with and in some cases may be better than current physical therapy methods, with an RMSE of 0.907 seconds. Our system also tracks the angles of the knee and ankle. The knee results are more accurate than similar systems, with an RMSE of 3.03°.
{"title":"A real-time, mobile timed up and go system","authors":"Brianne Y. Williams, Brandon Allen, Hanna True, N. Fell, D. Levine, Mina Sartipi","doi":"10.1109/BSN.2015.7299382","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299382","url":null,"abstract":"With the growing population of the elderly, the need for mobile health solutions is also increasing. We propose a system which allows patients to perform basic stroke rehabilitation tests from their own homes. This drastically cuts down on patient/therapist visits, freeing up therapists for more pressing work. This paper will focus on the Timed Up and Go Test (TUG) portion of our system. Our system requires very little setup, is relatively low cost, and is able to provide immediate feedback to the user. Our results show that the timing portion of the system is on par with and in some cases may be better than current physical therapy methods, with an RMSE of 0.907 seconds. Our system also tracks the angles of the knee and ankle. The knee results are more accurate than similar systems, with an RMSE of 3.03°.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114683292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299410
D. Ravì, Benny P. L. Lo, Guang-Zhong Yang
Assessment of food intake has a wide range of applications in public health and life-style related chronic disease management. In this paper, we propose a real-time food recognition platform combined with daily activity and energy expenditure estimation. In the proposed method, food recognition is based on hierarchical classification using multiple visual cues, supported by efficient software implementation suitable for realtime mobile device execution. A Fischer Vector representation together with a set of linear classifiers are used to categorize food intake. Daily energy expenditure estimation is achieved by using the built-in inertial motion sensors of the mobile device. The performance of the vision-based food recognition algorithm is compared to the current state-of-the-art, showing improved accuracy and high computational efficiency suitable for realtime feedback. Detailed user studies have also been performed to demonstrate the practical value of the software environment.
{"title":"Real-time food intake classification and energy expenditure estimation on a mobile device","authors":"D. Ravì, Benny P. L. Lo, Guang-Zhong Yang","doi":"10.1109/BSN.2015.7299410","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299410","url":null,"abstract":"Assessment of food intake has a wide range of applications in public health and life-style related chronic disease management. In this paper, we propose a real-time food recognition platform combined with daily activity and energy expenditure estimation. In the proposed method, food recognition is based on hierarchical classification using multiple visual cues, supported by efficient software implementation suitable for realtime mobile device execution. A Fischer Vector representation together with a set of linear classifiers are used to categorize food intake. Daily energy expenditure estimation is achieved by using the built-in inertial motion sensors of the mobile device. The performance of the vision-based food recognition algorithm is compared to the current state-of-the-art, showing improved accuracy and high computational efficiency suitable for realtime feedback. Detailed user studies have also been performed to demonstrate the practical value of the software environment.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132362765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299375
Katharina Full, Heike Leutheuser, J. Schlessman, R. Armitage, B. Eskofier
Athletes and their coaches aim for enhancing the sports performance. Collecting data from athletes, transforming them into useful information related to their sports performance (e.g., their type of gait), and transmitting the information to the coaches supports the enhancement. The types of gait standing, walking, and running were often examined. Lack of research remains for the two types of running, jogging and sprinting. In this work, standing, walking, jogging, and sprinting were classified with a single inertial-magnetic measurement unit that was placed at a novel position at the trunk. A comparison was made between classification systems using different combinations of accelerometer, gyroscope, and magnetometer data as well as different classifiers (Naïve Bayes, k-Nearest Neighbors, Support Vector Machine, Adaptive Boosting). After collecting data from 15 male subjects, the data were preprocessed, features were extracted and selected, and the data were classified. All classification systems were successful. With a mean true positive rate of 95.68% ±1.80%, the classification system using accelerometer and gyroscope data as well as the Naïve Bayes classifier performed best. The classification system can be used for applications in sport and sports performance analysis in particular.
