Pub Date : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006667
Miyuki Yamamoto, K. Fukuoka, R. Kiyohara, Y. Terashima
In recent years, project-based learning (PBL) in university education has been emphasized for distributed software development courses. Therefore, by assuming distributed development, this research targets PBL and proposes a progress management method for solving project delays of individual students while maintaining the independence of distributed development. Typically, a teaching assistant (TA) provides support to students they recognize as facing issues in class. We propose a progress management method that uses an automated TA (TA-BOT) to solve students' development progress delays by detecting development delays and advising them accordingly in a timely manner. In the proposed method, the timing for advising a student is determined by the degree of his/her delay. We conducted experiments using several student projects, assessed the importance and validity of the advice contents provided by TA-BOT, and verified the effectiveness of the proposed method in some cases.
{"title":"Progress Management Method for Software Development Project-based Learning Using Automated Teaching Assistants","authors":"Miyuki Yamamoto, K. Fukuoka, R. Kiyohara, Y. Terashima","doi":"10.23919/ICMU48249.2019.9006667","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006667","url":null,"abstract":"In recent years, project-based learning (PBL) in university education has been emphasized for distributed software development courses. Therefore, by assuming distributed development, this research targets PBL and proposes a progress management method for solving project delays of individual students while maintaining the independence of distributed development. Typically, a teaching assistant (TA) provides support to students they recognize as facing issues in class. We propose a progress management method that uses an automated TA (TA-BOT) to solve students' development progress delays by detecting development delays and advising them accordingly in a timely manner. In the proposed method, the timing for advising a student is determined by the degree of his/her delay. We conducted experiments using several student projects, assessed the importance and validity of the advice contents provided by TA-BOT, and verified the effectiveness of the proposed method in some cases.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125787114","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006635
Anum Nawaz, Tuan Anh Nguyen Gia, J. P. Queralta, Tomi Westerlund
The edge and fog computing paradigms enable more responsive and smarter systems without relying on cloud servers for data processing and storage. This reduces network load as well as latency. Nonetheless, the addition of new layers in the network architecture increases the number of security vulnerabilities. In privacy-critical systems, the appearance of new vulnerabilities is more significant. To cope with this issue, we propose and implement an Ethereum Blockchain based architecture with edge artificial intelligence to analyze data at the edge of the network and keep track of the parties that access the results of the analysis, which are stored in distributed databases.
{"title":"Edge AI and Blockchain for Privacy-Critical and Data-Sensitive Applications","authors":"Anum Nawaz, Tuan Anh Nguyen Gia, J. P. Queralta, Tomi Westerlund","doi":"10.23919/ICMU48249.2019.9006635","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006635","url":null,"abstract":"The edge and fog computing paradigms enable more responsive and smarter systems without relying on cloud servers for data processing and storage. This reduces network load as well as latency. Nonetheless, the addition of new layers in the network architecture increases the number of security vulnerabilities. In privacy-critical systems, the appearance of new vulnerabilities is more significant. To cope with this issue, we propose and implement an Ethereum Blockchain based architecture with edge artificial intelligence to analyze data at the edge of the network and keep track of the parties that access the results of the analysis, which are stored in distributed databases.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116770502","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006639
Koki Iwai, Chiaki Doi, Nanaka Asai, H. Shigeno, S. Ideno, Jungo Kato, Takashige Yamada, H. Morisaki, H. Seki
Electronic anesthesia record data have been accumulated, and efforts to solve medical problems using data analysis methods and machine learning have been conducted. Post-induction hypotension frequently occurred after induction of anesthesia. Intraoperative hypotension is associated with various adverse events such as myocardial infarction and cerebral infarction. In a related study, eight machine learning methods were used to construct hypotension prediction models and evaluated by area under the curve (AUC), using data collected from an institution in the United States. Nevertheless, it was not focused on improving prediction power. This paper aims to predict post-induction hypotension with high prediction power using 1,626 electronic anesthesia record data. Our hypotension prediction model using a stacking method is introduced. F-measure 0.60 was achieved by using our method through the evaluation.
