Pub Date : 2019-07-01DOI: 10.1109/IIAI-AAI.2019.00125
Mitsuo Wakatsuki, Yuta Kado, Yamato Takeuchi, Seiya Okubo, T. Nishino
Combinatorial game theory has many ways of measuring game complexity. In this paper, several measures of complexity for the card game Daihinmin are presented to obtain some of its characteristics. Furthermore, we show the difference in playing styles of Daihinmin between humans and computers.
{"title":"What are the Characteristics of the Card Game Daihinmin?","authors":"Mitsuo Wakatsuki, Yuta Kado, Yamato Takeuchi, Seiya Okubo, T. Nishino","doi":"10.1109/IIAI-AAI.2019.00125","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00125","url":null,"abstract":"Combinatorial game theory has many ways of measuring game complexity. In this paper, several measures of complexity for the card game Daihinmin are presented to obtain some of its characteristics. Furthermore, we show the difference in playing styles of Daihinmin between humans and computers.","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":"116529941","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.2019.00124
A.S. Polyakova, L. Lipinskiy, E. Semenkin
One of the main methods in data reduction processes is the instance selection method. Reducing the dataset has two main objectives: reducing the requirements for computing resources, and the time for processing the learning task. The paper studies the problem of reducing the size of a reference set of points (reference sample) in collective decision making. In the paper, the reference sample refers to the sample that is used in ensemble output based on fuzzy logic system. The fuzzy controller makes a decision which agent should be used for each point from a test set. The nearest point from the reference sample is determined for any point from a test set. Depending on the distance to the object from a test set and the successfulness of the algorithm on this object, the confidence of the algorithm on this test point is determined. Also, it is proposed to apply the instance selection to choose instances for the reference set from the training set when solving regression problems based on such methods as genetic algorithms (GA), the k-means clustering algorithm, and the random instance selection (RIS). Computational experiments show that effective instance selection in the reference set can significantly reduce the computational costs while maintaining the accuracy of the result.
{"title":"Investigation of Reference Sample Reduction Methods for Ensemble Output with Fuzzy Logic-Based Systems","authors":"A.S. Polyakova, L. Lipinskiy, E. Semenkin","doi":"10.1109/IIAI-AAI.2019.00124","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00124","url":null,"abstract":"One of the main methods in data reduction processes is the instance selection method. Reducing the dataset has two main objectives: reducing the requirements for computing resources, and the time for processing the learning task. The paper studies the problem of reducing the size of a reference set of points (reference sample) in collective decision making. In the paper, the reference sample refers to the sample that is used in ensemble output based on fuzzy logic system. The fuzzy controller makes a decision which agent should be used for each point from a test set. The nearest point from the reference sample is determined for any point from a test set. Depending on the distance to the object from a test set and the successfulness of the algorithm on this object, the confidence of the algorithm on this test point is determined. Also, it is proposed to apply the instance selection to choose instances for the reference set from the training set when solving regression problems based on such methods as genetic algorithms (GA), the k-means clustering algorithm, and the random instance selection (RIS). Computational experiments show that effective instance selection in the reference set can significantly reduce the computational costs while maintaining the accuracy of the result.","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":"116789699","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}
Requirements elicitation is the first step in software development, methods such as data collection, questionnaire, interview, field observation are used in requirements elicitation, either way, the requirements from customer need to be properly extracted. For the interview, the accuracy of requirements elicitation depends on the dialog ability of software engineer (extractor) and customer (respondent). Among software engineers, there is a difference in the ability of requirements elicitation. Besides, it is difficult for experienced software engineers to extract customer requirements without fail. In this paper, in order to extract requirements without omission, the scope of the requirements is determined in advance, and a tree-like requirements decomposition structure is proposed for constructing the requirement questions. At last, a comparative experiment was carried out, and the effectiveness of the approach was positively supported by the experiment result.
