Recently, inferring the state of people’s mental health via passive mobile sensing has attracted significant attention. Previous studies have used the self-assessed stress levels as the ground truth; however, these are subjective measures. In this study, we use a physiologically-assessed stress metric to minimize the effect of participant subjectivity and further estimate it using behavioral features based on the smartphone usage logs. We initially requested the study participants (39 participants) to attach heart rate sensors for 8 hours per day and simultaneously collected continuous heart rate data and smartphone logs for 42 days. Further, we divided the participants into four types via clustering using the behavioral features derived from their smartphone sensor logs and trained each model via supervised learning using the heart rate data as the ground truth. Our results exhibit that the proposed method is more accurate (71%) as compared to the baseline method (54%). This demonstrates that physiologically-assessed stress levels can be estimated based on the implicit features that are gathered from the smartphone logs.
{"title":"Physiological Stress Level Estimation Based on Smartphone Logs","authors":"Naoki Yamamoto, Keiichi Ochiai, Akiya Inagaki, Yusuke Fukazawa, Masatoshi Kimoto, Kazuki Kiriu, Kouhei Kaminishi, J. Ota, Tsukasa Okimura, Yuri Terasawa, Takaki Maeda","doi":"10.23919/ICMU.2018.8653590","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653590","url":null,"abstract":"Recently, inferring the state of people’s mental health via passive mobile sensing has attracted significant attention. Previous studies have used the self-assessed stress levels as the ground truth; however, these are subjective measures. In this study, we use a physiologically-assessed stress metric to minimize the effect of participant subjectivity and further estimate it using behavioral features based on the smartphone usage logs. We initially requested the study participants (39 participants) to attach heart rate sensors for 8 hours per day and simultaneously collected continuous heart rate data and smartphone logs for 42 days. Further, we divided the participants into four types via clustering using the behavioral features derived from their smartphone sensor logs and trained each model via supervised learning using the heart rate data as the ground truth. Our results exhibit that the proposed method is more accurate (71%) as compared to the baseline method (54%). This demonstrates that physiologically-assessed stress levels can be estimated based on the implicit features that are gathered from the smartphone logs.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124103463","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653263
Ryota Kimoto, Takahiro Yamamoto, S. Ishida, S. Tagashira, Akira Fukuda
Sensor localization is one of the big problems when building large scale indoor sensor networks. We are developing ZigLoc, a sensor localization system using Wi-Fi (IEEE802.11) APs (access points) as references [1], [2]. ZigLoc measures RSS (received signal strength) of Wi-Fi AP signals to localize ZigBee (IEEE802.15.4) sensor nodes. However, ZigLoc exhibits low accuracy because of inaccurate RSS measured on a single narrow-band ZigBee channel. In this paper, we present a highly accurate sensor localization system MultiZigLoc, which is an extended system of ZigLoc. Our key idea is to employ RSS measured in multiple ZigBee channels in fingerprinting localization. The RSS in multiple channels is dependent on the measured location because ZigBee uses narrow-band channels. Narrow-band ZigBee communication is highly affected by frequency selective fading, whose influence is dependent on channels and locations of both Wi-Fi APs and a sensor. We utilize fingerprints that separately handles RSS in multiple ZigBee channels to employ channel specific features. We conducted initial evaluations using RSS measured in a practical environment. The evaluations reveal that MultiZigLoc improved the localization accuracy by more than 10 points.
