{"title":"Fast face recognition on GPU","authors":"Zhiquan Guo, Jungang Han, Junyan Chen","doi":"10.1109/ICSESS.2015.7339173","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339173","url":null,"abstract":"In this paper, we propose a fast parallelized implementation of face recognition based on local binary pattern (LBP) using Open computing Language (OpenCL), which is a novel open standard for heterogeneous computing. The LBP as well as its modifications CLBP (Circle Local Binary Patterns) and ULB (Uniform Local Binary Patterns) have been developed on a CPU and GPU using OpenCL. This paper also addresses several optimizations and parallelization problems related to the algorithms, such as LBP features extraction and Chi-dist computing to maximize the resource exploitation available on GPU. The optimizations are realized based on OpenCL memory and execution model. The experimental results based on the implementation on AMD GPU processor show that the GPU parallel implementation is about 50 times faster than the counterpart on CPU.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"95 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121925225","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":"Robust image denoising with an improved wavelet threshold method","authors":"Hong Zhang, Hui Liu, Zhenhong Shang, Ruixin Li","doi":"10.1109/ICSESS.2015.7339060","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339060","url":null,"abstract":"This paper proposed an improved threshold function and threshold estimation method for analyzing the characteristics of the wavelet threshold denoising. Because hard threshold denoising makes boundaries fuzzy and soft threshold denoising has Gibbs phenomenon, the new threshold function and estimation method have better adaptive. Results show that the improved method can effectively remove the white noise, the improved method is better than the soft, hard threshold denoising.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115118953","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":"Data warehousing of vehicle trajectory","authors":"Baicheng Tang, Guicheng Shen, Cailin Zhang","doi":"10.1109/ICSESS.2015.7339208","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339208","url":null,"abstract":"With the rising number of vehicles equipped with GPS system, a lot of vehicle trajectories are produced every day. At present researchers begin to study the vehicles' trajectory data. But the current trajectory compression technology cannot be very simple and will lose much information. Therefore, this paper puts forward a data warehousing design of vehicle trajectory. It can store compressed vehicle trajectory, simplify the data volume, and save the feature points. Thus, it provides a sound base for finding useful information from vehicle trajectory.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115386209","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 selection and evaluation on data mining algorithms","authors":"Ye Yuan, Ping Sun, Hongfei Fan","doi":"10.1109/ICSESS.2015.7339000","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339000","url":null,"abstract":"For traditional data mining tasks, algorithms are commonly selected by manual effort. However, it is a challenge for any practitioner to select the most appropriate algorithm from hundreds of candidates. To address this issue, we have proposed a novel model for supporting automatic selection on data mining algorithms. The model incorporates the extracted characteristics of data sets and the dynamically established rule sets into the procedures of automatic algorithm selection, which significantly accelerates the progress of algorithm se lection for a variety of data mining tasks. In addition, we have investigated a set of quantized and subdivided evaluation criteria for supporting high quality algorithm selection. Experimental work has been conducted to ve rify the feasibility and effectiveness of the proposed model.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115677417","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":"An effective test case prioritization method based on fault severity","authors":"Yiting Wang, Xiaomin Zhao, Xiaoming Ding","doi":"10.1109/ICSESS.2015.7339162","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339162","url":null,"abstract":"In regression testing area, test case prioritization is one of the main techniques to improve the test validity and test effectiveness. However, when the test cases have the same maximum coverage rate, the random selection of the additional statement will influence the effect of sorting. For dealing with this problem, a new method is proposed to optimize test case prioritization based on fault severity, referred to as additional-statement-on-fault-severity. Facing those same maximum coverage rate, the new technique main consider a factor, fault severity, to sort test cases, it figures out the value of test case based on the algorithm of the new technique and order the sequence from high to low. Experiment results show that the improved technique of test case prioritizaftion can improve the efficiency of regression testing.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"222 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122404774","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":"Image denoising based on wavelet transform","authors":"Binyi Zou, Hui Liu, Zhenhong Shang, Ruixin Li","doi":"10.1109/ICSESS.2015.7339070","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339070","url":null,"abstract":"Image processing denoising is a very important step, the hot issue is also the current research. Wavelet transform multi-resolution is frequency analysis features, in order to further improve the image denoising quality, improve visual effect, the paper image denoising methods based on wavelet transform, and which points out the further researching directions.