{"title":"Comparative study on classifying gait with a single trunk-mounted inertial-magnetic measurement unit","authors":"Katharina Full, Heike Leutheuser, J. Schlessman, R. Armitage, B. Eskofier","doi":"10.1109/BSN.2015.7299375","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299375","url":null,"abstract":"Athletes and their coaches aim for enhancing the sports performance. Collecting data from athletes, transforming them into useful information related to their sports performance (e.g., their type of gait), and transmitting the information to the coaches supports the enhancement. The types of gait standing, walking, and running were often examined. Lack of research remains for the two types of running, jogging and sprinting. In this work, standing, walking, jogging, and sprinting were classified with a single inertial-magnetic measurement unit that was placed at a novel position at the trunk. A comparison was made between classification systems using different combinations of accelerometer, gyroscope, and magnetometer data as well as different classifiers (Naïve Bayes, k-Nearest Neighbors, Support Vector Machine, Adaptive Boosting). After collecting data from 15 male subjects, the data were preprocessed, features were extracted and selected, and the data were classified. All classification systems were successful. With a mean true positive rate of 95.68% ±1.80%, the classification system using accelerometer and gyroscope data as well as the Naïve Bayes classifier performed best. The classification system can be used for applications in sport and sports performance analysis in particular.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"486 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133759467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299408
O. Dehzangi, Cayce Williams
The objective of this paper is to propose initial steps towards the design of the next generation multi-modal driver monitoring platform to be facilitated in urban driving scenarios. The main novel ingredient is the adaptation of the proposed driver safety platform operation to the individual driver behavior (e.g., aggressive driving) and his/her current biological state (e.g., attention level). We have developed a robust driver monitoring platform consisting of automotive sensors (i.e. OBD-II) that capture the real-time information of the vehicle and driving behavior as well as a heterogeneous wearable body sensor network that collects the driver biometrics (e.g., electroencephalography (EEG) and electrocardiogram (ECG)). In this investigation, we intend to examine the effect of the driving condition on the driver distraction as one aspect of the driver monitoring platform. Distraction during driving has been identified as a leading cause of car accidents. Our aim is to investigate EEG-based brain biometric measures in response to driving distraction. Using our proposed driver monitoring platform, we study driver cognition under real driving task in two different road conditions including of peak and non-peak traffic periods. Five subjects are recruited in our study and their EEG signals are recorded throughout the driving experience. The experimental results illustrated that the power of theta and beta bands in the frontal cortex were substantially correlated with the road condition. Our investigations suggested that the features extracted from the time-frequency brain dynamics can be employed as statistical measures of the biometric indexes for early detection of driver distraction in real driving scenarios.
{"title":"Towards multi-modal wearable driver monitoring: Impact of road condition on driver distraction","authors":"O. Dehzangi, Cayce Williams","doi":"10.1109/BSN.2015.7299408","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299408","url":null,"abstract":"The objective of this paper is to propose initial steps towards the design of the next generation multi-modal driver monitoring platform to be facilitated in urban driving scenarios. The main novel ingredient is the adaptation of the proposed driver safety platform operation to the individual driver behavior (e.g., aggressive driving) and his/her current biological state (e.g., attention level). We have developed a robust driver monitoring platform consisting of automotive sensors (i.e. OBD-II) that capture the real-time information of the vehicle and driving behavior as well as a heterogeneous wearable body sensor network that collects the driver biometrics (e.g., electroencephalography (EEG) and electrocardiogram (ECG)). In this investigation, we intend to examine the effect of the driving condition on the driver distraction as one aspect of the driver monitoring platform. Distraction during driving has been identified as a leading cause of car accidents. Our aim is to investigate EEG-based brain biometric measures in response to driving distraction. Using our proposed driver monitoring platform, we study driver cognition under real driving task in two different road conditions including of peak and non-peak traffic periods. Five subjects are recruited in our study and their EEG signals are recorded throughout the driving experience. The experimental results illustrated that the power of theta and beta bands in the frontal cortex were substantially correlated with the road condition. Our investigations suggested that the features extracted from the time-frequency brain dynamics can be employed as statistical measures of the biometric indexes for early detection of driver distraction in real driving scenarios.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132748817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299377
