2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)最新文献_第7页

Multi-modal learning for social image classification 社会图像分类的多模态学习

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603345

Chunyang Liu, Xu Zhang, Xiong Li, Rui Li, Xiaoming Zhang, Wen-Han Chao

{"title":"Multi-modal learning for social image classification","authors":"Chunyang Liu, Xu Zhang, Xiong Li, Rui Li, Xiaoming Zhang, Wen-Han Chao","doi":"10.1109/FSKD.2016.7603345","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603345","url":null,"abstract":"There is growing interest in social image classification because of its importance in web-based image application. Though there are many approaches on image classification, it is a great problem to integrate multi-modal content of social images simultaneously for social image classification, since the textual content and visual content are represented in two heterogeneous feature spaces. In this study, we proposed a multi-modal learning algorithm to fuse the multiple features through their correlation seamlessly. Specifically, we learn two linear classification modules for the two types of feature, and then they are integrated by the l2 normalization via a joint model. With the joint model, the classification based on visual feature can be reinforced by the classification based on textual feature, and vice verse. Then, the test image can be classified based on both the textual feature and visual feature by combing the results of the two classifiers. The evaluate the approach, we conduct some experiments on real-world datasets, and the result shows the superiority of our proposed algorithm against the baselines.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122188963","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}

引用次数: 3

A novel object tracking algorithm based on enhanced perception hash and online template matching 一种基于增强感知哈希和在线模板匹配的目标跟踪算法

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603223

Jin Yuan, Dong Xu, Heng-Chang Xiong, Zhiyong Li

{"title":"A novel object tracking algorithm based on enhanced perception hash and online template matching","authors":"Jin Yuan, Dong Xu, Heng-Chang Xiong, Zhiyong Li","doi":"10.1109/FSKD.2016.7603223","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603223","url":null,"abstract":"Object tracking task faces serious challenges when a desired target is in complex circumstances such as obstacle occlusion, pose variation, illumination change and motion blur. Despite lots of excellent tracking algorithms have been proposed, many issues remain to be addressed. In this paper, we propose a novel object tracking algorithm to combine both Enhanced Perception Hash and Coarse-to-fine Sliding Window search strategy. First, we calculate the feature template of target by using the perception hash approach integrating Fast Fourier Transform (FFT). We make a FFT on the target area in a frame and only retain low-frequency part to save storage. Moreover, the new template is generated by fusing the templates from the current and previous frames, thus it is robust to the severe deformation and drastic variation problem. Second, we propose a coarse-to-fine sliding window search strategy to provide potential target candidates efficiently. Based on this strategy, our tracking algorithm can implement an effective online detection for target. Extensive tests on thirteen videos are conducted and demonstrate that our approach achieves promising performance as compared to the state-of-the-art methods.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121072351","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}

引用次数: 4

Research on algorithm of attribute reduction based on concept with introducer 引入概念的属性约简算法研究

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603369

Can Wang, D. He, Lijuan Wang, H. Hou, Ruijie Liu

{"title":"Research on algorithm of attribute reduction based on concept with introducer","authors":"Can Wang, D. He, Lijuan Wang, H. Hou, Ruijie Liu","doi":"10.1109/FSKD.2016.7603369","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603369","url":null,"abstract":"As the size of data table grows, the concepts generated become larger in number. Making sure the set of extent remaining unchanged, the purpose of attribute reduction of concept lattice is to find out minimum subsets of attributes and make knowledge presented by concept lattice simpler, decision problem simplified as well. This paper introduced the definition of introducer which was minimum closure set of certain attribute; reduced attributes from the perspective of concept with introducer for the first time: if a concept with introducer with regard to certain attribute was degenerate then this attribute was core; otherwise this attribute was unnecessary or relative necessary; proved that if a concept with introducer of certain attribute was non-degenerate(degenerate), then the concepts on the path containing this attribute were non-degenerate(degenerate) simultaneously. Afterwards, this paper put forward an algorithm of attribute reduction and discussed the time complexity. Experimental results showed that algorithm proposed in this paper achieved excellent runtime.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116104720","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}

