Pub Date : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00139
Iwao Maeda, Hiroyasu Matsushima, Hiroki Sakaji, K. Izumi, David deGraw, Atsuo Kato, Michiharu Kitano
Accurate prediction of financial markets is considered one of the most difficult problems due to the nature of its complexity, influenceability, and nonstationarity. Recent financial forecasting applications using neural networks typically have not taken the predictive uncertainty into consideration. Without proper consideration of predictive uncertainty, such approaches may lead to unintended investment losses. Therefore, consideration of predictive uncertainty in neural network-based financial forecasting should lead to improved investment decision-making. In this study, the effectiveness of uncertainty consideration in neural network-based financial forecasting was verified through a simulated investment portfolio. We show that ensemble and Bayesian neural network models are effective in realizing more stable investment outcomes.
{"title":"Effectiveness of Uncertainty Consideration in Neural-Network-Based Financial Forecasting","authors":"Iwao Maeda, Hiroyasu Matsushima, Hiroki Sakaji, K. Izumi, David deGraw, Atsuo Kato, Michiharu Kitano","doi":"10.1109/IIAI-AAI.2019.00139","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00139","url":null,"abstract":"Accurate prediction of financial markets is considered one of the most difficult problems due to the nature of its complexity, influenceability, and nonstationarity. Recent financial forecasting applications using neural networks typically have not taken the predictive uncertainty into consideration. Without proper consideration of predictive uncertainty, such approaches may lead to unintended investment losses. Therefore, consideration of predictive uncertainty in neural network-based financial forecasting should lead to improved investment decision-making. In this study, the effectiveness of uncertainty consideration in neural network-based financial forecasting was verified through a simulated investment portfolio. We show that ensemble and Bayesian neural network models are effective in realizing more stable investment outcomes.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114931296","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00220
Mei-Yao Chang, Jan-Pan Hwang
this research combines the artificial intelligence technique RNN/LSTM to develop a dialogue system, which mainly used in the bargaining unit of a negotiation course. The chatbot was applied in the dialogue of student drills in bargaining situations and investigates the feasibility of the dialogue system used in the course. The two-hour course has 48 second-year university students with different colleges and departments. The results show that most students have a positive view of instant messaging conducts dialogue exercises, and feel interesting. The groups targeting dialogue robots, students prefer courses. For groups with real people, students think it is more helpful for learning, and they have higher satisfaction with the results of bargaining negotiations.
{"title":"Developing Chatbot with Deep Learning Techniques for Negotiation Course","authors":"Mei-Yao Chang, Jan-Pan Hwang","doi":"10.1109/IIAI-AAI.2019.00220","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00220","url":null,"abstract":"this research combines the artificial intelligence technique RNN/LSTM to develop a dialogue system, which mainly used in the bargaining unit of a negotiation course. The chatbot was applied in the dialogue of student drills in bargaining situations and investigates the feasibility of the dialogue system used in the course. The two-hour course has 48 second-year university students with different colleges and departments. The results show that most students have a positive view of instant messaging conducts dialogue exercises, and feel interesting. The groups targeting dialogue robots, students prefer courses. For groups with real people, students think it is more helpful for learning, and they have higher satisfaction with the results of bargaining negotiations.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129944817","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00042
Yiyi Wang, Alaa M. Allakany, Srishti Kulshrestha, Wei Shi, R. Bose, K. Okamura
The Internet-of-Things is a network platform which provides service to physical world by connecting electronic devices, processing and analyzing data. Meanwhile, such fragile connectivity, low security awareness and the lack of knowledge of users can lead IoT devices to be the target of some attackers and then becomes insecurity of things. To solve that problem, in this research, we aim to build an E-learning system which is based on Ontology method to educate users in order to improve their security awareness. Basically, our system mainly consists of three steps. Firstly, we classified, analyzed and characterized the concepts of IoT security domain. Then we built an IoT security Ontology based on the output of classification and analysis. Finally, we developed a java program to implement the function of automatically generate Multiple Choice Questions based on IoT security Ontology descriptions. In this research, we made E-learning materials by extracting and rearranging useful knowledge from on results of classification and analysis. And using a Moodle as e-Learning platform, we upload those learning materials and all the outputs from our system to Moodle and utilized Moodle to create courses and quizzes in order to let user study through our system.
