Weisong Hu, Chao Tian, Xiaowei Liu, Hongwei Qi, L. Zha, Huaming Liao, Yuezhuo Zhang, Jie Zhang
Map Reduce cluster is emerging as a solution of data-intensive scalable computing system. The open source implementation Hadoop has already been adopted for building clusters containing thousands of nodes. Such cloud infrastructure was used to processing many different jobs depending on different hardware resources, such as memory, CPU, Disk I/O and Network I/O, simultaneously. If the schedule policy does not consider the heterogeneity of running jobs’ resource utilization types, resource contention may happen. In this paper, we analyze this multiple job parallelization problems in Map Reduce, and propose the multiple-job optimization (MJO) scheduler. Our scheduler detects job’s resource utilization type on the fly and improves the hardware utilization by parallel different kinds of jobs. We give two scenarios which are “same plan” and “same job” to illustrate the multiple jobs’ submission traces in Map Reduce clusters. Our experiments show that in these scenarios, MJO scheduler could save the make span by about 20%.
{"title":"Multiple-Job Optimization in MapReduce for Heterogeneous Workloads","authors":"Weisong Hu, Chao Tian, Xiaowei Liu, Hongwei Qi, L. Zha, Huaming Liao, Yuezhuo Zhang, Jie Zhang","doi":"10.1109/SKG.2010.23","DOIUrl":"https://doi.org/10.1109/SKG.2010.23","url":null,"abstract":"Map Reduce cluster is emerging as a solution of data-intensive scalable computing system. The open source implementation Hadoop has already been adopted for building clusters containing thousands of nodes. Such cloud infrastructure was used to processing many different jobs depending on different hardware resources, such as memory, CPU, Disk I/O and Network I/O, simultaneously. If the schedule policy does not consider the heterogeneity of running jobs’ resource utilization types, resource contention may happen. In this paper, we analyze this multiple job parallelization problems in Map Reduce, and propose the multiple-job optimization (MJO) scheduler. Our scheduler detects job’s resource utilization type on the fly and improves the hardware utilization by parallel different kinds of jobs. We give two scenarios which are “same plan” and “same job” to illustrate the multiple jobs’ submission traces in Map Reduce clusters. Our experiments show that in these scenarios, MJO scheduler could save the make span by about 20%.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"65 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120867513","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 presented a Kahn Process Network (KPN) based service composition environment called CSCE which can establish interactions among computational service nodes. KPN is a model of computation and commonly used for describing a set of cooperative processes that communicate with each other using FIFO buffered channel. KPN has several advantages which make it adequate to model service interactions: 1) parallelism and communication mechanism in KPNs, which enable distributed service interactions on internet, 2) KPNs are compositional, which corresponds to the possibility to build bigger behaviors from small ones, 3) KPN can be executed, which ensures a executable service interaction environment for actual application. In order to describe service interactions in CSCE, we provide four kinds of service interaction events which enrich KPN operations. Finally we present an application case to show how to describe service interactions in CSCE.
{"title":"Service Interactions in CSCE Service Composition Environment","authors":"Xiuguo Zhang, Yingjun Zhang","doi":"10.1109/SKG.2010.63","DOIUrl":"https://doi.org/10.1109/SKG.2010.63","url":null,"abstract":"This paper presented a Kahn Process Network (KPN) based service composition environment called CSCE which can establish interactions among computational service nodes. KPN is a model of computation and commonly used for describing a set of cooperative processes that communicate with each other using FIFO buffered channel. KPN has several advantages which make it adequate to model service interactions: 1) parallelism and communication mechanism in KPNs, which enable distributed service interactions on internet, 2) KPNs are compositional, which corresponds to the possibility to build bigger behaviors from small ones, 3) KPN can be executed, which ensures a executable service interaction environment for actual application. In order to describe service interactions in CSCE, we provide four kinds of service interaction events which enrich KPN operations. Finally we present an application case to show how to describe service interactions in CSCE.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114936906","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}
Cognition overload is one of the major problems in current self-learning intelligent learning systems. Providing learners with the personalized learning path can effectively smooth over users’ learning disorientation. In this paper, we propose a multi-faceted recommendation framework that provides learners with personalized learning paths based on their different learning styles. Building the recommendation system mainly involves the following three steps: (1) analyze the influences of the learning style in different dimensions during the learning process, (2) automatically organize the Learning Objects (LOs) into a multi-faceted Semantic Linked Network (SLN) via self-organized rules, (3) recommend the learning path to the learner through a reasoning machine based on the constructed SLN. The experiments verify the efficiency of the proposed method.
