Recently, the interactive sound is researched in the field of an artificial life or Kansei engineering as one of interactive arts. An interactive sound changes the aspect variously by the interaction of human and a system, and it aims at generating the sound which was full of the complexity and diversity beyond expectations of human. In our laboratory, the chaotic sound generation system which shows various aspects has been developed by using the Globally Coupled Map (GCM) which puts plural chaos elements in order and operates each chaos and the whole synchronicity. However, in the present system, what we can operate is only a chaos parameter. Therefore this is the system which it is hard to reflect the human's intention in the generated sound. So, in this research, the system which analyzes human motions and instructions with an external camera and defines the directivity of the output sound is proposed. Motion capture system detects coordinates of human's joint. We designed the sound generation system to which the element of sound pitch, length, volume, and tonality are changed by the detected motion. The intention of desired sound by human is able to be reflected to the system, and we can expect to realize the large interaction effect. Moreover, it is also reported by Kansei evaluation to confirm the efficiency of the designed system.
{"title":"Interactive Sound Generation System Based on Instruction Recognition of Human Body Motion","authors":"Hotaka Kitabora, Y. Maeda, Yasutake Takahashi","doi":"10.1109/SNPD.2012.54","DOIUrl":"https://doi.org/10.1109/SNPD.2012.54","url":null,"abstract":"Recently, the interactive sound is researched in the field of an artificial life or Kansei engineering as one of interactive arts. An interactive sound changes the aspect variously by the interaction of human and a system, and it aims at generating the sound which was full of the complexity and diversity beyond expectations of human. In our laboratory, the chaotic sound generation system which shows various aspects has been developed by using the Globally Coupled Map (GCM) which puts plural chaos elements in order and operates each chaos and the whole synchronicity. However, in the present system, what we can operate is only a chaos parameter. Therefore this is the system which it is hard to reflect the human's intention in the generated sound. So, in this research, the system which analyzes human motions and instructions with an external camera and defines the directivity of the output sound is proposed. Motion capture system detects coordinates of human's joint. We designed the sound generation system to which the element of sound pitch, length, volume, and tonality are changed by the detected motion. The intention of desired sound by human is able to be reflected to the system, and we can expect to realize the large interaction effect. Moreover, it is also reported by Kansei evaluation to confirm the efficiency of the designed system.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115643722","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}
Software cost estimation is a crucial element in project management. Failing to use a proper cost estimation method might lead to project failures. According to the Standish Chaos Report, 65% of software projects are delivered over budget or after the delivery deadline. Conducting software cost estimation in the early stages of the software life cycle is important and this would be helpful to project managers to bid on projects. In this paper, we propose a novel model to predict software effort from use case diagrams using a cascade correlation neural network approach. The proposed model was evaluated based on the MMER and PRED criteria using 214 industrial and 26 educational projects against a multiple linear regression model and the Use Case Point model. The results show that the proposed cascade correlation neural network can be used with promising results as an alternative approach to predict software effort.
{"title":"Software Effort Estimation in the Early Stages of the Software Life Cycle Using a Cascade Correlation Neural Network Model","authors":"A. B. Nassif, Luiz Fernando Capretz, D. Ho","doi":"10.1109/SNPD.2012.40","DOIUrl":"https://doi.org/10.1109/SNPD.2012.40","url":null,"abstract":"Software cost estimation is a crucial element in project management. Failing to use a proper cost estimation method might lead to project failures. According to the Standish Chaos Report, 65% of software projects are delivered over budget or after the delivery deadline. Conducting software cost estimation in the early stages of the software life cycle is important and this would be helpful to project managers to bid on projects. In this paper, we propose a novel model to predict software effort from use case diagrams using a cascade correlation neural network approach. The proposed model was evaluated based on the MMER and PRED criteria using 214 industrial and 26 educational projects against a multiple linear regression model and the Use Case Point model. The results show that the proposed cascade correlation neural network can be used with promising results as an alternative approach to predict software effort.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126110052","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}
We propose a method of identifying purchase-stage to enhance the success rate of recommendations. When a user purchases a commodity through the Web, she goes through several stages, for example, " Interest in commodity, Search for commodity, Comparison of commodities, Action of purchasing". To increase the purchase rate, we need to identify the different purchase stages and construct web sites so that they better support each purchase-stage. This paper hypothesizes that the purchase-stage of the user is evidenced by his/her web-access pattern. An experiment is conducted to collect the Web access logs of several subjects when they purchase commodities on electronic commerce (EC) sites. The proposed method is shown to approximately discriminate the purchase-stages.
