Sunit Verma, J. Milazzo, Yu-Fei Xie, P. Bagade, Ayan Banerjee, S. Gupta
Well-being and fitness are major focuses pushing the need for a simple and effective method to monitor health. Researchers have pointed out safety, lifetime, and reliability as the key requirements of medical devices. Mismatch between requirements of wearable medical sensor and smart phone and their implementation is one of the major causes of failure. We demonstrate a Wireless Health System (WHS) design tool, which abstracts detail between model and implementation and generates sensor and smart phone code.
{"title":"Model-based wireless health system design tool","authors":"Sunit Verma, J. Milazzo, Yu-Fei Xie, P. Bagade, Ayan Banerjee, S. Gupta","doi":"10.1145/2448096.2448115","DOIUrl":"https://doi.org/10.1145/2448096.2448115","url":null,"abstract":"Well-being and fitness are major focuses pushing the need for a simple and effective method to monitor health. Researchers have pointed out safety, lifetime, and reliability as the key requirements of medical devices. Mismatch between requirements of wearable medical sensor and smart phone and their implementation is one of the major causes of failure. We demonstrate a Wireless Health System (WHS) design tool, which abstracts detail between model and implementation and generates sensor and smart phone code.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"3 1","pages":"19:1-19:2"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81210829","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}
Shanshan Chen, Adam T. Barth, J. T. Barth, B. Bennett, Maite Brandt-Pearce, D. Broshek, Jason R. Freeman, Hillary Samples, J. Lach
Normal Pressure Hydrocephalus (NPH) is a neurological condition that challenges differential diagnosis, as the symptoms -- cognitive and gait impairment and urinary incontinence -- are similar to those of many aging disorders, including Alzheimer's disease and other forms of dementia. Since NPH is caused by abnormal accumulation of cerebrospinal fluid (CSF) around the brain, a high volume lumbar puncture (HVLP) to remove excess fluid is used as the stimulus for a suspected NPH patient, and a diagnosis is made based on the observed cognitive and functional response. Gait features have long been used as functional indicators in the pre- and post-HVLP assessment. However, these assessments are limited to visual observation in the clinic. Therefore, only simple gait features such as walking speed (based on time to walk 10m) and average stride length/time (based on the number of steps to walk 10m) are used. However, these features provide limited separability in the NPH diagnosis. This paper presents methods for enhanced diagnostic separability using additional gait features extracted from an inertial body sensor network (BSN), including stride time variability, double support time, and stability. A pilot study on six HVLP patients -- four of whom were ultimately diagnosed with NPH -- revealed that gait stability assessed by Lyapunov exponent provides better separability and can enhance the differential diagnosis. In addition, these results suggest that additional testing can be performed continuously outside of the clinic to account for patients' variable HVLP response times.
{"title":"Aiding diagnosis of normal pressure hydrocephalus with enhanced gait feature separability","authors":"Shanshan Chen, Adam T. Barth, J. T. Barth, B. Bennett, Maite Brandt-Pearce, D. Broshek, Jason R. Freeman, Hillary Samples, J. Lach","doi":"10.1145/2448096.2448099","DOIUrl":"https://doi.org/10.1145/2448096.2448099","url":null,"abstract":"Normal Pressure Hydrocephalus (NPH) is a neurological condition that challenges differential diagnosis, as the symptoms -- cognitive and gait impairment and urinary incontinence -- are similar to those of many aging disorders, including Alzheimer's disease and other forms of dementia. Since NPH is caused by abnormal accumulation of cerebrospinal fluid (CSF) around the brain, a high volume lumbar puncture (HVLP) to remove excess fluid is used as the stimulus for a suspected NPH patient, and a diagnosis is made based on the observed cognitive and functional response.\u0000 Gait features have long been used as functional indicators in the pre- and post-HVLP assessment. However, these assessments are limited to visual observation in the clinic. Therefore, only simple gait features such as walking speed (based on time to walk 10m) and average stride length/time (based on the number of steps to walk 10m) are used. However, these features provide limited separability in the NPH diagnosis.\u0000 This paper presents methods for enhanced diagnostic separability using additional gait features extracted from an inertial body sensor network (BSN), including stride time variability, double support time, and stability. A pilot study on six HVLP patients -- four of whom were ultimately diagnosed with NPH -- revealed that gait stability assessed by Lyapunov exponent provides better separability and can enhance the differential diagnosis. In addition, these results suggest that additional testing can be performed continuously outside of the clinic to account for patients' variable HVLP response times.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"7 1","pages":"3:1-3:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72572914","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}