{"title":"Prediction of Post-induction Hypotension Using Stacking Method","authors":"Koki Iwai, Chiaki Doi, Nanaka Asai, H. Shigeno, S. Ideno, Jungo Kato, Takashige Yamada, H. Morisaki, H. Seki","doi":"10.23919/ICMU48249.2019.9006639","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006639","url":null,"abstract":"Electronic anesthesia record data have been accumulated, and efforts to solve medical problems using data analysis methods and machine learning have been conducted. Post-induction hypotension frequently occurred after induction of anesthesia. Intraoperative hypotension is associated with various adverse events such as myocardial infarction and cerebral infarction. In a related study, eight machine learning methods were used to construct hypotension prediction models and evaluated by area under the curve (AUC), using data collected from an institution in the United States. Nevertheless, it was not focused on improving prediction power. This paper aims to predict post-induction hypotension with high prediction power using 1,626 electronic anesthesia record data. Our hypotension prediction model using a stacking method is introduced. F-measure 0.60 was achieved by using our method through the evaluation.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115819787","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006644
A. Paul, M. Arifuzzaman, Keping Yu, Takuro Sato
The location estimation accuracy of range-free localization (RFL) is a crucial issue in Wireless Sensor Networks (WSNs). The accuracy has significant impact on localization dependent routing protocols and applications. The assumption that the sensor nodes are deployed in regular areas without any obstacles do not match the practical deployment scenarios, especially for scenarios like outdoor deployment of WSNs. In this paper, we propose a hybrid solution by combining a RFL method and range-based localization (RBL) method namely Received Signal Strength Indication (RSSI) to tackle the detoured path between sensors in anisotropic network and to combat the last hop distance calculation problem respectively. As a result, our hybrid approach significantly improves the localization accuracy in anisotropic network as compared to range free method only. We calculate the average hop distance (AHD) of detoured path by estimating the angle of the middle of the transmission path between every two anchor pairs one by one. The AHD is finally adjusted by estimating the RSSI based last hop distance measurement. Based on the simulation results, it is observed that our hybrid approach with few anchor nodes outperforms other RFL algorithms in anisotropic network and indicates an improvement in the localization accuracy.
{"title":"Detour Path Angular Information based Range Free Localization with Last Hop RSSI Measurement based Distance Calculation","authors":"A. Paul, M. Arifuzzaman, Keping Yu, Takuro Sato","doi":"10.23919/ICMU48249.2019.9006644","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006644","url":null,"abstract":"The location estimation accuracy of range-free localization (RFL) is a crucial issue in Wireless Sensor Networks (WSNs). The accuracy has significant impact on localization dependent routing protocols and applications. The assumption that the sensor nodes are deployed in regular areas without any obstacles do not match the practical deployment scenarios, especially for scenarios like outdoor deployment of WSNs. In this paper, we propose a hybrid solution by combining a RFL method and range-based localization (RBL) method namely Received Signal Strength Indication (RSSI) to tackle the detoured path between sensors in anisotropic network and to combat the last hop distance calculation problem respectively. As a result, our hybrid approach significantly improves the localization accuracy in anisotropic network as compared to range free method only. We calculate the average hop distance (AHD) of detoured path by estimating the angle of the middle of the transmission path between every two anchor pairs one by one. The AHD is finally adjusted by estimating the RSSI based last hop distance measurement. Based on the simulation results, it is observed that our hybrid approach with few anchor nodes outperforms other RFL algorithms in anisotropic network and indicates an improvement in the localization accuracy.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"177 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114243583","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006631
I. Satoh
MapReduce processing, which was originally designed to be executed on a cluster of high-performance servers, is also useful for processing data generated at the edge of a network. To support edge computing, we previously developed an approach to enable processing in embedded computers connected through wired or wireless local area networks in a peer-to-peer manner. Here, we extend our approach to give it with the ability to work 5G networks, which connects nodes at the edge to base stations but not directly nodes. This paper describes the extension and its performance. The extension has several contributions in common with other embedded computing systems for 5G networks.
{"title":"MapReduce Processing with 5G networks","authors":"I. Satoh","doi":"10.23919/ICMU48249.2019.9006631","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006631","url":null,"abstract":"MapReduce processing, which was originally designed to be executed on a cluster of high-performance servers, is also useful for processing data generated at the edge of a network. To support edge computing, we previously developed an approach to enable processing in embedded computers connected through wired or wireless local area networks in a peer-to-peer manner. Here, we extend our approach to give it with the ability to work 5G networks, which connects nodes at the edge to base stations but not directly nodes. This paper describes the extension and its performance. The extension has several contributions in common with other embedded computing systems for 5G networks.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117005339","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006650
Madhup Khatiwada, R. Budhathoki, Aniket Mahanti
With the proliferation of Internet-based technologies over the past two decades and the associated growth in the volume and diversity of Internet traffic, it becomes increasingly important to understand how these changes affect the overall workload characteristics of servers. This paper revisits the seminal work of Arlitt and Williamson [1] to determine whether or not the ten invariants they derived from server logs continue to adequately characterise modern web traffic. Furthermore, a specialised analysis is performed to determine how well these invariants model mobile web traffic in particular. Our results show that while the majority of the invariants hold, some do not. In particular, combined and mobile web traffic has dramatically changed in the file types requested, and the origin of the hosts making requests, as well as a noticeable change in response types. Furthermore, mobile web traffic demonstrated significantly fewer one-time requests as compared to the original study and the combined logs from this study.