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125013390","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":"Extension of model for research and design of complex cyber physical system","authors":"Gangqiang Liang, Lichen Zhang","doi":"10.1109/ICSESS.2015.7339101","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339101","url":null,"abstract":"Cyper Physical System(CPS) is a complex embedded system of a physical system, cyper system and the control logic depth fusion, because of the complexity and heterogeneity of the CPS part and interactive interface, there is no a unified framework for the CPS system modeling, analysis and design. Design the CPS system increasingly need using a variety of modeling forms in the whole development process. In this paper, we present a extension of existing modeling tools to model the CPS system. We present a mapping rules between AADL and multi-domin modeling language Modelica that transform Modelica model into AADL model. For system space behavior modeling, we present using Timed Automata to extend the behavior model of AADL, make extended behavior model can describe the spatial behavior of the system, at the same time, we present a mapping rules between AADL behavior model and Timed Automata model under the UPPAAL. The use of the expansion of the proposed modeling method is illustrated in the context of a uav CPS system.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127594159","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}
Haifeng Chen, Liang Xiao, Zhenzhen Yan, Yiming Yang
{"title":"Research of multi-agent system based on CDA message structure in clinical decision support","authors":"Haifeng Chen, Liang Xiao, Zhenzhen Yan, Yiming Yang","doi":"10.1109/ICSESS.2015.7339226","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339226","url":null,"abstract":"Multi-Agent system is designed for distributed environment, and has been proved efficient in the making of clinical decision support. Usually, agents communicate with each other by using messages in a distributed system, hence a well formed and organized message structure might be the key point to get high quality of message transport between different agents. Clinical Document Architecture(CDA), which is a standard for clinical document information exchange, could convey more standardized clinical information to help physicians make much more accurate clinical decisions. In this paper, a document structure based on CDA is proposed as a message strcture for information exchange between different agents and it is proved flexible and efficient in the clinical information transportation and exchange. Through using the proposed message strcture, agents cooperate with each other much more efficiently, which could help doctors make much more scientific clinical decisions, reduce medical errors and then provide higer quality of heathcare.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127853283","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":"Research on model and construction of CSLN","authors":"Weiling Chen, G. Wang, Wei Lan","doi":"10.1109/ICSESS.2015.7339239","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339239","url":null,"abstract":"CSLN is the citation semantic link network that combines the citation network and the semantic network. This paper firstly gives the model of CSLN. CSLN model not only makes the citation network to have semantics, but also make the citation network to have reasoning ability. Then the paper gives the method of constructing the citation semantic link network. Finally, the experiment verifies the effectiveness and feasibility of the construction method of the CSLN. The model of CSLN and the construction of CSLN not only are basis of the citation semantic similarity calculation of CSLN and the community discovery of CSLN, but also are the key of the community discovery of CSLN.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124579432","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":"Predicting the quality of web services based on two layer model","authors":"Le Van Thinh","doi":"10.1109/ICSESS.2015.7339002","DOIUrl":"https://doi.org/10.1109/ICSESS.2015.7339002","url":null,"abstract":"Recently, Web service has become an important issue in the research community. Especially, predicting the Quality of Service (QoS) for users has been a hot topic which needs researching and applicating. In the other hand, with the rapid growth of the number of service providers and users, it results a large number of datasets. It significantly effects on the QoS as management and supervision to describe the functional and non-functional characteristics of Web service. In this context, predicting QoS on big data dataset is an urgent issue that needs to be solved. In this paper, we present a new model to handle this issue based on a Restricted Boltzmann Machines (RBM), it is called Two Layer Model (TLM). We have used this model to deal with the big data datasets and the model used in efficient learning and inference procedures to predict the missing QoS value of web service. Our experiments have been performed based on two data sets in the WS-DREAM dataset and the experimental results have proved that the proposed model was effective.","PeriodicalId":335871,"journal":{"name":"2015 6th IEEE International Conference on Software Engineering and Service Science (ICSESS)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121130378","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}