Marian Haescher, Denys J. C. Matthies, Karthik Srinivasan, G. Bieber
We present a novel Smartwatch-based approach, to enable Mobile Assisted Living (MAL) for users with special needs. A major focus group for this approach are elderly people. We developed a tool for caregivers applicable in home environments, nursing care, and hospitals, to assess the vitality of their patients. Hereby, we particularly focus on the prediction of falls, because falls are a major reason for serious injuries and premature death among elderly. Therefore, we propose a multi parametric score based on standardized fall risk assessment tests, as well as on sleep quality, medication, patient history, motor skills, and environmental factors. The resulting total fall risk score reflects individual changes in behavior and vitality, which consequently enables for fall preventing interventions. Our system has been deployed and evaluated in a pilot study among 30 elderly patients over a period of four weeks.
{"title":"Mobile Assisted Living: Smartwatch-based Fall Risk Assessment for Elderly People","authors":"Marian Haescher, Denys J. C. Matthies, Karthik Srinivasan, G. Bieber","doi":"10.1145/3266157.3266210","DOIUrl":"https://doi.org/10.1145/3266157.3266210","url":null,"abstract":"We present a novel Smartwatch-based approach, to enable Mobile Assisted Living (MAL) for users with special needs. A major focus group for this approach are elderly people. We developed a tool for caregivers applicable in home environments, nursing care, and hospitals, to assess the vitality of their patients. Hereby, we particularly focus on the prediction of falls, because falls are a major reason for serious injuries and premature death among elderly. Therefore, we propose a multi parametric score based on standardized fall risk assessment tests, as well as on sleep quality, medication, patient history, motor skills, and environmental factors. The resulting total fall risk score reflects individual changes in behavior and vitality, which consequently enables for fall preventing interventions. Our system has been deployed and evaluated in a pilot study among 30 elderly patients over a period of four weeks.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129618386","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 sensors are consistently decreasing in size, while their computational power simultaneously rises. Current wearables enable high-quality measurements of vital signs and activity data, comparable to state-of-the-art technologies. However, they are rarely implemented in caregiving facilities, such as hospitals or elderly homes. A framework using a wearable sensing unit is proposed that mainly relies on an Inertial Measurement Unit (IMU), where an extension to a variety of sensor types are possible. This sensing unit is worn by the patient and connected to a base station. This will be locally distributed by placing one unit in each room. The sensor unit extracts various vital signs and activity parameters, transmitting such information wirelessly through a low-energy transmission standard. The data is easily accessible to any caregiver using a common mobile end-user device. The proposed approach is superior to previous attempts, as it overcomes common barriers that prevented implementation. By outlining current challenges, solutions are recommended to appropriately overcome these issues within a future system.
{"title":"Outlining a Novel Framework for Monitoring User's Vital Signs and Activity Data in Caregiving Facilities","authors":"Denys J. C. Matthies","doi":"10.1145/3266157.3266224","DOIUrl":"https://doi.org/10.1145/3266157.3266224","url":null,"abstract":"Wearable sensors are consistently decreasing in size, while their computational power simultaneously rises. Current wearables enable high-quality measurements of vital signs and activity data, comparable to state-of-the-art technologies. However, they are rarely implemented in caregiving facilities, such as hospitals or elderly homes. A framework using a wearable sensing unit is proposed that mainly relies on an Inertial Measurement Unit (IMU), where an extension to a variety of sensor types are possible. This sensing unit is worn by the patient and connected to a base station. This will be locally distributed by placing one unit in each room. The sensor unit extracts various vital signs and activity parameters, transmitting such information wirelessly through a low-energy transmission standard. The data is easily accessible to any caregiver using a common mobile end-user device. The proposed approach is superior to previous attempts, as it overcomes common barriers that prevented implementation. By outlining current challenges, solutions are recommended to appropriately overcome these issues within a future system.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122195268","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}
Human activity recognition using wearable sensors is an area of interest for various domains like healthcare, surveillance etc. Various approaches have been used to solve the problem of activity recognition. Recently deep learning methods like RNNs and LSTMs have been used for this task. But these architectures are unable to capture long term dependencies in time series data. In this work, we propose to use the Temporal Convolutional Network architecture for recognizing the activities from the sensor data obtained from a smartphone. Due to the potential of the architecture to take variable length input sequences along with significantly better ability to capture long term dependencies, it performs better than other deep learning methods. The results of the proposed methods shows an improved performance over the existing methods.
