Pub Date : 2008-09-28DOI: 10.1109/ISWC.2008.4911579
S. Reddy, J. Burke, D. Estrin, Mark H. Hansen, M. Srivastava
As mobile phones advance in functionality and capability, they are increasingly being used as instruments for personal monitoring. Applications are being developed that take advantage of the sensing capabilities of mobile phones - many have accelerometers, location capabilities, imagers, and microphones - to infer contextual information. We focus on one type of context, the transportation mode of an individual, with the goal of creating a convenient (no requirement to place sensors externally or have specific position/orientation settings) classification system that uses a mobile phone with a GPS receiver and an accelerometer sensor to determine if an individual is stationary, walking, running, biking, or in motorized transport. The target application for this transportation mode inference involves assessing the hazard exposure and environmental impact of an individual's travel patterns. Our prototype classification system consisting of a decision tree followed by a first-order hidden Markov model achieves the application requirement of having accuracy level greater than 90% when testing with our dataset consisting of twenty hours of data collected across six individuals.
{"title":"Determining transportation mode on mobile phones","authors":"S. Reddy, J. Burke, D. Estrin, Mark H. Hansen, M. Srivastava","doi":"10.1109/ISWC.2008.4911579","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911579","url":null,"abstract":"As mobile phones advance in functionality and capability, they are increasingly being used as instruments for personal monitoring. Applications are being developed that take advantage of the sensing capabilities of mobile phones - many have accelerometers, location capabilities, imagers, and microphones - to infer contextual information. We focus on one type of context, the transportation mode of an individual, with the goal of creating a convenient (no requirement to place sensors externally or have specific position/orientation settings) classification system that uses a mobile phone with a GPS receiver and an accelerometer sensor to determine if an individual is stationary, walking, running, biking, or in motorized transport. The target application for this transportation mode inference involves assessing the hazard exposure and environmental impact of an individual's travel patterns. Our prototype classification system consisting of a decision tree followed by a first-order hidden Markov model achieves the application requirement of having accuracy level greater than 90% when testing with our dataset consisting of twenty hours of data collected across six individuals.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133490342","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911580
K. Farrahi, D. Gática-Pérez
We present a framework to automatically discover people's routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples' daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including ldquogoing to work early/laterdquo, ldquobeing home all dayrdquo, ldquoworking constantlyrdquo, ldquoworking sporadicallyrdquo and ldquomeeting at lunch timerdquo.
{"title":"Discovering human routines from cell phone data with topic models","authors":"K. Farrahi, D. Gática-Pérez","doi":"10.1109/ISWC.2008.4911580","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911580","url":null,"abstract":"We present a framework to automatically discover people's routines from information extracted by cell phones. The framework is built from a probabilistic topic model learned on novel bag type representations of activity-related cues (location, proximity and their temporal variations over a day) of peoples' daily routines. Using real-life data from the Reality Mining dataset, covering 68 000+ hours of human activities, we can successfully discover location-driven (from cell tower connections) and proximity-driven (from Bluetooth information) routines in an unsupervised manner. The resulting topics meaningfully characterize some of the underlying co-occurrence structure of the activities in the dataset, including ldquogoing to work early/laterdquo, ldquobeing home all dayrdquo, ldquoworking constantlyrdquo, ldquoworking sporadicallyrdquo and ldquomeeting at lunch timerdquo.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115667131","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911592
T. Deyle, M. Reynolds
Motivated by the prevalence of small, battery-powered devices in many pervasive computing research and deployment scenarios, and the frustration encountered when a particular device is found to be useless due to a discharged internal battery, we present a backpack-worn wireless (non-contact) power distribution system. This system is designed to distribute power from a single point of generation or bulk storage to a variety of endpoint devices. Endpoint devices can operate or recharge their internal batteries from the central source when they are stowed in a powered pocket in the backpack. We also demonstrate low bandwidth (10 Kbps) bidirectional communication across the power link. This communication channel could be used to inventory the coupled devices, prioritize power delivery to more important devices, detect the unauthorized removal of a device, authenticate the recipients of power, or distribute cryptographic keys for further data exchange using a Bluetooth, WiFi, or another high data rate connection. Using a 125 KHz resonant inductive coupling mechanism and a dynamic tuning system, we demonstrate a power transfer efficiency of 80% for small (USB class) device loads.
