Perceptibility on the part of the user is a key influence on the success or failure of a wearable sensor. Most wearable sensors seek to measure or monitor parameters of the body as accurately as possible, yet wearable sensors are notoriously plagued by the error (also referred as noise) that may be introduced by the movement of the sensor over the body surface. In this paper, we implement a novel method for analyzing error introduced by garment properties in garment-integrated wearable sensing during body movement, and assess in detail the errors introduced by donning and doffing of a garment (garment positioning error) and by garment drift during the gait cycle (drift error).
{"title":"Garment Positioning and Drift in Garment-Integrated Wearable Sensing","authors":"Guido Gioberto, Lucy E. Dunne","doi":"10.1109/ISWC.2012.35","DOIUrl":"https://doi.org/10.1109/ISWC.2012.35","url":null,"abstract":"Perceptibility on the part of the user is a key influence on the success or failure of a wearable sensor. Most wearable sensors seek to measure or monitor parameters of the body as accurately as possible, yet wearable sensors are notoriously plagued by the error (also referred as noise) that may be introduced by the movement of the sensor over the body surface. In this paper, we implement a novel method for analyzing error introduced by garment properties in garment-integrated wearable sensing during body movement, and assess in detail the errors introduced by donning and doffing of a garment (garment positioning error) and by garment drift during the gait cycle (drift error).","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"13 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133043125","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}
The common practice of manual synchronization of body-worn, logging accelerometers and video cameras is impractical for integration into everyday practice for applications such as real-world behavior analysis. We significantly extend an existing technique for automatic cross-modal synchronization and evaluate its performance in a realistic experimental setting. Distinctive gestures, captured by a camera, are matched with recorded acceleration signal(s) using cross-correlation based time-delay estimation. PCA-based data pre-processing makes the procedure robust against orientation mismatches between the marking gesture and the camera plane. We evaluated five different marker gestures and report very promising results for actual use.
{"title":"Automatic Synchronization of Wearable Sensors and Video-Cameras for Ground Truth Annotation -- A Practical Approach","authors":"T. Plötz, Cheng Chen, Nils Y. Hammerla, G. Abowd","doi":"10.1109/ISWC.2012.15","DOIUrl":"https://doi.org/10.1109/ISWC.2012.15","url":null,"abstract":"The common practice of manual synchronization of body-worn, logging accelerometers and video cameras is impractical for integration into everyday practice for applications such as real-world behavior analysis. We significantly extend an existing technique for automatic cross-modal synchronization and evaluate its performance in a realistic experimental setting. Distinctive gestures, captured by a camera, are matched with recorded acceleration signal(s) using cross-correlation based time-delay estimation. PCA-based data pre-processing makes the procedure robust against orientation mismatches between the marking gesture and the camera plane. We evaluated five different marker gestures and report very promising results for actual use.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131749500","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}
The International Symposium on Wearable Computers is now in its 16th year. With little research available into the historical content of wearable computing literature, this paper attempts to identify key trends within the 510 conference articles currently published. A longitudinal study is undertaken using word frequency analysis, which suggests a shift in emphasis from describing and prototyping wearable computers, to evaluative methods and activity sensing techniques.
{"title":"A Textual Analysis of the International Symposium on Wearable Computers: 1997 -- 2011 Proceedings","authors":"Adam Martin","doi":"10.1109/ISWC.2012.31","DOIUrl":"https://doi.org/10.1109/ISWC.2012.31","url":null,"abstract":"The International Symposium on Wearable Computers is now in its 16th year. With little research available into the historical content of wearable computing literature, this paper attempts to identify key trends within the 510 conference articles currently published. A longitudinal study is undertaken using word frequency analysis, which suggests a shift in emphasis from describing and prototyping wearable computers, to evaluative methods and activity sensing techniques.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123926553","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}
Mining patterns of human behavior from large-scale mobile phone data has potential to understand certain phenomena in society. The study of such human-centric massive datasets requires new mathematical models. In this paper, we propose a probabilistic topic model that we call the distant n-gram topic model (DNTM) to address the problem of learning long duration human location sequences. The DNTM is based on Latent Dirichlet Allocation (LDA). We define the generative process for the model, derive the inference procedure and evaluate our model on real mobile data. We consider two different real-life human datasets, collected by mobile phone locations, the first considering GPS locations and the second considering cell tower connections. The DNTM successfully discovers topics on the two datasets. Finally, the DNTM is compared to LDA by considering log-likelihood performance on unseen data, showing the predictive power of the model on unseen data. We find that the DNTM consistantly outperforms LDA as the sequence length increases.
