Dibyayan Patra, Suresh Chavhan, Deepak Gupta, Ashish Khanna, J. Rodrigues
With the development of Vehicle-to-everything (V2X) communication systems, the need to increase efficiency of the VANET or vehicular ad-hoc networks has risen. One of the methods of doing so is to improve the topology control, especially the dynamic topology. In this paper, we propose a V2X communication based mixed approach for dynamic topology control. The mixed approach consists of both Proximity Graph and Map-matching algorithms, each of them get activates depending upon the context and traffic scenarios. We compared the proposed approach with various existing topology control systems. The proposed mixed approach is simulated using various scenarios in MATLAB and SIMULINK. Further, we have simulated a real-world scenario using road lanes, traffic signals, and actual vehicles on SIMULINK using the VANET toolbox. In the simulation, we have used various parameters to analyze the performance measures such as energy consumption, throughput, network life time, etc. The results analysis shows the effectiveness of the proposed mixed approach for dynamic topology control in the VANET.
{"title":"V2X Communication based Dynamic Topology Control in VANETs","authors":"Dibyayan Patra, Suresh Chavhan, Deepak Gupta, Ashish Khanna, J. Rodrigues","doi":"10.1145/3427477.3429993","DOIUrl":"https://doi.org/10.1145/3427477.3429993","url":null,"abstract":"With the development of Vehicle-to-everything (V2X) communication systems, the need to increase efficiency of the VANET or vehicular ad-hoc networks has risen. One of the methods of doing so is to improve the topology control, especially the dynamic topology. In this paper, we propose a V2X communication based mixed approach for dynamic topology control. The mixed approach consists of both Proximity Graph and Map-matching algorithms, each of them get activates depending upon the context and traffic scenarios. We compared the proposed approach with various existing topology control systems. The proposed mixed approach is simulated using various scenarios in MATLAB and SIMULINK. Further, we have simulated a real-world scenario using road lanes, traffic signals, and actual vehicles on SIMULINK using the VANET toolbox. In the simulation, we have used various parameters to analyze the performance measures such as energy consumption, throughput, network life time, etc. The results analysis shows the effectiveness of the proposed mixed approach for dynamic topology control in the VANET.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132995583","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}
Risa Tamaki, Manato Fujimoto, H. Suwa, K. Yasumoto
Since approximately 10% of people have now diabetes in Japan, the importance of diabetes prevention is increasing. Recently, there are many support programs which allow a person with diabetes to control blood glucose level. However, there are few ways to help non-diabetic people avoid becoming diabetics. Too high peak blood glucose level and prolonged postprandial hyperglycemia can lead to lifestyle-related diseases such as type 2 diabetes. Therefore, it is important to prevent before patients get these diseases. For this purpose, blood glucose level control is required. In this paper, we propose a system for non-diabetic persons to control blood glucose level by predicting it before eating a meal from its image captured. Specifically, we recommend not eating a meal that causes a significant increase in blood glucose level. We analyzed data to create and validate a blood glucose estimation model as the first step toward the realization of a blood glucose level control system. We collected and characterized data on Glycemic Index(GI) of the meal, the time elapsed since the last meal, and the bedtime and sleeping time from four participants to construct a blood glucose level estimation model for each participant using Random Forest.As a result, the constructed estimation models for four participants could estimate blood glucose level with RMSE of 15.41, 12.84, 10, and 10.09, R2 of 0.21, 0.54, 0.75, and 0.82, and finally, MAE of 11.64, 9.232, 6.44, and 6.00.