A. Q. Javaid, Nathaniel Forrest Fesmire, M. A. Weitnauer, O. Inan
Continuous measurement of cardiac time intervals throughout normal activities of daily living is of interest for both chronic disease management and preventive wellness monitoring. Systolic time intervals in particular - i.e., pre-ejection period (PEP) and left ventricular ejection time (LVET) - have been shown to be relevant to assessing myocardial health and performance, but are challenging to measure with wearable sensors. In this paper, we present novel methods for estimating PEP and LVET from a single three-axis accelerometer placed at the sternum, based on the measurement of cardiogenic vibrations: seismocardiography (SCG) and ballistocardiography (BCG). Although such signals have been examined in the existing literature, the analysis and interpretation has focused mainly on the dorso-ventral components only in the context of systolic time interval estimation. In this paper, we find that features extracted from the head-to-foot accelerations yield better correlations to PEP measured from impedance cardiogram (ICG) than standard approaches based on dorso-ventral components. Additionally, we examine the effects of postural variations on the correlation between PEP estimated from accelerometer and ICG signals and also on correlation between LVET estimated from both sensors. We determine that such correlations are robust to postural changes. Based on these findings, we anticipate that wearable, accelerometer based vibration measurements from standing subjects can be used for robust systolic time interval estimation in a variety of ubiquitous cardiovascular health and fitness sensing applications.
{"title":"Towards robust estimation of systolic time intervals using head-to-foot and dorso-ventral components of sternal acceleration signals","authors":"A. Q. Javaid, Nathaniel Forrest Fesmire, M. A. Weitnauer, O. Inan","doi":"10.1109/BSN.2015.7299377","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299377","url":null,"abstract":"Continuous measurement of cardiac time intervals throughout normal activities of daily living is of interest for both chronic disease management and preventive wellness monitoring. Systolic time intervals in particular - i.e., pre-ejection period (PEP) and left ventricular ejection time (LVET) - have been shown to be relevant to assessing myocardial health and performance, but are challenging to measure with wearable sensors. In this paper, we present novel methods for estimating PEP and LVET from a single three-axis accelerometer placed at the sternum, based on the measurement of cardiogenic vibrations: seismocardiography (SCG) and ballistocardiography (BCG). Although such signals have been examined in the existing literature, the analysis and interpretation has focused mainly on the dorso-ventral components only in the context of systolic time interval estimation. In this paper, we find that features extracted from the head-to-foot accelerations yield better correlations to PEP measured from impedance cardiogram (ICG) than standard approaches based on dorso-ventral components. Additionally, we examine the effects of postural variations on the correlation between PEP estimated from accelerometer and ICG signals and also on correlation between LVET estimated from both sensors. We determine that such correlations are robust to postural changes. Based on these findings, we anticipate that wearable, accelerometer based vibration measurements from standing subjects can be used for robust systolic time interval estimation in a variety of ubiquitous cardiovascular health and fitness sensing applications.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125986570","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299350
Nicholas Constant, Orrett Douglas-Prawl, Samuel Johnson, K. Mankodiya
The concurrent popularity of wearable sensors and Internet-of-Things (IoT) brings significant benefits to body sensor networks (BSN) that could communicate with the cloud computing platforms for bringing interoperability in health and wellness monitoring. We designed Pulse-Glasses that are cloud-connected, wearable, smart eyeglasses for unobtrusive and continuous heart rate (HR) monitoring. We 3D-printed the first prototype of Pulse-Glasses that use a photoplethysmography (PPG) sensor on one of the nose-pads to collect HR data. We integrated other circuits including an embedded board with Bluetooth low energy (BLE) and a rechargeable battery inside the two temples of Pulse-Glasses. We implemented IoT functionalities such that HR data are recorded from Pulse-Glasses, visualized on an Android smartphone, and stored seamlessly on the cloud. In this paper, we present the developments of Pulse-Glasses hardware including IoT services and the preliminary results from validation experiments. We compared Pulse-Glasses with a laboratory ECG system to cross-validate HR data collected during various activities-sitting, talking, and walking-performed by a participant. We used Pulse-Glasses to record HR data of a driver to test IoT functionalities of location services and BLE and cloud connectivity. The first set of results is promising and demonstrates the prospect of Pulse-Glasses in the field of cloud-connected BSN.
