Pub Date : 2013-11-01DOI: 10.1109/ICAWST.2013.6765450
S. Maneewongvatana, S. Maneewongvatana
Hybrid cloud is a cloud computing model that combines internal resources of the organization with external resources. One major advantage of hybrid cloud computing is to accommodate short but significant transient loads that enterprise server cannot handle. A challenge of managing load balancing in this environment is usually on the tradeoff between user satisfaction and cost of external resources. In some applications, like learning management system (LMS), it is possible to predict load in advance using existing class activity patterns stored in its own database, and therefore it makes resource provisioning easier. In this paper, we analyze the class activity data of an LMS site and model the self-aware load prediction based on these patterns.
{"title":"Hybrid cloud load prediction model for LMS applications based on class activity patterns","authors":"S. Maneewongvatana, S. Maneewongvatana","doi":"10.1109/ICAWST.2013.6765450","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765450","url":null,"abstract":"Hybrid cloud is a cloud computing model that combines internal resources of the organization with external resources. One major advantage of hybrid cloud computing is to accommodate short but significant transient loads that enterprise server cannot handle. A challenge of managing load balancing in this environment is usually on the tradeoff between user satisfaction and cost of external resources. In some applications, like learning management system (LMS), it is possible to predict load in advance using existing class activity patterns stored in its own database, and therefore it makes resource provisioning easier. In this paper, we analyze the class activity data of an LMS site and model the self-aware load prediction based on these patterns.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"5 1","pages":"292-298"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86580600","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765493
Linlin Chen, Xiaohong Ma, Jifei Song, Shuxue Ding
A new approach for one source signal extraction based on metrics transform is proposed and investigated in this paper. First, the mixing matrix is estimated by employing the K-means algorithm on single-source-points with higher energies. Then, the time-frequency points that incorporate one source, which can be used to approximately denote the source signals that include main information of them, are found out by employing a novel metrics transform separation algorithm. Next, the Mel Frequency Cepstral Coefficients of these signals as well as the referenced signal are extracted respectively. And here we will get the index of the target signal which has the maximum similarity to the referenced signal. After that, we apply the metrics transform step by step to find the time-frequency points that incorporate two sources, three sources and so on. A key point is that only those points which contain the contributions of the target signal will be processed. Finally the target signal is obtained through the inverse short-time Fourier transform. Compared with existing methods, our approach can be used even for the case in which the number of mixtures is smaller than that of sources and does not need any extra process after the separating. Experimental results indicate the validity of the method.
{"title":"One source signal extraction based on metrics transform","authors":"Linlin Chen, Xiaohong Ma, Jifei Song, Shuxue Ding","doi":"10.1109/ICAWST.2013.6765493","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765493","url":null,"abstract":"A new approach for one source signal extraction based on metrics transform is proposed and investigated in this paper. First, the mixing matrix is estimated by employing the K-means algorithm on single-source-points with higher energies. Then, the time-frequency points that incorporate one source, which can be used to approximately denote the source signals that include main information of them, are found out by employing a novel metrics transform separation algorithm. Next, the Mel Frequency Cepstral Coefficients of these signals as well as the referenced signal are extracted respectively. And here we will get the index of the target signal which has the maximum similarity to the referenced signal. After that, we apply the metrics transform step by step to find the time-frequency points that incorporate two sources, three sources and so on. A key point is that only those points which contain the contributions of the target signal will be processed. Finally the target signal is obtained through the inverse short-time Fourier transform. Compared with existing methods, our approach can be used even for the case in which the number of mixtures is smaller than that of sources and does not need any extra process after the separating. Experimental results indicate the validity of the method.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"15 1","pages":"508-513"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77966716","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765475
Lin Hui, Wan-chi Lin, Xiwen Li
As the World Wide Web developed and the utilization rate of the mobile device grew up, a lot of computer game companies chose to expand their product platform to the web games or the smart phone apps. These two kinds of game categories can become as popular as nowadays, because these are the ways that users can easily have access to and to play the games with. Based on the above and the fact that social networking service has become a part of our daily life, we decided to merge all social network features into our web game to make our games more compatible. This research is focused on virtual pet game with ability of allowing interaction between friends' pets and sharing messages among friends and the system are accessible through the web browser. In the future, we will combine social network system and the virtual pet game and also make a smart phone app version out of the combination, so that the users can take care of their own virtual pets anytime and anywhere as long as they have access to the Internet.
