The effectiveness of an evacuation process in an emergency situation is heavily dependent on the understanding of the dynamics of crowds. Evidence has been delivered supporting the hypothesis that crowd behavior is self referential in the sense that movement patterns of individuals constitutes crowd movement, which in turn impacts the behavior of individuals. In this paper we build on this evidence and propose a belt like wearable device for vibro tactile directional guidance, LifeBelt, to notify individuals in panic about exits. To assess the potential improvement in evacuation efficiency when using the LifeBelt instead of when not, we empirically analyze the behavior of individuals in panic on the microscopic level, and parameterize large scale simulations (of up to 2000 individuals) with this evidence on the macroscopic level. Simulations show that LifeBelt based guidance can damp panic growth and increase the number of successful evacuations per unit time.
{"title":"LifeBelt: Silent Directional Guidance for Crowd Evacuation","authors":"A. Ferscha, K. Zia","doi":"10.1109/ISWC.2009.37","DOIUrl":"https://doi.org/10.1109/ISWC.2009.37","url":null,"abstract":"The effectiveness of an evacuation process in an emergency situation is heavily dependent on the understanding of the dynamics of crowds. Evidence has been delivered supporting the hypothesis that crowd behavior is self referential in the sense that movement patterns of individuals constitutes crowd movement, which in turn impacts the behavior of individuals. In this paper we build on this evidence and propose a belt like wearable device for vibro tactile directional guidance, LifeBelt, to notify individuals in panic about exits. To assess the potential improvement in evacuation efficiency when using the LifeBelt instead of when not, we empirically analyze the behavior of individuals in panic on the microscopic level, and parameterize large scale simulations (of up to 2000 individuals) with this evidence on the macroscopic level. Simulations show that LifeBelt based guidance can damp panic growth and increase the number of successful evacuations per unit time.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114279644","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}
Tracy L. Westeyn, P. Presti, Jeremy M. Johnson, Thad Starner
Wireless sensor data collected under real world conditionscan contain a variety of errors and inconsistenciesthat can affect pattern recognition algorithms. We describea naıve method for correcting wireless sensor data collectedvia non–real–time platforms and visualize the results usingwireless accelerometer data.
{"title":"A Naive Technique Correcting Time-Series Data for Recognition Applications","authors":"Tracy L. Westeyn, P. Presti, Jeremy M. Johnson, Thad Starner","doi":"10.1109/ISWC.2009.19","DOIUrl":"https://doi.org/10.1109/ISWC.2009.19","url":null,"abstract":"Wireless sensor data collected under real world conditionscan contain a variety of errors and inconsistenciesthat can affect pattern recognition algorithms. We describea naıve method for correcting wireless sensor data collectedvia non–real–time platforms and visualize the results usingwireless accelerometer data.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128770085","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}
Jerald Yoo, Long Yan, Seulki Lee, Hyejung Kim, Binhee Kim, H. Yoo
An attachable ECG sensor adhesive bandage is implemented for continuous ECG monitoring system by using Planar-Fashionable Circuit Board (P-FCB) technology. The sensor patch improves convenience at low cost: it is composed of dry electrodes and an inductor directly screen printed on fabric, and the sensor chip is also directly wire bonded on fabric. The sensor patch is wirelessly powered to remove battery for safety. Dry electrodes minimize skin irritation to enable long term monitoring. The implemented sensor patch successfully demonstrates capturing of ECG signal while dissipating only 12uW power.
