2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)最新文献

{"title":"Deep Reinforcement Learning for Multi-agent Simulation using a partial floor field cutout","authors":"Yasuki Iizuka","doi":"10.1109/IIAIAAI55812.2022.00137","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00137","url":null,"abstract":"The purpose of this study is to easily create agent behavior for disaster evacuation simulation. Multi-agent simulation is commonly used in disaster evacuation simulations, but it is difficult to program agents. Floor field models and reinforcement learning have been proposed as a way of solving this problem. However, there are issues with unnatural stagnation or learning times. In this paper, we report the reinforcement learning method for an evacuation simulation agent, using the local environment. As a result of the experiment, it was confirmed that efficient movement of the agent can be achieved in a short learning time.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126032656","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}

{"title":"Development of Learning Support System with Problem Posing of Fill-in-the-Blank Questions","authors":"Hiroshi Shigematsu, S. Matsumoto","doi":"10.1109/iiaiaai55812.2022.00043","DOIUrl":"https://doi.org/10.1109/iiaiaai55812.2022.00043","url":null,"abstract":"There is a learning method called \"problem posing\" in which learners create their own tasks. Previous research show that the problem posing can make the learner initiative, which enables more effective review and helps to consolidate the understanding than in conventional learning. For this reason, the learning with problem posing is said to be more effective than general learning. There have been several studies on programming learning support focusing on the effects of problem posing. In this study, we focus on fill-in-blank problems, which are widely used in programming education, and design and develop a new system that provides a learning task of problem posing on fill- in-the-blank programming problem. Fill-in-blank is a programming learning task that has been generally recognized as effective for learning. Therefore, asking students to post a learning task of fill-in-blank would be appropriate, and the problem posing of fill-in-blank programming problems is expected to be a higher learning effectiveness than usual fill-in-blank task.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125526583","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}

{"title":"Segmental Distance between Rooted Labeled Caterpillars","authors":"Manami Hagihara, Tomoya Miyazaki, K. Hirata","doi":"10.1109/IIAIAAI55812.2022.00030","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00030","url":null,"abstract":"A segmental distance for rooted labeled unordered trees is the edit distance such that the insertion and the deletion in the edit operations are allowed to either the root or the leaves. In this paper, we design the algorithm of computing the segmental distance for rooted labeled caterpillars in O(n+h2σ) time under the unit cost function, where n is the maximum number of vertices, h is the maximum height and σ is the number of labels, whereas the problem of computing the segmental distance for rooted labeled unordered trees is MAX SNP-hard.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116992548","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}

{"title":"Investigating the effect of various types of audio reinforcement on memory retention","authors":"Parisa Supitayakul, Zeynep Yücel, Misato Nose, Akito Monden","doi":"10.1109/IIAIAAI55812.2022.00057","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00057","url":null,"abstract":"Most e-learning systems deliver solely visual information, even though they boast a huge potential for supporting the learners using various other capabilities (e.g. camera, speakers) of the hosting platform (i.e. computer, smart phone etc.). In this study, we focus deploying one such potential, namely audio stimuli (informative and non-informative), for supporting rote learning of different types of learning material (i.e. easy verbal, hard verbal and numerical). Our results indicate that audio stimuli do not provide a significant benefit for studying easy verbal content, but there is a big room for improvement concerning other content types (hard verbal and numerical). Interestingly, despite the general implications of dual-coding theory, human-readout of hard verbal contents is observed not to provide any significant improvement over visual-only stimuli. However, to our surprise, non-informative audio stimuli (i.e. bell sound) are observed to provide an improvement, whereas numerical content is observed to benefit in a similar way from informative and non-informative audio. Based on these results, in the future we aim developing an automatic learning support system, which triggers the appropriate audio stimuli, taking in consideration the type of content.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"253 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117307763","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}