{"title":"Multi-faceted Learning Paths Recommendation Via Semantic Linked Network","authors":"Juan Yang, Zhixing Huang, Hongtao Liu","doi":"10.1109/SKG.2010.12","DOIUrl":"https://doi.org/10.1109/SKG.2010.12","url":null,"abstract":"Cognition overload is one of the major problems in current self-learning intelligent learning systems. Providing learners with the personalized learning path can effectively smooth over users’ learning disorientation. In this paper, we propose a multi-faceted recommendation framework that provides learners with personalized learning paths based on their different learning styles. Building the recommendation system mainly involves the following three steps: (1) analyze the influences of the learning style in different dimensions during the learning process, (2) automatically organize the Learning Objects (LOs) into a multi-faceted Semantic Linked Network (SLN) via self-organized rules, (3) recommend the learning path to the learner through a reasoning machine based on the constructed SLN. The experiments verify the efficiency of the proposed method.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114255241","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}
Distributed graphics rendering is a sub domain of grid computing problem. In this paper, aimed at the characteristics of Internet-based distributed rendering system, we discussed the uniform description of rendering resources, defined the calculating method of rendering ability of the system, and discussed the system’s performance on Internet-based tree structure. A possible performance assessment is proposed for Internet-based distributed rendering system.
{"title":"Research on Internet-Based Distributed Rendering","authors":"Q. Yang","doi":"10.1109/SKG.2010.50","DOIUrl":"https://doi.org/10.1109/SKG.2010.50","url":null,"abstract":"Distributed graphics rendering is a sub domain of grid computing problem. In this paper, aimed at the characteristics of Internet-based distributed rendering system, we discussed the uniform description of rendering resources, defined the calculating method of rendering ability of the system, and discussed the system’s performance on Internet-based tree structure. A possible performance assessment is proposed for Internet-based distributed rendering system.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124340527","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}
B. Holtkamp, Sebastian Steinbuß, H. Gsell, Thorsten Löffeler, U. Springer
This paper describes an approach for the development of a logistics cloud as a “vertical cloud”. In contrast to a generic or “horizontal cloud” components of the cloud platform are custom tailored to the specific needs of the logistics application area. The NIST cloud services model serves as a basis for structuring logistics specific cloud service requirements. In the next step the domain specific model is used as a basis for the development of Logistics Mall, a domain specific cloud platform for the trading and usage of logistics IT services and logistics processes. The paper closes with an overview of the implementation status and an outlook to future work.
{"title":"Towards a Logistics Cloud","authors":"B. Holtkamp, Sebastian Steinbuß, H. Gsell, Thorsten Löffeler, U. Springer","doi":"10.1109/SKG.2010.46","DOIUrl":"https://doi.org/10.1109/SKG.2010.46","url":null,"abstract":"This paper describes an approach for the development of a logistics cloud as a “vertical cloud”. In contrast to a generic or “horizontal cloud” components of the cloud platform are custom tailored to the specific needs of the logistics application area. The NIST cloud services model serves as a basis for structuring logistics specific cloud service requirements. In the next step the domain specific model is used as a basis for the development of Logistics Mall, a domain specific cloud platform for the trading and usage of logistics IT services and logistics processes. The paper closes with an overview of the implementation status and an outlook to future work.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131341004","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}
Up to now, 3D watermarking has mainly focused on triangle meshes which are the most used digital representations of the shape of a 3D model. In this paper, we present a watermarking technique for authentication of 3D polygonal meshes. We propose a robust 3D watermarking method for high rate embedding of a watermark into 3D polygonal meshes. The proposed technique is based on spectral mesh compression, The core idea behind our technique is to apply laplacial spectral compression to each sub-mesh, the watermark embedding and extraction algorithms are applied to each sub-mesh. The proposed scheme improves the performance of the data embedding system, perceptual invisibility and it is resistant to a variety of the most common attacks.