M. Lan, Lauren Samy, N. Alshurafa, Myung-kyung Suh, Hassan Ghasemzadeh, Aurelia Macabasco-O'Connell, M. Sarrafzadeh
Recent advances in wireless sensors, mobile technologies, and cloud computing have made continuous remote monitoring of patients possible. In this paper, we introduce the design and implementation of WANDA, an end-to-end remote health monitoring and analytics system designed for heart failure patients. The system consists of a smartphone-based data collection gateway, an Internet-scale data storage and search system, and a backend analytics engine for diagnostic and prognostic purposes. The system supports the collection of data from a wide range of sensory devices that measure patients' vital signs as well as self-reported questionnaires. The main objective of the analytics engine is to predict future events by examining physiological readings of the patients. We demonstrate the efficiency of the proposed analytics engine using the data gathered from a pilot study of 18 heart failure patients. In particular, our results show that the advanced analytic algorithms used in our system are capable of predicting the worsening of patients' heart failure symptoms with up to 74% accuracy while improving the sensitivity performance by more than 45% compared to the commonly used thresholding algorithm based on daily weight change. Moreover, the accuracy attained by our system is only 9% lower than the theoretical upper bound. The proposed framework is currently deployed in a large ongoing heart failure study that targets 1500 congestive heart failure patients.
{"title":"WANDA: an end-to-end remote health monitoring and analytics system for heart failure patients","authors":"M. Lan, Lauren Samy, N. Alshurafa, Myung-kyung Suh, Hassan Ghasemzadeh, Aurelia Macabasco-O'Connell, M. Sarrafzadeh","doi":"10.1145/2448096.2448105","DOIUrl":"https://doi.org/10.1145/2448096.2448105","url":null,"abstract":"Recent advances in wireless sensors, mobile technologies, and cloud computing have made continuous remote monitoring of patients possible. In this paper, we introduce the design and implementation of WANDA, an end-to-end remote health monitoring and analytics system designed for heart failure patients. The system consists of a smartphone-based data collection gateway, an Internet-scale data storage and search system, and a backend analytics engine for diagnostic and prognostic purposes. The system supports the collection of data from a wide range of sensory devices that measure patients' vital signs as well as self-reported questionnaires. The main objective of the analytics engine is to predict future events by examining physiological readings of the patients.\u0000 We demonstrate the efficiency of the proposed analytics engine using the data gathered from a pilot study of 18 heart failure patients. In particular, our results show that the advanced analytic algorithms used in our system are capable of predicting the worsening of patients' heart failure symptoms with up to 74% accuracy while improving the sensitivity performance by more than 45% compared to the commonly used thresholding algorithm based on daily weight change. Moreover, the accuracy attained by our system is only 9% lower than the theoretical upper bound. The proposed framework is currently deployed in a large ongoing heart failure study that targets 1500 congestive heart failure patients.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"491 1-2 1","pages":"9:1-9:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78400813","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}
Accurate estimation of Energy Expenditure (EE) in ambulatory settings is a key element in determining the causal relation between aspects of human behavior related to physical activity and health. We present a new methodology for activity-specific EE algorithms. The proposed methodology models activity clusters using specific parameters that capture differences in EE within a cluster, and combines these models with Metabolic Equivalents (METs) derived from the compendium of physical activities. We designed a protocol consisting of a wide set of sedentary, household, lifestyle and gym activities, and developed a new activity-specific EE algorithm applying the proposed methodology. The algorithm uses accelerometer (ACC) and heart rate (HR) data acquired by a single monitoring device, together with anthropometric variables, to predict EE. Our model recognizes six clusters of activities independent of the subject in 52.6 hours of recordings from 19 participants. Increases in EE estimation accuracy ranged from 18 to 31% compared to state of the art single and multi-sensor activity-specific methods.
