Pub Date : 2021-06-30DOI: 10.52731/ijscai.v5.i1.575
Naoto Kai, Kota Sakasegawa, Tsunenori Mine, S. Hirokawa
{"title":"Machine Learning of Ambiguous Sentences and Analysis of relation between Ambiguous Sentences and Diagrams in Technical Manual for Tacit Knowledge Acquisition","authors":"Naoto Kai, Kota Sakasegawa, Tsunenori Mine, S. Hirokawa","doi":"10.52731/ijscai.v5.i1.575","DOIUrl":"https://doi.org/10.52731/ijscai.v5.i1.575","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114210167","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 : 2020-05-30DOI: 10.52731/ijscai.v4.i1.514
Seiya Okubo, Mitsuo Wakatsuki, Tasuku Mitsuishi, Yasuki Dobashi, T. Nishino
{"title":"New Applications of the Monte-Carlo Tree Search to Computer Daihinmin","authors":"Seiya Okubo, Mitsuo Wakatsuki, Tasuku Mitsuishi, Yasuki Dobashi, T. Nishino","doi":"10.52731/ijscai.v4.i1.514","DOIUrl":"https://doi.org/10.52731/ijscai.v4.i1.514","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130342627","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 : 2020-05-30DOI: 10.52731/ijscai.v4.i1.500
Yoshiyuki Suimon, Hiroki Sakaji, K. Izumi, T. Shimada, Hiroyasu Matsushima
In recent years, overseas financial system crises (e.g., Lehman shock and European debt crisis) and the effects of monetary policy changes by US and European central banks exerted major influence on the Japanese interest rates market. In this research, we developed a forecasting model of Japanese interest rate based on a variety of machine learning methods, by considering the information obtained from overseas rates markets and currency markets. Finally, we confirmed that the prediction accuracy of Japanese long-term interest rate improved by using the US interest rates data in addition to the Japanese interest rates data for machine learning. Furthermore, we confirmed that the prediction accuracy increased by using US and Japanese rates markets data in recent years, particularly after 2006. This result suggests that information of overseas interest rates can be used to forecast Japanese rates market nowadays.
{"title":"Japanese Interest Rate Forecast Considering the Linkage of Global Markets Using Machine Learning Methods","authors":"Yoshiyuki Suimon, Hiroki Sakaji, K. Izumi, T. Shimada, Hiroyasu Matsushima","doi":"10.52731/ijscai.v4.i1.500","DOIUrl":"https://doi.org/10.52731/ijscai.v4.i1.500","url":null,"abstract":"In recent years, overseas financial system crises (e.g., Lehman shock and European debt crisis) and the effects of monetary policy changes by US and European central banks exerted major influence on the Japanese interest rates market. In this research, we developed a forecasting model of Japanese interest rate based on a variety of machine learning methods, by considering the information obtained from overseas rates markets and currency markets. Finally, we confirmed that the prediction accuracy of Japanese long-term interest rate improved by using the US interest rates data in addition to the Japanese interest rates data for machine learning. Furthermore, we confirmed that the prediction accuracy increased by using US and Japanese rates markets data in recent years, particularly after 2006. This result suggests that information of overseas interest rates can be used to forecast Japanese rates market nowadays.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123767223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-20DOI: 10.52731/ijscai.v3.i2.292
Hiromasa Ijuin, Y. Kinoshita, Tetsuo Yamada, A. Ishigaki, M. Inoue
In recent years, economic growth and an increasing population have led to increased consumption of numerous amounts of assembly products and material resources all over the world. As the result, material shortages have become a serious global problem. To circulate materials from end-of-life (EOL) assembly products, manufacturers have to design reverse supply chain networks for EOL products. The reverse supply chain includes transportation of the EOL products from collection centers to recovery and/or disposal facilities. There are costs involved in recycling, transporting the EOL products and opening facilities. In addition, the EOL product statuses differ by user situation, and the recycling rate and cost of each product and part are dependent on the statuses. To design a reverse supply chain network, a decision maker (DM) decides the transportation route, the number of products on each route, and the production volumes at each facility to minimize the total cost while maximizing the recycling rate of the whole network. However, the relationship between the recycling rate and the total cost becomes a tradeoff. Therefore, the DM has to solve these issues simultaneously. On the other hand, Linear Physical Programming (LPP) is one of the effective methods for solving multi-objective problems. It allows the DM to express desirable ranges for each criterion. One of the most significant advantages of using LPP is that the DM does not need to specify the mathematical weights for each criterion. This study designs a bi-objective reverse supply chain network to collect and recycle the EOL assembly products using LPP. First, based on our previous study, the reverse supply chain network is modeled to transport the EOL products from collection centers to recycling facilities depending on the EOL product status, which includes the possible recycling cost and rate. Next, the reverse supply chain network is formulated using LPP to minimize the total cost while maintaining the recycling rate of the whole network. Third, a case study is conducted and the results obtained by the LPP and the integer programming from our previous study are compared. Finally, the sensitivity analysis for facility cost and the effect of changing the preference ranges of objective functions are investigated.