{"title":"PowerPACK: A wireless power distribution system for wearable devices","authors":"T. Deyle, M. Reynolds","doi":"10.1109/ISWC.2008.4911592","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911592","url":null,"abstract":"Motivated by the prevalence of small, battery-powered devices in many pervasive computing research and deployment scenarios, and the frustration encountered when a particular device is found to be useless due to a discharged internal battery, we present a backpack-worn wireless (non-contact) power distribution system. This system is designed to distribute power from a single point of generation or bulk storage to a variety of endpoint devices. Endpoint devices can operate or recharge their internal batteries from the central source when they are stowed in a powered pocket in the backpack. We also demonstrate low bandwidth (10 Kbps) bidirectional communication across the power link. This communication channel could be used to inventory the coupled devices, prioritize power delivery to more important devices, detect the unauthorized removal of a device, authenticate the recipients of power, or distribute cryptographic keys for further data exchange using a Bluetooth, WiFi, or another high data rate connection. Using a 125 KHz resonant inductive coupling mechanism and a dynamic tuning system, we demonstrate a power transfer efficiency of 80% for small (USB class) device loads.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126371764","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911602
Geeta Shroff, A. Smailagic, D. Siewiorek
We propose DiaWear, a novel assistive mobile phone-based calorie monitoring system to improve the quality of life of diabetes patients and individuals with unique nutrition management needs. Our goal is to achieve improved daily semi-automatic food recognition using a mobile wearable cell phone. DiaWear currently uses a neural network classification scheme to identify food items from a captured image. It is difficult to account for the varying and implicit nature of certain foods using traditional image recognition techniques. To overcome these limitations, we introduce the role of the mobile phone as a platform to gather contextual information from the user and system in obtaining better food recognition.
{"title":"Wearable context-aware food recognition for calorie monitoring","authors":"Geeta Shroff, A. Smailagic, D. Siewiorek","doi":"10.1109/ISWC.2008.4911602","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911602","url":null,"abstract":"We propose DiaWear, a novel assistive mobile phone-based calorie monitoring system to improve the quality of life of diabetes patients and individuals with unique nutrition management needs. Our goal is to achieve improved daily semi-automatic food recognition using a mobile wearable cell phone. DiaWear currently uses a neural network classification scheme to identify food items from a captured image. It is difficult to account for the varying and implicit nature of certain foods using traditional image recognition techniques. To overcome these limitations, we introduce the role of the mobile phone as a platform to gather contextual information from the user and system in obtaining better food recognition.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126829830","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911593
Yuvraj Agarwal, T. Pering, R. Want, Rajesh K. Gupta
Multiple wireless network interfaces in a single mobile device exist in order to support their diverse communications and networking needs. This paper proposes a general switching architecture, SwitchR, for managing radio communications for multiple (client) devices utilizing multiple heterogeneous radios per device. SwitchR is deployable incrementally within existing wireless infrastructures, and considers the load imposed on the wireless channel by other communicating clients. SwitchR demonstrates reduction in energy consumption of a mobile device by 47% - 72%, depending upon the application, over the Power Save Mode in WiFi and 13% - 60% reduction in energy over previous multi-radio architectures that do not consider the interactions between multiple clients.
{"title":"SwitchR: Reducing system power consumption in a multi-client, multi-radio environment","authors":"Yuvraj Agarwal, T. Pering, R. Want, Rajesh K. Gupta","doi":"10.1109/ISWC.2008.4911593","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911593","url":null,"abstract":"Multiple wireless network interfaces in a single mobile device exist in order to support their diverse communications and networking needs. This paper proposes a general switching architecture, SwitchR, for managing radio communications for multiple (client) devices utilizing multiple heterogeneous radios per device. SwitchR is deployable incrementally within existing wireless infrastructures, and considers the load imposed on the wireless channel by other communicating clients. SwitchR demonstrates reduction in energy consumption of a mobile device by 47% - 72%, depending upon the application, over the Power Save Mode in WiFi and 13% - 60% reduction in energy over previous multi-radio architectures that do not consider the interactions between multiple clients.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130696434","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911586
Kristof Van Laerhoven, David Kilian, B. Schiele
This paper reports on research where users' activities are logged for extended periods by wrist-worn sensors. These devices operated for up to 27 consecutive days, day and night, while logging features from motion, light, and temperature. This data, labeled via 24-hour self-recall annotation, is explored for occurrences of daily activities. An evaluation shows that using a model of the users' rhythms can improve recognition of daily activities significantly within the logged data, compared to models that exclusively use the sensor data for activity recognition.