{"title":"Data Analysis for Developing Blood Glucose Level Control System","authors":"Risa Tamaki, Manato Fujimoto, H. Suwa, K. Yasumoto","doi":"10.1145/3427477.3428191","DOIUrl":"https://doi.org/10.1145/3427477.3428191","url":null,"abstract":"Since approximately 10% of people have now diabetes in Japan, the importance of diabetes prevention is increasing. Recently, there are many support programs which allow a person with diabetes to control blood glucose level. However, there are few ways to help non-diabetic people avoid becoming diabetics. Too high peak blood glucose level and prolonged postprandial hyperglycemia can lead to lifestyle-related diseases such as type 2 diabetes. Therefore, it is important to prevent before patients get these diseases. For this purpose, blood glucose level control is required. In this paper, we propose a system for non-diabetic persons to control blood glucose level by predicting it before eating a meal from its image captured. Specifically, we recommend not eating a meal that causes a significant increase in blood glucose level. We analyzed data to create and validate a blood glucose estimation model as the first step toward the realization of a blood glucose level control system. We collected and characterized data on Glycemic Index(GI) of the meal, the time elapsed since the last meal, and the bedtime and sleeping time from four participants to construct a blood glucose level estimation model for each participant using Random Forest.As a result, the constructed estimation models for four participants could estimate blood glucose level with RMSE of 15.41, 12.84, 10, and 10.09, R2 of 0.21, 0.54, 0.75, and 0.82, and finally, MAE of 11.64, 9.232, 6.44, and 6.00.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126979407","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 Software Defined Internet of Things-Fog (SDIoT-Fog) has provided a new connectivity paradigm for effective service provisioning. SDIoT-Fog uses network resource virtualization to provide services to heterogeneous IoT devices. However, data privacy, and security are the two major challenges that prevents faster realization of SDIoT-based frameworks. Motivated from the aforementioned challenges, we present a Privacy-Preserving based Intrusion Detection Framework (P2IDF) for protecting confidential data and to detect malicious instances in SDIoT-Fog network traffic. This framework has two key engines. Firstly, a Sparse AutoEncoder (SAE)-based privacy-preservation engine is suggested that transforms original data into a new encoded form that avoids inference attacks. Secondly, an intrusion detection engine is suggested that uses Artificial Neural Network (ANN) to train and evaluate the outcomes of the proposed privacy-preservation engine using an IoT-based dataset named ToN-IoT. Finally, experimental results showed that the proposed P2IDF framework outperforms with some recent state-of-the-art frameworks in terms of detection rate, accuracy and precision score.
{"title":"P2IDF: A Privacy-Preserving based Intrusion Detection Framework for Software Defined Internet of Things-Fog (SDIoT-Fog)","authors":"Prabhat Kumar, Rakesh Tripathi, Govind P. Gupta","doi":"10.1145/3427477.3429989","DOIUrl":"https://doi.org/10.1145/3427477.3429989","url":null,"abstract":"The Software Defined Internet of Things-Fog (SDIoT-Fog) has provided a new connectivity paradigm for effective service provisioning. SDIoT-Fog uses network resource virtualization to provide services to heterogeneous IoT devices. However, data privacy, and security are the two major challenges that prevents faster realization of SDIoT-based frameworks. Motivated from the aforementioned challenges, we present a Privacy-Preserving based Intrusion Detection Framework (P2IDF) for protecting confidential data and to detect malicious instances in SDIoT-Fog network traffic. This framework has two key engines. Firstly, a Sparse AutoEncoder (SAE)-based privacy-preservation engine is suggested that transforms original data into a new encoded form that avoids inference attacks. Secondly, an intrusion detection engine is suggested that uses Artificial Neural Network (ANN) to train and evaluate the outcomes of the proposed privacy-preservation engine using an IoT-based dataset named ToN-IoT. Finally, experimental results showed that the proposed P2IDF framework outperforms with some recent state-of-the-art frameworks in terms of detection rate, accuracy and precision score.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116279345","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}
When a user browses a web page, user can wait until web page is displayed. This time is called tolerable delay time. A conventional method to maximize the number of web accesses of web page is displayed within tolerable delay time has been proposed. In general some web pages can convert ordinary web pages (ordinary contents) that you usually use to simple web pages (simple contents) reduced contents such as images. By converting from an ordinary content to simple content, the number of web accesses satisfying the tolerable delay time may be increased. However, conventional method assumed that type of content is only the ordinary content. Moreover, tolerable delay time of each content was the fixed value. In this paper, we propose a method to maximize the number of web accesses by converting ordinary contents to simple contents when the waiting time for access does not satisfied tolerable delay time. In addition, we analyze the characteristic of our proposal method by changing tolerable delay time of content.
