Uwe Maurer, Anthony G. Rowe, A. Smailagic, D. Siewiorek
The eWatch is a wearable sensing, notification, and computing platform built into a wrist watch form factor making it highly available, instantly viewable, ideally located for sensors, and unobtrusive to users. Bluetooth communication provides a wireless link to a cellular phone or stationary computer. eWatch senses light, motion, audio, and temperature and provides visual, audio, and tactile notification. The system provides ample processing capabilities with multiple day battery life enabling realistic user studies. This paper provides the motivation for developing a wearable computing platform, a description of the power aware hardware and software architectures, and results showing how online nearest neighbor classification can identify and recognize a set of frequently visited locations
{"title":"eWatch: a wearable sensor and notification platform","authors":"Uwe Maurer, Anthony G. Rowe, A. Smailagic, D. Siewiorek","doi":"10.1109/BSN.2006.24","DOIUrl":"https://doi.org/10.1109/BSN.2006.24","url":null,"abstract":"The eWatch is a wearable sensing, notification, and computing platform built into a wrist watch form factor making it highly available, instantly viewable, ideally located for sensors, and unobtrusive to users. Bluetooth communication provides a wireless link to a cellular phone or stationary computer. eWatch senses light, motion, audio, and temperature and provides visual, audio, and tactile notification. The system provides ample processing capabilities with multiple day battery life enabling realistic user studies. This paper provides the motivation for developing a wearable computing platform, a description of the power aware hardware and software architectures, and results showing how online nearest neighbor classification can identify and recognize a set of frequently visited locations","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129392813","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}
T. Hester, D. Sherrill, P. Bonato, M. Hamel, K. Perreault, P. Boissy
Many older adults with chronic disabilities and diminished movement abilities use mobility assistive devices such as canes. Once taken home, these mobility assistive devices are commonly misused or not used at all. A means for assessing the use of a cane in the home setting is needed to aid clinicians in the prescription of such devices. In this study, we propose the use of wearable sensors to monitor the quality of use of a cane. Wearable sensors are used to identify the motor task (e.g. level walking, walking on an incline, stair climbing) that a subject is performing whereas sensors on the cane are utilized to evaluate the use of the cane in the context of the identified task. Results from 15 patients with arthritis indicate that the motor tasks of interest can be reliably identified (i.e. for average sensitivity equal to 95%, specificity is greater than 95%). The distribution of load values and features derived from the sensors on the cane suggest that the proposed technique is highly sensitive to differences in quality of use across individuals and differences in the dynamics of loading the cane across motor tasks
{"title":"Using wearable sensors to analyze the quality of use of mobility assistive devices","authors":"T. Hester, D. Sherrill, P. Bonato, M. Hamel, K. Perreault, P. Boissy","doi":"10.1109/BSN.2006.56","DOIUrl":"https://doi.org/10.1109/BSN.2006.56","url":null,"abstract":"Many older adults with chronic disabilities and diminished movement abilities use mobility assistive devices such as canes. Once taken home, these mobility assistive devices are commonly misused or not used at all. A means for assessing the use of a cane in the home setting is needed to aid clinicians in the prescription of such devices. In this study, we propose the use of wearable sensors to monitor the quality of use of a cane. Wearable sensors are used to identify the motor task (e.g. level walking, walking on an incline, stair climbing) that a subject is performing whereas sensors on the cane are utilized to evaluate the use of the cane in the context of the identified task. Results from 15 patients with arthritis indicate that the motor tasks of interest can be reliably identified (i.e. for average sensitivity equal to 95%, specificity is greater than 95%). The distribution of load values and features derived from the sensors on the cane suggest that the proposed technique is highly sensitive to differences in quality of use across individuals and differences in the dynamics of loading the cane across motor tasks","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966642","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}
Ubiquitous computing has established a vision of computation where computers are so deeply integrated into our lives that they become both invisible and everywhere. In order to have computers out of sight and out of mind, they will need a deeper understanding of human life. LifeNet (Singh and Williams, 2003) is a model that functions as a computational model of human life that attempts to anticipate and predict what humans do in the world from a first-person point of view. LifeNet utilizes a general knowledge storage (Singh, 2002) gathered from assertions about the world input by the web community at large. In this work, we extend this general knowledge with sensor data gathered in vivo. By adding these sensor-network data to LifeNet, we are enabling a bidirectional learning process: both bottom-up segregation of sensor data and top-down conceptual constraint propagation, thus correcting current metric assumptions in the LifeNet conceptual model by using sensor measurements. Also, in addition to having LifeNet learning general common sense metrics of physical time and space, it will also learn metrics to a specific lab space and chances for recognizing specific individual human activities, and thus be able to make both general and specific spatial/temporal inferences, such as predicting how many people are in a given room and what they might be doing. This paper discusses the following topics: (1) details of the LifeNet probabilistic human model, (2) a description of the plug sensor network used in this research, and (3) a description of an experimental design for evaluation of the LifeNet learning method