{"title":"Energy expenditure estimation using wearable sensors: a new methodology for activity-specific models","authors":"M. Altini, J. Penders, O. Amft","doi":"10.1145/2448096.2448097","DOIUrl":"https://doi.org/10.1145/2448096.2448097","url":null,"abstract":"Accurate estimation of Energy Expenditure (EE) in ambulatory settings is a key element in determining the causal relation between aspects of human behavior related to physical activity and health. We present a new methodology for activity-specific EE algorithms. The proposed methodology models activity clusters using specific parameters that capture differences in EE within a cluster, and combines these models with Metabolic Equivalents (METs) derived from the compendium of physical activities. We designed a protocol consisting of a wide set of sedentary, household, lifestyle and gym activities, and developed a new activity-specific EE algorithm applying the proposed methodology. The algorithm uses accelerometer (ACC) and heart rate (HR) data acquired by a single monitoring device, together with anthropometric variables, to predict EE. Our model recognizes six clusters of activities independent of the subject in 52.6 hours of recordings from 19 participants. Increases in EE estimation accuracy ranged from 18 to 31% compared to state of the art single and multi-sensor activity-specific methods.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"16 1","pages":"1:1-1:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80471708","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}
Nima Nikzad, Nakul Verma, Celal Ziftci, Elizabeth S. Bales, Nichole Quick, P. Zappi, K. Patrick, S. Dasgupta, Ingolf Krüger, T. Simunic, W. Griswold
Environmental exposures are a critical component in the development of chronic conditions such as asthma and cancer. Yet, medical and public health practitioners typically must depend on sparse regional measurements of the environment that provide macro-scale summaries. Recent projects have begun to measure an individual's exposure to these factors, often utilizing body-worn sensors and mobile phones to visualize the data. Such data, collected from many individuals and analyzed across an entire geographic region, holds the potential to revolutionize the practice of public health. We present CitiSense, a participatory air quality sensing system that bridges the gap between personal sensing and regional measurement to provide micro-level detail at a regional scale. In a user study of 16 commuters using CitiSense, measurements were found to vary significantly from those provided by official regional pollution monitoring stations. Moreover, applying geostatistical kriging techniques to our data allows CitiSense to infer a regional map that contains considerably greater detail than official regional summaries. These results suggest that the cumulative impact of many individuals using personal sensing devices may have an important role to play in the future of environmental measurement for public health.
{"title":"CitiSense: improving geospatial environmental assessment of air quality using a wireless personal exposure monitoring system","authors":"Nima Nikzad, Nakul Verma, Celal Ziftci, Elizabeth S. Bales, Nichole Quick, P. Zappi, K. Patrick, S. Dasgupta, Ingolf Krüger, T. Simunic, W. Griswold","doi":"10.1145/2448096.2448107","DOIUrl":"https://doi.org/10.1145/2448096.2448107","url":null,"abstract":"Environmental exposures are a critical component in the development of chronic conditions such as asthma and cancer. Yet, medical and public health practitioners typically must depend on sparse regional measurements of the environment that provide macro-scale summaries. Recent projects have begun to measure an individual's exposure to these factors, often utilizing body-worn sensors and mobile phones to visualize the data. Such data, collected from many individuals and analyzed across an entire geographic region, holds the potential to revolutionize the practice of public health.\u0000 We present CitiSense, a participatory air quality sensing system that bridges the gap between personal sensing and regional measurement to provide micro-level detail at a regional scale. In a user study of 16 commuters using CitiSense, measurements were found to vary significantly from those provided by official regional pollution monitoring stations. Moreover, applying geostatistical kriging techniques to our data allows CitiSense to infer a regional map that contains considerably greater detail than official regional summaries. These results suggest that the cumulative impact of many individuals using personal sensing devices may have an important role to play in the future of environmental measurement for public health.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"29 1","pages":"11:1-11:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76764814","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}
Wearable sensing systems are paving the way for significant advances in diagnosis, preventative healthcare and tele-healthcare, by facilitating a variety of wireless health applications for medical signal and diagnostic monitoring and assessment. However, the considerable spatial and temporal sampling for multiple sensed modalities that enable these applications, also makes them power hungry, requiring large, heavy power supplies, and leading to a tradeoff between usability and lifetime. We propose a sampling algorithm to overcome this trade-off by capitalizing on the spatio-temporal redundancy inherent to Body Area Networks owing to their localized nature, as well as, assessing sample relevance based on its contribution to the predicted diagnostic(s). Our approach improves energy-efficiency and raises contextual sample quality, by tackling sample selection simultaneously in the spatial and temporal domains, yielding improved diagnostic accuracy under power-constraints. We present our algorithm in the context of diagnostics gleaned from a foot plantar pressure measurement platform and illustrate its efficacy based on real datasets collected by the platform.