{"title":"Pulse-Glasses: An unobtrusive, wearable HR monitor with Internet-of-Things functionality","authors":"Nicholas Constant, Orrett Douglas-Prawl, Samuel Johnson, K. Mankodiya","doi":"10.1109/BSN.2015.7299350","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299350","url":null,"abstract":"The concurrent popularity of wearable sensors and Internet-of-Things (IoT) brings significant benefits to body sensor networks (BSN) that could communicate with the cloud computing platforms for bringing interoperability in health and wellness monitoring. We designed Pulse-Glasses that are cloud-connected, wearable, smart eyeglasses for unobtrusive and continuous heart rate (HR) monitoring. We 3D-printed the first prototype of Pulse-Glasses that use a photoplethysmography (PPG) sensor on one of the nose-pads to collect HR data. We integrated other circuits including an embedded board with Bluetooth low energy (BLE) and a rechargeable battery inside the two temples of Pulse-Glasses. We implemented IoT functionalities such that HR data are recorded from Pulse-Glasses, visualized on an Android smartphone, and stored seamlessly on the cloud. In this paper, we present the developments of Pulse-Glasses hardware including IoT services and the preliminary results from validation experiments. We compared Pulse-Glasses with a laboratory ECG system to cross-validate HR data collected during various activities-sitting, talking, and walking-performed by a participant. We used Pulse-Glasses to record HR data of a driver to test IoT functionalities of location services and BLE and cloud connectivity. The first set of results is promising and demonstrates the prospect of Pulse-Glasses in the field of cloud-connected BSN.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130975547","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299381
Arturo Guizar, A. Ouni, C. Goursaud, Claude Chaudet, J. Gorce
In the context of radiolocation in Wireless Body Area Networks (WBANs), nodes positions can be estimated through time-based ranging algorithms. For instance, the distance separating a couple of nodes can be estimated accurately by measuring the Round Trip Time of Flight of an Impulse Radio Ultra Wideband (IR-UWB) link. This measure usually relies on two or three messages transactions. Such exchanges take time and a rapid mobility of the nodes can reduce the ranging accuracy and consequently impact nodes localization process. In this paper, we quantify this localization error by confronting two broadcast-based optimized implementations of the three-way ranging algorithm with real mobility traces, acquired through a motion capture system. We then evaluate, in the same scenarios, the impact of the MAC-level scheduling of the packets within a TDMA frame localization accuracy. The results, obtained with the WSNet simulator, show that MAC scheduling can be utilized to mitigate the effect of nodes mobility.
{"title":"Quantifying the impact of scheduling and mobility on IR-UWB localization in body area networks","authors":"Arturo Guizar, A. Ouni, C. Goursaud, Claude Chaudet, J. Gorce","doi":"10.1109/BSN.2015.7299381","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299381","url":null,"abstract":"In the context of radiolocation in Wireless Body Area Networks (WBANs), nodes positions can be estimated through time-based ranging algorithms. For instance, the distance separating a couple of nodes can be estimated accurately by measuring the Round Trip Time of Flight of an Impulse Radio Ultra Wideband (IR-UWB) link. This measure usually relies on two or three messages transactions. Such exchanges take time and a rapid mobility of the nodes can reduce the ranging accuracy and consequently impact nodes localization process. In this paper, we quantify this localization error by confronting two broadcast-based optimized implementations of the three-way ranging algorithm with real mobility traces, acquired through a motion capture system. We then evaluate, in the same scenarios, the impact of the MAC-level scheduling of the packets within a TDMA frame localization accuracy. The results, obtained with the WSNet simulator, show that MAC scheduling can be utilized to mitigate the effect of nodes mobility.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127452535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299352
M. Buller, Alexander P. Welles, Michelle Stevens, Jayme Leger, A. Gribok, O. Jenkins, K. Friedl, W. Rumpler