{"title":"A study of integrating social networking service into the virtual pet web game system","authors":"Lin Hui, Wan-chi Lin, Xiwen Li","doi":"10.1109/ICAWST.2013.6765475","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765475","url":null,"abstract":"As the World Wide Web developed and the utilization rate of the mobile device grew up, a lot of computer game companies chose to expand their product platform to the web games or the smart phone apps. These two kinds of game categories can become as popular as nowadays, because these are the ways that users can easily have access to and to play the games with. Based on the above and the fact that social networking service has become a part of our daily life, we decided to merge all social network features into our web game to make our games more compatible. This research is focused on virtual pet game with ability of allowing interaction between friends' pets and sharing messages among friends and the system are accessible through the web browser. In the future, we will combine social network system and the virtual pet game and also make a smart phone app version out of the combination, so that the users can take care of their own virtual pets anytime and anywhere as long as they have access to the Internet.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"40 1","pages":"412-418"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74927230","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}
Attention computational model is widely used in the embedded intelligent vision system to help it offload the processing effort. In this paper, we proposed a visual attention computational model based on the biological mechanism that the dorsal pathway will guide the ventral visual information process. The model involves two feature processing subsystems, one is the dorsal pathway feature processing subsystem and the other is the ventral pathway feature processing subsystem. Moreover, the dorsal pathway feature processing subsystem will generate a signal based on its processing result to modulate the information processing of the ventral pathway feature processing subsystem. The experiment results show that the proposed model outperforms the comparison models in four different test scenarios, which indicates that the proposed model may be more biologically plausible and can help the embedded intelligent vision system to find out the interested objects more accurately.
{"title":"A dorsal pathway guided visual attention model","authors":"Lingxiang Zheng, Xianchao Zheng, Zhanjian Lin, Weiwei Tang, Changle Zhou","doi":"10.1109/ICAWST.2013.6765517","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765517","url":null,"abstract":"Attention computational model is widely used in the embedded intelligent vision system to help it offload the processing effort. In this paper, we proposed a visual attention computational model based on the biological mechanism that the dorsal pathway will guide the ventral visual information process. The model involves two feature processing subsystems, one is the dorsal pathway feature processing subsystem and the other is the ventral pathway feature processing subsystem. Moreover, the dorsal pathway feature processing subsystem will generate a signal based on its processing result to modulate the information processing of the ventral pathway feature processing subsystem. The experiment results show that the proposed model outperforms the comparison models in four different test scenarios, which indicates that the proposed model may be more biologically plausible and can help the embedded intelligent vision system to find out the interested objects more accurately.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"19 1","pages":"638-644"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74738769","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765409
Y. Liu, Qiangfu Zhao, N. Yen
Transition learning means the short learning period after switching from one learning method to another in this paper. The idea of transition learning is to apply balanced ensemble learning for a certain time, and then to switch to negative correlation learning. Because of the different learning functions between the two methods, the learning behaviors are expected to have a sudden changes in transition learning. Experimental studies had been conducted to examine such learning behaviors in the transition process. It was found that the training error rates jumped immediately in the transition while the testing error rates often appeared to fall slightly. Such large changes in error rates suggested that the decision boundary formed by balanced ensemble learning had been greatly altered in transition learning. This paper presents the explanations of the transition learning from both the ensemble and individual neural network levels.
{"title":"Make decision boundary smoother by transition learning","authors":"Y. Liu, Qiangfu Zhao, N. Yen","doi":"10.1109/ICAWST.2013.6765409","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765409","url":null,"abstract":"Transition learning means the short learning period after switching from one learning method to another in this paper. The idea of transition learning is to apply balanced ensemble learning for a certain time, and then to switch to negative correlation learning. Because of the different learning functions between the two methods, the learning behaviors are expected to have a sudden changes in transition learning. Experimental studies had been conducted to examine such learning behaviors in the transition process. It was found that the training error rates jumped immediately in the transition while the testing error rates often appeared to fall slightly. Such large changes in error rates suggested that the decision boundary formed by balanced ensemble learning had been greatly altered in transition learning. This paper presents the explanations of the transition learning from both the ensemble and individual neural network levels.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"106 1","pages":"58-63"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72815652","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765411
M. Lukac, M. Kameyama
In order to obtain the best result in image understanding it is desirable to select the best algorithm on a case by case basis. An algorithm can be selected using only image features, however such selected algorithms will often generate errors due to occlusion, shadows and other environmental conditions. To avoid such errors, it is necessary to understand processing errors on a symbolic level. Using symbolic information to determine the best algorithm is however difficult task because the possible combinations of elements and environmental conditions are almost infinite. Consequently it is impossible to predict best algorithm for all possible combinations of objects, environment conditions and context variations. In this paper we investigate selection of algorithms using symbolic image description and the determination of algorithms' error from high level image description. The proposed method transforms and minimize the high level information contained in the symbolic image description in such manner that will preserve the algorithm selection quality. The transformation takes a high level information label and transforms it into a set of generic features while the minimization uses hierarchy to reduce the specific nature of the information. Both methods of information reduction are used in a Bayesian Network because a BN is well known for using the generalization and hierarchy. As is shown in this paper, such representation efficiently reduces the fine grain high-level symbolic description to a coarser-grain hierarchy that preserves the selection quality but reduces the number of nodes.