{"title":"Evaluation of MultiZigLoc: Indoor ZigBee Localization System Using Inter-Channel Characteristics","authors":"Ryota Kimoto, Takahiro Yamamoto, S. Ishida, S. Tagashira, Akira Fukuda","doi":"10.23919/ICMU.2018.8653263","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653263","url":null,"abstract":"Sensor localization is one of the big problems when building large scale indoor sensor networks. We are developing ZigLoc, a sensor localization system using Wi-Fi (IEEE802.11) APs (access points) as references [1], [2]. ZigLoc measures RSS (received signal strength) of Wi-Fi AP signals to localize ZigBee (IEEE802.15.4) sensor nodes. However, ZigLoc exhibits low accuracy because of inaccurate RSS measured on a single narrow-band ZigBee channel. In this paper, we present a highly accurate sensor localization system MultiZigLoc, which is an extended system of ZigLoc. Our key idea is to employ RSS measured in multiple ZigBee channels in fingerprinting localization. The RSS in multiple channels is dependent on the measured location because ZigBee uses narrow-band channels. Narrow-band ZigBee communication is highly affected by frequency selective fading, whose influence is dependent on channels and locations of both Wi-Fi APs and a sensor. We utilize fingerprints that separately handles RSS in multiple ZigBee channels to employ channel specific features. We conducted initial evaluations using RSS measured in a practical environment. The evaluations reveal that MultiZigLoc improved the localization accuracy by more than 10 points.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125224461","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653586
Zhishu Shen, A. Tagami, T. Higashino
Wireless sensor networks (WSNs) are playing an increasingly important role in monitoring massive sensors to precisely detect anomalous phenomena, including anomalous events and sensor data faults. Prior studies preferred to dig the event anomaly (e.g., hotspots in a room), while sensor data faults were simply regarded as noise. Considering that different anomalies arise for different reasons, some substantial hidden problems such as internal sensor failures may be ignored. In this study, we propose an efficient data processing scheme using machine learning model with the objective of achieving satisfactory anomaly detection performance during WSN monitoring. Our proposal analyzes the difficulty of detecting different types of fault data and the influence of each type on event detection results. The machine learning model is adopted to analyze the sensor data correlation, to achieve satisfactory performance for both event detection and fault detection by analyzing the correlated sensor data. At each monitoring time during the data monitoring process, the trivial sensor data faults that might affect the event detection results are filtered out before executing event detection. Meanwhile, at much longer monitoring time intervals, random fault detection is performed to find potentially hidden failures of sensors. Numerical experiments conducted in a real WSN environment show that neural network model outperforms other machine learning models in anomaly detection, and the results by adopting neural network model verify the feasibility of our proposed scheme which attains acceptable performance in detecting both types of anomalies.
{"title":"An Efficient Data Processing Scheme for Wireless Sensor Network Monitoring Using a Machine Learning Model","authors":"Zhishu Shen, A. Tagami, T. Higashino","doi":"10.23919/ICMU.2018.8653586","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653586","url":null,"abstract":"Wireless sensor networks (WSNs) are playing an increasingly important role in monitoring massive sensors to precisely detect anomalous phenomena, including anomalous events and sensor data faults. Prior studies preferred to dig the event anomaly (e.g., hotspots in a room), while sensor data faults were simply regarded as noise. Considering that different anomalies arise for different reasons, some substantial hidden problems such as internal sensor failures may be ignored. In this study, we propose an efficient data processing scheme using machine learning model with the objective of achieving satisfactory anomaly detection performance during WSN monitoring. Our proposal analyzes the difficulty of detecting different types of fault data and the influence of each type on event detection results. The machine learning model is adopted to analyze the sensor data correlation, to achieve satisfactory performance for both event detection and fault detection by analyzing the correlated sensor data. At each monitoring time during the data monitoring process, the trivial sensor data faults that might affect the event detection results are filtered out before executing event detection. Meanwhile, at much longer monitoring time intervals, random fault detection is performed to find potentially hidden failures of sensors. Numerical experiments conducted in a real WSN environment show that neural network model outperforms other machine learning models in anomaly detection, and the results by adopting neural network model verify the feasibility of our proposed scheme which attains acceptable performance in detecting both types of anomalies.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125545626","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653609
Yuta Sakoguchi, Toshiya Miyazaki, H. Shigeno
Dynamic Route Guidance (DRG) system, which determines the traveling routes of vehicles, alleviates traffic problems in urban areas. On the other hand, ad-hoc network composed of vehicles, called VANET attracts attention from many researchers and VANET-based DRG systems are proposed. However, the existing DRG systems do not consider that degradation of communication performance causes degradation of application performance. Packet loss of traffic information hinders determining proper travelling routes. In this paper, we propose VANET-based DRG system with dynamic communication path selection by considering vehicle density, called DRG-DCPS. Each vehicle acquires traffic information by a request/response packet. Relay vehicles select crowded road segments as packet paths to improve communication performance. As a result, since each vehicle receives traffic information more correctly and can select appropriate travelling routes. To confirm effectiveness of DRG-DCPS, we implemented on a simulation environment integrating traffic simulator and network simulator.