{"title":"Human Activity Recognition Using Temporal Convolutional Network","authors":"Nitin Nair, Chinchu Thomas, D. Jayagopi","doi":"10.1145/3266157.3266221","DOIUrl":"https://doi.org/10.1145/3266157.3266221","url":null,"abstract":"Human activity recognition using wearable sensors is an area of interest for various domains like healthcare, surveillance etc. Various approaches have been used to solve the problem of activity recognition. Recently deep learning methods like RNNs and LSTMs have been used for this task. But these architectures are unable to capture long term dependencies in time series data. In this work, we propose to use the Temporal Convolutional Network architecture for recognizing the activities from the sensor data obtained from a smartphone. Due to the potential of the architecture to take variable length input sequences along with significantly better ability to capture long term dependencies, it performs better than other deep learning methods. The results of the proposed methods shows an improved performance over the existing methods.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125403264","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 are at a point in history, where it seems feasible that we create technologies that could become smarter than humans. This raises the fundamental question of what roles humans play in a future world. I argue that by using these advances in technologies and in particular in sensing and AI we can amplify human perception and cognition to levels that we could never before in history even imagine. We are at the beginning of this fundamental transformation: the use of digital tools to amplify the mind. Many products, ranging from mobile access to search engines, to wearable devices for lifelogging and augmented realty application give us first indications of this transition. In our research we create novel digital technologies that systematically explore how to enhance human cognition and perception. Our experimental approach is to: first, understand the users in their context as well as the potential for enhancement. Second, we create innovative interventions that provide functionality that amplifies human capabilities. And third, we empirically evaluate and quantify the enhancement that is gained by these developments. It is exciting to see how ultimately these new ubiquitous computing technologies have the potential for overcoming fundamental limitations in human perception and cognition and lead the way for creating cognitive and perceptual super powers. If we succeed to create technologies that seamlessly amplify human cognition and perception, humans augmented with these technologies will outsmart artificial intelligence.
{"title":"Is artificial intelligence (AI) taking over the world?: Are humans losing out to AI in the work place?","authors":"A. Schmidt","doi":"10.1145/3266157.3266205","DOIUrl":"https://doi.org/10.1145/3266157.3266205","url":null,"abstract":"We are at a point in history, where it seems feasible that we create technologies that could become smarter than humans. This raises the fundamental question of what roles humans play in a future world. I argue that by using these advances in technologies and in particular in sensing and AI we can amplify human perception and cognition to levels that we could never before in history even imagine. We are at the beginning of this fundamental transformation: the use of digital tools to amplify the mind. Many products, ranging from mobile access to search engines, to wearable devices for lifelogging and augmented realty application give us first indications of this transition. In our research we create novel digital technologies that systematically explore how to enhance human cognition and perception. Our experimental approach is to: first, understand the users in their context as well as the potential for enhancement. Second, we create innovative interventions that provide functionality that amplifies human capabilities. And third, we empirically evaluate and quantify the enhancement that is gained by these developments. It is exciting to see how ultimately these new ubiquitous computing technologies have the potential for overcoming fundamental limitations in human perception and cognition and lead the way for creating cognitive and perceptual super powers. If we succeed to create technologies that seamlessly amplify human cognition and perception, humans augmented with these technologies will outsmart artificial intelligence.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130037710","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}
E. Casilari-Pérez, J. Santoyo-Ramón, J. Cano-García
The use of publicly available repositories containing movement traces of real or experimental subjects is a key aspect to define an evaluation framework that allows a systematic assessment of wearable fall detection systems. This papers presents a detailed analysis of a public dataset of traces which employed five sensing points to characterize the user's mobility during the execution of ADLs (Activities of Daily Living) and emulated falls. The analysis is aimed at analysing two main factors: the importance of the election of the position of the sensor and the possible impact of the user's personal features on the statistical characterization of the movements. Results reveal the importance of the nature of the ADL for the effectiveness of the discrimination of the falls.