{"title":"Elaborating sensor data using temporal and spatial commonsense reasoning","authors":"Bo Morgan, Push Singh","doi":"10.1109/BSN.2006.22","DOIUrl":"https://doi.org/10.1109/BSN.2006.22","url":null,"abstract":"Ubiquitous computing has established a vision of computation where computers are so deeply integrated into our lives that they become both invisible and everywhere. In order to have computers out of sight and out of mind, they will need a deeper understanding of human life. LifeNet (Singh and Williams, 2003) is a model that functions as a computational model of human life that attempts to anticipate and predict what humans do in the world from a first-person point of view. LifeNet utilizes a general knowledge storage (Singh, 2002) gathered from assertions about the world input by the web community at large. In this work, we extend this general knowledge with sensor data gathered in vivo. By adding these sensor-network data to LifeNet, we are enabling a bidirectional learning process: both bottom-up segregation of sensor data and top-down conceptual constraint propagation, thus correcting current metric assumptions in the LifeNet conceptual model by using sensor measurements. Also, in addition to having LifeNet learning general common sense metrics of physical time and space, it will also learn metrics to a specific lab space and chances for recognizing specific individual human activities, and thus be able to make both general and specific spatial/temporal inferences, such as predicting how many people are in a given room and what they might be doing. This paper discusses the following topics: (1) details of the LifeNet probabilistic human model, (2) a description of the plug sensor network used in this research, and (3) a description of an experimental design for evaluation of the LifeNet learning method","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126557494","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}
An inductive link is presented that can handle freedom of motion. The envisaged application is to power a wireless camera capsule used for noninvasive visual inspection of the small bowel. Up to 150 mW of usable DC power can be delivered to the capsule for the entire duration of its travel along the gastric track. The realization of the link is discussed in detail. Measured data of the link performance are presented and evaluated
{"title":"An omnidirectional transcutaneous power link for capsule endoscopy","authors":"B. Lenaerts, R. Puers","doi":"10.1109/BSN.2006.9","DOIUrl":"https://doi.org/10.1109/BSN.2006.9","url":null,"abstract":"An inductive link is presented that can handle freedom of motion. The envisaged application is to power a wireless camera capsule used for noninvasive visual inspection of the small bowel. Up to 150 mW of usable DC power can be delivered to the capsule for the entire duration of its travel along the gastric track. The realization of the link is discussed in detail. Measured data of the link performance are presented and evaluated","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125822407","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}
We have designed a Bluetooth-based body sensor network platform for physiological diary applications and have addressed its challenges in cost, energy efficiency, and user interface. In our platform, an Internet-capable phone serves as the center and manages every network member. We designed a Bluetooth sensor node for general sensing devices to join the network without much alteration. Since Bluetooth imposes a large power overhead, we have taken extreme care to minimize its duty cycle. We also incorporated a wrist-worn device as the user interface. It displays information under the instruction of the phone in an ambient fashion, and enables the user to interact with the network conveniently. By leveraging resources on the phone, we are able to minimize the cost and energy consumption of the sensor nodes and the wrist-worn device
{"title":"A phone-centered body sensor network platform cost, energy efficiency & user interface","authors":"Lin Zhong, M. Sinclair, Ray Bittner","doi":"10.1109/BSN.2006.4","DOIUrl":"https://doi.org/10.1109/BSN.2006.4","url":null,"abstract":"We have designed a Bluetooth-based body sensor network platform for physiological diary applications and have addressed its challenges in cost, energy efficiency, and user interface. In our platform, an Internet-capable phone serves as the center and manages every network member. We designed a Bluetooth sensor node for general sensing devices to join the network without much alteration. Since Bluetooth imposes a large power overhead, we have taken extreme care to minimize its duty cycle. We also incorporated a wrist-worn device as the user interface. It displays information under the instruction of the phone in an ambient fashion, and enables the user to interact with the network conveniently. By leveraging resources on the phone, we are able to minimize the cost and energy consumption of the sensor nodes and the wrist-worn device","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123763933","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}
