Pub Date : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00076
S. Katayama, A. Pindur, H. Iba
DeepIE3D, a recent research, enables users to generate their favorite 3D structures by combining GAN and IEC. However, due to the stochastic nature of IEC, it is very difficult to evolve and generate specific structure, even under human guidance. To solve this problem, the system needs to pick out 3D structures that are desirable to users, and for this purpose, it is necessary to define some kind of similarity measure to extract advantageous features from selected structures. We would like to propose to use DeepIE3D with graph kernels. In this work, we represent planes/chairs as graphs and used Weisfeiler-Lehman graph kernels to implement recommendation system. The result shows that the proposed method is superior in generating specific types of planes/chairs and the proposed similarity calculation method are very intuitive from a human point of view.
{"title":"Extending Deep Interactive Evolution with Graph Kernel for 3D Design","authors":"S. Katayama, A. Pindur, H. Iba","doi":"10.1109/iiai-aai53430.2021.00076","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00076","url":null,"abstract":"DeepIE3D, a recent research, enables users to generate their favorite 3D structures by combining GAN and IEC. However, due to the stochastic nature of IEC, it is very difficult to evolve and generate specific structure, even under human guidance. To solve this problem, the system needs to pick out 3D structures that are desirable to users, and for this purpose, it is necessary to define some kind of similarity measure to extract advantageous features from selected structures. We would like to propose to use DeepIE3D with graph kernels. In this work, we represent planes/chairs as graphs and used Weisfeiler-Lehman graph kernels to implement recommendation system. The result shows that the proposed method is superior in generating specific types of planes/chairs and the proposed similarity calculation method are very intuitive from a human point of view.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121276197","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00013
H. Yanagimoto, Shin Yoshida
We propose a neural conversation system with memory mechanism to realize natural conversation exchanges considering the previous utterances. The neural conversation system consists of a Sequence-to-Sequence model and a memory mechanism. The Sequence-to-Sequence model can generate gramatically correct replies and the memory network can consider the previous utterances. The proposed method is trained with Cornell Movie-Dialog corpus and realize conversations between human and a; computer. We confirm that the proposed method can generate replies depending on the previous utterances but it is difficult to generate semantically correct utterances.
{"title":"Neural Conversation with Memory Mechanism","authors":"H. Yanagimoto, Shin Yoshida","doi":"10.1109/iiai-aai53430.2021.00013","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00013","url":null,"abstract":"We propose a neural conversation system with memory mechanism to realize natural conversation exchanges considering the previous utterances. The neural conversation system consists of a Sequence-to-Sequence model and a memory mechanism. The Sequence-to-Sequence model can generate gramatically correct replies and the memory network can consider the previous utterances. The proposed method is trained with Cornell Movie-Dialog corpus and realize conversations between human and a; computer. We confirm that the proposed method can generate replies depending on the previous utterances but it is difficult to generate semantically correct utterances.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133730457","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00016
Jun Fukumoto
There are various Internet sites for tourists and a lot of positive and negative word-of-mouses are posted from tourists. Negative information can be used as attention points for sightseeing to prevent the same mistakes for their first visit. The purpose of this research is to extract such negative information from word-of-mouth as tourist attention points and classify them for easy-to-understand. In the experiments, we extracted attention points from actual tourist reviews and classified them based on target of the points.
{"title":"Extraction of Tourist Attention Points from Low-rated Reviews and their Classification","authors":"Jun Fukumoto","doi":"10.1109/iiai-aai53430.2021.00016","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00016","url":null,"abstract":"There are various Internet sites for tourists and a lot of positive and negative word-of-mouses are posted from tourists. Negative information can be used as attention points for sightseeing to prevent the same mistakes for their first visit. The purpose of this research is to extract such negative information from word-of-mouth as tourist attention points and classify them for easy-to-understand. In the experiments, we extracted attention points from actual tourist reviews and classified them based on target of the points.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114694157","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00009
Ryoya Kaneda, M. Okada, Naoki Mori
In this study, we focus on conjunctions between sentences to estimate the semantic relations between sentences. As a method for estimating the types of hidden conjunctions, we propose a method using a word embedding with bidirectional encoder representations from the transformer (BERT), which has shown high accuracy in various natural language processing tasks. By using Japanese newspaper articles, we have confirmed the effectiveness of the proposed method in estimating the presence or absence of conjunctions and the types of conjunctions. There was a difference in the accuracy by changing the estimator used to input word embedding. The result varied greatly depending on the conjunction.