{"title":"Using SNS for loan review at the bank","authors":"M. Iwashita, Naoko Nomoto","doi":"10.1109/iiaiaai55812.2022.00112","DOIUrl":"https://doi.org/10.1109/iiaiaai55812.2022.00112","url":null,"abstract":"Financial technology(FinTech) has rapidly affected how numerous financial services are provided presently. The efficiency of financial tasks is expected to give merits for both financial enterprises and consumers. Loan review is one of the most critical tasks for managing conventional banks. A bank evaluates the submitted documents and interviews by the applied enterprise. A large amount of time is spent on credibility evaluation, which is not an ideal situation for both parties. Therefore, this study proposes a more efficient credibility evaluation method by applying social networking services (SNS). The method mainly analyzes applicant information based on their relationship with credible words.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115547310","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}

{"title":"Dataset Construction and Classification Based on Pre-trained Models for Opinion Holder Detection","authors":"Al-Mahmud, Kazutaka Shimada","doi":"10.1109/IIAIAAI55812.2022.00023","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00023","url":null,"abstract":"Nowadays, it is getting increased in the massive amount of internet users. People express subjective thinking (i.e., opinion) implicitly and explicitly on online platforms such as Facebook, Twitter, Amazon product reviews, etc. Opinion holders are the people or entities who express opinions implicitly and explicitly on the online platform. With the increasing trends of online opinion mass information, it is impossible to detect them manually. For this reason, an automatic approach for opinion holder detection is essential. Opinion holder detection is useful to detect specific person’s/entity’s concerns about a particular topic, product, or problem. Opinion holder detection consists of two steps: the presence of opinion holders in text and identification of opinion holders. In this paper, we focus on the first step, namely the presence of opinion holders in text. We handle this task as a binary classification problem: INSIDE or OUTSIDE. At first, we prepare a new English dataset for this task. Then, we apply two types of pre-trained models, BERT and DistilBERT, to the INSIDE/OUTSIDE classification task. BERT is a transformer-based pre-trained language model. DistilBERT is a small, fast, cheap, and light model based on knowledge distillation from the BERT architecture. As to the binary classification task, we employ a logistic regression model on the top layer of the pre-trained models. We compare the language models employed in our experiment in terms of the F1 score and accuracy. The experimental result shows that DistilBERT obtained superior performance among the models: 0.901 on the F1 score and 0.924 on the accuracy.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130923843","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}

{"title":"Design and Implementation of System for URL Signature Construction and Impact Assessment","authors":"Shota Fujii, N. Kawaguchi, Shoya Kojima, Tomoya Suzuki, Toshihiro Yamauchi","doi":"10.1109/IIAIAAI55812.2022.00028","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00028","url":null,"abstract":"The attacker’s server plays an important role in sending attack orders and receiving stolen information, particularly in the more recent cyberattacks. Under these circumstances, it is important to use network-based signatures to block malicious communications in order to reduce the damage. However, in addition to blocking malicious communications, signatures are also required not to block benign communications during normal business operations. Therefore, the generation of signatures requires a high level of understanding of the business, and highly depends on individual skills. In addition, in actual operation, it is necessary to test whether the generated signatures do not interfere with benign communications, which results in high operational costs. In this paper, we propose SIGMA, a system that automatically generates signatures to block malicious communication without interfering with benign communication and then automatically evaluates the impact of the signatures. SIGMA automatically extracts the common parts of malware communication destinations by clustering them and generates multiple candidate signatures. After that, SIGMA automatically calculates the impact on normal communication based on business logs, etc., and presents the final signature to the analyst, which has the highest blockability of malicious communication and non-blockability of normal communication. Our objectives with this system are to reduce the human factor in generating the signatures, reduce the cost of the impact evaluation, and support the decision of whether to apply the signatures. In the preliminary evaluation, we showed that SIGMA can automatically generate a set of signatures that detect 100% of suspicious URLs with an over-detection rate of just 0.87%, using the results of 14,238 malware analyses and actual business logs. This result suggests that the cost for generation of signatures and the evaluation of their impact on business operations can be suppressed, which used to be a time-consuming and human-intensive process.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123974547","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}