Summary form only given. We discuss how programmable analog electronics may be used to lower overall power consumption over traditional A-to-D-then-DSP architectures in portable medical applications. One example includes a bionic ear processor for the deaf whose power consumption is an order of magnitude below the best designs today, that are unbeatable even at the end of Moore's law, and which enable 30 year operation on an implanted 100mAh rechargeable battery. Another example includes an ultra low power portable pulse oximeter for measuring oxygen saturation, an important vital sign. This paper discusses implications for future medical applications that are battery free and that operate by rectifying ambient RF energy, for example for cardiac monitoring. Medical applications in the future are likely to benefit greatly from ultra low power electronics especially in implanted, home care, surgical, and emergency monitoring
{"title":"Ultra low power electronics for medicine","authors":"R. Sarpeshkar","doi":"10.1109/BSN.2006.38","DOIUrl":"https://doi.org/10.1109/BSN.2006.38","url":null,"abstract":"Summary form only given. We discuss how programmable analog electronics may be used to lower overall power consumption over traditional A-to-D-then-DSP architectures in portable medical applications. One example includes a bionic ear processor for the deaf whose power consumption is an order of magnitude below the best designs today, that are unbeatable even at the end of Moore's law, and which enable 30 year operation on an implanted 100mAh rechargeable battery. Another example includes an ultra low power portable pulse oximeter for measuring oxygen saturation, an important vital sign. This paper discusses implications for future medical applications that are battery free and that operate by rectifying ambient RF energy, for example for cardiac monitoring. Medical applications in the future are likely to benefit greatly from ultra low power electronics especially in implanted, home care, surgical, and emergency monitoring","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114836458","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}
D. Krebs, J. Huddleston, Dov Goldvasser, D. Scarborough, W. Harris, H. Malchau
The arrival of copious and cheap flash memory, as well as micromanufacturing techniques, permitted us to generate a pager-sized whole-body activity and knee range of motion monitor - and record these kinematics continuously at 32 Hz for two days on a single AA battery. Thus, we report here data from a healthy convenience sample of 5 males and 5 females, and 3 women and 7 men who had total knee replacements (TKR) 25plusmn4 mo previously. Prior to our project, TKRs, artificial (transfemoral) limbs, airline seats, and other ergonomic knee-motion based designs were based on simulated motion lab studies. These latter indicated that les105deg knee flexion was sufficient to accommodate most activities; recently, however, TKR manufacturers began supplying "high flexion" knees that permit >150deg knee flexion. Our data show that healthy Caucasian health care workers rarely employ >120deg knee flexion, nor do Caucasians even with high flexion TKRs-even outside the lab environment
{"title":"Biomotion community-wearable human activity monitor: total knee replacement and healthy control subjects","authors":"D. Krebs, J. Huddleston, Dov Goldvasser, D. Scarborough, W. Harris, H. Malchau","doi":"10.1109/BSN.2006.13","DOIUrl":"https://doi.org/10.1109/BSN.2006.13","url":null,"abstract":"The arrival of copious and cheap flash memory, as well as micromanufacturing techniques, permitted us to generate a pager-sized whole-body activity and knee range of motion monitor - and record these kinematics continuously at 32 Hz for two days on a single AA battery. Thus, we report here data from a healthy convenience sample of 5 males and 5 females, and 3 women and 7 men who had total knee replacements (TKR) 25plusmn4 mo previously. Prior to our project, TKRs, artificial (transfemoral) limbs, airline seats, and other ergonomic knee-motion based designs were based on simulated motion lab studies. These latter indicated that les105deg knee flexion was sufficient to accommodate most activities; recently, however, TKR manufacturers began supplying \"high flexion\" knees that permit >150deg knee flexion. Our data show that healthy Caucasian health care workers rarely employ >120deg knee flexion, nor do Caucasians even with high flexion TKRs-even outside the lab environment","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122869869","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}
Summary form only given. We describe the design of a compact, wireless sensor module designed to capture expressive gestures in real-time when worn at the hands and feet of a dancer. Each sensor includes a 6-axis inertial measurement unit (IMU) that contains three orthogonal gyroscopes and accelerometers in order to capture local dynamics, as well as a capacitive sensor to measure node-to-node proximity. Signal conditioning to support a resistive sensor (e.g., bend or pressure measurement) is also included, and a compact expansion port is available with free digital inputs and an SPI interface. The onboard radio transceiver supports a power-efficient, high-speed RF network capable of real-time data acquisition from several devices simultaneously, thereby meeting the requirements of instrumenting a small dance ensemble for interactive applications. This paper describes the application goals, presents the prototype hardware design, introduces concepts for feature extraction, and shows early test results