{"title":"Automatically Generate E-Learning Quizzes from IoT Security Ontology","authors":"Yiyi Wang, Alaa M. Allakany, Srishti Kulshrestha, Wei Shi, R. Bose, K. Okamura","doi":"10.1109/IIAI-AAI.2019.00042","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00042","url":null,"abstract":"The Internet-of-Things is a network platform which provides service to physical world by connecting electronic devices, processing and analyzing data. Meanwhile, such fragile connectivity, low security awareness and the lack of knowledge of users can lead IoT devices to be the target of some attackers and then becomes insecurity of things. To solve that problem, in this research, we aim to build an E-learning system which is based on Ontology method to educate users in order to improve their security awareness. Basically, our system mainly consists of three steps. Firstly, we classified, analyzed and characterized the concepts of IoT security domain. Then we built an IoT security Ontology based on the output of classification and analysis. Finally, we developed a java program to implement the function of automatically generate Multiple Choice Questions based on IoT security Ontology descriptions. In this research, we made E-learning materials by extracting and rearranging useful knowledge from on results of classification and analysis. And using a Moodle as e-Learning platform, we upload those learning materials and all the outputs from our system to Moodle and utilized Moodle to create courses and quizzes in order to let user study through our system.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127833350","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00169
Shuichiro Yamamoto
This paper proposes an approach to unify different knowledge using Enterprise Architecture. The approach concerns on the theory and engineering of knowledge unification. We also propose a design pattern for describing and reuse the transdisciplinary knowledge unification. A case study is also shown for the nursing narrative to create a unified knowledge. Moreover, the types of transdisciplinary knowledge unification are clarified.
{"title":"Enterprise Architecture Towards Transdisciplinary Knowledge Unification","authors":"Shuichiro Yamamoto","doi":"10.1109/IIAI-AAI.2019.00169","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00169","url":null,"abstract":"This paper proposes an approach to unify different knowledge using Enterprise Architecture. The approach concerns on the theory and engineering of knowledge unification. We also propose a design pattern for describing and reuse the transdisciplinary knowledge unification. A case study is also shown for the nursing narrative to create a unified knowledge. Moreover, the types of transdisciplinary knowledge unification are clarified.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125560002","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00206
M. Tanifuji, Asahiko Matsuda, Hideki Yoshikawa
We have identified five important approaches as requirements for a FAIR (findable, accessible, interoperable, reusable) materials data platform. To realize these, we are designing a data platform that consists of about ten interconnected subsystems. We aim to incorporate next generation repository (NGR) concepts into our platform; the subsystems share features such as persistent identifier (PID) based resource management, a common metadata model, and vocabulary control. Another vital requirement is that all datasets must be machine-readable and translatable. These features are highly important in developing a platform as a research pipeline capable of handling various materials data – from data creation and efficient collection, to advanced data usage, secure storage, and open publishing.
{"title":"Materials Data Platform - a FAIR System for Data-Driven Materials Science","authors":"M. Tanifuji, Asahiko Matsuda, Hideki Yoshikawa","doi":"10.1109/IIAI-AAI.2019.00206","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00206","url":null,"abstract":"We have identified five important approaches as requirements for a FAIR (findable, accessible, interoperable, reusable) materials data platform. To realize these, we are designing a data platform that consists of about ten interconnected subsystems. We aim to incorporate next generation repository (NGR) concepts into our platform; the subsystems share features such as persistent identifier (PID) based resource management, a common metadata model, and vocabulary control. Another vital requirement is that all datasets must be machine-readable and translatable. These features are highly important in developing a platform as a research pipeline capable of handling various materials data – from data creation and efficient collection, to advanced data usage, secure storage, and open publishing.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121609451","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00186
Natsuki Mimura, H. Washizaki, Katsutoshi Shintani, Shuji Okuda
Many businesses align their business goals, IT strategies and system to strengthen the validity of business processes. However, the relationships between goals, strategies and system are often vague. Thus, the level of success derived from their interrelationships may be ambiguous. In addition, adjusting the system to accommodate changing goals and strategies is becoming more and more difficult due to increasing agile development in recent years. By coupling GQM+Strategies and SysML, we propose a framework to systematically associate business requirements and system functions.
{"title":"Linking Business Strategies and System Demands Using GQM+Strategies and Systems Modeling Language","authors":"Natsuki Mimura, H. Washizaki, Katsutoshi Shintani, Shuji Okuda","doi":"10.1109/IIAI-AAI.2019.00186","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00186","url":null,"abstract":"Many businesses align their business goals, IT strategies and system to strengthen the validity of business processes. However, the relationships between goals, strategies and system are often vague. Thus, the level of success derived from their interrelationships may be ambiguous. In addition, adjusting the system to accommodate changing goals and strategies is becoming more and more difficult due to increasing agile development in recent years. By coupling GQM+Strategies and SysML, we propose a framework to systematically associate business requirements and system functions.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114097235","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00174
Natsuko Fujikawa, Shuichiro Yamamoto
In this paper, We showed a method of risk management against information leakage of companies which has been frequent in recent years. We classified the risk of information leakage into four types from impact and probability, and showed each type of countermeasures through case studies. We also clarified the risk management procedure using ArchiMate. Risk analysis, risk assessment, and selection of risk measures depend on the company's situation. This paper concludes that companies are required to manage the risk of information leakage appropriate to the situation.