{"title":"Identifying Purchase-Stage by Applying Pattern Mining to Web Access Logs","authors":"M. Motegi, Yusuke Ichikawa, Toru Kobayashi","doi":"10.1109/SNPD.2012.89","DOIUrl":"https://doi.org/10.1109/SNPD.2012.89","url":null,"abstract":"We propose a method of identifying purchase-stage to enhance the success rate of recommendations. When a user purchases a commodity through the Web, she goes through several stages, for example, \" Interest in commodity, Search for commodity, Comparison of commodities, Action of purchasing\". To increase the purchase rate, we need to identify the different purchase stages and construct web sites so that they better support each purchase-stage. This paper hypothesizes that the purchase-stage of the user is evidenced by his/her web-access pattern. An experiment is conducted to collect the Web access logs of several subjects when they purchase commodities on electronic commerce (EC) sites. The proposed method is shown to approximately discriminate the purchase-stages.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123253333","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}
Anakorn Jongyindee, P. Leelaprute, M. Ohira, Ken-ichi Matsumoto
Time zone, different work schedule, limited real-time information sharing, steep learning curve and different personal specialties, these are common limitations in the collaborative studies, especially when a researcher has just been introduced to the research field or working in a different environment (i.e. Internship programs). This paper introduces you with the experiences, challenges, difficulties, lessons learned, common fallacies and pitfalls in the collaborative software engineering research through the experience of 2-months collaborative research program between Kasetsart University in Thailand and Nara Institute of Science and Technology in Japan. Good mentoring and flat-style communication between professors and students are good indicators of the high quality result in the internship program. These information can be useful to professors, young researchers and internship students who will be conducting researches in such manner.
{"title":"Lessons Learned from Collaborative Research in Software Engineering: A Student's Perspective","authors":"Anakorn Jongyindee, P. Leelaprute, M. Ohira, Ken-ichi Matsumoto","doi":"10.1109/SNPD.2012.81","DOIUrl":"https://doi.org/10.1109/SNPD.2012.81","url":null,"abstract":"Time zone, different work schedule, limited real-time information sharing, steep learning curve and different personal specialties, these are common limitations in the collaborative studies, especially when a researcher has just been introduced to the research field or working in a different environment (i.e. Internship programs). This paper introduces you with the experiences, challenges, difficulties, lessons learned, common fallacies and pitfalls in the collaborative software engineering research through the experience of 2-months collaborative research program between Kasetsart University in Thailand and Nara Institute of Science and Technology in Japan. Good mentoring and flat-style communication between professors and students are good indicators of the high quality result in the internship program. These information can be useful to professors, young researchers and internship students who will be conducting researches in such manner.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117072853","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}
Gholamreza Esfandani, Mohsen Sayyadi, A. Namadchian
This paper addresses the density based clustering problem in data mining where clusters are established based on density of regions. The most well-known algorithm proposed in this area is DBSCAN [1] which employs two parameters influencing the shape of resulted clusters. Therefore, one of the major weaknesses of this algorithm is lack of ability to handle clusters in multi-density environments. In this paper, a new density based grid clustering algorithm, GDCLU, is proposed which uses a new definition for dense regions. It determines dense grids based on densities of their neighbors. This new definition enables GDCLU to handle different shaped clusters in multi-density environments. Also this algorithm benefits from scale independency feature. The time complexity of the algorithm is O(n) in which n is number of points in dataset. Several examples are presented showing promising improvement in performance over other basic algorithms like optics in multi-density environments.