{"title":"Using rhythm awareness in long-term activity recognition","authors":"Kristof Van Laerhoven, David Kilian, B. Schiele","doi":"10.1109/ISWC.2008.4911586","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911586","url":null,"abstract":"This paper reports on research where users' activities are logged for extended periods by wrist-worn sensors. These devices operated for up to 27 consecutive days, day and night, while logging features from motion, light, and temperature. This data, labeled via 24-hour self-recall annotation, is explored for occurrences of daily activities. An evaluation shows that using a model of the users' rhythms can improve recognition of daily activities significantly within the logged data, compared to models that exclusively use the sensor data for activity recognition.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133454940","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911589
Brian French, Divya Tyamagundlu, D. Siewiorek, A. Smailagic, D. Ding
We introduce the concept of a Virtual Coach (VC) for providing advice to manual wheelchair users to help them avoid damaging forms of locomotion. The primary form of context for this system is the user's propulsion pattern. The contexts of self vs. external propulsion and the surface over which propulsion is occurring can be used to improve the accuracy of the system's propulsion pattern classifications. To obtain these forms of context, we explore the use of both wearable and wheelchair-mounted accelerometers. We show achievable accuracy rates of up to 80-90% for all desired contextual information using two common machine learning techniques: k-nearest neighbor (kNN) and support vector machines (SVM).
{"title":"Towards a Virtual Coach for manual wheelchair users","authors":"Brian French, Divya Tyamagundlu, D. Siewiorek, A. Smailagic, D. Ding","doi":"10.1109/ISWC.2008.4911589","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911589","url":null,"abstract":"We introduce the concept of a Virtual Coach (VC) for providing advice to manual wheelchair users to help them avoid damaging forms of locomotion. The primary form of context for this system is the user's propulsion pattern. The contexts of self vs. external propulsion and the surface over which propulsion is occurring can be used to improve the accuracy of the system's propulsion pattern classifications. To obtain these forms of context, we explore the use of both wearable and wheelchair-mounted accelerometers. We show achievable accuracy rates of up to 80-90% for all desired contextual information using two common machine learning techniques: k-nearest neighbor (kNN) and support vector machines (SVM).","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115938361","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 : 2008-09-28DOI: 10.1109/ISWC.2008.4911575
Burcu Cinaz, H. Kenn
Self-localization of users and their wearable computers is essential to many applications, but so far, most implementation rely on a-priori information and pre-deployed infrastructures such as maps. We show how techniques from mobile robotics, namely simultaneous localization and mapping can be used to automatically generate both localization information and 2D environment maps using head-mounted inertial and laser range sensors. We present an initial implementation and the results of a number of experiments conducted in an office environment with focus on map degradation caused by shape ambiguities in the environment such as corridors.
{"title":"HeadSLAM - simultaneous localization and mapping with head-mounted inertial and laser range sensors","authors":"Burcu Cinaz, H. Kenn","doi":"10.1109/ISWC.2008.4911575","DOIUrl":"https://doi.org/10.1109/ISWC.2008.4911575","url":null,"abstract":"Self-localization of users and their wearable computers is essential to many applications, but so far, most implementation rely on a-priori information and pre-deployed infrastructures such as maps. We show how techniques from mobile robotics, namely simultaneous localization and mapping can be used to automatically generate both localization information and 2D environment maps using head-mounted inertial and laser range sensors. We present an initial implementation and the results of a number of experiments conducted in an office environment with focus on map degradation caused by shape ambiguities in the environment such as corridors.","PeriodicalId":336550,"journal":{"name":"2008 12th IEEE International Symposium on Wearable Computers","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126843792","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：