{"title":"Analysis of a Public Repository for the Study of Automatic Fall Detection Algorithms","authors":"E. Casilari-Pérez, J. Santoyo-Ramón, J. Cano-García","doi":"10.1145/3266157.3266211","DOIUrl":"https://doi.org/10.1145/3266157.3266211","url":null,"abstract":"The use of publicly available repositories containing movement traces of real or experimental subjects is a key aspect to define an evaluation framework that allows a systematic assessment of wearable fall detection systems. This papers presents a detailed analysis of a public dataset of traces which employed five sensing points to characterize the user's mobility during the execution of ADLs (Activities of Daily Living) and emulated falls. The analysis is aimed at analysing two main factors: the importance of the election of the position of the sensor and the possible impact of the user's personal features on the statistical characterization of the movements. Results reveal the importance of the nature of the ADL for the effectiveness of the discrimination of the falls.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124564745","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}
Recently, Lifted Marginal Filtering [5] has been proposed, an approach for efficient probabilistic inference in systems with multiple, (inter-)acting agents and objects (entities). The algorithm achieves its efficiency by performing inference jointly over groups of similar entities (i.e. their properties follow the same distribution). In this paper, we explore the case where there are no entities that are directly suitable for grouping. We propose to use methods from Gaussian mixture fitting and merging to identify entity groups and keep the number of groups constant over time. Empirical results suggest that decrease in prediction accuracy is small, while the algorithm runtime decreases significantly.
{"title":"Gaussian Lifted Marginal Filtering","authors":"S. Lüdtke, Alejandro Molina, T. Kirste","doi":"10.1145/3266157.3266225","DOIUrl":"https://doi.org/10.1145/3266157.3266225","url":null,"abstract":"Recently, Lifted Marginal Filtering [5] has been proposed, an approach for efficient probabilistic inference in systems with multiple, (inter-)acting agents and objects (entities). The algorithm achieves its efficiency by performing inference jointly over groups of similar entities (i.e. their properties follow the same distribution). In this paper, we explore the case where there are no entities that are directly suitable for grouping. We propose to use methods from Gaussian mixture fitting and merging to identify entity groups and keep the number of groups constant over time. Empirical results suggest that decrease in prediction accuracy is small, while the algorithm runtime decreases significantly.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124923027","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}
Christopher Reining, Michelle Schlangen, Leon Hissmann, M. T. Hompel, Fernando Moya Rueda, G. Fink
Semantic descriptions or attribute representations have been used successfully for object and scene recognition, and for word-spotting. However, these representations have not been explored deeply on human activity recognition (HAR). Particularly, in the manual order picking process, attribute representations are beneficial for dealing with the versatility of activities in the process. This paper compares the performance of deep architectures trained using different attribute representations for HAR. Besides, it evaluates their quality from the perspective of practical application.
{"title":"Attribute Representation for Human Activity Recognition of Manual Order Picking Activities","authors":"Christopher Reining, Michelle Schlangen, Leon Hissmann, M. T. Hompel, Fernando Moya Rueda, G. Fink","doi":"10.1145/3266157.3266214","DOIUrl":"https://doi.org/10.1145/3266157.3266214","url":null,"abstract":"Semantic descriptions or attribute representations have been used successfully for object and scene recognition, and for word-spotting. However, these representations have not been explored deeply on human activity recognition (HAR). Particularly, in the manual order picking process, attribute representations are beneficial for dealing with the versatility of activities in the process. This paper compares the performance of deep architectures trained using different attribute representations for HAR. Besides, it evaluates their quality from the perspective of practical application.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125660191","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}
People are increasingly exposed to stress these days. There are numerous possible triggers for stress, e.g. multitasking or frequent interruptions. Although stress cannot be considered fundamentally negative, high stress levels can lead to negative health effects like depression or burnout. Therefore, it is important to act early in order to prevent stress or cope with it appropriately. While advances in sensor technology offer new opportunities to measure stressors and stress reactions automatically, considering individual appraisal is important in order to provide tailored assistance. We propose a framework for IT-supported stress-management that also integrates cognitive appraisal.