{"title":"A proposal of Web accesses method considering tolerable delay for each content","authors":"Kosuke Watanabe, S. Miyata","doi":"10.1145/3427477.3428186","DOIUrl":"https://doi.org/10.1145/3427477.3428186","url":null,"abstract":"When a user browses a web page, user can wait until web page is displayed. This time is called tolerable delay time. A conventional method to maximize the number of web accesses of web page is displayed within tolerable delay time has been proposed. In general some web pages can convert ordinary web pages (ordinary contents) that you usually use to simple web pages (simple contents) reduced contents such as images. By converting from an ordinary content to simple content, the number of web accesses satisfying the tolerable delay time may be increased. However, conventional method assumed that type of content is only the ordinary content. Moreover, tolerable delay time of each content was the fixed value. In this paper, we propose a method to maximize the number of web accesses by converting ordinary contents to simple contents when the waiting time for access does not satisfied tolerable delay time. In addition, we analyze the characteristic of our proposal method by changing tolerable delay time of content.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132883443","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}
Y. Nakagawa, Toru Maeda, A. Uchiyama, T. Higashino
Context recognition has attracted attention for various daily life applications, such as healthcare, fitness tracking, and elderly care. Many existing approaches for context recognition use micro-electro-mechanical systems (MEMS) sensors such as accelerometer and gyroscope. However, they require maintenance for charging or replacing batteries. In this paper, we propose a context recognition method using a frequency shift backscatter tag with ultra-low power consumption. The backscatter tag consists of an antenna, an oscillator, and a motion switch. The tag uses backscatter which leverages surrounding radio frequency (RF) waves emitted from an exciter for ultra-low power wireless communication. The tag changes the state of the motion switch according to the movement of humans or the change of the situation of things. The frequency of the backscattered signal is shifted according to the oscillation frequency. Context recognition is achieved by observing the existence of this frequency shift and its change over time. To demonstrate the feasibility of context recognition using the backscatter tag, we implemented a prototype and evaluated its performance. Our results demonstrate that our system using a BLE exciter can detect the frequency shift within 3 m.
{"title":"Design and Evaluation of a Frequency Shift Backscatter Tag for Context Recognition","authors":"Y. Nakagawa, Toru Maeda, A. Uchiyama, T. Higashino","doi":"10.1145/3427477.3429461","DOIUrl":"https://doi.org/10.1145/3427477.3429461","url":null,"abstract":"Context recognition has attracted attention for various daily life applications, such as healthcare, fitness tracking, and elderly care. Many existing approaches for context recognition use micro-electro-mechanical systems (MEMS) sensors such as accelerometer and gyroscope. However, they require maintenance for charging or replacing batteries. In this paper, we propose a context recognition method using a frequency shift backscatter tag with ultra-low power consumption. The backscatter tag consists of an antenna, an oscillator, and a motion switch. The tag uses backscatter which leverages surrounding radio frequency (RF) waves emitted from an exciter for ultra-low power wireless communication. The tag changes the state of the motion switch according to the movement of humans or the change of the situation of things. The frequency of the backscattered signal is shifted according to the oscillation frequency. Context recognition is achieved by observing the existence of this frequency shift and its change over time. To demonstrate the feasibility of context recognition using the backscatter tag, we implemented a prototype and evaluated its performance. Our results demonstrate that our system using a BLE exciter can detect the frequency shift within 3 m.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129277513","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}
Wi-Fi signal based detection is widely implemented in indoor action detection because of its low-cost and easy implementation. But it is still rarely used in equipment vibration detection. Moreover, it is hard to detect multiple targets where we need to monitor multiple equipments’ vibration state such as in the factory environment. In this paper, we propose a wireless based vibration sensing method using Wi-Fi for factory equipment fault detection. First, we use CSI amplitude data to distinguish sensing target equipments. Then, we apply an anomaly detection method to detect faulty machine operation. We conducted initial experiments to validate the feasibility of our proposed fault detection method. The experimental results show that our method detected abnormal situations with an accuracy of 100%, while 10% of normal situations were mistakenly recognized as abnormal.
{"title":"Initial Attempt on Wi-Fi CSI Based Vibration Sensing for Factory Equipment Fault Detection","authors":"Sirui Jian, S. Ishida, Y. Arakawa","doi":"10.1145/3427477.3429462","DOIUrl":"https://doi.org/10.1145/3427477.3429462","url":null,"abstract":"Wi-Fi signal based detection is widely implemented in indoor action detection because of its low-cost and easy implementation. But it is still rarely used in equipment vibration detection. Moreover, it is hard to detect multiple targets where we need to monitor multiple equipments’ vibration state such as in the factory environment. In this paper, we propose a wireless based vibration sensing method using Wi-Fi for factory equipment fault detection. First, we use CSI amplitude data to distinguish sensing target equipments. Then, we apply an anomaly detection method to detect faulty machine operation. We conducted initial experiments to validate the feasibility of our proposed fault detection method. The experimental results show that our method detected abnormal situations with an accuracy of 100%, while 10% of normal situations were mistakenly recognized as abnormal.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127846193","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}
V. Erdélyi, Hamada Rizk, H. Yamaguchi, T. Higashino
The capability to recognize nearby objects automatically has numerous applications including asset tracking, lifestyle analysis, and navigation assistance for blind people. In recent years, several approaches were proposed, but they are either limited to electric objects or objects instrumented with tags, which cannot scale. There are also acoustic or vision-based techniques for recognizing uninstrumented objects, but they may have privacy issues. In this paper, we present a microwave-based object detection and recognition approach. Specifically, the proposed system leverages Universal Software Radio Peripherals (USRPs) to transmit microwave signals through the target object and capture them on the opposite side. To reduce the privacy impact, we use a single antenna for receiving a single-pixel “image”. Then, a Random Forest classifier learns the characteristics of the received signals altered by a given object, enabling object recognition. Using a wide range of microwave frequencies, we evaluated the proposed system’s capability to detect and differentiate between four different objects of different materials. The evaluation results show that, using only a signal, the system can correctly detect the presence of the object 98.7% of the time. The system can also differentiate between different objects 92% of the time.