{"title":"VANET-based Dynamic Route Guidance System Considering Communication Performance","authors":"Yuta Sakoguchi, Toshiya Miyazaki, H. Shigeno","doi":"10.23919/ICMU.2018.8653609","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653609","url":null,"abstract":"Dynamic Route Guidance (DRG) system, which determines the traveling routes of vehicles, alleviates traffic problems in urban areas. On the other hand, ad-hoc network composed of vehicles, called VANET attracts attention from many researchers and VANET-based DRG systems are proposed. However, the existing DRG systems do not consider that degradation of communication performance causes degradation of application performance. Packet loss of traffic information hinders determining proper travelling routes. In this paper, we propose VANET-based DRG system with dynamic communication path selection by considering vehicle density, called DRG-DCPS. Each vehicle acquires traffic information by a request/response packet. Relay vehicles select crowded road segments as packet paths to improve communication performance. As a result, since each vehicle receives traffic information more correctly and can select appropriate travelling routes. To confirm effectiveness of DRG-DCPS, we implemented on a simulation environment integrating traffic simulator and network simulator.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122218704","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653621
C. Rapson, Boon-Chong Seet, P. Chong, R. Klette
Visible Light Communications (VLC) is being developed as an alternative to radio frequency (RF) communication for vehicular applications. It has the advantages of high signal-to-noise ratio (SNR), limited interference due to line-of-sight transmission and dual use of existing hardware (LED lights and cameras) on most modern vehicles. Camera based receivers typically sample light signals at a much slower rate than the frequency at which they are modulated by LED-based transmitters. To address the aliasing due to sampling at sub-Nyquist rate, a range of undersampled encoding methods have been proposed. A common disadvantage of these proposals has been a data rate on the order of ten bits per second, which is too low for most applications. This paper investigates the use of Non-Orthogonal Multiple Access(NOMA) to leverage the high SNR and increase the data rate for undersampled Optical Camera Communication (OCC). A significant increase in data rate can be achieved at the cost of some tradeoff in SNR. Further increase in data rate is possible when used in conjunction with other methods such as Wavelength Division Multiplexing, polarisation and MIMO arrays.
{"title":"Applying NOMA to Undersampled Optical Camera Communication for Vehicular Communication","authors":"C. Rapson, Boon-Chong Seet, P. Chong, R. Klette","doi":"10.23919/ICMU.2018.8653621","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653621","url":null,"abstract":"Visible Light Communications (VLC) is being developed as an alternative to radio frequency (RF) communication for vehicular applications. It has the advantages of high signal-to-noise ratio (SNR), limited interference due to line-of-sight transmission and dual use of existing hardware (LED lights and cameras) on most modern vehicles. Camera based receivers typically sample light signals at a much slower rate than the frequency at which they are modulated by LED-based transmitters. To address the aliasing due to sampling at sub-Nyquist rate, a range of undersampled encoding methods have been proposed. A common disadvantage of these proposals has been a data rate on the order of ten bits per second, which is too low for most applications. This paper investigates the use of Non-Orthogonal Multiple Access(NOMA) to leverage the high SNR and increase the data rate for undersampled Optical Camera Communication (OCC). A significant increase in data rate can be achieved at the cost of some tradeoff in SNR. Further increase in data rate is possible when used in conjunction with other methods such as Wavelength Division Multiplexing, polarisation and MIMO arrays.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122327839","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653610
Yuki Katsumata, Daisuke Nojima, A. Yamada
In order to provide high-bandwidth services to visitors such as sports fans in a stadium, we propose a High-Density Wi-Fi system design that enhances network performance through dynamic parameter control and that automates system operations. In High-Density Wi-Fi, high-density and high-performance areas are formed by miniaturizing the cell size and increasing the number of access points (APs). In order to increase the performance, highly skilled engineers analyze and control a massive number of deployed APs via a wireless local area network (WLAN) controller. The purpose of this study is to enhance the Quality of Experience of visitors. Toward this end, we propose a system design that automatically optimizes the network using the WLAN controller in High-Density Wi-Fi to increase the Quality of Service. Incorporated in the system is a proposed method that analyzes and controls APs and stations (STAs) dynamically to enhance network performance. We focus on addressing the problem of clients that do not release a poor connection, i.e., the Sticky Client Problem, which results in degraded performance. The proposed method is unique in that it mitigates this problem using dynamic parameter control on each STA based on massive amounts of information stored in the database. Simulation results show that the proposed method, which instructs 4.3x STAs to handover to another available AP in 100 min, improves the system throughput by 12 %.