{"title":"Estimating Semantic Relationships between Sentences Using Word Embedding with BERT","authors":"Ryoya Kaneda, M. Okada, Naoki Mori","doi":"10.1109/iiai-aai53430.2021.00009","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00009","url":null,"abstract":"In this study, we focus on conjunctions between sentences to estimate the semantic relations between sentences. As a method for estimating the types of hidden conjunctions, we propose a method using a word embedding with bidirectional encoder representations from the transformer (BERT), which has shown high accuracy in various natural language processing tasks. By using Japanese newspaper articles, we have confirmed the effectiveness of the proposed method in estimating the presence or absence of conjunctions and the types of conjunctions. There was a difference in the accuracy by changing the estimator used to input word embedding. The result varied greatly depending on the conjunction.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115809955","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00074
Jamy Chahal, A. E. Seghrouchni, A. Belbachir
Observation and patrolling methods assure the coverage of the entire environment while dealing with moving targets. The efficiency of these methods rely on a wide range of parameters, such as the number of targets, the communication range of the patrolling agent or the map's shape. Thus, in this paper we propose a decision-making tool to optimize a set of parameters among the settings defining the observation and patrolling problem. The obtained optimal configuration has to ensure the expected efficiencies by the user, through the use of evaluation criteria. This tool is based on a simulation-assisted machine learning architecture, which performs a faster prediction response than running the simulation directly to obtain evaluation result. We evaluate the efficiency of the decision-making tool through several scenario, implying one or two parameters to be optimized.
{"title":"A decision-making architecture for observation and patrolling problems using machine learning","authors":"Jamy Chahal, A. E. Seghrouchni, A. Belbachir","doi":"10.1109/iiai-aai53430.2021.00074","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00074","url":null,"abstract":"Observation and patrolling methods assure the coverage of the entire environment while dealing with moving targets. The efficiency of these methods rely on a wide range of parameters, such as the number of targets, the communication range of the patrolling agent or the map's shape. Thus, in this paper we propose a decision-making tool to optimize a set of parameters among the settings defining the observation and patrolling problem. The obtained optimal configuration has to ensure the expected efficiencies by the user, through the use of evaluation criteria. This tool is based on a simulation-assisted machine learning architecture, which performs a faster prediction response than running the simulation directly to obtain evaluation result. We evaluate the efficiency of the decision-making tool through several scenario, implying one or two parameters to be optimized.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116074372","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00003
H. Sakai, Zhiwen Jian
This paper copes with rule generation from table data sets and applies the obtained rules to decision support. Here, two types of table data sets are considered. One type of them is specified as a Deterministic Information System (DIS). The other type is specified as a Non-deterministic Information System (NIS) for dealing with incomplete information. Two rule generation algorithms are refined and newly implemented in Python. Every obtained rule is applied as evidence of decision-making. Therefore, the reasoning process preserves its transparency, which will be an essential characteristic for Explainable AI. The decision support environment is strengthened due to some described improvements and is also brushed up in Python. Some execution videos in Python are uploaded to the web page. This framework applies to almost any table dataset, and we can generate rules from them. This framework based on discrete data will complement statistical data analysis based on numerical data.