{"title":"An Attachable ECG Sensor Bandage with Planar-Fashionable Circuit Board","authors":"Jerald Yoo, Long Yan, Seulki Lee, Hyejung Kim, Binhee Kim, H. Yoo","doi":"10.1109/ISWC.2009.16","DOIUrl":"https://doi.org/10.1109/ISWC.2009.16","url":null,"abstract":"An attachable ECG sensor adhesive bandage is implemented for continuous ECG monitoring system by using Planar-Fashionable Circuit Board (P-FCB) technology. The sensor patch improves convenience at low cost: it is composed of dry electrodes and an inductor directly screen printed on fabric, and the sensor chip is also directly wire bonded on fabric. The sensor patch is wirelessly powered to remove battery for safety. Dry electrodes minimize skin irritation to enable long term monitoring. The implemented sensor patch successfully demonstrates capturing of ECG signal while dissipating only 12uW power.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123023347","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. Bächlin, D. Roggen, G. Tröster, M. Plotnik, Noit Inbar, I. Maidan, T. Herman, M. Brozgol, E. Shaviv, Nir Giladi, Jeffrey M. Hausdorff
Freezing of gait (FOG) is a common gait deficit in advanced Parkinson’s disease (PD). It is often a cause of falls, interferes with daily activities and significantly impairs quality of life. Gait deficits in PD patients are often resistant to pharmacologic treatment; therefore effective nonpharmacologic assistance is needed.In this paper we show the potential of context aware assistance for PD patients with FOG and present our first results on start and turn FOG assistance using our modular wearable research platform. We developed a real-time FOG detection system which provides external acoustic cues when FOG is detected from on-body motion sensors, until the subject resumes walking. In an evaluation study, ten PD patients tested our device. We recorded over 8h of data. Eight patients experienced FOG during the study, and 237 FOG events have been identified by physiotherapists in a post video analysis. For the first time PD patients with the FOG syndrome were assisted by a context-aware wearable system. We report a high accuracy of freeze detection (73.1% sensitivity, 81.6% specificity, user independent). Based on subjective reports, the majority of patients indicated a benefit from the automatic cueing.We discuss how additional sensor modalities can paint a more complete view of the user’s context and may increase the system’s accuracy, decrease its latency, and eventually allow going from freeze detection to freeze preemption.
{"title":"Potentials of Enhanced Context Awareness in Wearable Assistants for Parkinson's Disease Patients with the Freezing of Gait Syndrome","authors":"M. Bächlin, D. Roggen, G. Tröster, M. Plotnik, Noit Inbar, I. Maidan, T. Herman, M. Brozgol, E. Shaviv, Nir Giladi, Jeffrey M. Hausdorff","doi":"10.1109/ISWC.2009.14","DOIUrl":"https://doi.org/10.1109/ISWC.2009.14","url":null,"abstract":"Freezing of gait (FOG) is a common gait deficit in advanced Parkinson’s disease (PD). It is often a cause of falls, interferes with daily activities and significantly impairs quality of life. Gait deficits in PD patients are often resistant to pharmacologic treatment; therefore effective nonpharmacologic assistance is needed.In this paper we show the potential of context aware assistance for PD patients with FOG and present our first results on start and turn FOG assistance using our modular wearable research platform. We developed a real-time FOG detection system which provides external acoustic cues when FOG is detected from on-body motion sensors, until the subject resumes walking. In an evaluation study, ten PD patients tested our device. We recorded over 8h of data. Eight patients experienced FOG during the study, and 237 FOG events have been identified by physiotherapists in a post video analysis. For the first time PD patients with the FOG syndrome were assisted by a context-aware wearable system. We report a high accuracy of freeze detection (73.1% sensitivity, 81.6% specificity, user independent). Based on subjective reports, the majority of patients indicated a benefit from the automatic cueing.We discuss how additional sensor modalities can paint a more complete view of the user’s context and may increase the system’s accuracy, decrease its latency, and eventually allow going from freeze detection to freeze preemption.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115281268","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}
Nicholas Komor, Scott M. Gilliland, James Clawson, Manish Bhardwaj, Mayank Garg, C. Zeagler, Thad Starner
In a mobile environment, the visual attention a person can devote to a computer is often limited. In such situations, a manual interface should be “gropable,” that is, the user should be able to access and use the interface with little to no visual attention. We compare stationary and mobile input on two embroidered textile interfaces; a single touch three button interface and a multitouch four button interface that is activated by pressing two buttons at the same time. Sixteen participants completed 480 trials while walking a path and sitting. While multitouch increases the expressiveness of gestures that can be performed, our user study only shows a slight, not statistically signi¿cant, increase in accuracy and an understandable decrease in speed for simple selection tasks.
