Pub Date : 1900-01-01DOI: 10.52731/ijscai.v3.i2.374
Yasuki Iizuka, Akira Hamada, Yosuke Suzuki
In recent years, multicore or many-core processors have gained significant attention as they enable computation with a large degree of parallelism on desktop computers. However, conventional parallel processing methods often cannot easily achieve parallel effects due to various factors. In this study, we evaluated the effect of applying MultiStartbased speculative parallel computation to combinatorial optimization problems. Using probability theory, we performed theoretical verification to determine whether speculative computation is more effective than conventional parallel computation methods. In addition, we conducted experiments and compared the result with those of conventional parallel processing. In this paper, we report the results of the theoretical verification and experiments, and we show that speculative computation is more effective than conventional parallel processing.
{"title":"The Effect of Speculative Computation on Combinatorial Optimization Problems","authors":"Yasuki Iizuka, Akira Hamada, Yosuke Suzuki","doi":"10.52731/ijscai.v3.i2.374","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i2.374","url":null,"abstract":"In recent years, multicore or many-core processors have gained significant attention as they enable computation with a large degree of parallelism on desktop computers. However, conventional parallel processing methods often cannot easily achieve parallel effects due to various factors. In this study, we evaluated the effect of applying MultiStartbased speculative parallel computation to combinatorial optimization problems. Using probability theory, we performed theoretical verification to determine whether speculative computation is more effective than conventional parallel computation methods. In addition, we conducted experiments and compared the result with those of conventional parallel processing. In this paper, we report the results of the theoretical verification and experiments, and we show that speculative computation is more effective than conventional parallel processing.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116790883","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 : 1900-01-01DOI: 10.52731/ijscai.v6.i1.640
T. Ichimura, Shin Kamada
{"title":"An Ensemble Learning Method of Adaptive Structural Deep Belief Network for AffectNet","authors":"T. Ichimura, Shin Kamada","doi":"10.52731/ijscai.v6.i1.640","DOIUrl":"https://doi.org/10.52731/ijscai.v6.i1.640","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114463756","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 : 1900-01-01DOI: 10.52731/ijscai.v5.i1.637
S. Karakama, Natsuki Matsunami, Masayuki Ito
In spite of the impressive advances in artificial intelligence (AI), close collaboration between humans and AI systems is still difficult to achieve. To overcome this problem, we designed AI agents with a behavior tree that enables us to know what they are trying to do, and by using a consensus building algorithm, that is, a contract net protocol, a human and a group of AI agents were put together as one team. Taking advantage of this architecture, we designed an approach to decomposing cooperative tasks into appropriate roles. The effectiveness and feasibility of this approach were evaluated with teams in a simulated Tail Tag game. Matches were held with up to 29 AI agents and 1 person on one team and 30 people on the other team. The results indicate that our approach works almost evenly with human-human collaboration by sharing roles be-tween a human and AI swarm. By understanding the roles of AI agents, a person can immediately understand the role that he/she should take. For further improvement, we also identified that it is necessary for a person to be able to give concise and global instructions.
{"title":"Task Decomposition and Role Sharing for Real-time Human-AI Swarm Collaboration","authors":"S. Karakama, Natsuki Matsunami, Masayuki Ito","doi":"10.52731/ijscai.v5.i1.637","DOIUrl":"https://doi.org/10.52731/ijscai.v5.i1.637","url":null,"abstract":"In spite of the impressive advances in artificial intelligence (AI), close collaboration between humans and AI systems is still difficult to achieve. To overcome this problem, we designed AI agents with a behavior tree that enables us to know what they are trying to do, and by using a consensus building algorithm, that is, a contract net protocol, a human and a group of AI agents were put together as one team. Taking advantage of this architecture, we designed an approach to decomposing cooperative tasks into appropriate roles. The effectiveness and feasibility of this approach were evaluated with teams in a simulated Tail Tag game. Matches were held with up to 29 AI agents and 1 person on one team and 30 people on the other team. The results indicate that our approach works almost evenly with human-human collaboration by sharing roles be-tween a human and AI swarm. By understanding the roles of AI agents, a person can immediately understand the role that he/she should take. For further improvement, we also identified that it is necessary for a person to be able to give concise and global instructions.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123630579","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 : 1900-01-01DOI: 10.52731/ijscai.v3.i2.369
Feng‐Li Lian, Jia-En Lee, Hou-Tsan Lee
Perception and localization are the keys in autonomous vehicle systems and driver assistance systems. The perception provides the information of environments around the vehicle, like other vehicles, pedestrians, and road signs. The localization provides the position and heading of vehicle, which can be used for path planning, navigation. With perception and localization process, the safety of vehicle driving could be increased. In this paper, an image segmentation method called region growing, using threshold estimated from previous indicated road region, is proposed to determine that the pixels in the image belong to road region or not. With a defined initial partial road region, the whole road region can be obtained. On the other hand, with a prior birdeye view map of the area where the vehicle drives, the contours of road region extracted from captured images are matching with the contour on the map by iterative closest point to obtain the vehicle position. In addition, in order to increase the precision of matching, the movements of camera are also estimated by matching the contour in consecutive frames. Furthermore, the position estimated from visual information integrated with the information from GPS to obtain more accurate position. Comparing with vision-based localization only, the integration with GPS reduces the weight and influence of bad matching results, which make the estimated position more accurate. The experimental results show that in structured road, with the localization by road signs, stop lines, and lane lines, the global positions of vehicle can be estimated while the relative movements are very close to GPS data.