{"title":"A direct brain interface to restore function in humans with spinal cord injury","authors":"J. Donoghue","doi":"10.1109/BSN.2006.33","DOIUrl":"https://doi.org/10.1109/BSN.2006.33","url":null,"abstract":"Summary form only given. We describe the design of a compact, wireless sensor module designed to capture expressive gestures in real-time when worn at the hands and feet of a dancer. Each sensor includes a 6-axis inertial measurement unit (IMU) that contains three orthogonal gyroscopes and accelerometers in order to capture local dynamics, as well as a capacitive sensor to measure node-to-node proximity. Signal conditioning to support a resistive sensor (e.g., bend or pressure measurement) is also included, and a compact expansion port is available with free digital inputs and an SPI interface. The onboard radio transceiver supports a power-efficient, high-speed RF network capable of real-time data acquisition from several devices simultaneously, thereby meeting the requirements of instrumenting a small dance ensemble for interactive applications. This paper describes the application goals, presents the prototype hardware design, introduces concepts for feature extraction, and shows early test results","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"211 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131669029","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}
We describe a wearable device that perceives and reports on social-emotional information in realtime human interaction. Using a wearable camera and other sensors combined with machine perception algorithms, the system records and analyzes the facial expressions and head movements of the person with whom the wearer is interacting. We propose the application of the social-emotional prosthetic to assist the growing number of individuals diagnosed with autism spectrum disorder (ASD) in perceiving communication in a natural rather than a structured environment, bootstrapping their ability to learn and develop in social settings. The wearable device is an exploratory platform for researchers to gain a better understanding of social-emotional communication, enabling new kinds of measurements and interventions that may also help advance the theory of autism
{"title":"An exploratory social-emotional prosthetic for autism spectrum disorders","authors":"R. E. Kaliouby, Alea Teeters, Rosalind W. Picard","doi":"10.1109/BSN.2006.34","DOIUrl":"https://doi.org/10.1109/BSN.2006.34","url":null,"abstract":"We describe a wearable device that perceives and reports on social-emotional information in realtime human interaction. Using a wearable camera and other sensors combined with machine perception algorithms, the system records and analyzes the facial expressions and head movements of the person with whom the wearer is interacting. We propose the application of the social-emotional prosthetic to assist the growing number of individuals diagnosed with autism spectrum disorder (ASD) in perceiving communication in a natural rather than a structured environment, bootstrapping their ability to learn and develop in social settings. The wearable device is an exploratory platform for researchers to gain a better understanding of social-emotional communication, enabling new kinds of measurements and interventions that may also help advance the theory of autism","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127247872","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}
O. Amft, G. Tröster, P. Lukowicz, C. Schuster-Amft
We demonstrate that simple, unobtrusive sensors attached to the lower arm can be used to capture muscle activations during specific hand and arm activities such as grasping. Specifically, we investigate the use of force sensitive resistors and fabric stretch sensors, that can both be easily integrated into clothing. We use the above sensors to detect the contractions of arm muscles. We present and compare the signals that both sensors produce for a set of typical hand actions. We finally argue that they can provide important information for activity recognition
{"title":"Sensing muscle activities with body-worn sensors","authors":"O. Amft, G. Tröster, P. Lukowicz, C. Schuster-Amft","doi":"10.1109/BSN.2006.48","DOIUrl":"https://doi.org/10.1109/BSN.2006.48","url":null,"abstract":"We demonstrate that simple, unobtrusive sensors attached to the lower arm can be used to capture muscle activations during specific hand and arm activities such as grasping. Specifically, we investigate the use of force sensitive resistors and fabric stretch sensors, that can both be easily integrated into clothing. We use the above sensors to detect the contractions of arm muscles. We present and compare the signals that both sensors produce for a set of typical hand actions. We finally argue that they can provide important information for activity recognition","PeriodicalId":246227,"journal":{"name":"International Workshop on Wearable and Implantable Body Sensor Networks (BSN'06)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2006-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124535172","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：