Pub Date : 2014-06-27DOI: 10.1109/ICSESS.2014.6933678
Wenbing Zhao, Hai Feng, Roanna Lun, D. Espy, M. A. Reinthal
In this paper, we describe the design and implementation of a Kinect-based system for rehabilitation exercises monitoring and guidance. We choose to use the Unity framework to implement our system because it enables us to use virtual reality techniques to demonstrate detailed movements to the patient, and to facilitate examination of the quality and quantity of the patient sessions by the clinician. The avatar-based rendering of motion also preserves the privacy of the patients, which is essential for healthcare systems. The key contribution of our research is a rule-based approach to realtime exercise quality assessment and feedback. We developed a set of basic rule elements that can be used to express the correctness rules for common rehabilitation exercises.
{"title":"A Kinect-based rehabilitation exercise monitoring and guidance system","authors":"Wenbing Zhao, Hai Feng, Roanna Lun, D. Espy, M. A. Reinthal","doi":"10.1109/ICSESS.2014.6933678","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933678","url":null,"abstract":"In this paper, we describe the design and implementation of a Kinect-based system for rehabilitation exercises monitoring and guidance. We choose to use the Unity framework to implement our system because it enables us to use virtual reality techniques to demonstrate detailed movements to the patient, and to facilitate examination of the quality and quantity of the patient sessions by the clinician. The avatar-based rendering of motion also preserves the privacy of the patients, which is essential for healthcare systems. The key contribution of our research is a rule-based approach to realtime exercise quality assessment and feedback. We developed a set of basic rule elements that can be used to express the correctness rules for common rehabilitation exercises.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"14 1","pages":"762-765"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82417567","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933636
Zhengjie Zhou, Huiping Jiang, Xiaoyuan Song
This paper described a research project conducted to recognize to finding the relationship between EEG signals and Human emotions. EEG signals are used to classify three kinds of emotions, positive, neuter and negative. Firstly, literature research has been performed to establish a suitable approach for emotion recognition. Secondly, we extracted features from original EEG data using 4-order wavelet and put them in SVM classifier with different kernel functions. The result shows that an SVM with linear kernel has higher average test accuracy than other kernel function.
{"title":"EEG-based emotion recognition using wavelet features","authors":"Zhengjie Zhou, Huiping Jiang, Xiaoyuan Song","doi":"10.1109/ICSESS.2014.6933636","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933636","url":null,"abstract":"This paper described a research project conducted to recognize to finding the relationship between EEG signals and Human emotions. EEG signals are used to classify three kinds of emotions, positive, neuter and negative. Firstly, literature research has been performed to establish a suitable approach for emotion recognition. Secondly, we extracted features from original EEG data using 4-order wavelet and put them in SVM classifier with different kernel functions. The result shows that an SVM with linear kernel has higher average test accuracy than other kernel function.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"56 1","pages":"585-588"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83963495","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933650
Dan Zhang, Rui Zheng, Guosheng Yang
This paper presents a 3D virtual tour schema based on image clusters. With the development of the Internet, various image-based applications have generated large amounts of image data. Vast amounts of image data can be effectively organized by clustering algorithms according to their geographic location information and content, thus forming image clusters. These data then can be reconstructed for 3D virtual tour using the state-of-the-art computer vision methods. This paper analyzes the popular photo tours application and Photosynth, and proposes an image clusters based 3D virtual tour schema on the basis of these applications. This paper also points out the room for improvement in the future, and several possible applications based on this schema are discussed finally.