{"title":"Risk Assessment Quantification for Remote Learning Based on Lecture Type","authors":"Teruo Endo, Nao Ohmori, S. Tanimoto, T. Hatashima, Atsushi Kanai","doi":"10.1109/iiaiaai55812.2022.00113","DOIUrl":"https://doi.org/10.1109/iiaiaai55812.2022.00113","url":null,"abstract":"The rapid development of ICT has promoted various approaches to remote learning. By surveying and analyzing the actual situation in other countries (the U.S., the UK, Denmark, etc.) and the implementation methods and systems of advanced initiatives, measures to improve the quality of higher education have been studied. With the advent of COVID-19 in 2020, teleworking has been implemented in companies and remote learning in universities and other educational institutions to control the spread of infection. University classes, which are traditionally conducted face-to-face, are increasingly being taught remotely, but there are many risks and issues inherent in this method. These risks have caused anxiety and dissatisfaction among both students and faculty, and in some cases have prevented the smooth implementation of classes at a distance. This paper proposes and evaluates specific countermeasures by conducting a risk assessment of remote learning for universities. This will contribute to safe and secure remote learning in the new normal era. Specifically, risk assessments were conducted for two main types of remote learning formats: on-demand and live-streaming. Then, on the basis of the results, we proposed countermeasures such as the enhancement of environmental facilities (for the on-demand type) and privacy-conscious countermeasures (for the live-streaming type). We also clarified the effectiveness of the proposed measures by comparing the risk values before and after their implementation.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116955335","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}

{"title":"Analyzing Process of Distance Learning Using Resilience Engineering and Qualitative Approach","authors":"Shigeru Kusakabe, Daisaku Arita","doi":"10.1109/IIAIAAI55812.2022.00062","DOIUrl":"https://doi.org/10.1109/IIAIAAI55812.2022.00062","url":null,"abstract":"Due to the COVID situation, it has become impossible to continue the conventional face-to-face classes and distance learning has become popular. The development and implementation of distance learning materials and scenarios that utilize ICT technology are similar to the development and operation of software systems. We will explore the methodology for effectively developing and implementing distance learning materials and scenarios by using software engineering methods such as process and modeling technology. We try to formalize implicit knowledge and skills in designing and implementing distance learning materials and scenarios by using process improvement methodologies. In addition to the conventional software engineering approach, we will use the methods of qualitative approach and resilience engineering, as people are the main implementing bodies of classes even with the advancement of ICT and their behaviors are sometimes non-deterministic and flexible when the situation changes. We explain our approach with actual interview data and models for distance learning, showing how we use these data and models in the process.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115027489","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}

{"title":"Towards Sustainable Road Network in the Era of Shrinking Population: Case Study Using MATSim","authors":"Shun Higashikawa, S. Abe, Kazuhiko Iwase, Tomoaki Takemura, Jie-Fang Zhang, Tomoyuki Ohkubo, Hisashi Hayashi","doi":"10.1109/iiaiaai55812.2022.00109","DOIUrl":"https://doi.org/10.1109/iiaiaai55812.2022.00109","url":null,"abstract":"Assuming an aging society where the number of expressway users decreases and maintenance costs for infrastructures remain high, we propose a new method for analyzing whether expressway routes should be closed when their cost-benefit ratios deteriorate owing to decreases in users. As a case study, we analyzed the Kawasaki route (the Kanagawa No. 6 Kawasaki route of the metropolitan expressway in Japan) according to the proposed method. It was found that the costbenefit ratio of the route would be less than 1 in 2025 owing to the decrease in users. However, if the Kawasaki route was closed, the vehicles there would run on National Route 409 as an alternative route, and its congestion rate would increase significantly.","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"286 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115292155","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}