{"title":"Characterizing Mobile Web Traffic: A Case Study of an Academic Web Server","authors":"Madhup Khatiwada, R. Budhathoki, Aniket Mahanti","doi":"10.23919/ICMU48249.2019.9006650","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006650","url":null,"abstract":"With the proliferation of Internet-based technologies over the past two decades and the associated growth in the volume and diversity of Internet traffic, it becomes increasingly important to understand how these changes affect the overall workload characteristics of servers. This paper revisits the seminal work of Arlitt and Williamson [1] to determine whether or not the ten invariants they derived from server logs continue to adequately characterise modern web traffic. Furthermore, a specialised analysis is performed to determine how well these invariants model mobile web traffic in particular. Our results show that while the majority of the invariants hold, some do not. In particular, combined and mobile web traffic has dramatically changed in the file types requested, and the origin of the hosts making requests, as well as a noticeable change in response types. Furthermore, mobile web traffic demonstrated significantly fewer one-time requests as compared to the original study and the combined logs from this study.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132112422","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006636
H. Inoue, K. Kaji
There are passengers who to ride on the train in a harry. They may not know the arrival time to the destination. Therefore, the arrival time of their target station is essential information for them. To acquire the information by using currently available application, it is necessary to search or input their train on board. Therefore, the arrival time is display on a smartphone by a passenger. Moreover, a passenger does not need to operate the smartphone. A passenger can get the arrival time of a train and train information such as train type and train destination. This system estimates the train on which the passenger is riding by using current location information from the passenger's smartphone. This system processes train route estimation function and train direction estimation function before train estimation function. There is a system can display simply arrival time at local train. However, this system can display arrival time information of superior train. Also, this system displays arrival time information of adjacent route when running on a parallel route section. We examined whether arrival time information of adjacent route was displayed correctly. We confirmed that there are sections that are displayed correctly and sections that are displayed incorrectly.
{"title":"A Smartphone Application that Automatically Provides Arrival Time based on Estimation of Train on Board","authors":"H. Inoue, K. Kaji","doi":"10.23919/ICMU48249.2019.9006636","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006636","url":null,"abstract":"There are passengers who to ride on the train in a harry. They may not know the arrival time to the destination. Therefore, the arrival time of their target station is essential information for them. To acquire the information by using currently available application, it is necessary to search or input their train on board. Therefore, the arrival time is display on a smartphone by a passenger. Moreover, a passenger does not need to operate the smartphone. A passenger can get the arrival time of a train and train information such as train type and train destination. This system estimates the train on which the passenger is riding by using current location information from the passenger's smartphone. This system processes train route estimation function and train direction estimation function before train estimation function. There is a system can display simply arrival time at local train. However, this system can display arrival time information of superior train. Also, this system displays arrival time information of adjacent route when running on a parallel route section. We examined whether arrival time information of adjacent route was displayed correctly. We confirmed that there are sections that are displayed correctly and sections that are displayed incorrectly.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125171118","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006662
Yingying Duan, W. Lu, Weiwei Xing, Peng Bao, Xiang Wei
With the rapid popularity of mobile devices, a vast amount of trajectory-based check-in data are shared in many social network applications, which is an important data source for user location prediction. The location category prediction, a branch of location prediction, is a vital task in a wide range of areas, including urban planning, advertising and recommendation systems. In this paper, we propose a novel two-step Pattern-Based Embedding Model (PBEM) for predicting the next location category that user will go to. Based on the observation that some users behave frequently in a similarity pattern, a new feature termed as user cluster label is defined. In order to mine user's behavior patterns and extract the cluster label, a Category-Importance-Decay learning strategy is proposed and implemented, which provides a quantitative standard for evaluating the importance of each category. Thus, a comprehensive feature set is obtained including user, time, historical location category, text content, and user cluster label, which greatly enhances the robustness of data representation and contains more knowledge. Then the extracted feature set is fed into Recurrent Neural Network (RNN) in a unified framework, which improves the prediction accuracy. We evaluate the performance of PBEM on two real-life trajectory-based check-in datasets. Experimental results demonstrate that the proposed model can outperform the state-of-the-art methods.