{"title":"Integration Framework of Monocular Vision-Based Drivable Region Detection and Contour-Based Vehicle Localization for Autonomous Driving Systems","authors":"Feng‐Li Lian, Jia-En Lee, Hou-Tsan Lee","doi":"10.52731/ijscai.v3.i2.369","DOIUrl":"https://doi.org/10.52731/ijscai.v3.i2.369","url":null,"abstract":"Perception and localization are the keys in autonomous vehicle systems and driver assistance systems. The perception provides the information of environments around the vehicle, like other vehicles, pedestrians, and road signs. The localization provides the position and heading of vehicle, which can be used for path planning, navigation. With perception and localization process, the safety of vehicle driving could be increased. In this paper, an image segmentation method called region growing, using threshold estimated from previous indicated road region, is proposed to determine that the pixels in the image belong to road region or not. With a defined initial partial road region, the whole road region can be obtained. On the other hand, with a prior birdeye view map of the area where the vehicle drives, the contours of road region extracted from captured images are matching with the contour on the map by iterative closest point to obtain the vehicle position. In addition, in order to increase the precision of matching, the movements of camera are also estimated by matching the contour in consecutive frames. Furthermore, the position estimated from visual information integrated with the information from GPS to obtain more accurate position. Comparing with vision-based localization only, the integration with GPS reduces the weight and influence of bad matching results, which make the estimated position more accurate. The experimental results show that in structured road, with the localization by road signs, stop lines, and lane lines, the global positions of vehicle can be estimated while the relative movements are very close to GPS data.","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125797877","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 : 1900-01-01DOI: 10.52731/ijscai.v4.i1.510
N. Ishii, K. Iwata, Kazuya Odagiri, Toyoshiro Nakashima, T. Matsuo
{"title":"Reduction of Variables through Nearest Neighbor Relations in Threshold Networks","authors":"N. Ishii, K. Iwata, Kazuya Odagiri, Toyoshiro Nakashima, T. Matsuo","doi":"10.52731/ijscai.v4.i1.510","DOIUrl":"https://doi.org/10.52731/ijscai.v4.i1.510","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121169229","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":"Automatic comment generation for source code using external information by neural networks for computational thinking","authors":"Hiromitsu Shiina, Sakuei Onishi, Akiyoshi Takahashi, Nobuyuki Kobayashi","doi":"10.52731/ijscai.v4.i2.572","DOIUrl":"https://doi.org/10.52731/ijscai.v4.i2.572","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116518938","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 : 1900-01-01DOI: 10.52731/ijscai.v7.i1.669
R. Ando, Yoshiyasu Takefuji
{"title":"constrained recursion algorithm for tree-structured LSTM with mini-batch SGD","authors":"R. Ando, Yoshiyasu Takefuji","doi":"10.52731/ijscai.v7.i1.669","DOIUrl":"https://doi.org/10.52731/ijscai.v7.i1.669","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129462783","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 : 1900-01-01DOI: 10.52731/ijscai.v6.i1.628
Koshiro Sekine, T. Hochin, Hiroki Nomiya, H. Yoshida
{"title":"Extraction of Genes and Transcripts Associated with Liver Cancer Using Machine Learning","authors":"Koshiro Sekine, T. Hochin, Hiroki Nomiya, H. Yoshida","doi":"10.52731/ijscai.v6.i1.628","DOIUrl":"https://doi.org/10.52731/ijscai.v6.i1.628","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121197535","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 : 1900-01-01DOI: 10.52731/ijscai.v6.i1.684
Takuma Nitta, Shinpei Hagimoto, Ari Yanase, Ryotaro Okada, Virach Sornlertlamvanich, T. Nakanishi
{"title":"Realization for Finger Character Recognition Method by Similarity Measure of Finger Features","authors":"Takuma Nitta, Shinpei Hagimoto, Ari Yanase, Ryotaro Okada, Virach Sornlertlamvanich, T. Nakanishi","doi":"10.52731/ijscai.v6.i1.684","DOIUrl":"https://doi.org/10.52731/ijscai.v6.i1.684","url":null,"abstract":"","PeriodicalId":179818,"journal":{"name":"International Journal of Smart Computing and Artificial Intelligence","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115211605","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}