{"title":"Learn to See: A Microwave-based Object Recognition System Using Learning Techniques","authors":"V. Erdélyi, Hamada Rizk, H. Yamaguchi, T. Higashino","doi":"10.1145/3427477.3429459","DOIUrl":"https://doi.org/10.1145/3427477.3429459","url":null,"abstract":"The capability to recognize nearby objects automatically has numerous applications including asset tracking, lifestyle analysis, and navigation assistance for blind people. In recent years, several approaches were proposed, but they are either limited to electric objects or objects instrumented with tags, which cannot scale. There are also acoustic or vision-based techniques for recognizing uninstrumented objects, but they may have privacy issues. In this paper, we present a microwave-based object detection and recognition approach. Specifically, the proposed system leverages Universal Software Radio Peripherals (USRPs) to transmit microwave signals through the target object and capture them on the opposite side. To reduce the privacy impact, we use a single antenna for receiving a single-pixel “image”. Then, a Random Forest classifier learns the characteristics of the received signals altered by a given object, enabling object recognition. Using a wide range of microwave frequencies, we evaluated the proposed system’s capability to detect and differentiate between four different objects of different materials. The evaluation results show that, using only a signal, the system can correctly detect the presence of the object 98.7% of the time. The system can also differentiate between different objects 92% of the time.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"172 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124180822","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}
Accurate prediction of the macroscopic traffic stream variables such as speed and flow is important for traffic operation and management in an intelligent transportation system. Adverse weather conditions like fog, snow, and rainfall affect the driver’s visibility, road capacity, and mobility. The accurate prediction of the traffic stream variables in adverse weather conditions is challenging because of the non-linear and complex characteristics of the traffic stream and spatiotemporal correlation between traffic and weather variables. Prolonged heavy rain causes massive waterlogging in developing countries due to weak drainage systems, narrow streets, and encroachment, further affecting these traffic stream variables. Snow reduces the road capacity as much as waterlogging does. Prolonged snowfall creates a thick layer on the road, which affects the traffic stream variables. Traffic data has a high spatial and temporal resolution compared to weather data, which makes the problem more challenging. In this paper, we define a soft temporal threshold to capture the prolonged impact of weather variables. To capture the traffic and weather data’s spatiotemporal and temporal features, we propose a hybrid CNN-LSTM model. To validate model performance, data from San Diego and Minneapolis Minnesota Twin city are used. The test experiments show that the hybrid CNN-LSTM model learns spatiotemporal and temporal features accurately compared to other deep learning models.
{"title":"Macroscopic Traffic Stream Variables Prediction with Weather Impact Using Hybrid CNN-LSTM model","authors":"Archana Nigam, S. Srivastava","doi":"10.1145/3427477.3429780","DOIUrl":"https://doi.org/10.1145/3427477.3429780","url":null,"abstract":"Accurate prediction of the macroscopic traffic stream variables such as speed and flow is important for traffic operation and management in an intelligent transportation system. Adverse weather conditions like fog, snow, and rainfall affect the driver’s visibility, road capacity, and mobility. The accurate prediction of the traffic stream variables in adverse weather conditions is challenging because of the non-linear and complex characteristics of the traffic stream and spatiotemporal correlation between traffic and weather variables. Prolonged heavy rain causes massive waterlogging in developing countries due to weak drainage systems, narrow streets, and encroachment, further affecting these traffic stream variables. Snow reduces the road capacity as much as waterlogging does. Prolonged snowfall creates a thick layer on the road, which affects the traffic stream variables. Traffic data has a high spatial and temporal resolution compared to weather data, which makes the problem more challenging. In this paper, we define a soft temporal threshold to capture the prolonged impact of weather variables. To capture the traffic and weather data’s spatiotemporal and temporal features, we propose a hybrid CNN-LSTM model. To validate model performance, data from San Diego and Minneapolis Minnesota Twin city are used. The test experiments show that the hybrid CNN-LSTM model learns spatiotemporal and temporal features accurately compared to other deep learning models.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117258872","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}
With the spread of the Internet of things, a variety of sensors have been attached to home appliances, and it has become possible to obtain life-logs based on the information obtained from these sensors. Life-logs are easy to collect for home appliances that have sensors, but are difficult to collect for home appliances, doors, chairs, and other furniture without special sensors. Previously, acceleration sensors and Wi-Fi radio waves have been used to estimate the state of such home appliances or furniture. However, the estimation accuracy greatly depends on the presence or absence of movement and the size of the estimation object. Therefore, we propose a method to place Bluetooth low energy beacons directly into objects such as home appliances or furniture. This method allows for state estimation based on the radio wave intensity of the beacon, which changes depending on the state of the object. The method was applied to state estimation of the opening or closing of a refrigerator, the opening or closing of a safe, and the occupancy of a chair, and the estimation accuracy was confirmed. Our results showed that the method could estimate the opening or closing of the refrigerator with 99.2% accuracy, the opening or closing of the safe with 93.8% accuracy, and the occupancy of the chair with 98.9% accuracy.