{"title":"PBEM: A Pattern-Based Embedding Model for User Location Category Prediction","authors":"Yingying Duan, W. Lu, Weiwei Xing, Peng Bao, Xiang Wei","doi":"10.23919/ICMU48249.2019.9006662","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006662","url":null,"abstract":"With the rapid popularity of mobile devices, a vast amount of trajectory-based check-in data are shared in many social network applications, which is an important data source for user location prediction. The location category prediction, a branch of location prediction, is a vital task in a wide range of areas, including urban planning, advertising and recommendation systems. In this paper, we propose a novel two-step Pattern-Based Embedding Model (PBEM) for predicting the next location category that user will go to. Based on the observation that some users behave frequently in a similarity pattern, a new feature termed as user cluster label is defined. In order to mine user's behavior patterns and extract the cluster label, a Category-Importance-Decay learning strategy is proposed and implemented, which provides a quantitative standard for evaluating the importance of each category. Thus, a comprehensive feature set is obtained including user, time, historical location category, text content, and user cluster label, which greatly enhances the robustness of data representation and contains more knowledge. Then the extracted feature set is fed into Recurrent Neural Network (RNN) in a unified framework, which improves the prediction accuracy. We evaluate the performance of PBEM on two real-life trajectory-based check-in datasets. Experimental results demonstrate that the proposed model can outperform the state-of-the-art methods.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"20 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126926925","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006629
Yi Tian, Takuya Yoshihiro
Using multiple channels in wireless mesh networks (WMNs) can reduce collision and interference, which improves network performance. Reasonable channel allocation is an effective method for eliminating collisions in WMNs. In this paper, we aim to achieve collision-free channel allocation that is suitable for the traffic patterns in the target networks. Given a traffic-demand matrix of a network, we propose the Traffic-Aware Centralized Channel Allocation (TACCA) method to satisfy traffic demand without collisions in multi-channel WMNs. By incorporating a Carrier Sense Multiple Access aware (CSMA-aware) interference model, we formulate an optimization problem as Mixed Integer Linear Programming (MILP), which generates an optimal channel allocation when solved by an efficient solver. In TACCA, routing paths are consistently selected with satisfying capacity. Simulation studies show that TACCA can drastically improve performance for multi-channel WMNs by adjusting channel assignment incorporating the given traffic patterns.
{"title":"A Traffic-Demand-Aware Collision-free Channel Allocation for Multi-channel Wireless Mesh Networks","authors":"Yi Tian, Takuya Yoshihiro","doi":"10.23919/ICMU48249.2019.9006629","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006629","url":null,"abstract":"Using multiple channels in wireless mesh networks (WMNs) can reduce collision and interference, which improves network performance. Reasonable channel allocation is an effective method for eliminating collisions in WMNs. In this paper, we aim to achieve collision-free channel allocation that is suitable for the traffic patterns in the target networks. Given a traffic-demand matrix of a network, we propose the Traffic-Aware Centralized Channel Allocation (TACCA) method to satisfy traffic demand without collisions in multi-channel WMNs. By incorporating a Carrier Sense Multiple Access aware (CSMA-aware) interference model, we formulate an optimization problem as Mixed Integer Linear Programming (MILP), which generates an optimal channel allocation when solved by an efficient solver. In TACCA, routing paths are consistently selected with satisfying capacity. Simulation studies show that TACCA can drastically improve performance for multi-channel WMNs by adjusting channel assignment incorporating the given traffic patterns.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130747804","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 : 2019-11-01DOI: 10.23919/ICMU48249.2019.9006672
Nanaka Asai, Chiaki Doi, Koki Iwai, S. Ideno, H. Seki, Jungo Kato, Takashige Yamada, H. Morisaki, H. Shigeno
Post-induction hypotension frequently occurred after anesthesia induction. Avoiding post-induction hypotension is important as it is associated with postoperative adverse outcomes. Related studies have shown that the dose of anesthetic induction drugs affects the post-induction hypotension. The purpose of this study is to propose an anesthetic dose that does not cause post-induction hypotension according to the patient's condition. A model for predicting the optimal dose of an anesthetic induction drug is constructed using a regression model which is one of machine learning methods by focusing on electronic anesthesia records. The prediction coefficient of determination 0.5008 was achieved by adjusting the explanatory variables and parameters and using ridge regression.
{"title":"Proposal of Anesthetic Dose Prediction Model to Avoid Post-induction Hypotension Using Electronic Anesthesia Records","authors":"Nanaka Asai, Chiaki Doi, Koki Iwai, S. Ideno, H. Seki, Jungo Kato, Takashige Yamada, H. Morisaki, H. Shigeno","doi":"10.23919/ICMU48249.2019.9006672","DOIUrl":"https://doi.org/10.23919/ICMU48249.2019.9006672","url":null,"abstract":"Post-induction hypotension frequently occurred after anesthesia induction. Avoiding post-induction hypotension is important as it is associated with postoperative adverse outcomes. Related studies have shown that the dose of anesthetic induction drugs affects the post-induction hypotension. The purpose of this study is to propose an anesthetic dose that does not cause post-induction hypotension according to the patient's condition. A model for predicting the optimal dose of an anesthetic induction drug is constructed using a regression model which is one of machine learning methods by focusing on electronic anesthesia records. The prediction coefficient of determination 0.5008 was achieved by adjusting the explanatory variables and parameters and using ridge regression.","PeriodicalId":348402,"journal":{"name":"2019 Twelfth International Conference on Mobile Computing and Ubiquitous Network (ICMU)","volume":"9 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134190193","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：