{"title":"Robust 3D Watermarking Technique for Authentication of 3D Polygonal Medel","authors":"Yan-Hong Zhang","doi":"10.1109/SKG.2010.51","DOIUrl":"https://doi.org/10.1109/SKG.2010.51","url":null,"abstract":"Up to now, 3D watermarking has mainly focused on triangle meshes which are the most used digital representations of the shape of a 3D model. In this paper, we present a watermarking technique for authentication of 3D polygonal meshes. We propose a robust 3D watermarking method for high rate embedding of a watermark into 3D polygonal meshes. The proposed technique is based on spectral mesh compression, The core idea behind our technique is to apply laplacial spectral compression to each sub-mesh, the watermark embedding and extraction algorithms are applied to each sub-mesh. The proposed scheme improves the performance of the data embedding system, perceptual invisibility and it is resistant to a variety of the most common attacks.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130701631","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 applies such data mining techniques as clustering and classifying to customer segmentation based on insurance Customer Risk Contribution matrix. A solution for segmentation management based on Clementine is put forwarded. It is brought forward that the insurance customer segmentation method, which can provide decision bases for insurance companies’ making premium rate and controlling claim risk. At the same time, it makes segmentation management more scientific and lifts the capability of insurance market competition.
{"title":"Research for Customer Segmentation of Medical Insurance Based on K-means and C&R Tree Algorithms","authors":"Jianxin Bi","doi":"10.1109/SKG.2010.59","DOIUrl":"https://doi.org/10.1109/SKG.2010.59","url":null,"abstract":"This paper applies such data mining techniques as clustering and classifying to customer segmentation based on insurance Customer Risk Contribution matrix. A solution for segmentation management based on Clementine is put forwarded. It is brought forward that the insurance customer segmentation method, which can provide decision bases for insurance companies’ making premium rate and controlling claim risk. At the same time, it makes segmentation management more scientific and lifts the capability of insurance market competition.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"281 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133734800","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}
As an important part of multimedia retrieval, researches on 3D model retrieval concentrate on the shape-based retrieval method. It is a promising way to improve retrieval performance by adopting semantic information. At present, semantics of an object is usually represented by several keywords. However, acquiring each 3D model's semantics is very difficult and expensive. To solve the problem, the paper proposes to describe a 3D model's semantics based on its relationship with the semantics of the others, and states an automatic semantic annotation based on noisy user feedbacks. The paper first analyzes the semantic relationship reflected by user feedbacks. Then, the semantic relationship is treated as one 3D model's semantic property and is adopted in clustering to detect semantic groups that is named as semantic community. Thirdly, based on the semantic community, the semantics for models is automatically and efficiently annotated based on semantic keywords of a few 3D models. Finally, a retrieval mechanism with long-term semantic learning ability is proposed. The experiments performed on Princeton Shape Benchmark show that the proposed method achieves good performance not only in semantic clustering and annotation but also in semantic retrieval.