{"title":"Power constrained sensor sample selection for improved form factor and lifetime in localized BANs","authors":"V. Goudar, M. Potkonjak","doi":"10.1145/2448096.2448101","DOIUrl":"https://doi.org/10.1145/2448096.2448101","url":null,"abstract":"Wearable sensing systems are paving the way for significant advances in diagnosis, preventative healthcare and tele-healthcare, by facilitating a variety of wireless health applications for medical signal and diagnostic monitoring and assessment. However, the considerable spatial and temporal sampling for multiple sensed modalities that enable these applications, also makes them power hungry, requiring large, heavy power supplies, and leading to a tradeoff between usability and lifetime. We propose a sampling algorithm to overcome this trade-off by capitalizing on the spatio-temporal redundancy inherent to Body Area Networks owing to their localized nature, as well as, assessing sample relevance based on its contribution to the predicted diagnostic(s). Our approach improves energy-efficiency and raises contextual sample quality, by tackling sample selection simultaneously in the spatial and temporal domains, yielding improved diagnostic accuracy under power-constraints. We present our algorithm in the context of diagnostics gleaned from a foot plantar pressure measurement platform and illustrate its efficacy based on real datasets collected by the platform.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"45 1","pages":"5:1-5:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78530958","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}
J. McGillicuddy, M. Gregoski, B. Brunner-Jackson, Ana K. Weiland, Sachin K Patel, Rebecca A. Rock, Eveline M. Treiber, Lydia K. Davidson, F. Treiber
Effective and efficient management of chronic illness remains a significant clinical problem. To improve chronic illness management, two obstacles that must be overcome are patient non-adherence to medication regimens and provider therapeutic inertia (failure to respond in timely manner to clinical data). Using an iterative approach, behavioral theory was used to develop a mobile health (mHealth) medication and blood pressure self-management system that was patient and provider centered. Electronic medication trays provided reminder signals and smart phone text messages reminded patients to measure blood pressures using a Bluetooth-enabled monitor. Patients received mobile phone-delivered personalized motivational and reinforcement messages based upon adherence levels to these regimens. Two 3-month proof of concept randomized control trials were conducted with 2 patient groups; 1) Hispanics with uncontrolled essential hypertension (n=6), and 2) patients with hypertension after kidney transplantation. (n=6). Hispanic patients who received the mHealth intervention all exhibited significant improvements in both medication adherence and reductions in resting and 24-hour blood pressures during the trial and at 3-month follow-up, as compared to the control group. The still ongoing kidney transplant trial has shown that recipients randomized to the mHealth intervention have demonstrated significant improvements in medication adherence and reduced blood pressure two months into the trial. Following completion of both studies, patient and provider focus groups will allow further iterative refinement of the mHealth system and a feasibility trial of larger scale and longer duration.