{"title":"Is It Gropable? – Assessing the Impact of Mobility on Textile Interfaces","authors":"Nicholas Komor, Scott M. Gilliland, James Clawson, Manish Bhardwaj, Mayank Garg, C. Zeagler, Thad Starner","doi":"10.1109/ISWC.2009.21","DOIUrl":"https://doi.org/10.1109/ISWC.2009.21","url":null,"abstract":"In a mobile environment, the visual attention a person can devote to a computer is often limited. In such situations, a manual interface should be “gropable,” that is, the user should be able to access and use the interface with little to no visual attention. We compare stationary and mobile input on two embroidered textile interfaces; a single touch three button interface and a multitouch four button interface that is activated by pressing two buttons at the same time. Sixteen participants completed 480 trials while walking a path and sitting. While multitouch increases the expressiveness of gestures that can be performed, our user study only shows a slight, not statistically signi¿cant, increase in accuracy and an understandable decrease in speed for simple selection tasks.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114643853","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}
Thomas Holleczek, C. Zysset, B. Arnrich, D. Roggen, G. Tröster
Snowboarding is one of the fastest growing sports in the world. However, it is rather difficult to learn. Snowboarders, who have reached an average level of expertise, often find it difficult to improve their style without taking expensive private lessons. Moreover, some of their performed actions would not even be visible for the instructors, as they happen inside the shoes. We are therefore developing an interactive integrated sensor system on the snowboard and on the body, which is capable of assisting snowboarders on the piste and helps them improve their riding style.
{"title":"Towards an Interactive Snowboarding Assistance System","authors":"Thomas Holleczek, C. Zysset, B. Arnrich, D. Roggen, G. Tröster","doi":"10.1109/ISWC.2009.30","DOIUrl":"https://doi.org/10.1109/ISWC.2009.30","url":null,"abstract":"Snowboarding is one of the fastest growing sports in the world. However, it is rather difficult to learn. Snowboarders, who have reached an average level of expertise, often find it difficult to improve their style without taking expensive private lessons. Moreover, some of their performed actions would not even be visible for the instructors, as they happen inside the shoes. We are therefore developing an interactive integrated sensor system on the snowboard and on the body, which is capable of assisting snowboarders on the piste and helps them improve their riding style.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126180531","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}
Thomas L. Martin, Mark T. Jones, Justin Chong, Meghan Quirk, Kara Baumann, Leah Passauer
This paper provides a case study of the construction of an electronic textile jumpsuit with an on-fabric digital network of sensors, including details of the weave, garment construction, and network bandwidth.
{"title":"Design and Implementation of an Electronic Textile Jumpsuit","authors":"Thomas L. Martin, Mark T. Jones, Justin Chong, Meghan Quirk, Kara Baumann, Leah Passauer","doi":"10.1109/ISWC.2009.25","DOIUrl":"https://doi.org/10.1109/ISWC.2009.25","url":null,"abstract":"This paper provides a case study of the construction of an electronic textile jumpsuit with an on-fabric digital network of sensors, including details of the weave, garment construction, and network bandwidth.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129632611","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. Fujimoto, N. Fujita, Yoshinari Takegawa, T. Terada, M. Tsukamoto
In this paper, we constructed a system for realizing a new style of dance performance that dancers play music by dancing. From pilot study, we have found that the motion recognition for dance performance needed the synchronism to back ground music (BGM). Therefore, we propose a new motion recognition method specialized to dance performances. The key techniques of the proposed method are (1) adaptive decision of the size of recognition window to recognize a motion in sync with BGM, and (2) motion recognition in two-phase (rough and detailed) to fulfill the accuracy in high speed recognition. Data was recorded using a 3-axis wireless accelerometers mounted on both shoes. We evaluated the method on a dataset of 5 different dance steps (each repeated 100 times).The results show that this method is capable of improving recognition for all steps (in one case improving recognition from 62% to 99%) while retaining a feeling of seamless connection between movement and sound.