{"title":"Rules from Table Data Sets and Their Application to Decision SupportN","authors":"H. Sakai, Zhiwen Jian","doi":"10.1109/iiai-aai53430.2021.00003","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00003","url":null,"abstract":"This paper copes with rule generation from table data sets and applies the obtained rules to decision support. Here, two types of table data sets are considered. One type of them is specified as a Deterministic Information System (DIS). The other type is specified as a Non-deterministic Information System (NIS) for dealing with incomplete information. Two rule generation algorithms are refined and newly implemented in Python. Every obtained rule is applied as evidence of decision-making. Therefore, the reasoning process preserves its transparency, which will be an essential characteristic for Explainable AI. The decision support environment is strengthened due to some described improvements and is also brushed up in Python. Some execution videos in Python are uploaded to the web page. This framework applies to almost any table dataset, and we can generate rules from them. This framework based on discrete data will complement statistical data analysis based on numerical data.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"34 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126106854","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00142
Ari Yanase, T. Nakanishi
In this paper, we represent an impression extraction method for music by relationship between acoustic features and impression terms. Our method extracts impression terms with weights from acoustic features extracted from music as wav file. We define the acoustic features as tempo, inter-onset interval, melody register, accompaniment register, and tonality. In this paper, we use 37 kinds of impression terms to describe musical impressions. We use a data set consisting of a music file and impression terms to create a model that relates acoustic features extracted from music with impression terms using clustering and TF-ICF (Term Frequency-Inversed Cluster Frequency). By using the model, our method can extract impression terms from music as wav file. We will realize a recommendation system according to impression by our method.
{"title":"Musical Impression Extraction Method by Discovering Relationships between Acoustic Features and Impression Terms","authors":"Ari Yanase, T. Nakanishi","doi":"10.1109/iiai-aai53430.2021.00142","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00142","url":null,"abstract":"In this paper, we represent an impression extraction method for music by relationship between acoustic features and impression terms. Our method extracts impression terms with weights from acoustic features extracted from music as wav file. We define the acoustic features as tempo, inter-onset interval, melody register, accompaniment register, and tonality. In this paper, we use 37 kinds of impression terms to describe musical impressions. We use a data set consisting of a music file and impression terms to create a model that relates acoustic features extracted from music with impression terms using clustering and TF-ICF (Term Frequency-Inversed Cluster Frequency). By using the model, our method can extract impression terms from music as wav file. We will realize a recommendation system according to impression by our method.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126115468","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 : 2021-07-01DOI: 10.1109/iiai-aai53430.2021.00127
Yangchen Palmo, S. Tanimoto, Hiroyuki Sato, Atsushi Kanai
Software Defined Perimeter (SDP), a zero trust model developed by Cloud Security Alliance, has been attracted attention in the technological industry since its introduction to a world adapting to digital transformation. The SDP market is expected to grow from USD 3,141 million in 2019 to USD 10,613.87 million by 2025 globally at a Compound Annual Growth Rate (CAGR) of 22.49% during the forecast period. Many trust models have been introduced since the realization for the need of cyber security, such as public key infrastructure, software defined network, and virtual private network. SDP gained importance as a zero trust model since in the digital world no one can be trusted. With the introduction of new models and technical devices, there arises the need to improve newly introduced technology on various grounds when customers adapt to devices. Hence, we discussed overcoming current issues of SDP of scalability, reliability, and usability, etc. With the number of organizations sharing information online expanding, there is need for scalable and reliable SDP that is easy to maintain and cost efficient for evolving organizations. Thus, we newly proposed several scalable SDP models that enable easier installation management of real networks of organizations with different organizational structures.
{"title":"A Consideration of Scalability for Software Defined Perimeter Based on the Zero-trust Model","authors":"Yangchen Palmo, S. Tanimoto, Hiroyuki Sato, Atsushi Kanai","doi":"10.1109/iiai-aai53430.2021.00127","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00127","url":null,"abstract":"Software Defined Perimeter (SDP), a zero trust model developed by Cloud Security Alliance, has been attracted attention in the technological industry since its introduction to a world adapting to digital transformation. The SDP market is expected to grow from USD 3,141 million in 2019 to USD 10,613.87 million by 2025 globally at a Compound Annual Growth Rate (CAGR) of 22.49% during the forecast period. Many trust models have been introduced since the realization for the need of cyber security, such as public key infrastructure, software defined network, and virtual private network. SDP gained importance as a zero trust model since in the digital world no one can be trusted. With the introduction of new models and technical devices, there arises the need to improve newly introduced technology on various grounds when customers adapt to devices. Hence, we discussed overcoming current issues of SDP of scalability, reliability, and usability, etc. With the number of organizations sharing information online expanding, there is need for scalable and reliable SDP that is easy to maintain and cost efficient for evolving organizations. Thus, we newly proposed several scalable SDP models that enable easier installation management of real networks of organizations with different organizational structures.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125883421","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 : 2021-07-01DOI: 10.1109/IIAI-AAI53430.2021.00010
Kento Kaku, M. Kikuchi, Tadachika Ozono, T. Shintani
The formulation of good academic paper titles in English is challenging for intermediate English authors (particularly students). This is because such authors are not aware of the type of titles that are generally in use. We aim to realize a support system for formulating more effective English titles for intermediate English and beginner authors. This study develops an extractive title generation system that formulates titles from keywords extracted from an abstract. Moreover, we realize a title evaluation model that can evaluate the appropriateness of paper titles. We train the model with titles of top-conference papers by using BERT. This paper describes the training data, implementation, and experimental results. The results show that our evaluation model can identify top-conference titles more effectively than intermediate English and beginner students.