{"title":"Image clusters based 3D virtual tour schema","authors":"Dan Zhang, Rui Zheng, Guosheng Yang","doi":"10.1109/ICSESS.2014.6933650","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933650","url":null,"abstract":"This paper presents a 3D virtual tour schema based on image clusters. With the development of the Internet, various image-based applications have generated large amounts of image data. Vast amounts of image data can be effectively organized by clustering algorithms according to their geographic location information and content, thus forming image clusters. These data then can be reconstructed for 3D virtual tour using the state-of-the-art computer vision methods. This paper analyzes the popular photo tours application and Photosynth, and proposes an image clusters based 3D virtual tour schema on the basis of these applications. This paper also points out the room for improvement in the future, and several possible applications based on this schema are discussed finally.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"67 1","pages":"641-644"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80267949","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933702
Fenghua Hu, Xiaogang Qiu, Lei Luo
There are many semantic inconsistencies between domain concepts, which made it difficult to model, to interoperate and also to compose models semantically in software engineering, M&S (modeling and simulation) or semantic web. Thus we described the domain concepts and concepts taxonomy by hypernetwork (concept hypergraph), whose nodes set is the concepts set and edge is consisted of the correlative properties. Firstly, we have found out that the nodes set of concept hypergraph has the feature of order. In addition, by the definition of formal context, we have proved that the concept set is a complete concept lattice. And then, the domain knowledge has been extended from both of aspects of concept's extent and intent simultaneously, while the hypernetwork system has also been expanded according to the extended concept set. Finally, to achieve the semantically consistent taxonomy of the domain concepts through the hypernetwork system's adjacency and path matrices sequentially, we illustrated the example of the semantic inconsistencies of the military domain artillery concept's taxonomy and have given the method and steps perfectly.
{"title":"The method of using hypernetworks and concept lattice to solve domain concepts' semantic inconsistencies","authors":"Fenghua Hu, Xiaogang Qiu, Lei Luo","doi":"10.1109/ICSESS.2014.6933702","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933702","url":null,"abstract":"There are many semantic inconsistencies between domain concepts, which made it difficult to model, to interoperate and also to compose models semantically in software engineering, M&S (modeling and simulation) or semantic web. Thus we described the domain concepts and concepts taxonomy by hypernetwork (concept hypergraph), whose nodes set is the concepts set and edge is consisted of the correlative properties. Firstly, we have found out that the nodes set of concept hypergraph has the feature of order. In addition, by the definition of formal context, we have proved that the concept set is a complete concept lattice. And then, the domain knowledge has been extended from both of aspects of concept's extent and intent simultaneously, while the hypernetwork system has also been expanded according to the extended concept set. Finally, to achieve the semantically consistent taxonomy of the domain concepts through the hypernetwork system's adjacency and path matrices sequentially, we illustrated the example of the semantic inconsistencies of the military domain artillery concept's taxonomy and have given the method and steps perfectly.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"94 1","pages":"863-867"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80703623","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933569
Fei Wang, Yi Yang, Xianchao Lv, Jiao Xu, Lian Li
In this paper, we propose a multi-stage feature selection algorithm, which focuses on the reduction of redundant features and the improvement of classification performance using feature ranking (FR), correlation analysis (CA) and chaotic binary particle swarm optimization (CBPSO). In the first stage, with the purpose of selecting the most effective features for classification, FR is introduced to select the top-ranked features according to the classification accuracies. In the second stage, CA is used to measure the correlation among the selected top-ranked features for reducing redundant features. In the third stage, in order to further eliminate redundant features and improve the classification performances, CBPSO is adopted to search the optimal feature subset. Ultimately, feature selection can be completed by using only some top-ranked features with less redundancy for classification. Support vector machine (SVM) with n-fold cross-validation is adopted to assess the classification performances on six datasets in the experiments. Experimental results show that the proposed algorithm can achieve better performance in terms of classification accuracy and the number of features than benchmark algorithms.