{"title":"Extracting Mobile Behavioral Patterns with the Distant N-Gram Topic Model","authors":"K. Farrahi, D. Gática-Pérez","doi":"10.1109/ISWC.2012.20","DOIUrl":"https://doi.org/10.1109/ISWC.2012.20","url":null,"abstract":"Mining patterns of human behavior from large-scale mobile phone data has potential to understand certain phenomena in society. The study of such human-centric massive datasets requires new mathematical models. In this paper, we propose a probabilistic topic model that we call the distant n-gram topic model (DNTM) to address the problem of learning long duration human location sequences. The DNTM is based on Latent Dirichlet Allocation (LDA). We define the generative process for the model, derive the inference procedure and evaluate our model on real mobile data. We consider two different real-life human datasets, collected by mobile phone locations, the first considering GPS locations and the second considering cell tower connections. The DNTM successfully discovers topics on the two datasets. Finally, the DNTM is compared to LDA by considering log-likelihood performance on unseen data, showing the predictive power of the model on unseen data. We find that the DNTM consistantly outperforms LDA as the sequence length increases.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122673568","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}
Kevin Huang, P. Sparto, S. Kiesler, D. Siewiorek, A. Smailagic
When people fall and experience problems of balance, physical therapists (PTs) often prescribe home balance exercises involving repetitive head movements. Currently, patients' compliance and performance of these home exercises are invisible to PTs, who need the data to make informed decisions for treatment adjustments. We present an easy-to-use tool that monitors patients' home balance exercises and provides PTs with accurate, quantitative patient data. The tool, Head Coach, is a wearable device implemented in an iPod, fitted in a pocket on a baseball cap, and worn by patients while doing their exercises. We tested the reliability of the system using a magnetic field tracking device (Polhemus) as the gold standard. The test showed that the iPod can be used to accurately track home balance exercises.
{"title":"iPod for Home Balance Rehabilitation Exercise Monitoring","authors":"Kevin Huang, P. Sparto, S. Kiesler, D. Siewiorek, A. Smailagic","doi":"10.1109/ISWC.2012.30","DOIUrl":"https://doi.org/10.1109/ISWC.2012.30","url":null,"abstract":"When people fall and experience problems of balance, physical therapists (PTs) often prescribe home balance exercises involving repetitive head movements. Currently, patients' compliance and performance of these home exercises are invisible to PTs, who need the data to make informed decisions for treatment adjustments. We present an easy-to-use tool that monitors patients' home balance exercises and provides PTs with accurate, quantitative patient data. The tool, Head Coach, is a wearable device implemented in an iPod, fitted in a pocket on a baseball cap, and worn by patients while doing their exercises. We tested the reliability of the system using a magnetic field tracking device (Polhemus) as the gold standard. The test showed that the iPod can be used to accurately track home balance exercises.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126498728","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}
This work presents an approach to model daily life contexts from web-collected audio data. Being available in vast quantities from many different sources, audio data from the web provides heterogeneous training data to construct recognition systems. Crowd-sourced textual descriptions (tags) related to individual sound samples were used in a configurable recognition system to model 23 sound context categories. We analysed our approach using different outlier filtering techniques with dedicated recordings of all 23 categories and in a study with 230 hours of full-day recordings of 10 participants using smart phones. Depending on the outlier technique, our system achieved recognition accuracies between 51% and 80%.