{"title":"GDCLU: A New Grid-Density Based ClustrIng Algorithm","authors":"Gholamreza Esfandani, Mohsen Sayyadi, A. Namadchian","doi":"10.1109/SNPD.2012.118","DOIUrl":"https://doi.org/10.1109/SNPD.2012.118","url":null,"abstract":"This paper addresses the density based clustering problem in data mining where clusters are established based on density of regions. The most well-known algorithm proposed in this area is DBSCAN [1] which employs two parameters influencing the shape of resulted clusters. Therefore, one of the major weaknesses of this algorithm is lack of ability to handle clusters in multi-density environments. In this paper, a new density based grid clustering algorithm, GDCLU, is proposed which uses a new definition for dense regions. It determines dense grids based on densities of their neighbors. This new definition enables GDCLU to handle different shaped clusters in multi-density environments. Also this algorithm benefits from scale independency feature. The time complexity of the algorithm is O(n) in which n is number of points in dataset. Several examples are presented showing promising improvement in performance over other basic algorithms like optics in multi-density environments.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128325482","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}
Multi-Agent Systems have been in the focus of research interest for a long time. These systems are used widely in such areas as logistics, management, various simulations, game development and many others. In this paper, we search for a method to increase flexibility and efficiency of Multi-Agent Systems by investigating the usefulness of Decision Support Systems for intelligent agents in multi-agent environment. We also research advantages, such as the ability to add new agents at run-time, and disadvantages, such as increased complexity, of creating and modifying Decision Support Systems dynamically in Multi-Agent System.
{"title":"Self-Evolving Decision Support Systems in Multi-agent Environment","authors":"Tofig Hasanov, Motoyuki Ozeki, N. Oka","doi":"10.1109/SNPD.2012.83","DOIUrl":"https://doi.org/10.1109/SNPD.2012.83","url":null,"abstract":"Multi-Agent Systems have been in the focus of research interest for a long time. These systems are used widely in such areas as logistics, management, various simulations, game development and many others. In this paper, we search for a method to increase flexibility and efficiency of Multi-Agent Systems by investigating the usefulness of Decision Support Systems for intelligent agents in multi-agent environment. We also research advantages, such as the ability to add new agents at run-time, and disadvantages, such as increased complexity, of creating and modifying Decision Support Systems dynamically in Multi-Agent System.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130019850","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 proposes the semantic generalization. This generalization makes it possible for a shape graph, which corresponds to a relation schema in the relational data model, to have elements by considering the semantics of the elements of the original shape graphs even if there is no common element in the original shape graphs. For this purpose, viewpoints and relationship trees are introduced. A viewpoint is a sub graph of a schema graph, and plays a role of a kind of hierarchy of concepts. A relationship tree is a hierarchy of relationships. The semantic generalization is informally and formally described. It is shown that the conventional generalization could be realized by using the semantic generalization.
{"title":"Semantic Generalization in a Graph-Based Data Model","authors":"Y. Ohira, T. Hochin, Hiroki Nomiya","doi":"10.1109/SNPD.2012.77","DOIUrl":"https://doi.org/10.1109/SNPD.2012.77","url":null,"abstract":"This paper proposes the semantic generalization. This generalization makes it possible for a shape graph, which corresponds to a relation schema in the relational data model, to have elements by considering the semantics of the elements of the original shape graphs even if there is no common element in the original shape graphs. For this purpose, viewpoints and relationship trees are introduced. A viewpoint is a sub graph of a schema graph, and plays a role of a kind of hierarchy of concepts. A relationship tree is a hierarchy of relationships. The semantic generalization is informally and formally described. It is shown that the conventional generalization could be realized by using the semantic generalization.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133961588","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}
S. Koka, Koichi Anada, Y. Nakayama, K. Sugita, T. Yaku, Ryusuke Yokoyama
We deal with ridge detection methods from digital elevation map (DEM) data. As ridge detection methods, the O (N2) -time steepest ascent method and the O (N) -time discrete Lap lace transform (D.L.T.) method are known, where N is the number of cells. However, the D.L.T. method is too blurry to form ridge lines. In this paper, we introduce a 12 neighbor D.L.T. method which is a modification of the 4 neighbor D.L.T. method. And we also introduce another ridge detection method by the classification of local shapes around each cell. We can consider 32 patterns for ridges or valleys. Furthermore, we compare and evaluate their ridge detection methods in a certain area. We note that our two methods provide blurry terrain maps, but it require only O (N) -time for N cells, in comparison with the steepest ascent method.