{"title":"A Motion Recognition Method for a Wearable Dancing Musical Instrument","authors":"M. Fujimoto, N. Fujita, Yoshinari Takegawa, T. Terada, M. Tsukamoto","doi":"10.1109/ISWC.2009.22","DOIUrl":"https://doi.org/10.1109/ISWC.2009.22","url":null,"abstract":"In this paper, we constructed a system for realizing a new style of dance performance that dancers play music by dancing. From pilot study, we have found that the motion recognition for dance performance needed the synchronism to back ground music (BGM). Therefore, we propose a new motion recognition method specialized to dance performances. The key techniques of the proposed method are (1) adaptive decision of the size of recognition window to recognize a motion in sync with BGM, and (2) motion recognition in two-phase (rough and detailed) to fulfill the accuracy in high speed recognition. Data was recorded using a 3-axis wireless accelerometers mounted on both shoes. We evaluated the method on a dataset of 5 different dance steps (each repeated 100 times).The results show that this method is capable of improving recognition for all steps (in one case improving recognition from 62% to 99%) while retaining a feeling of seamless connection between movement and sound.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124552627","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 computing, where users can wear computers anywhere and at any time, is slowly becoming a reality because of recent technological advancements. When users access various services in wearable computing environments, they want to define new services by themselves. Therefore, we propose a new framework for constructing context-aware applications in wearable computing environments. Our framework, called Wearable Toolkit, consists of an event-driven rule processing engine and tools to develop applications. By using our framework, we can define and customise services anywhere and at any time. We found our system helps to create context-aware wearable services from the results we obtained by evaluating it.
{"title":"Toward Achieving On-Site Programming","authors":"T. Terada, Masakazu Miyamae","doi":"10.1109/ISWC.2009.11","DOIUrl":"https://doi.org/10.1109/ISWC.2009.11","url":null,"abstract":"Wearable computing, where users can wear computers anywhere and at any time, is slowly becoming a reality because of recent technological advancements. When users access various services in wearable computing environments, they want to define new services by themselves. Therefore, we propose a new framework for constructing context-aware applications in wearable computing environments. Our framework, called Wearable Toolkit, consists of an event-driven rule processing engine and tools to develop applications. By using our framework, we can define and customise services anywhere and at any time. We found our system helps to create context-aware wearable services from the results we obtained by evaluating it.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117343201","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}
Achieving a robust recognition of physical activities or gestures despite variability in sensor placement is highly important for the real-world deployment of wearable context-aware systems.It provides robustness against unintentional displacement of sensors, such as when doing intense physical activities or wearing sensors over extended periods of time.Here we focus on the problem of context recognition when sensors are displaced on body segments. We present an online unsupervised classifier self-calibration algorithm.Upon re-occurring context occurrences, the self-calibration algorithm adjusts the decision boundaries through online learning to better reflect the classes statistics, effectively allowing to track and adjust when classes drift in the feature space.We characterize the theoretical behavior of the system on a synthetic two-class problem dataset.We then analyze the real-world applicability of the method on a 5-class HCI related dataset, and a 6-class fitness scenario dataset.Our results show that the calibration increases the classification accuracy for displaced sensor positions by 33.3% in the HCI scenario and by 13.4% in the fitness scenario.
{"title":"Unsupervised Classifier Self-Calibration through Repeated Context Occurences: Is there Robustness against Sensor Displacement to Gain?","authors":"Kilian Förster, D. Roggen, G. Tröster","doi":"10.1109/ISWC.2009.12","DOIUrl":"https://doi.org/10.1109/ISWC.2009.12","url":null,"abstract":"Achieving a robust recognition of physical activities or gestures despite variability in sensor placement is highly important for the real-world deployment of wearable context-aware systems.It provides robustness against unintentional displacement of sensors, such as when doing intense physical activities or wearing sensors over extended periods of time.Here we focus on the problem of context recognition when sensors are displaced on body segments. We present an online unsupervised classifier self-calibration algorithm.Upon re-occurring context occurrences, the self-calibration algorithm adjusts the decision boundaries through online learning to better reflect the classes statistics, effectively allowing to track and adjust when classes drift in the feature space.We characterize the theoretical behavior of the system on a synthetic two-class problem dataset.We then analyze the real-world applicability of the method on a 5-class HCI related dataset, and a 6-class fitness scenario dataset.Our results show that the calibration increases the classification accuracy for displaced sensor positions by 33.3% in the HCI scenario and by 13.4% in the fitness scenario.","PeriodicalId":394421,"journal":{"name":"2009 International Symposium on Wearable Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126054470","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：