This experiment demonstrated that automated pace guidance generated from real-time physiological monitoring allowed less stressful completion of a timed (60 minute limit) 5 mile treadmill exercise. An optimal pacing policy was estimated from a Markov decision process that balanced the goals of the movement task and the thermal-work strain safety constraints. The machine guided pace was based on current physiological strain index (PSI), the time, and the distance already completed. Fourteen healthy and fit young subjects participated in the study (9 men, 5 women). Each participated in an unguided exercise session followed by a guided one. In the unguided session, they were instructed to complete 5 miles in 60 minutes and to try to finish at the lowest body temperature possible; in the guided sessions, participants were instructed to match machine-provided pacing guidance provided every 2 minutes. Continuous real-time measures of heart rate and core body temperature were obtained from a wearable Hidalgo EquivitalTM EQ-02 and the MiniMitter Jonah thermometer pill. Of the fourteen subjects, 13 completed the 5 miles in one hour for the unguided session; at least three different self-pacing strategies were observed, with an alternating speed proving to be most effective. In the guided sessions, 6 subjects were stopped by the machine guidance for exceeding the algorithms PSI “safety” limit. Eight subjects were guided to complete the task with significantly lower PSIs. The results indicate that machine guided advice shows promise for preventing hyperthermia and improving outcomes for performers of an unfamiliar task.
{"title":"Automated guidance from physiological sensing to reduce thermal-work strain levels on a novel task","authors":"M. Buller, Alexander P. Welles, Michelle Stevens, Jayme Leger, A. Gribok, O. Jenkins, K. Friedl, W. Rumpler","doi":"10.1109/BSN.2015.7299352","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299352","url":null,"abstract":"This experiment demonstrated that automated pace guidance generated from real-time physiological monitoring allowed less stressful completion of a timed (60 minute limit) 5 mile treadmill exercise. An optimal pacing policy was estimated from a Markov decision process that balanced the goals of the movement task and the thermal-work strain safety constraints. The machine guided pace was based on current physiological strain index (PSI), the time, and the distance already completed. Fourteen healthy and fit young subjects participated in the study (9 men, 5 women). Each participated in an unguided exercise session followed by a guided one. In the unguided session, they were instructed to complete 5 miles in 60 minutes and to try to finish at the lowest body temperature possible; in the guided sessions, participants were instructed to match machine-provided pacing guidance provided every 2 minutes. Continuous real-time measures of heart rate and core body temperature were obtained from a wearable Hidalgo EquivitalTM EQ-02 and the MiniMitter Jonah thermometer pill. Of the fourteen subjects, 13 completed the 5 miles in one hour for the unguided session; at least three different self-pacing strategies were observed, with an alternating speed proving to be most effective. In the guided sessions, 6 subjects were stopped by the machine guidance for exceeding the algorithms PSI “safety” limit. Eight subjects were guided to complete the task with significantly lower PSIs. The results indicate that machine guided advice shows promise for preventing hyperthermia and improving outcomes for performers of an unfamiliar task.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114370517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299356
J. Williamson, Andrew Dumas, G. Ciccarelli, A. Hess, B. Telfer, M. Buller
Heavy loads increase the risk of musculoskeletal injury for foot soldiers and first responders. Continuous monitoring of load carriage in the field has proven difficult. We propose an algorithm for estimating load from a single body-worn accelerometer. The algorithm utilizes three different methods for characterizing torso movement dynamics, and maps the extracted dynamics features to load estimates using two machine learning multivariate regression techniques. The algorithm is applied, using leave-one-subject-out cross-validation, to two field collections of soldiers and civilians walking with varying loads. Rapid, accurate estimates of load are obtained, demonstrating robustness to changes in equipment configuration, walking conditions, and walking speeds. On soldier data with loads ranging from 45 to 89 lbs, load estimates result in mean absolute error (MAE) of 6.64 lbs and correlation of r = 0.81. On combined soldier and civilian data, with loads ranging from 0 to 89 lbs, results are MAE = 9.57 lbs and r = 0.91.