{"title":"Corporate Risk Analysis Approach for Information Leakage","authors":"Natsuko Fujikawa, Shuichiro Yamamoto","doi":"10.1109/IIAI-AAI.2019.00174","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00174","url":null,"abstract":"In this paper, We showed a method of risk management against information leakage of companies which has been frequent in recent years. We classified the risk of information leakage into four types from impact and probability, and showed each type of countermeasures through case studies. We also clarified the risk management procedure using ArchiMate. Risk analysis, risk assessment, and selection of risk measures depend on the company's situation. This paper concludes that companies are required to manage the risk of information leakage appropriate to the situation.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121819725","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper conducted a case study in a simulation control software system. In the case study, we analyzed defects that required significant correction effort. The defects were ambiguity defects injected by misunderstandings and inconsistencies among stakeholders during interpreting requirements and specifying design documents. The ambiguities of the specifications are found in the definitions of distance, time (time zone), and calculation accuracy. These cause non-conformance in the implementations and errors in the control simulation execution results. Based on the analysis, as a low-effort defect prevention approach, we propose clearly defining the units to avoid such ambiguities and estimated the expected effort reduction by the definitions in the target control simulation software development.
{"title":"A Case Study of Requirements Ambiguities and Goal-oriented Focused Requirements Specification","authors":"Michiyo Wakimoto, Shuji Morisaki, Shuichiro Yamamoto","doi":"10.1109/IIAI-AAI.2019.00183","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00183","url":null,"abstract":"This paper conducted a case study in a simulation control software system. In the case study, we analyzed defects that required significant correction effort. The defects were ambiguity defects injected by misunderstandings and inconsistencies among stakeholders during interpreting requirements and specifying design documents. The ambiguities of the specifications are found in the definitions of distance, time (time zone), and calculation accuracy. These cause non-conformance in the implementations and errors in the control simulation execution results. Based on the analysis, as a low-effort defect prevention approach, we propose clearly defining the units to avoid such ambiguities and estimated the expected effort reduction by the definitions in the target control simulation software development.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116576827","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}
An AR-enhanced contextualized learning was developed to facilitate EFL learning for junior high school students. A preliminary study was conducted to examine the effects of levels of prior knowledge (low vs. high) on participants' learning effectiveness and attitude toward the implemented AR-enhanced theme-based contextualized learning. The analysis suggested that prior knowledge affected participants' learning from the experimental AR-enhanced learning. With the advantage in prior knowledge, the high prior knowledge learners outperformed the low prior knowledge learners both in comprehension and application performance and possessed higher degrees of confidence, preferences, deep learning and learning strategy but with lower degrees of anxiety. It was suggested that suitable learning supports need to be considered to adapt to EFL beginners' levels of prior knowledge in order to facilitate their learning.
{"title":"Enhancing Contextualized Learning via AR","authors":"Ming-Puu Chen, Li-Chun Wang, Shu-Yuan Lin, D. Zou, Haoran Xie, Chin-Chung Tsai","doi":"10.1109/IIAI-AAI.2019.00064","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00064","url":null,"abstract":"An AR-enhanced contextualized learning was developed to facilitate EFL learning for junior high school students. A preliminary study was conducted to examine the effects of levels of prior knowledge (low vs. high) on participants' learning effectiveness and attitude toward the implemented AR-enhanced theme-based contextualized learning. The analysis suggested that prior knowledge affected participants' learning from the experimental AR-enhanced learning. With the advantage in prior knowledge, the high prior knowledge learners outperformed the low prior knowledge learners both in comprehension and application performance and possessed higher degrees of confidence, preferences, deep learning and learning strategy but with lower degrees of anxiety. It was suggested that suitable learning supports need to be considered to adapt to EFL beginners' levels of prior knowledge in order to facilitate their learning.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133568194","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 : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00071
Seiko Masuda, K. Ishigaki, H. Nishimura
Information education in the nursing profession has emphasized statistical processing. The content is not desirable to foster an ability to perform activities under the ongoing data health plan in Japan. For that reason, in this study, we aimed at developing a curriculum that incorporates a data health perspective for nursing college students, putting it into practice, and evaluating the results. As a result, it was confirmed that students' awareness and skills on data health response ability were improved.
{"title":"Informatics Curriculum for Nursing College Students According to the Data Health Perspective","authors":"Seiko Masuda, K. Ishigaki, H. Nishimura","doi":"10.1109/IIAI-AAI.2019.00071","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00071","url":null,"abstract":"Information education in the nursing profession has emphasized statistical processing. The content is not desirable to foster an ability to perform activities under the ongoing data health plan in Japan. For that reason, in this study, we aimed at developing a curriculum that incorporates a data health perspective for nursing college students, putting it into practice, and evaluating the results. As a result, it was confirmed that students' awareness and skills on data health response ability were improved.","PeriodicalId":136474,"journal":{"name":"2019 8th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132568316","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：