{"title":"IT-supported Stress Management: Mediating between Sensor Data and Individual Appraisal","authors":"M. Fellmann, Fabienne Lambusch, L. Pieper","doi":"10.1145/3266157.3266223","DOIUrl":"https://doi.org/10.1145/3266157.3266223","url":null,"abstract":"People are increasingly exposed to stress these days. There are numerous possible triggers for stress, e.g. multitasking or frequent interruptions. Although stress cannot be considered fundamentally negative, high stress levels can lead to negative health effects like depression or burnout. Therefore, it is important to act early in order to prevent stress or cope with it appropriately. While advances in sensor technology offer new opportunities to measure stressors and stress reactions automatically, considering individual appraisal is important in order to provide tailored assistance. We propose a framework for IT-supported stress-management that also integrates cognitive appraisal.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132572384","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}
There were several trials to detect the movement of fingers, they necessitated special sensors, either rings or gloves, attached to the fingers. Based on the background, we have developed a system to identify the moved finger called FinD using the acceleration signals obtained with Commercial Off-The-Shelf (COTS) smart watches. We have investigated two methods: Non Matrix Factorization (NMF)-based (FinD-NMF) and time-series-based (FinD-TS) analyses. We have compared the two methods for three fingers with three subjects and found that FinD-TS exceeds FinD-NMF in the accuracy up to 40%-80%.
{"title":"FinD: Detection of Finger Movement using Smart Watch","authors":"Hiroto Ishikawa, Wataro Takahashi, Y. Tobe","doi":"10.1145/3266157.3266226","DOIUrl":"https://doi.org/10.1145/3266157.3266226","url":null,"abstract":"There were several trials to detect the movement of fingers, they necessitated special sensors, either rings or gloves, attached to the fingers. Based on the background, we have developed a system to identify the moved finger called FinD using the acceleration signals obtained with Commercial Off-The-Shelf (COTS) smart watches. We have investigated two methods: Non Matrix Factorization (NMF)-based (FinD-NMF) and time-series-based (FinD-TS) analyses. We have compared the two methods for three fingers with three subjects and found that FinD-TS exceeds FinD-NMF in the accuracy up to 40%-80%.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130147370","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}
Although, gaze-based interaction has been investigated since the 1980s and provides promising concepts to realize cognitive systems and support universal interaction within distributed environments, the main challenges, such as the Midas touch problem [16] or calibration are still frequent topics of research. In this work, Natural Pursuit Calibration is presented, which is a comfortable, unobtrusive technique enabling ongoing attention detection and eye tracker calibration within an off-screen context. The user is able to perform calibration, without a digital user interface, artificial annotation of the environment nor further assistance, by simply following any arbitrary moving target. Due to the characteristics of the calibration process, it can be executed simultaneously to any primary task, without active user participation. A two-stage evaluation process is conducted to (i) optimize parameter settings in a first setup and (ii) compare the accuracy as well as the user acceptance of the proposed procedure to prevailing calibration techniques.
{"title":"Natural Pursuits for Eye Tracker Calibration","authors":"Michaela Murauer, Michael Haslgrübler, A. Ferscha","doi":"10.1145/3266157.3266207","DOIUrl":"https://doi.org/10.1145/3266157.3266207","url":null,"abstract":"Although, gaze-based interaction has been investigated since the 1980s and provides promising concepts to realize cognitive systems and support universal interaction within distributed environments, the main challenges, such as the Midas touch problem [16] or calibration are still frequent topics of research. In this work, Natural Pursuit Calibration is presented, which is a comfortable, unobtrusive technique enabling ongoing attention detection and eye tracker calibration within an off-screen context. The user is able to perform calibration, without a digital user interface, artificial annotation of the environment nor further assistance, by simply following any arbitrary moving target. Due to the characteristics of the calibration process, it can be executed simultaneously to any primary task, without active user participation. A two-stage evaluation process is conducted to (i) optimize parameter settings in a first setup and (ii) compare the accuracy as well as the user acceptance of the proposed procedure to prevailing calibration techniques.","PeriodicalId":151070,"journal":{"name":"Proceedings of the 5th International Workshop on Sensor-based Activity Recognition and Interaction","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124254733","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：