{"title":"Facilitating medication adherence and eliminating therapeutic inertia using wireless technology: proof of concept findings with uncontrolled hypertensives and kidney transplant recipients","authors":"J. McGillicuddy, M. Gregoski, B. Brunner-Jackson, Ana K. Weiland, Sachin K Patel, Rebecca A. Rock, Eveline M. Treiber, Lydia K. Davidson, F. Treiber","doi":"10.1145/2448096.2448108","DOIUrl":"https://doi.org/10.1145/2448096.2448108","url":null,"abstract":"Effective and efficient management of chronic illness remains a significant clinical problem. To improve chronic illness management, two obstacles that must be overcome are patient non-adherence to medication regimens and provider therapeutic inertia (failure to respond in timely manner to clinical data). Using an iterative approach, behavioral theory was used to develop a mobile health (mHealth) medication and blood pressure self-management system that was patient and provider centered. Electronic medication trays provided reminder signals and smart phone text messages reminded patients to measure blood pressures using a Bluetooth-enabled monitor. Patients received mobile phone-delivered personalized motivational and reinforcement messages based upon adherence levels to these regimens. Two 3-month proof of concept randomized control trials were conducted with 2 patient groups; 1) Hispanics with uncontrolled essential hypertension (n=6), and 2) patients with hypertension after kidney transplantation. (n=6). Hispanic patients who received the mHealth intervention all exhibited significant improvements in both medication adherence and reductions in resting and 24-hour blood pressures during the trial and at 3-month follow-up, as compared to the control group.\u0000 The still ongoing kidney transplant trial has shown that recipients randomized to the mHealth intervention have demonstrated significant improvements in medication adherence and reduced blood pressure two months into the trial. Following completion of both studies, patient and provider focus groups will allow further iterative refinement of the mHealth system and a feasibility trial of larger scale and longer duration.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"111 1","pages":"12:1-12:9"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84854402","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}
Personal area networks are enablers for many new medical applications. In this work, we present an implementation of such a network through a guided wave on body communication channel. This method allows the creation of high bandwidth communication channels which are confined to the body and improve on previous technologies in terms of privacy and resilience to interference and bandwidth. The technology proposed can also be used for other applications such as tracking infections and especially Nosocomial infections. Nosocomial infections (hospital-acquired infections) are believed to be linked to the death of around 100,000 patients each year in the U.S. only. The technology proposed here allows the detection of a handshake between people and interaction with other objects, thus registering them for analysis of the root cause of an infection.
{"title":"Confined intra-arm communication for medical applications","authors":"T. Thai, G. DeJean, Ran Gilad-Bachrach","doi":"10.1145/2448096.2448114","DOIUrl":"https://doi.org/10.1145/2448096.2448114","url":null,"abstract":"Personal area networks are enablers for many new medical applications. In this work, we present an implementation of such a network through a guided wave on body communication channel. This method allows the creation of high bandwidth communication channels which are confined to the body and improve on previous technologies in terms of privacy and resilience to interference and bandwidth. The technology proposed can also be used for other applications such as tracking infections and especially Nosocomial infections. Nosocomial infections (hospital-acquired infections) are believed to be linked to the death of around 100,000 patients each year in the U.S. only. The technology proposed here allows the detection of a handshake between people and interaction with other objects, thus registering them for analysis of the root cause of an infection.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"161 1","pages":"18:1-18:2"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83334562","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}
Body sensors networks (BSNs) are emerging technologies that are enabling long-term, continuous, remote monitoring of physiologic and biokinematic information for various medical applications. Because of the varying computational, storage, and communication capabilities of different components in the BSN, system designers must make design choices that trade off information quality with resource consumption and system battery lifetime. Given these trade-offs, there is the possibility that the information presented to the health practitioner at the end point may deviate from what was originally sensed. In some cases, these deviations may cause a practitioner to make a different decision from what would have been made given the original data. Engineers working on such systems typically resort to traditional measures of data quality like RMSE; however, these metrics have been shown in many cases to not correlate well with the notions of information quality for the particular application. Objective metrics of information distortion and its effects on decision making are therefore necessary to help BSN designers make more informed trade-offs between design constraints and information quality and to help practitioners understand the kind of information being produced by BSNs, on which they have to base decisions. In this paper, we present a general methodology for developing such metrics for various BSN applications, illustrate how this methodology can be applied to a real application through a case study, and discuss issues with developing such metrics.