{"title":"Recognizing Daily Life Context Using Web-Collected Audio Data","authors":"M. Rossi, G. Tröster, O. Amft","doi":"10.1109/ISWC.2012.12","DOIUrl":"https://doi.org/10.1109/ISWC.2012.12","url":null,"abstract":"This work presents an approach to model daily life contexts from web-collected audio data. Being available in vast quantities from many different sources, audio data from the web provides heterogeneous training data to construct recognition systems. Crowd-sourced textual descriptions (tags) related to individual sound samples were used in a configurable recognition system to model 23 sound context categories. We analysed our approach using different outlier filtering techniques with dedicated recordings of all 23 categories and in a study with 230 hours of full-day recordings of 10 participants using smart phones. Depending on the outlier technique, our system achieved recognition accuracies between 51% and 80%.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116625036","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}
Zhixian Yan, Vigneshwaran Subbaraju, D. Chakraborty, Archan Misra, K. Aberer
Power consumption on mobile phones is a painful obstacle towards adoption of continuous sensing driven applications, e.g., continuously inferring individual's locomotive activities (such as 'sit', 'stand' or 'walk') using the embedded accelerometer sensor. To reduce the energy overhead of such continuous activity sensing, we first investigate how the choice of accelerometer sampling frequency & classification features affects, separately for each activity, the "energy overhead" vs. "classification accuracy" tradeoff. We find that such tradeoff is activity specific. Based on this finding, we introduce an activity-sensitive strategy (dubbed "A3R" - Adaptive Accelerometer-based Activity Recognition) for continuous activity recognition, where the choice of both the accelerometer sampling frequency and the classification features are adapted in real-time, as an individual performs daily lifestyle-based activities. We evaluate the performance of A3R using longitudinal, multi-day observations of continuous activity traces. We also implement A3R for the Android platform and carry out evaluation of energy savings. We show that our strategy can achieve an energy savings of 50% under ideal conditions. For users running the A3R application on their Android phones, we achieve an overall energy savings of 20-25%.
{"title":"Energy-Efficient Continuous Activity Recognition on Mobile Phones: An Activity-Adaptive Approach","authors":"Zhixian Yan, Vigneshwaran Subbaraju, D. Chakraborty, Archan Misra, K. Aberer","doi":"10.1109/ISWC.2012.23","DOIUrl":"https://doi.org/10.1109/ISWC.2012.23","url":null,"abstract":"Power consumption on mobile phones is a painful obstacle towards adoption of continuous sensing driven applications, e.g., continuously inferring individual's locomotive activities (such as 'sit', 'stand' or 'walk') using the embedded accelerometer sensor. To reduce the energy overhead of such continuous activity sensing, we first investigate how the choice of accelerometer sampling frequency & classification features affects, separately for each activity, the \"energy overhead\" vs. \"classification accuracy\" tradeoff. We find that such tradeoff is activity specific. Based on this finding, we introduce an activity-sensitive strategy (dubbed \"A3R\" - Adaptive Accelerometer-based Activity Recognition) for continuous activity recognition, where the choice of both the accelerometer sampling frequency and the classification features are adapted in real-time, as an individual performs daily lifestyle-based activities. We evaluate the performance of A3R using longitudinal, multi-day observations of continuous activity traces. We also implement A3R for the Android platform and carry out evaluation of energy savings. We show that our strategy can achieve an energy savings of 50% under ideal conditions. For users running the A3R application on their Android phones, we achieve an overall energy savings of 20-25%.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114854503","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}
Order picking is the process of collecting items from an assortment in inventory. In previous studies, we focused on carefully-controlled, internally-valid studies comparing the speed and accuracy of various versions of mobile order picking systems. However, such studies lack the ecological validity of testing on a manufacturing line with experienced employees fulfilling actual orders under time and accuracy constraints. In this work we discuss our experiences from planning and conducting a study in a large automobile company.