{"title":"Estimating load carriage from a body-worn accelerometer","authors":"J. Williamson, Andrew Dumas, G. Ciccarelli, A. Hess, B. Telfer, M. Buller","doi":"10.1109/BSN.2015.7299356","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299356","url":null,"abstract":"Heavy loads increase the risk of musculoskeletal injury for foot soldiers and first responders. Continuous monitoring of load carriage in the field has proven difficult. We propose an algorithm for estimating load from a single body-worn accelerometer. The algorithm utilizes three different methods for characterizing torso movement dynamics, and maps the extracted dynamics features to load estimates using two machine learning multivariate regression techniques. The algorithm is applied, using leave-one-subject-out cross-validation, to two field collections of soldiers and civilians walking with varying loads. Rapid, accurate estimates of load are obtained, demonstrating robustness to changes in equipment configuration, walking conditions, and walking speeds. On soldier data with loads ranging from 45 to 89 lbs, load estimates result in mean absolute error (MAE) of 6.64 lbs and correlation of r = 0.81. On combined soldier and civilian data, with loads ranging from 0 to 89 lbs, results are MAE = 9.57 lbs and r = 0.91.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114688038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2015-06-09DOI: 10.1109/BSN.2015.7299363
R. Richer, Tim Maiwald, C. Pasluosta, B. Hensel, B. Eskofier
This work presents a system for unobtrusive cardiac feedback in daily life. It addresses the whole pipeline from data acquisition over data processing to data visualization including wearable integration. ECG signals are recorded with a novel ECG sensor supporting Bluetooth Low Energy, which is able to transmit raw ECG data as well as estimated heart rate. ECG signals are processed in real-time on a mobile device to automatically classify the user's heart beats. A novel application for Android-based mobile devices was developed for data visualization. It offers several modes for cardiac feedback, from measuring the current heart rate to continuously monitoring the user's heart status. It also allows to store acquired data in an internal database as well as in the Google Fit platform. Further, the application provides extensions for wearables like Google Glass and smartwatches running on Android Wear. Hardware performance evaluation was performed by comparing the course of heart rate between the novel ECG sensor and a commercial ECG sensor. The mean absolute error between the two sensors was 4.83 bpm with a standard deviation of 4.46 bpm, and a Pearson correlation of 0.922. A qualitative evaluation was performed for the Android application with special emphasis on the daily usability and the wearable integration. When the Google Glass was integrated, the subjects rated the application as 2.8/5 (0 = Bad, 5 = Excellent), whereas when the application was integrated with a smartwatch the rating increased to 4.2/5.
{"title":"Novel human computer interaction principles for cardiac feedback using google glass and Android wear","authors":"R. Richer, Tim Maiwald, C. Pasluosta, B. Hensel, B. Eskofier","doi":"10.1109/BSN.2015.7299363","DOIUrl":"https://doi.org/10.1109/BSN.2015.7299363","url":null,"abstract":"This work presents a system for unobtrusive cardiac feedback in daily life. It addresses the whole pipeline from data acquisition over data processing to data visualization including wearable integration. ECG signals are recorded with a novel ECG sensor supporting Bluetooth Low Energy, which is able to transmit raw ECG data as well as estimated heart rate. ECG signals are processed in real-time on a mobile device to automatically classify the user's heart beats. A novel application for Android-based mobile devices was developed for data visualization. It offers several modes for cardiac feedback, from measuring the current heart rate to continuously monitoring the user's heart status. It also allows to store acquired data in an internal database as well as in the Google Fit platform. Further, the application provides extensions for wearables like Google Glass and smartwatches running on Android Wear. Hardware performance evaluation was performed by comparing the course of heart rate between the novel ECG sensor and a commercial ECG sensor. The mean absolute error between the two sensors was 4.83 bpm with a standard deviation of 4.46 bpm, and a Pearson correlation of 0.922. A qualitative evaluation was performed for the Android application with special emphasis on the daily usability and the wearable integration. When the Google Glass was integrated, the subjects rated the application as 2.8/5 (0 = Bad, 5 = Excellent), whereas when the application was integrated with a smartwatch the rating increased to 4.2/5.","PeriodicalId":447934,"journal":{"name":"2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130047441","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：