{"title":"Dynamic Parameter Control Method Mitigating Sticky Client Problem in High-Density Wi-Fi","authors":"Yuki Katsumata, Daisuke Nojima, A. Yamada","doi":"10.23919/ICMU.2018.8653610","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653610","url":null,"abstract":"In order to provide high-bandwidth services to visitors such as sports fans in a stadium, we propose a High-Density Wi-Fi system design that enhances network performance through dynamic parameter control and that automates system operations. In High-Density Wi-Fi, high-density and high-performance areas are formed by miniaturizing the cell size and increasing the number of access points (APs). In order to increase the performance, highly skilled engineers analyze and control a massive number of deployed APs via a wireless local area network (WLAN) controller. The purpose of this study is to enhance the Quality of Experience of visitors. Toward this end, we propose a system design that automatically optimizes the network using the WLAN controller in High-Density Wi-Fi to increase the Quality of Service. Incorporated in the system is a proposed method that analyzes and controls APs and stations (STAs) dynamically to enhance network performance. We focus on addressing the problem of clients that do not release a poor connection, i.e., the Sticky Client Problem, which results in degraded performance. The proposed method is unique in that it mitigates this problem using dynamic parameter control on each STA based on massive amounts of information stored in the database. Simulation results show that the proposed method, which instructs 4.3x STAs to handover to another available AP in 100 min, improves the system throughput by 12 %.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131347616","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 : 2018-10-01DOI: 10.23919/icmu.2018.8653622
{"title":"ICMU 2018 Program","authors":"","doi":"10.23919/icmu.2018.8653622","DOIUrl":"https://doi.org/10.23919/icmu.2018.8653622","url":null,"abstract":"","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"299302 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116576132","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653594
Toru Kobayashi, Taishi Miyazaki, Kenichi Arai
We developed Dementia Diagnosis System based on the natural conversation between an elderly person and a robot. This system consists of the function to generate a scenario from Hasegawa dementia rating scale-revised (HDS-R). This system also includes the function to calculate the recognition score through the interactive communication based on the scenarios. We confirmed the effectiveness of this system by evaluation experiment in comparing with the conventional HDS-R method operated by examiners.
{"title":"Dementia Diagnosis System Using Social Media Agency Robot","authors":"Toru Kobayashi, Taishi Miyazaki, Kenichi Arai","doi":"10.23919/ICMU.2018.8653594","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653594","url":null,"abstract":"We developed Dementia Diagnosis System based on the natural conversation between an elderly person and a robot. This system consists of the function to generate a scenario from Hasegawa dementia rating scale-revised (HDS-R). This system also includes the function to calculate the recognition score through the interactive communication based on the scenarios. We confirmed the effectiveness of this system by evaluation experiment in comparing with the conventional HDS-R method operated by examiners.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131405428","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653262
Kosuke Yotsuya, Nobuyuki Ito, K. Naito, N. Chujo, T. Mizuno, K. Kaji
Building structure information is essential for achieving various indoor location-based services (ILBSs). Our approach integrates a large amount of pedestrian trajectories acquired by pedestrian dead reckoning (PDR) for generating a pedestrian network structure. To generate highly accurate pedestrian network structures, the accuracy of each trajectory must be improved. In this paper, we propose a method to improve the accuracy of indoor PDR trajectories using many of them. First, we select reliable trajectories based on the stability of the sensing data. Next, by analyzing the trend of step lengths, we correct the length of the trajectories. Finally, with same-route trajectories, we generate average trajectories for each route. We experimentally used HASC-IPSC and found that our proposed method improved the accuracy of the trajectories. The cumulative error rate of the original pedestrian trajectory was 0.1111 [m/s]. After adapting our proposed method, the rate improved to 0.0622[m/s].