引用次数: 1

Analysis of computer event logs to assess student engagement in classroom: A case study in the United States 计算机事件日志分析评估学生课堂参与度:美国个案研究

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603448

Yamada Koji, Inoue Atsushi, Tsuruoka Shinji, Kawanaka Hiroharu, T. Haruhiko

引用次数: 1

Study on the next generation library integrated system 下一代图书馆集成系统的研究

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603363

Jianwei Li

引用次数: 0

A heterogeneous wireless network selection algorithm for smart distribution grid 智能配电网的异构无线网络选择算法

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603480

Jiangyu Yan, Xiaoyan Wang, Shuxian Li, Liangrui Tang

引用次数: 1

A theoretical line losses calculation method of distribution system based on boosting algorithm 一种基于升压算法的配电系统线损理论计算方法

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603262

Yufei Wang, Chenlong Wang, Jing Wang, Luo Zuo, Yong-Hong Shi

{"title":"A theoretical line losses calculation method of distribution system based on boosting algorithm","authors":"Yufei Wang, Chenlong Wang, Jing Wang, Luo Zuo, Yong-Hong Shi","doi":"10.1109/FSKD.2016.7603262","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603262","url":null,"abstract":"Existing intelligent theoretical line losses calculation methods that prevalent on worse line calculation error, are all based on single learning algorithm. In order to overcome this defect, a novel intelligent calculation method based on boosting algorithm is proposed. In this calculation method, the theoretical line losses calculation is abstracted into function fitting problem, in addition, the sample set - which is structured by the lines' information of known theoretical line losses - is input to many single learning algorithms of boosting algorithm for training many sub-calculation model and constituting them as a sequence, which sequence is the final theoretical line losses calculation model. In the sub-calculation model training process, this intelligent method effectively reduces the calculation error by the boosting algorithm's internal mechanism that the large calculation error lines are constantly reinforcement training. Finally the experiment shows that this intelligent calculation method based on boosting algorithm has lower calculation error than traditions.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"117 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113983356","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}

引用次数: 0

Performance optimization for CPU-GPU heterogeneous parallel system CPU-GPU异构并行系统的性能优化

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603359

Yanhua Wang, Jianzhong Qiao, Shukuan Lin, Tinglei Zhao

{"title":"Performance optimization for CPU-GPU heterogeneous parallel system","authors":"Yanhua Wang, Jianzhong Qiao, Shukuan Lin, Tinglei Zhao","doi":"10.1109/FSKD.2016.7603359","DOIUrl":"https://doi.org/10.1109/FSKD.2016.7603359","url":null,"abstract":"With GPU (Graphics Processing Unit) taking part in general-purpose computing, a heterogeneous system usually achieves higher performance and efficiency. There are many studies on how to improve the performance of a heterogeneous system, among of which are a number of researches to achieve the goal by allocating workload into processors with different strategies. In the paper, we implement a task allocation model in the principle of making execution time of the partition on CPU closer to the partition on GPU to the maximum extent. The task allocation process contains two stages. Firstly, we make use of SVM (Support Vector Machine) to classify the tasks into two sets as CPU-kind and GPU-kind in pre-treating stage. Secondly, we adjust the two task sets in the light of the characteristic and current running status of processors, then we map the two well-adjusted task sets to processors. Moreover, we evaluate the proposed model by implementing them on a real heterogeneous system and several benchmarks. Experimental results demonstrate that our model can achieve up to 23.43% of performance improvement compared to some states of the art allocation strategies averagely.","PeriodicalId":373155,"journal":{"name":"2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131543967","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}

引用次数: 2

An efficient hybrid algorithm based on harmony search and invasive weed optimization 基于和谐搜索和入侵杂草优化的高效混合算法

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603169

Aijia Ouyang, Zhiguo Yang

引用次数: 5

Improved hybrid semantic similarity algorithm for terminology application 术语应用的改进混合语义相似度算法

2016 12th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery (ICNC-FSKD) Pub Date : 2016-08-01 DOI: 10.1109/FSKD.2016.7603439

Tong Wei, Yangli Jia, Zhenling Zhang, Julien Roche, C. Roche

引用次数: 2