{"title":"Designing Reverse Supply Chain Network with Costs and Recycling Rate by Using Linear Physical Programming","authors":"Hiromasa Ijuin, Y. Kinoshita, Tetsuo Yamada, A. Ishigaki, M. Inoue","doi":"10.52731/ijscai.v3.i2.292","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i2.292","url":null,"abstract":"In recent years, economic growth and an increasing population have led to increased consumption of numerous amounts of assembly products and material resources all over the world. As the result, material shortages have become a serious global problem. To circulate materials from end-of-life (EOL) assembly products, manufacturers have to design reverse supply chain networks for EOL products. The reverse supply chain includes transportation of the EOL products from collection centers to recovery and/or disposal facilities. There are costs involved in recycling, transporting the EOL products and opening facilities. In addition, the EOL product statuses differ by user situation, and the recycling rate and cost of each product and part are dependent on the statuses. To design a reverse supply chain network, a decision maker (DM) decides the transportation route, the number of products on each route, and the production volumes at each facility to minimize the total cost while maximizing the recycling rate of the whole network. However, the relationship between the recycling rate and the total cost becomes a tradeoff. Therefore, the DM has to solve these issues simultaneously. On the other hand, Linear Physical Programming (LPP) is one of the effective methods for solving multi-objective problems. It allows the DM to express desirable ranges for each criterion. One of the most significant advantages of using LPP is that the DM does not need to specify the mathematical weights for each criterion. This study designs a bi-objective reverse supply chain network to collect and recycle the EOL assembly products using LPP. First, based on our previous study, the reverse supply chain network is modeled to transport the EOL products from collection centers to recycling facilities depending on the EOL product status, which includes the possible recycling cost and rate. Next, the reverse supply chain network is formulated using LPP to minimize the total cost while maintaining the recycling rate of the whole network. Third, a case study is conducted and the results obtained by the LPP and the integer programming from our previous study are compared. Finally, the sensitivity analysis for facility cost and the effect of changing the preference ranges of objective functions are investigated.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128604237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-11-19DOI: 10.52731/ijscai.v3.i2.416
Guu Kofujita
A traffic flow allocation has been studied by many researches. This problem is treated by both urban planning research and game theoretical approaches. We stand on game theory to consider the traffic flow allocation problem by treating a class of congestion games on the network. The traffic flow allocation is called, in context the congestion game, a selfish routing game. In this game, our proposal is to find an equilibria of decision making of the players. The player's decision is amounts of flows for each origin-destination path. It is known that the equilibrium searching problem as edge based modeling is able to compute easily by using Frank-Wolfe method, however, the edge based model has weak expressiveness. Thus we employ a path based modeling that can treat some complex phenomena. In this model, since we need to handle many paths in a network, it is known that the equilibrium searching problem is difficult. In this paper, we study a solving method for a multi OD selfish routing game, and a method for solving standard routing games and its high speeding method. Our algorithm employs a replicator dynamics which is one of iterative optimization techniques. In the solution based on the replicator dynamics, the calculation time is very large, since the calculation is also performed for all paths. Therefore, as a preprocessing of solving by replicator dynamics, the policy of the proposed method is to make computation time faster by deleting unused paths. This paper evaluates the algorithm by numerical experiment.