{"title":"Method to Improve Accuracy of Indoor PDR Trajectories Using a Large Amount of Trajectories","authors":"Kosuke Yotsuya, Nobuyuki Ito, K. Naito, N. Chujo, T. Mizuno, K. Kaji","doi":"10.23919/ICMU.2018.8653262","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653262","url":null,"abstract":"Building structure information is essential for achieving various indoor location-based services (ILBSs). Our approach integrates a large amount of pedestrian trajectories acquired by pedestrian dead reckoning (PDR) for generating a pedestrian network structure. To generate highly accurate pedestrian network structures, the accuracy of each trajectory must be improved. In this paper, we propose a method to improve the accuracy of indoor PDR trajectories using many of them. First, we select reliable trajectories based on the stability of the sensing data. Next, by analyzing the trend of step lengths, we correct the length of the trajectories. Finally, with same-route trajectories, we generate average trajectories for each route. We experimentally used HASC-IPSC and found that our proposed method improved the accuracy of the trajectories. The cumulative error rate of the original pedestrian trajectory was 0.1111 [m/s]. After adapting our proposed method, the rate improved to 0.0622[m/s].","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131316424","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 : 2018-10-01DOI: 10.23919/ICMU.2018.8653616
Research Dawadi, Teruhiro Mizumoto, K. Yasumoto
There has been a steady increase in the number of elderly people living alone. The isolation occurs due to children moving away from their parents house and also because of the loss of spouse or relatives. Therefore, to ensure security and comfort of the elderly, their children employ caretakers to assist and monitor them in their daily life. However, caretakers are fewer in number to the elderly people, and expensive as well. Similarly, children are too busy with their own lives to focus in regular monitoring of their parents. To tackle this situation, we present a system called MutualMonitor, which enables elderly people to monitor each other by using a mobile application. To maintain security and privacy of individuals and prevent the disclosure of any personal details, the monitoring is carried out anonymously. We collect information from 4 areas of the house: bedroom, living room, kitchen, and bathroom, about daily activities such as cooking, sleeping, taking medicine, etc. through the use of different kinds of sensors and electricity consumption units available in the home of the elderly. A record of daily activities and their duration is generated. Similarly, notifications are sent at regular intervals to the monitoring elderly to encourage them to view the current state of the elderly. To test the effectiveness of notification in mutual monitoring, in this study we test a service application that sends regular notifications to the user. We determined the response rate and delay, and how often the user missed or ignored the notifications. We collected a total of 312 notifications from 8 users. We found that the participants dealt with an average of 6.4 notifications per day from our application, and responded to 87% of them.
{"title":"MutualMonitor: A Tool for Elderly People to Anonymously Monitor Each Other","authors":"Research Dawadi, Teruhiro Mizumoto, K. Yasumoto","doi":"10.23919/ICMU.2018.8653616","DOIUrl":"https://doi.org/10.23919/ICMU.2018.8653616","url":null,"abstract":"There has been a steady increase in the number of elderly people living alone. The isolation occurs due to children moving away from their parents house and also because of the loss of spouse or relatives. Therefore, to ensure security and comfort of the elderly, their children employ caretakers to assist and monitor them in their daily life. However, caretakers are fewer in number to the elderly people, and expensive as well. Similarly, children are too busy with their own lives to focus in regular monitoring of their parents. To tackle this situation, we present a system called MutualMonitor, which enables elderly people to monitor each other by using a mobile application. To maintain security and privacy of individuals and prevent the disclosure of any personal details, the monitoring is carried out anonymously. We collect information from 4 areas of the house: bedroom, living room, kitchen, and bathroom, about daily activities such as cooking, sleeping, taking medicine, etc. through the use of different kinds of sensors and electricity consumption units available in the home of the elderly. A record of daily activities and their duration is generated. Similarly, notifications are sent at regular intervals to the monitoring elderly to encourage them to view the current state of the elderly. To test the effectiveness of notification in mutual monitoring, in this study we test a service application that sends regular notifications to the user. We determined the response rate and delay, and how often the user missed or ignored the notifications. We collected a total of 312 notifications from 8 users. We found that the participants dealt with an average of 6.4 notifications per day from our application, and responded to 87% of them.","PeriodicalId":398108,"journal":{"name":"2018 Eleventh International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125576111","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：