{"title":"A methodology for developing quality of information metrics for body sensor design","authors":"Italo Armenti, Philip Asare, J. Su, J. Lach","doi":"10.1145/2448096.2448098","DOIUrl":"https://doi.org/10.1145/2448096.2448098","url":null,"abstract":"Body sensors networks (BSNs) are emerging technologies that are enabling long-term, continuous, remote monitoring of physiologic and biokinematic information for various medical applications. Because of the varying computational, storage, and communication capabilities of different components in the BSN, system designers must make design choices that trade off information quality with resource consumption and system battery lifetime. Given these trade-offs, there is the possibility that the information presented to the health practitioner at the end point may deviate from what was originally sensed. In some cases, these deviations may cause a practitioner to make a different decision from what would have been made given the original data. Engineers working on such systems typically resort to traditional measures of data quality like RMSE; however, these metrics have been shown in many cases to not correlate well with the notions of information quality for the particular application. Objective metrics of information distortion and its effects on decision making are therefore necessary to help BSN designers make more informed trade-offs between design constraints and information quality and to help practitioners understand the kind of information being produced by BSNs, on which they have to base decisions. In this paper, we present a general methodology for developing such metrics for various BSN applications, illustrate how this methodology can be applied to a real application through a case study, and discuss issues with developing such metrics.","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"41 1","pages":"2:1-2:8"},"PeriodicalIF":0.0,"publicationDate":"2012-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80560803","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}
Daily living activity monitoring is important for early detection of the onset of many diseases and for improving quality of life especially in elderly. A wireless wearable network of inertial sensor nodes can be used to observe daily motions. Continuous stream of data generated by these sensor networks can be used to recognize the movements of interest. Dynamic Time Warping (DTW) is a widely used signal processing method for time-series pattern matching because of its robustness to variations in time and speed as opposed to other template matching methods. Despite this flexibility, for the application of activity recognition, DTW can only find the similarity between the template of a movement and the incoming samples, when the location and orientation of the sensor remains unchanged. Due to this restriction, small sensor misplacements can lead to a decrease in the classification accuracy. In this work, we adopt DTW distance as a feature for real-time detection of human daily activities like sit to stand in the presence of sensor misplacement. To measure this performance of DTW, we need to create a large number of sensor configurations while the sensors are rotated or misplaced. Creating a large number of closely spaced sensors is impractical. To address this problem, we use the marker based optical motion capture system and generate simulated inertial sensor data for different locations and orientations on the body. We study the performance of the DTW under these conditions to determine the worst-case sensor location variations that the algorithm can accommodate.
{"title":"Impact of Sensor Misplacement on Dynamic Time Warping Based Human Activity Recognition using Wearable Computers.","authors":"Nimish Kale, Jaeseong Lee, Reza Lotfian, Roozbeh Jafari","doi":"10.1145/2448096.2448103","DOIUrl":"https://doi.org/10.1145/2448096.2448103","url":null,"abstract":"<p><p>Daily living activity monitoring is important for early detection of the onset of many diseases and for improving quality of life especially in elderly. A wireless wearable network of inertial sensor nodes can be used to observe daily motions. Continuous stream of data generated by these sensor networks can be used to recognize the movements of interest. Dynamic Time Warping (DTW) is a widely used signal processing method for time-series pattern matching because of its robustness to variations in time and speed as opposed to other template matching methods. Despite this flexibility, for the application of activity recognition, DTW can only find the similarity between the template of a movement and the incoming samples, when the location and orientation of the sensor remains unchanged. Due to this restriction, small sensor misplacements can lead to a decrease in the classification accuracy. In this work, we adopt DTW distance as a feature for real-time detection of human daily activities like <i>sit to stand</i> in the presence of sensor misplacement. To measure this performance of DTW, we need to create a large number of sensor configurations while the sensors are rotated or misplaced. Creating a large number of closely spaced sensors is impractical. To address this problem, we use the marker based optical motion capture system and generate <i>simulated</i> inertial sensor data for different locations and orientations on the body. We study the performance of the DTW under these conditions to determine the worst-case sensor location variations that the algorithm can accommodate.</p>","PeriodicalId":91386,"journal":{"name":"Proceedings Wireless Health ... [electronic resource]. Wireless Health (Conference)","volume":"2012 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2012-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1145/2448096.2448103","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"34857245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","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：