{"title":"Feature selection using feature ranking, correlation analysis and chaotic binary particle swarm optimization","authors":"Fei Wang, Yi Yang, Xianchao Lv, Jiao Xu, Lian Li","doi":"10.1109/ICSESS.2014.6933569","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933569","url":null,"abstract":"In this paper, we propose a multi-stage feature selection algorithm, which focuses on the reduction of redundant features and the improvement of classification performance using feature ranking (FR), correlation analysis (CA) and chaotic binary particle swarm optimization (CBPSO). In the first stage, with the purpose of selecting the most effective features for classification, FR is introduced to select the top-ranked features according to the classification accuracies. In the second stage, CA is used to measure the correlation among the selected top-ranked features for reducing redundant features. In the third stage, in order to further eliminate redundant features and improve the classification performances, CBPSO is adopted to search the optimal feature subset. Ultimately, feature selection can be completed by using only some top-ranked features with less redundancy for classification. Support vector machine (SVM) with n-fold cross-validation is adopted to assess the classification performances on six datasets in the experiments. Experimental results show that the proposed algorithm can achieve better performance in terms of classification accuracy and the number of features than benchmark algorithms.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"50 1","pages":"305-309"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80743497","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933559
R. Qiu, K. Wang, Shan Li, Jin Dong, Ming Xie
Energy overconsumption and greenhouse gas emission have been contributing to air pollutions and the global warming for years. The unceasingly increasing number of fossil fuels based vehicles around the world is considered as one of main factors making to the situation worse year by year. Electric vehicles (EV) are promoted as a viable and promising alternative transportation means for customers. However, there is an array of issues hindering EVs from the fast adoption in the global auto market. As these issues bear different priorities that surely vary with marketplaces, it becomes essential for EV makers and governments to capture and understand the dynamics of EV consumers in real time. This paper explores how the emerging big data technologies can be applied to facilitate the process of deciphering the acceptance and behavior of EV customers from marketplace to marketplace. A data-collecting web system is discussed. IBM BigInsights platform technologies, including Hadoop, Streams, SPSS modeler and text analytics, are utilized for looking into the insights of collected data. Examples are provided to show the promising future of big data technologies in the field of customer analytics in today's globalized economy.
{"title":"Big data technologies in support of real time capturing and understanding of electric vehicle customers dynamics","authors":"R. Qiu, K. Wang, Shan Li, Jin Dong, Ming Xie","doi":"10.1109/ICSESS.2014.6933559","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933559","url":null,"abstract":"Energy overconsumption and greenhouse gas emission have been contributing to air pollutions and the global warming for years. The unceasingly increasing number of fossil fuels based vehicles around the world is considered as one of main factors making to the situation worse year by year. Electric vehicles (EV) are promoted as a viable and promising alternative transportation means for customers. However, there is an array of issues hindering EVs from the fast adoption in the global auto market. As these issues bear different priorities that surely vary with marketplaces, it becomes essential for EV makers and governments to capture and understand the dynamics of EV consumers in real time. This paper explores how the emerging big data technologies can be applied to facilitate the process of deciphering the acceptance and behavior of EV customers from marketplace to marketplace. A data-collecting web system is discussed. IBM BigInsights platform technologies, including Hadoop, Streams, SPSS modeler and text analytics, are utilized for looking into the insights of collected data. Examples are provided to show the promising future of big data technologies in the field of customer analytics in today's globalized economy.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"36 1","pages":"263-267"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83122552","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933525
T. Zang, Yuan Yang, Zhengyou He, Q. Qian
To better identify harmonic pollution source, a software for harmonic analysis and harmonic source location is introduced in this paper. Firstly, the function framework of the software is established and the technical route of the software is designed. Besides, harmonic analysis is conducted by interpolation FFT algorithm with Hamming windowing. Location of harmonic source is determined by sparse reconstruction algorithm in allusion to undetermined harmonic measurement equation set. Furthermore, to ensure the observability of power network, the configuration algorithm of harmonic measurement nodes is given. The software has a good practicability, strong data processing ability, easy system maintenance, good application extension function and promotional value.
{"title":"A novel software for harmonic analysis and harmonic source location","authors":"T. Zang, Yuan Yang, Zhengyou He, Q. Qian","doi":"10.1109/ICSESS.2014.6933525","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933525","url":null,"abstract":"To better identify harmonic pollution source, a software for harmonic analysis and harmonic source location is introduced in this paper. Firstly, the function framework of the software is established and the technical route of the software is designed. Besides, harmonic analysis is conducted by interpolation FFT algorithm with Hamming windowing. Location of harmonic source is determined by sparse reconstruction algorithm in allusion to undetermined harmonic measurement equation set. Furthermore, to ensure the observability of power network, the configuration algorithm of harmonic measurement nodes is given. The software has a good practicability, strong data processing ability, easy system maintenance, good application extension function and promotional value.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"33 1","pages":"116-119"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77781220","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933565
Yang Liu
Stochastic model checking is using the verification method of model checking to quantitative verification system model with stochastic behaviours. In recent years, stochastic model checking make a great advancement. In this paper, the high level system model PPN is extended with label, and is used to as the formal model for system with stochastic behaviours; PCTL* is selected to as the property specification, which is strictly more expressive than PCTL and LTL with probability bounds. Then the PCTL* stochastic model checking algorithm for LPPN (label-extended probabilistic Petri net) is presented, and it is implemented in the visual tool which can model, simulation and stochastic model checking of LPPN. In the last, an illustrative example is used to demonstrate the feasibility of the algorithm and the tool.