{"title":"Studying Order Picking in an Operating Automobile Manufacturing Plant","authors":"Hannes Baumann, Thad Starner, Patrick Zschaler","doi":"10.1109/ISWC.2012.24","DOIUrl":"https://doi.org/10.1109/ISWC.2012.24","url":null,"abstract":"Order picking is the process of collecting items from an assortment in inventory. In previous studies, we focused on carefully-controlled, internally-valid studies comparing the speed and accuracy of various versions of mobile order picking systems. However, such studies lack the ecological validity of testing on a manufacturing line with experienced employees fulfilling actual orders under time and accuracy constraints. In this work we discuss our experiences from planning and conducting a study in a large automobile company.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126162380","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}
Zhixian Yan, D. Chakraborty, Archan Misra, Hoyoung Jeung, K. Aberer
We analyze the ability of mobile phone-generated accelerometer data to detect high-level (i.e., at the semantic level) indoor lifestyle activities, such as cooking at home and working at the workplace, in practical settings. We design a 2-Tier activity extraction framework (called SAMMPLE) for our purpose. Using this, we evaluate discriminatory power of activity structures along the dimension of statistical features and after a transformation to a sequence of individual locomotive micro-activities (e.g. sitting or standing). Our findings from 152 days of real-life behavioral traces reveal that locomotive signatures achieve an average accuracy of 77.14%, an improvement of 16.37% over directly using statistical features.
{"title":"SAMMPLE: Detecting Semantic Indoor Activities in Practical Settings Using Locomotive Signatures","authors":"Zhixian Yan, D. Chakraborty, Archan Misra, Hoyoung Jeung, K. Aberer","doi":"10.1109/ISWC.2012.22","DOIUrl":"https://doi.org/10.1109/ISWC.2012.22","url":null,"abstract":"We analyze the ability of mobile phone-generated accelerometer data to detect high-level (i.e., at the semantic level) indoor lifestyle activities, such as cooking at home and working at the workplace, in practical settings. We design a 2-Tier activity extraction framework (called SAMMPLE) for our purpose. Using this, we evaluate discriminatory power of activity structures along the dimension of statistical features and after a transformation to a sequence of individual locomotive micro-activities (e.g. sitting or standing). Our findings from 152 days of real-life behavioral traces reveal that locomotive signatures achieve an average accuracy of 77.14%, an improvement of 16.37% over directly using statistical features.","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"1990 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130857088","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}
Energy storage is quickly becoming the limiting factor in mobile pervasive technology. For intelligent wearable applications to be practical, methods for low power activity recognition must be embedded in mobile devices. We present a novel method for activity recognition which leverages the predictability of human behavior to conserve energy. The novel algorithm accomplishes this by quantifying activity-sensor dependencies, and using prediction methods to identify likely future activities. Sensors are then identified which can be temporarily turned off at little or no recognition cost. The approach is implemented and simulated using an activity recognition data set, revealing that large savings in energy are possible at very low cost (e.g. 84% energy savings for a loss of 1.2 pp in recognition).
{"title":"Energy-Efficient Activity Recognition Using Prediction","authors":"Dawud Gordon, J. Czerny, Takashi Miyaki, M. Beigl","doi":"10.1109/ISWC.2012.25","DOIUrl":"https://doi.org/10.1109/ISWC.2012.25","url":null,"abstract":"Energy storage is quickly becoming the limiting factor in mobile pervasive technology. For intelligent wearable applications to be practical, methods for low power activity recognition must be embedded in mobile devices. We present a novel method for activity recognition which leverages the predictability of human behavior to conserve energy. The novel algorithm accomplishes this by quantifying activity-sensor dependencies, and using prediction methods to identify likely future activities. Sensors are then identified which can be temporarily turned off at little or no recognition cost. The approach is implemented and simulated using an activity recognition data set, revealing that large savings in energy are possible at very low cost (e.g. 84% energy savings for a loss of 1.2 pp in recognition).","PeriodicalId":190627,"journal":{"name":"2012 16th International Symposium on Wearable Computers","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122488224","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：