{"title":"Development of an Extractive Title Generation System Using Titles of Papers of Top Conferences for Intermediate English Students","authors":"Kento Kaku, M. Kikuchi, Tadachika Ozono, T. Shintani","doi":"10.1109/IIAI-AAI53430.2021.00010","DOIUrl":"https://doi.org/10.1109/IIAI-AAI53430.2021.00010","url":null,"abstract":"The formulation of good academic paper titles in English is challenging for intermediate English authors (particularly students). This is because such authors are not aware of the type of titles that are generally in use. We aim to realize a support system for formulating more effective English titles for intermediate English and beginner authors. This study develops an extractive title generation system that formulates titles from keywords extracted from an abstract. Moreover, we realize a title evaluation model that can evaluate the appropriateness of paper titles. We train the model with titles of top-conference papers by using BERT. This paper describes the training data, implementation, and experimental results. The results show that our evaluation model can identify top-conference titles more effectively than intermediate English and beginner students.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129952070","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}
At Shibaura Institute of Technology (SIT), many students participate in short-term study abroad programs, and in Fiscal Year (FY) 2020, online study abroad programs were implemented due to pandemics of the COVID-19. First, this paper organizes study abroad programs leading to the online program. Second, this paper presents the possibility of using two indicators. One is student satisfaction indicators, and the other is the Japanese version of the Miville-Guzman Universality-Diversity Scale -Short form (MGUDS-S). The research question is whether student satisfaction indicators and global competency indicators can measure program effectiveness, even for online study abroad programs. From the questionnaire survey result, it makes clear the effectiveness of both indicators.
在柴浦工业大学(SIT)，许多学生参加短期海外留学项目，在2020财政年度(FY)，由于新冠肺炎大流行，实施了在线海外留学项目。首先，本文组织出国留学项目，从而形成在线项目。其次，本文提出了使用两个指标的可能性。一个是学生满意度指标，另一个是日本版的Miville-Guzman university - diversity Scale -Short form (mgads - s)。研究的问题是，学生满意度指标和全球能力指标是否可以衡量项目的有效性，即使是在线留学项目。从问卷调查结果中，可以看出两个指标的有效性。
{"title":"Can Online Study Abroad Programs During Covid-19 Promote Global Competencies?","authors":"Soichiro Aihara, Hatsuko Yoshikubo, Hiroyuki Ishizaki","doi":"10.1109/iiai-aai53430.2021.00044","DOIUrl":"https://doi.org/10.1109/iiai-aai53430.2021.00044","url":null,"abstract":"At Shibaura Institute of Technology (SIT), many students participate in short-term study abroad programs, and in Fiscal Year (FY) 2020, online study abroad programs were implemented due to pandemics of the COVID-19. First, this paper organizes study abroad programs leading to the online program. Second, this paper presents the possibility of using two indicators. One is student satisfaction indicators, and the other is the Japanese version of the Miville-Guzman Universality-Diversity Scale -Short form (MGUDS-S). The research question is whether student satisfaction indicators and global competency indicators can measure program effectiveness, even for online study abroad programs. From the questionnaire survey result, it makes clear the effectiveness of both indicators.","PeriodicalId":414070,"journal":{"name":"2021 10th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129730053","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：