{"title":"Pruning Algorithms for A Replicator Dynamics Method in Multiple OD Selfish Routing Games","authors":"Guu Kofujita","doi":"10.52731/ijscai.v3.i2.416","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i2.416","url":null,"abstract":"A traffic flow allocation has been studied by many researches. This problem is treated by both urban planning research and game theoretical approaches. We stand on game theory to consider the traffic flow allocation problem by treating a class of congestion games on the network. The traffic flow allocation is called, in context the congestion game, a selfish routing game. In this game, our proposal is to find an equilibria of decision making of the players. The player's decision is amounts of flows for each origin-destination path. It is known that the equilibrium searching problem as edge based modeling is able to compute easily by using Frank-Wolfe method, however, the edge based model has weak expressiveness. Thus we employ a path based modeling that can treat some complex phenomena. In this model, since we need to handle many paths in a network, it is known that the equilibrium searching problem is difficult. In this paper, we study a solving method for a multi OD selfish routing game, and a method for solving standard routing games and its high speeding method. Our algorithm employs a replicator dynamics which is one of iterative optimization techniques. In the solution based on the replicator dynamics, the calculation time is very large, since the calculation is also performed for all paths. Therefore, as a preprocessing of solving by replicator dynamics, the policy of the proposed method is to make computation time faster by deleting unused paths. This paper evaluates the algorithm by numerical experiment.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125948013","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 : 2019-05-31DOI: 10.52731/ijscai.v3.i1.291
Kengo Nakamura
Manufacturing firms are becoming more global and forming global supply chain networks in their pursuit of lower production costs and emerging markets, including those in Asia. The global supply chain network consists of domestic as well as international suppliers, factories, and markets. Then, the supply chain network applies customs duties when parts and products are transported across overseas borders. In addition, awareness about several cross-border treaties such as regional free trade agreements (FTAs) and the Trans-Pacific Partnership (TPP), is indispensable when designing a global supply chain network. The current fluctuations in oil and energy price also cannot be ignored. This study analyzes the effect of fluctuating material prices on the global supply chain network under customs duty rates and the TPP regime. First, the global supply chain network with customs duty and TPP is modeled. Next, the model is formulated with integer programming. Finally, sensitivity analysis is conducted in order to investigate the effect on the global supply chain network of the fluctuations in material prices.
{"title":"Design and Analysis of Global Supply Chain Network with Trans-Pacific Partnership under Fluctuating Material Prices","authors":"Kengo Nakamura","doi":"10.52731/ijscai.v3.i1.291","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i1.291","url":null,"abstract":"Manufacturing firms are becoming more global and forming global supply chain networks in their pursuit of lower production costs and emerging markets, including those in Asia. The global supply chain network consists of domestic as well as international suppliers, factories, and markets. Then, the supply chain network applies customs duties when parts and products are transported across overseas borders. In addition, awareness about several cross-border treaties such as regional free trade agreements (FTAs) and the Trans-Pacific Partnership (TPP), is indispensable when designing a global supply chain network. The current fluctuations in oil and energy price also cannot be ignored. This study analyzes the effect of fluctuating material prices on the global supply chain network under customs duty rates and the TPP regime. First, the global supply chain network with customs duty and TPP is modeled. Next, the model is formulated with integer programming. Finally, sensitivity analysis is conducted in order to investigate the effect on the global supply chain network of the fluctuations in material prices.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129227108","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 : 2019-05-31DOI: 10.52731/ijscai.v3.i1.321
S. Egami, Takahiro Kawamura, Kouji Kozaki, Akihiko Ohsuga
Municipalities in Japan have various urban problems such as traffic accidents, illegally parked bicycles, and noise pollution. However, using these data to solve urban problems is difficult, as these data are not structurally constructed. Hence, we aim to construct the Linked Data set that will facilitate the solving of urban problems. In this paper, we propose a method for semi-automatic construction of Linked Data with the causality of urban problems, based on Web pages and open government data. Specifically, we extracted causal relations using natural language processing and crowdsourcing to include problem causality in the Linked Data. Then, we provided an example query to confirm the relationships between several problems. Finally, we discussed our crowdsourcing task design for extracting urban problem causality.