{"title":"A Comparison of Ridge Detection Methods for DEM Data","authors":"S. Koka, Koichi Anada, Y. Nakayama, K. Sugita, T. Yaku, Ryusuke Yokoyama","doi":"10.1109/SNPD.2012.46","DOIUrl":"https://doi.org/10.1109/SNPD.2012.46","url":null,"abstract":"We deal with ridge detection methods from digital elevation map (DEM) data. As ridge detection methods, the O (N2) -time steepest ascent method and the O (N) -time discrete Lap lace transform (D.L.T.) method are known, where N is the number of cells. However, the D.L.T. method is too blurry to form ridge lines. In this paper, we introduce a 12 neighbor D.L.T. method which is a modification of the 4 neighbor D.L.T. method. And we also introduce another ridge detection method by the classification of local shapes around each cell. We can consider 32 patterns for ridges or valleys. Furthermore, we compare and evaluate their ridge detection methods in a certain area. We note that our two methods provide blurry terrain maps, but it require only O (N) -time for N cells, in comparison with the steepest ascent method.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132786960","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}
Satoshi Uchigaki, S. Uchida, Koji Toda, Akito Monden
In software development, prediction of fault-prone modules is an important challenge for effective software testing. However, high prediction accuracy may not be achieved in cross-project prediction, since there is a large difference in distribution of predictor variables between the base project (for building prediction model) and the target project (for applying prediction model.) In this paper we propose an prediction technique called "an ensemble of simple regression models" to improve the prediction accuracy of cross-project prediction. The proposed method uses weighted sum of outputs of simple (e.g. 1-predictor variable) logistic regression models to improve the generalization ability of logistic models. To evaluate the performance of the proposed method, we conducted 132 combinations of cross-project prediction using datasets of 12 projects from NASA IV&V Facility Metrics Data Program. As a result, the proposed method outperformed conventional logistic regression models in terms of AUC of the Alberg diagram.
{"title":"An Ensemble Approach of Simple Regression Models to Cross-Project Fault Prediction","authors":"Satoshi Uchigaki, S. Uchida, Koji Toda, Akito Monden","doi":"10.1109/SNPD.2012.34","DOIUrl":"https://doi.org/10.1109/SNPD.2012.34","url":null,"abstract":"In software development, prediction of fault-prone modules is an important challenge for effective software testing. However, high prediction accuracy may not be achieved in cross-project prediction, since there is a large difference in distribution of predictor variables between the base project (for building prediction model) and the target project (for applying prediction model.) In this paper we propose an prediction technique called \"an ensemble of simple regression models\" to improve the prediction accuracy of cross-project prediction. The proposed method uses weighted sum of outputs of simple (e.g. 1-predictor variable) logistic regression models to improve the generalization ability of logistic models. To evaluate the performance of the proposed method, we conducted 132 combinations of cross-project prediction using datasets of 12 projects from NASA IV&V Facility Metrics Data Program. As a result, the proposed method outperformed conventional logistic regression models in terms of AUC of the Alberg diagram.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126553688","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}
Yasunori Shiono, Shohei Noguchi, Mitsumasa Mochida, Tomoo Sumida, H. Mori, K. Ohmaki, K. Tsuchida
Embedded systems have become an essential technology in fields that require electronic control. These technologies must work in real time and have high reliability and low cost. Among them, safety verification of embedded systems is very important in fields related to human life. In addition, as multi-core and multiprocessors have spread, the processing power of the hardware has been improved. As a result, concurrent processing has become necessary. In developing concurrent embedded systems, Communicating Sequential Processes (CSP) is regarded as useful. The purpose of this study is to verify, implement, and evaluate the concurrent sorting algorithm using the characteristics of CSP. In this study, we use two characteristics of CSP: synchronous communication and verification based on the formal method. In addition, we describe the extended improvement concurrent sorting algorithm.
{"title":"Efficiency of Concurrent Processing of Sort Using CSP","authors":"Yasunori Shiono, Shohei Noguchi, Mitsumasa Mochida, Tomoo Sumida, H. Mori, K. Ohmaki, K. Tsuchida","doi":"10.1109/SNPD.2012.108","DOIUrl":"https://doi.org/10.1109/SNPD.2012.108","url":null,"abstract":"Embedded systems have become an essential technology in fields that require electronic control. These technologies must work in real time and have high reliability and low cost. Among them, safety verification of embedded systems is very important in fields related to human life. In addition, as multi-core and multiprocessors have spread, the processing power of the hardware has been improved. As a result, concurrent processing has become necessary. In developing concurrent embedded systems, Communicating Sequential Processes (CSP) is regarded as useful. The purpose of this study is to verify, implement, and evaluate the concurrent sorting algorithm using the characteristics of CSP. In this study, we use two characteristics of CSP: synchronous communication and verification based on the formal method. In addition, we describe the extended improvement concurrent sorting algorithm.","PeriodicalId":387936,"journal":{"name":"2012 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2012-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130719367","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：