{"title":"An Approach for Requirements Elicitation using Goal, Question, and Answer","authors":"Qiang Zhi, Zhengshu Zhou, Shuji Morisaki, Shuichiro Yamamoto","doi":"10.1109/IIAI-AAI.2019.00172","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00172","url":null,"abstract":"Requirements elicitation is the first step in software development, methods such as data collection, questionnaire, interview, field observation are used in requirements elicitation, either way, the requirements from customer need to be properly extracted. For the interview, the accuracy of requirements elicitation depends on the dialog ability of software engineer (extractor) and customer (respondent). Among software engineers, there is a difference in the ability of requirements elicitation. Besides, it is difficult for experienced software engineers to extract customer requirements without fail. In this paper, in order to extract requirements without omission, the scope of the requirements is determined in advance, and a tree-like requirements decomposition structure is proposed for constructing the requirement questions. At last, a comparative experiment was carried out, and the effectiveness of the approach was positively supported by the experiment result.","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":"122106270","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.2019.00189
T. Kakue, Y. Ichihashi, K. Wakunami, H. Amano, H. Hashimoto, T. Shimobaba, T. Ito
Light-in-flight recording by holography can record light propagation with a single-shot exposure in principle and can reconstruct it as spatially and temporally continuous motion pictures. We calculated computer-generated holograms based on light-in-flight recording by holography, and printed them by a wavefront printer in order to prove the validity of the numerical simulation model based on light-in-flight recording by holography. Because we reconstructed motion pictures of light propagation from the printed holograms, we successfully showed the validity of the numerical simulation model.
{"title":"Hologram Calculation, Printing, and Reconstruction Based on Light-in-Flight Recording by Holography","authors":"T. Kakue, Y. Ichihashi, K. Wakunami, H. Amano, H. Hashimoto, T. Shimobaba, T. Ito","doi":"10.1109/IIAI-AAI.2019.00189","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00189","url":null,"abstract":"Light-in-flight recording by holography can record light propagation with a single-shot exposure in principle and can reconstruct it as spatially and temporally continuous motion pictures. We calculated computer-generated holograms based on light-in-flight recording by holography, and printed them by a wavefront printer in order to prove the validity of the numerical simulation model based on light-in-flight recording by holography. Because we reconstructed motion pictures of light propagation from the printed holograms, we successfully showed the validity of the numerical simulation model.","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":"122361535","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.2019.00153
Hirofumi Mizuno, Satoshi Takahashi
In recent years, with the spread of personal computers and smartphones, the advertisement distribution market through the Internet is growing. Most of the advertisement distribution service is a listing advertisement displayed in accordance with attributes of users and search words. One of an interest topic of item allocation and pricing problem is an envy-freeness. A key idea of envy-free is that no buyer has incentive to exchange own items and its payment pair with another buyer's items and its payment pair. It is known that a revenue maximization problem with envy-freeness is a NP-hard problem. In this paper, we study a special case of multi items envy-free allocation problems. Every buyer has a unit valuation, a budget and a preferred item set the buyer wants.
{"title":"An Envy-free Pricing Algorithm for Multi Item Market with Covering Constraints","authors":"Hirofumi Mizuno, Satoshi Takahashi","doi":"10.1109/IIAI-AAI.2019.00153","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00153","url":null,"abstract":"In recent years, with the spread of personal computers and smartphones, the advertisement distribution market through the Internet is growing. Most of the advertisement distribution service is a listing advertisement displayed in accordance with attributes of users and search words. One of an interest topic of item allocation and pricing problem is an envy-freeness. A key idea of envy-free is that no buyer has incentive to exchange own items and its payment pair with another buyer's items and its payment pair. It is known that a revenue maximization problem with envy-freeness is a NP-hard problem. In this paper, we study a special case of multi items envy-free allocation problems. Every buyer has a unit valuation, a budget and a preferred item set the buyer wants.","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":"124719421","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.2019.00207
Yusuke Tozaki, Takahiko Suzuki, Tsunenori Mine, S. Hirokawa
It is known as Benford's law that the distribution of the first digits forms a specific shape for natural numerical datasets. Deviation from the Benford's distribution indicates the irregularity of the dataset. However, it does not tell any clue to interpret the reason of irregularity. The present paper constructs a search engine of cells that appear in tables by correlating a cell with the words in the title of row or column or in the explanation of the table. We generate an exhaustive dataset of cells for testing irregularity by enumerating the search conditions. We applied the method to the number of applicants, the number of candidates, and the number of successful applicants in each department of 565 private universities in Japan. We confirmed the effectiveness of the proposed method by extracting the characteristics of the irregular datasets.