{"title":"Construction of Urban Problem LOD using Crowdsourcing","authors":"S. Egami, Takahiro Kawamura, Kouji Kozaki, Akihiko Ohsuga","doi":"10.52731/ijscai.v3.i1.321","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i1.321","url":null,"abstract":"Municipalities in Japan have various urban problems such as traffic accidents, illegally parked bicycles, and noise pollution. However, using these data to solve urban problems is difficult, as these data are not structurally constructed. Hence, we aim to construct the Linked Data set that will facilitate the solving of urban problems. In this paper, we propose a method for semi-automatic construction of Linked Data with the causality of urban problems, based on Web pages and open government data. Specifically, we extracted causal relations using natural language processing and crowdsourcing to include problem causality in the Linked Data. Then, we provided an example query to confirm the relationships between several problems. Finally, we discussed our crowdsourcing task design for extracting urban problem causality.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125291864","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 : 2019-05-31DOI: 10.52731/ijscai.v3.i1.260
Manabu Yamazaki
Recently, due to the diversification of market needs, production plants are shifting to multi-item small-volume production. However, frequent item switching in a single facility increases the setup time, resulting in a decrease in the production rate or the operational ratio of facilities. In this study, we consider a process production scheduling for a factory with a long setup time that produces multiple variants of garbage bags. In the experiment, several item-switching patterns were set on the basis of actual examples, and the influence of the differences in the setup method in continuous production of difficult-to-process products on the production time and setup time was investigated. Based on the comparison to the conventional production schedule, it is possible to improve the production time and setup time without increasing the loss by changing the setup method.
{"title":"Effect of a Setup without Machine Stop in a Multi-item Process Production System","authors":"Manabu Yamazaki","doi":"10.52731/ijscai.v3.i1.260","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i1.260","url":null,"abstract":"Recently, due to the diversification of market needs, production plants are shifting to multi-item small-volume production. However, frequent item switching in a single facility increases the setup time, resulting in a decrease in the production rate or the operational ratio of facilities. In this study, we consider a process production scheduling for a factory with a long setup time that produces multiple variants of garbage bags. In the experiment, several item-switching patterns were set on the basis of actual examples, and the influence of the differences in the setup method in continuous production of difficult-to-process products on the production time and setup time was investigated. Based on the comparison to the conventional production schedule, it is possible to improve the production time and setup time without increasing the loss by changing the setup method.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132781555","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}
Melody recognition consists of three cognitive elements: pitch contour, rhythm, and tonality. Pitch contour and rhythm can be relatively easily represented by body motion. In comparison, tonality is difficult to understand and to represent for music beginners. In this paper, we focus on two approaches to supporting improvisational ensemble for music beginners on the basis of body motion tracking: (1) an approach by using a 3D motion capture camera and (2) an approach by using sensors in a smartphone. Users of our systems can participate in improvisational ensembles by making hand movements that correspond to the pitch contour and rhythm without considering tonality because the generated pitch is automatically adjusted to a consonant pitch with the chords of a background tune. To deal with the delay in gesture recognition by using the 3D motion capture camera, we improved a method for recognizing gestures. The experimental results show that the delay of our method was improved over that of the conventional one. Furthermore, we implemented a method for motion tracking on the basis of smartphone sensors. The experimental results show the difficulties of motion tracking with smartphone sensors. Moreover, we discuss perspectives on social reuse of improvisational melody data shared it as open data.
{"title":"Two Approaches to Supporting Improvisational Ensemble for Music Beginners based on Body Motion Tracking","authors":"Shugo Ichinose, Souta Mizuno, Shun Shiramatsu, Tetsuro Kitahara","doi":"10.52731/ijscai.v3.i1.286","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i1.286","url":null,"abstract":"Melody recognition consists of three cognitive elements: pitch contour, rhythm, and tonality. Pitch contour and rhythm can be relatively easily represented by body motion. In comparison, tonality is difficult to understand and to represent for music beginners. In this paper, we focus on two approaches to supporting improvisational ensemble for music beginners on the basis of body motion tracking: (1) an approach by using a 3D motion capture camera and (2) an approach by using sensors in a smartphone. Users of our systems can participate in improvisational ensembles by making hand movements that correspond to the pitch contour and rhythm without considering tonality because the generated pitch is automatically adjusted to a consonant pitch with the chords of a background tune. To deal with the delay in gesture recognition by using the 3D motion capture camera, we improved a method for recognizing gestures. The experimental results show that the delay of our method was improved over that of the conventional one. Furthermore, we implemented a method for motion tracking on the basis of smartphone sensors. The experimental results show the difficulties of motion tracking with smartphone sensors. Moreover, we discuss perspectives on social reuse of improvisational melody data shared it as open data.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2019-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116683723","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：