{"title":"Bayesian Network for algorithm selection: Real-world hierarchy for nodes reduction","authors":"M. Lukac, M. Kameyama","doi":"10.1109/ICAWST.2013.6765411","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765411","url":null,"abstract":"In order to obtain the best result in image understanding it is desirable to select the best algorithm on a case by case basis. An algorithm can be selected using only image features, however such selected algorithms will often generate errors due to occlusion, shadows and other environmental conditions. To avoid such errors, it is necessary to understand processing errors on a symbolic level. Using symbolic information to determine the best algorithm is however difficult task because the possible combinations of elements and environmental conditions are almost infinite. Consequently it is impossible to predict best algorithm for all possible combinations of objects, environment conditions and context variations. In this paper we investigate selection of algorithms using symbolic image description and the determination of algorithms' error from high level image description. The proposed method transforms and minimize the high level information contained in the symbolic image description in such manner that will preserve the algorithm selection quality. The transformation takes a high level information label and transforms it into a set of generic features while the minimization uses hierarchy to reduce the specific nature of the information. Both methods of information reduction are used in a Bayesian Network because a BN is well known for using the generalization and hierarchy. As is shown in this paper, such representation efficiently reduces the fine grain high-level symbolic description to a coarser-grain hierarchy that preserves the selection quality but reduces the number of nodes.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"29 4 1","pages":"69-75"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84237286","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765471
Yu-Hsiang Lin, R. Chen, Qiangfu Zhao
Context awareness has become an important issue in recent years. However, we still do not have a formal mechanism for solving related problems due to the complexity caused by personalization, service diversity, user intension, and so on. In this paper, we investigate the possibility of solving the problems using re-definable ontology. As a concrete example, we study smart phone based automatic service recommendation. The main idea of this work is to record the user behaviors, estimate the user intention based on the recorded data, induce first-order predicate logic rules, and re-define the structure of an ontology system. The re-definable ontology system can become smarter and smarter to understand the user intention and the correlation between users, and recommend proper services in proper timing. Based on the proposed mechanism, a simple prototype system is implemented. This paper provides some preliminary test results, and points out problems for future study.
{"title":"Dynamically re-definable ontology based user intension awareness","authors":"Yu-Hsiang Lin, R. Chen, Qiangfu Zhao","doi":"10.1109/ICAWST.2013.6765471","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765471","url":null,"abstract":"Context awareness has become an important issue in recent years. However, we still do not have a formal mechanism for solving related problems due to the complexity caused by personalization, service diversity, user intension, and so on. In this paper, we investigate the possibility of solving the problems using re-definable ontology. As a concrete example, we study smart phone based automatic service recommendation. The main idea of this work is to record the user behaviors, estimate the user intention based on the recorded data, induce first-order predicate logic rules, and re-define the structure of an ontology system. The re-definable ontology system can become smarter and smarter to understand the user intention and the correlation between users, and recommend proper services in proper timing. Based on the proposed mechanism, a simple prototype system is implemented. This paper provides some preliminary test results, and points out problems for future study.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"1 1","pages":"389-395"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82131091","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765529
M. Hsu, T. Shih
Human Computer Interaction is becoming a major component in computer science related fields allowing humans to communicate with machines in very simple ways exploring new dimensions of research. Kinect, the 3D sensing device introduced by Microsoft mainly aiming computer games domain now is used in different scopes, one is being generation or controlling of sound signals producing aesthetic music. Here, in this paper, authors' experimental efforts on three virtual music instruments: Drum, Guitar and Spider King, based on Kinect sensor are presented. All three instruments virtually set the relevant sensing input areas, as an example, strings of the guitar or cymbals of the drum, then, the player controls the instrument through those virtual inputs through the Kinect. Sound control data is then generated and fed to the audio library based on the musically oriented human computer interaction gestures, composing a realtime musical expressive performance. A live performance using the presented virtual instruments was carried out at the end.