{"title":"Researches on Semantic Annotation and Retrieval of 3D Models Based on User Feedback","authors":"Tianyang Lu, Shaobin Huang, Peng Wu, Yeran Jia","doi":"10.1109/SKG.2010.32","DOIUrl":"https://doi.org/10.1109/SKG.2010.32","url":null,"abstract":"As an important part of multimedia retrieval, researches on 3D model retrieval concentrate on the shape-based retrieval method. It is a promising way to improve retrieval performance by adopting semantic information. At present, semantics of an object is usually represented by several keywords. However, acquiring each 3D model's semantics is very difficult and expensive. To solve the problem, the paper proposes to describe a 3D model's semantics based on its relationship with the semantics of the others, and states an automatic semantic annotation based on noisy user feedbacks. The paper first analyzes the semantic relationship reflected by user feedbacks. Then, the semantic relationship is treated as one 3D model's semantic property and is adopted in clustering to detect semantic groups that is named as semantic community. Thirdly, based on the semantic community, the semantics for models is automatically and efficiently annotated based on semantic keywords of a few 3D models. Finally, a retrieval mechanism with long-term semantic learning ability is proposed. The experiments performed on Princeton Shape Benchmark show that the proposed method achieves good performance not only in semantic clustering and annotation but also in semantic retrieval.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114443219","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}
Some problematic cases, such as collective defeat and odd-length defeat cycles, which tend to be handled incorrectly by all of the current theories of no monotonic reasoning, including default logic and circumscription, have been well recognized in the literature. Although a powerful argument-based approach in the automated defeasible reasoner OSCAR has been proposed and they claim that this theory is able to reason correctly for the problems above all, but we don't consider it to be true completely through careful investigation. It seems to be the consequences of disconnection between epistemic reasoning and practical reasoning and not considering the possible consequences of the decision and individual preferences sufficiently. Following these observations, we propose a scalable probabilistic approach based on Bayesian decision theory that can solve all of the above paradoxes properly and has successfully been used in web of trust and knowledge integration for semantic Grid.
{"title":"Decision Under Insufficient Evidence: A Scalable Probabilistic Way","authors":"Xiaoqing Zheng, Hongjun Zhang, Feng Zhou","doi":"10.1109/SKG.2010.71","DOIUrl":"https://doi.org/10.1109/SKG.2010.71","url":null,"abstract":"Some problematic cases, such as collective defeat and odd-length defeat cycles, which tend to be handled incorrectly by all of the current theories of no monotonic reasoning, including default logic and circumscription, have been well recognized in the literature. Although a powerful argument-based approach in the automated defeasible reasoner OSCAR has been proposed and they claim that this theory is able to reason correctly for the problems above all, but we don't consider it to be true completely through careful investigation. It seems to be the consequences of disconnection between epistemic reasoning and practical reasoning and not considering the possible consequences of the decision and individual preferences sufficiently. Following these observations, we propose a scalable probabilistic approach based on Bayesian decision theory that can solve all of the above paradoxes properly and has successfully been used in web of trust and knowledge integration for semantic Grid.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114857810","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}
The health service ecosystem is a sub domain of the service ecosystem, which is an ecological view of the health service domain. Due to the importance and the speciality of health services, service consumers have rigorous requirements regarding the efficiency of health service search engines. However, as most health service consumers do not have enough domain knowledge, their service queries are sometimes not able to denote their actual service requests. Moreover, we find that the existing health service search engines lack the ability to help the consumers to disambiguate their service queries, which may impede the efficiency of the search engines. In this paper, by means of semantic search technologies, we design a framework enabling user query disambiguation in the health service ecosystem. The framework embodies a health service ontology for domain knowledge-based user query disambiguation and an ECBR algorithm for accurate service retrieval. In order to evaluate the framework, we build a system prototype and perform a series of experiments on it. Conclusions from the evaluation are drawn in the paper.
{"title":"A Framework Enabling Semantic Search in Health Service Ecosystems","authors":"Hai Dong, F. Hussain, E. Chang","doi":"10.1109/SKG.2010.34","DOIUrl":"https://doi.org/10.1109/SKG.2010.34","url":null,"abstract":"The health service ecosystem is a sub domain of the service ecosystem, which is an ecological view of the health service domain. Due to the importance and the speciality of health services, service consumers have rigorous requirements regarding the efficiency of health service search engines. However, as most health service consumers do not have enough domain knowledge, their service queries are sometimes not able to denote their actual service requests. Moreover, we find that the existing health service search engines lack the ability to help the consumers to disambiguate their service queries, which may impede the efficiency of the search engines. In this paper, by means of semantic search technologies, we design a framework enabling user query disambiguation in the health service ecosystem. The framework embodies a health service ontology for domain knowledge-based user query disambiguation and an ECBR algorithm for accurate service retrieval. In order to evaluate the framework, we build a system prototype and perform a series of experiments on it. Conclusions from the evaluation are drawn in the paper.","PeriodicalId":105513,"journal":{"name":"2010 Sixth International Conference on Semantics, Knowledge and Grids","volume":"21 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120851537","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：