{"title":"Extracting Irregular Datasets in University Admission Statistics using Text Mining and Benford's Law","authors":"Yusuke Tozaki, Takahiko Suzuki, Tsunenori Mine, S. Hirokawa","doi":"10.1109/IIAI-AAI.2019.00207","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00207","url":null,"abstract":"It is known as Benford's law that the distribution of the first digits forms a specific shape for natural numerical datasets. Deviation from the Benford's distribution indicates the irregularity of the dataset. However, it does not tell any clue to interpret the reason of irregularity. The present paper constructs a search engine of cells that appear in tables by correlating a cell with the words in the title of row or column or in the explanation of the table. We generate an exhaustive dataset of cells for testing irregularity by enumerating the search conditions. We applied the method to the number of applicants, the number of candidates, and the number of successful applicants in each department of 565 private universities in Japan. We confirmed the effectiveness of the proposed method by extracting the characteristics of the irregular datasets.","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":"130043964","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 describes the compact and low power AI DNN discriminator which is mounted on the small drone like a hobby type. By adopting this AI module, the effective plant monitoring system using the drone has been achieved. The experimental results applied to the pineapple fields in Okinawa are shown.
{"title":"A Compact Low Power AI Module Mounted on Drone for Plant Monitor System","authors":"Tomoki Kobayashi, Tomoyuki Yokogawa, Nao Igawa, Yoichiro Sato, S. Fujii, Kazutami Arimoto","doi":"10.1109/IIAI-AAI.2019.00236","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00236","url":null,"abstract":"This paper describes the compact and low power AI DNN discriminator which is mounted on the small drone like a hobby type. By adopting this AI module, the effective plant monitoring system using the drone has been achieved. The experimental results applied to the pineapple fields in Okinawa are shown.","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":"127712062","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.2019.00145
K. Yamaguchi, Y. Shirota
We investigated effects of President Trump remarks in May 2018 on Japanese automakers. We can extract the hidden relationship among companies just from seeing the movement of stock prices. When a large event happens, stocks are likely to move in a similar way if they have a tight relation. The analysis method we used is Random Matrix Theory and the data is the stock prices of 38 Japanese automakers. We found that Isuzu has a similar movement to Toyota compared with Suzuki and Matsuda, although Isuzu, Suzuki, and Matsuda belong to the Toyota group. In addition, we found that Suzuki and Yamaha are likely to move reversely, compared to other automakers, because Suzuki and Yamaha would not be given so large damages from the tariff rise. Then we found indices of minor damage of Suzuki.
{"title":"Effects of President Trump Remarks on Japanese Automakers","authors":"K. Yamaguchi, Y. Shirota","doi":"10.1109/IIAI-AAI.2019.00145","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00145","url":null,"abstract":"We investigated effects of President Trump remarks in May 2018 on Japanese automakers. We can extract the hidden relationship among companies just from seeing the movement of stock prices. When a large event happens, stocks are likely to move in a similar way if they have a tight relation. The analysis method we used is Random Matrix Theory and the data is the stock prices of 38 Japanese automakers. We found that Isuzu has a similar movement to Toyota compared with Suzuki and Matsuda, although Isuzu, Suzuki, and Matsuda belong to the Toyota group. In addition, we found that Suzuki and Yamaha are likely to move reversely, compared to other automakers, because Suzuki and Yamaha would not be given so large damages from the tariff rise. Then we found indices of minor damage of Suzuki.","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":"127765964","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.2019.00188
T. Shimobaba, David Blinder, P. Schelkens, Yota Yamamoto, I. Hoshi, T. Kakue, T. Ito
Digital holograms can be calculated by simulating light wave propagation on a computer. Hologram calculations are used for three-dimensional displays. However, the calculations take a long time, and the data size of the calculated holograms becomes large. This study presents a deep-learning-assisted hologram calculation using low-sampling holograms. We calculate holograms with low-sampling rates, resulting in the acceleration of the hologram calculation and the decrease of the hologram size. However, the low-sampling holograms decrease the quality of the reconstructed images and will occur the aliasing errors when not satisfying the Nyquist rate. The proposed method uses a deep neural network to retrieve the full-sampling holograms from the low-sampling holograms. We show elementary results of the proposed method in numerical simulation.