{"title":"Spider King: Virtual musical instruments based on microsoft Kinect","authors":"M. Hsu, T. Shih","doi":"10.1109/ICAWST.2013.6765529","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765529","url":null,"abstract":"Human Computer Interaction is becoming a major component in computer science related fields allowing humans to communicate with machines in very simple ways exploring new dimensions of research. Kinect, the 3D sensing device introduced by Microsoft mainly aiming computer games domain now is used in different scopes, one is being generation or controlling of sound signals producing aesthetic music. Here, in this paper, authors' experimental efforts on three virtual music instruments: Drum, Guitar and Spider King, based on Kinect sensor are presented. All three instruments virtually set the relevant sensing input areas, as an example, strings of the guitar or cymbals of the drum, then, the player controls the instrument through those virtual inputs through the Kinect. Sound control data is then generated and fed to the audio library based on the musically oriented human computer interaction gestures, composing a realtime musical expressive performance. A live performance using the presented virtual instruments was carried out at the end.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"56 1","pages":"707-713"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80201787","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765488
J. C. Hung, V. Hsu, Martin M. Weng
With the development of wireless environment, tourism marketing transfer from the traditional way to the new generation. The mobile commerce technology provides customer more directly and more timely information. Our study purpose a schema based on human portfolio combined with the global satellite positioning system (Global Positioning System; GPS) positioning function to make a proper localization and adaptive for the intelligent mobile devices in the recommendation system. First we catch the tourism position than cross match with the indicator in the Human Portfolio. This could filter the information and personalize the travel information. This provides personalized information via interactions with Smart Travel Service and Human Portfolio, a previously filtered product issues, and an interactions between tourism and provider to promote collaborative problem resolution. Furthermore, we proposed a Task Oriented Petri Net (TOPN) model to implement the award mechanism in order to provide the interaction and feedback for traveler during the journey. It's identifying the construction of different travel mission from users area and find a suitable mission for user. Meanwhile, an adaptive recommendation algorithm, complied with context-awareness and ambient-awareness, also provide an adaptive and omnibearing travel route planning for different user even from the same place.
{"title":"A study for task based recommendation system for travel navigation","authors":"J. C. Hung, V. Hsu, Martin M. Weng","doi":"10.1109/ICAWST.2013.6765488","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765488","url":null,"abstract":"With the development of wireless environment, tourism marketing transfer from the traditional way to the new generation. The mobile commerce technology provides customer more directly and more timely information. Our study purpose a schema based on human portfolio combined with the global satellite positioning system (Global Positioning System; GPS) positioning function to make a proper localization and adaptive for the intelligent mobile devices in the recommendation system. First we catch the tourism position than cross match with the indicator in the Human Portfolio. This could filter the information and personalize the travel information. This provides personalized information via interactions with Smart Travel Service and Human Portfolio, a previously filtered product issues, and an interactions between tourism and provider to promote collaborative problem resolution. Furthermore, we proposed a Task Oriented Petri Net (TOPN) model to implement the award mechanism in order to provide the interaction and feedback for traveler during the journey. It's identifying the construction of different travel mission from users area and find a suitable mission for user. Meanwhile, an adaptive recommendation algorithm, complied with context-awareness and ambient-awareness, also provide an adaptive and omnibearing travel route planning for different user even from the same place.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"11 1","pages":"481-486"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82873348","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 : 2013-11-01DOI: 10.1109/ICAWST.2013.6765406
Yury Sokolov, R. Kozma
This paper addresses the issue of stability of approximate dynamic programming (ADP) in various sequential decision making problems, including intelligent control. We employ an ADP control algorithm that iteratively improves an internal model of the external world in the autonomous system based on its continuous interaction with the environment. Through the incremental learning process, the system becomes aware of the consequences of its action into the world. We extend previous results on stability of the ADP control to the case of general multi-layer neural network approximators. We demonstrate the benefit of our results in the control of various systems, including the cart pole balancing problem. Our results show significantly improved learning and control performance as compared to the state-of-art.
{"title":"Improved stability criteria of ADP control for efficient context-aware decision support systems","authors":"Yury Sokolov, R. Kozma","doi":"10.1109/ICAWST.2013.6765406","DOIUrl":"https://doi.org/10.1109/ICAWST.2013.6765406","url":null,"abstract":"This paper addresses the issue of stability of approximate dynamic programming (ADP) in various sequential decision making problems, including intelligent control. We employ an ADP control algorithm that iteratively improves an internal model of the external world in the autonomous system based on its continuous interaction with the environment. Through the incremental learning process, the system becomes aware of the consequences of its action into the world. We extend previous results on stability of the ADP control to the case of general multi-layer neural network approximators. We demonstrate the benefit of our results in the control of various systems, including the cart pole balancing problem. Our results show significantly improved learning and control performance as compared to the state-of-art.","PeriodicalId":68697,"journal":{"name":"炎黄地理","volume":"2 1","pages":"41-47"},"PeriodicalIF":0.0,"publicationDate":"2013-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89281258","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：