{"title":"PCTL∗ stochastic model checking label-extended probabilistic Petri net system model","authors":"Yang Liu","doi":"10.1109/ICSESS.2014.6933565","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933565","url":null,"abstract":"Stochastic model checking is using the verification method of model checking to quantitative verification system model with stochastic behaviours. In recent years, stochastic model checking make a great advancement. In this paper, the high level system model PPN is extended with label, and is used to as the formal model for system with stochastic behaviours; PCTL* is selected to as the property specification, which is strictly more expressive than PCTL and LTL with probability bounds. Then the PCTL* stochastic model checking algorithm for LPPN (label-extended probabilistic Petri net) is presented, and it is implemented in the visual tool which can model, simulation and stochastic model checking of LPPN. In the last, an illustrative example is used to demonstrate the feasibility of the algorithm and the tool.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"24 1","pages":"287-290"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82231311","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933596
Li He
Improving the utilization of resources and service qualities, and reducing the system energy consumption are two important goals of dynamic virtual machine management in cloud computing. Nevertheless, the reduction of energy consumption is inconsistent with the improvement of resource utilization. In order to get the balance, a new multi-objective decision-making method of virtual machine placement based on gray correlation degree is proposed, three factors like the energy consumption, Service Level Agreement (SLA) violation and server load are used as the evaluation indexes, and corresponding evaluation functions are biut for them, finally the multi-objective decision-making model of the virtual machine placement based on gray correlation degree is established. Evaluations via experiments show that the proposed method of virtual machine placement can achieve good results under most virtual machine selection policies.
{"title":"A method of virtual machine placement based on gray correlation degree","authors":"Li He","doi":"10.1109/ICSESS.2014.6933596","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933596","url":null,"abstract":"Improving the utilization of resources and service qualities, and reducing the system energy consumption are two important goals of dynamic virtual machine management in cloud computing. Nevertheless, the reduction of energy consumption is inconsistent with the improvement of resource utilization. In order to get the balance, a new multi-objective decision-making method of virtual machine placement based on gray correlation degree is proposed, three factors like the energy consumption, Service Level Agreement (SLA) violation and server load are used as the evaluation indexes, and corresponding evaluation functions are biut for them, finally the multi-objective decision-making model of the virtual machine placement based on gray correlation degree is established. Evaluations via experiments show that the proposed method of virtual machine placement can achieve good results under most virtual machine selection policies.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"43 1","pages":"419-424"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81558318","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 : 2014-06-27DOI: 10.1109/ICSESS.2014.6933555
Lin Zhao, Weifeng Shi
Storm is a distributed realtime computing framework of open source by Twitter, it is becoming a leader since of many advantages in realtime computing. This paper presents optimization program for the storm taking up too much resource in the practical application environment, by using of Cgroups mechanism to limit CPU, memory, IO and other resources of worker process, the new mechanism can balance storm's resources usage and stable of system program well.
{"title":"Research on optimization of application model based on storm","authors":"Lin Zhao, Weifeng Shi","doi":"10.1109/ICSESS.2014.6933555","DOIUrl":"https://doi.org/10.1109/ICSESS.2014.6933555","url":null,"abstract":"Storm is a distributed realtime computing framework of open source by Twitter, it is becoming a leader since of many advantages in realtime computing. This paper presents optimization program for the storm taking up too much resource in the practical application environment, by using of Cgroups mechanism to limit CPU, memory, IO and other resources of worker process, the new mechanism can balance storm's resources usage and stable of system program well.","PeriodicalId":6473,"journal":{"name":"2014 IEEE 5th International Conference on Software Engineering and Service Science","volume":"88 1","pages":"248-250"},"PeriodicalIF":0.0,"publicationDate":"2014-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81133217","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：