{"title":"Deep-learning-assisted Hologram Calculation via Low-Sampling Holograms","authors":"T. Shimobaba, David Blinder, P. Schelkens, Yota Yamamoto, I. Hoshi, T. Kakue, T. Ito","doi":"10.1109/IIAI-AAI.2019.00188","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00188","url":null,"abstract":"Digital holograms can be calculated by simulating light wave propagation on a computer. Hologram calculations are used for three-dimensional displays. However, the calculations take a long time, and the data size of the calculated holograms becomes large. This study presents a deep-learning-assisted hologram calculation using low-sampling holograms. We calculate holograms with low-sampling rates, resulting in the acceleration of the hologram calculation and the decrease of the hologram size. However, the low-sampling holograms decrease the quality of the reconstructed images and will occur the aliasing errors when not satisfying the Nyquist rate. The proposed method uses a deep neural network to retrieve the full-sampling holograms from the low-sampling holograms. We show elementary results of the proposed method in numerical simulation.","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":"129662663","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}
Along with economic development, customers' expectations for the commercial value of a product or service tend to be diverse. Innovation of enterprise service and information technology is required to solve customer pain points and create new value. Enterprises that are insensitive in service innovation and technology innovation may gradually lose their customers and markets. In order to visualize and manage the business processes, resources, and the entire organization, including the information systems, this paper integrates Job Theory (JT), Business Model Canvas (BMC) and Balanced Scorecard (BSC), and proposes a method for EA (Enterprise Architecture) model development based on ArchiMate framework. First of all, the basic elements of traditional EA modeling approaches are analyzed and integrated. Next, the integrated elements are converted into ArchiMate concepts, a model-based method using ArchiMate elements is proposed and the detailed steps of this proposed method are defined. Last but not least, a case study on a Mental Health Care-Patient Management System (MHC-PMS) is carried out to verify the effectiveness of the proposed method.
{"title":"A Proposal for Developing EA Models toward Innovation","authors":"Zhengshu Zhou, Qiang Zhi, Shuichiro Yamamoto, Shuji Morisaki","doi":"10.1109/IIAI-AAI.2019.00173","DOIUrl":"https://doi.org/10.1109/IIAI-AAI.2019.00173","url":null,"abstract":"Along with economic development, customers' expectations for the commercial value of a product or service tend to be diverse. Innovation of enterprise service and information technology is required to solve customer pain points and create new value. Enterprises that are insensitive in service innovation and technology innovation may gradually lose their customers and markets. In order to visualize and manage the business processes, resources, and the entire organization, including the information systems, this paper integrates Job Theory (JT), Business Model Canvas (BMC) and Balanced Scorecard (BSC), and proposes a method for EA (Enterprise Architecture) model development based on ArchiMate framework. First of all, the basic elements of traditional EA modeling approaches are analyzed and integrated. Next, the integrated elements are converted into ArchiMate concepts, a model-based method using ArchiMate elements is proposed and the detailed steps of this proposed method are defined. Last but not least, a case study on a Mental Health Care-Patient Management System (MHC-PMS) is carried out to verify the effectiveness of the proposed method.","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":"128958639","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：