{"title":"State Estimation Method Using Radio Wave Intensity of BLE Beacon Installed Inside Object","authors":"Yuki Ogane, Ryoga Mizuno, K. Kaji","doi":"10.1145/3427477.3428189","DOIUrl":"https://doi.org/10.1145/3427477.3428189","url":null,"abstract":"With the spread of the Internet of things, a variety of sensors have been attached to home appliances, and it has become possible to obtain life-logs based on the information obtained from these sensors. Life-logs are easy to collect for home appliances that have sensors, but are difficult to collect for home appliances, doors, chairs, and other furniture without special sensors. Previously, acceleration sensors and Wi-Fi radio waves have been used to estimate the state of such home appliances or furniture. However, the estimation accuracy greatly depends on the presence or absence of movement and the size of the estimation object. Therefore, we propose a method to place Bluetooth low energy beacons directly into objects such as home appliances or furniture. This method allows for state estimation based on the radio wave intensity of the beacon, which changes depending on the state of the object. The method was applied to state estimation of the opening or closing of a refrigerator, the opening or closing of a safe, and the occupancy of a chair, and the estimation accuracy was confirmed. Our results showed that the method could estimate the opening or closing of the refrigerator with 99.2% accuracy, the opening or closing of the safe with 93.8% accuracy, and the occupancy of the chair with 98.9% accuracy.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128747830","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}
Juliana Miehle, Sabine Wieluch, W. Minker, Stefan Ultes
We present a study addressing the question how script knowledge based conversational assistants should act in situations of inconclusive information. Such situations occur for example in case of alternative or optional events that lead to multiple correct paths through the script. We have conducted a user study with four typical everyday activities (Making Coffee, Baking Cake, Finding the route to main station, Finding the route to camping ground) that may be represented in scripts. In this study, we have compared and evaluated four different presentation styles to handle situations of conflicting script information. A total of 182 persons participated in our study. The evaluation results show that, in case of a conflicting script state, users find the assistant most useful and are most satisfied if the assistant guesses the next correct event and provides a direct instruction instead of disclosing his incompetence. Alternatives in which the assistant delegates the decision to the user score worse.
{"title":"Decide or Delegate: How Script Knowledge Based Conversational Assistants Should Act in Inconclusive Situations","authors":"Juliana Miehle, Sabine Wieluch, W. Minker, Stefan Ultes","doi":"10.1145/3427477.3428185","DOIUrl":"https://doi.org/10.1145/3427477.3428185","url":null,"abstract":"We present a study addressing the question how script knowledge based conversational assistants should act in situations of inconclusive information. Such situations occur for example in case of alternative or optional events that lead to multiple correct paths through the script. We have conducted a user study with four typical everyday activities (Making Coffee, Baking Cake, Finding the route to main station, Finding the route to camping ground) that may be represented in scripts. In this study, we have compared and evaluated four different presentation styles to handle situations of conflicting script information. A total of 182 persons participated in our study. The evaluation results show that, in case of a conflicting script state, users find the assistant most useful and are most satisfied if the assistant guesses the next correct event and provides a direct instruction instead of disclosing his incompetence. Alternatives in which the assistant delegates the decision to the user score worse.","PeriodicalId":435827,"journal":{"name":"Adjunct Proceedings of the 2021 International Conference on Distributed Computing and Networking","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121464863","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：