Traditional k-nearest neighborhood (KNN) model is being widely used in the recommender systems. However, it behaves badly without enough history records for new users, called the cold starting problem. Both time and space complexity are huge for computing all pair wise similarities among items or users. A mixed neighborhood algorithm is proposed for treating new users and old users separately. For new users, this paper takes into account users' characteristics. For old users, combined with Singular Value Decomposition (SVD), we reduce the time and space complexity efficiently. Experiment on Movie Lens dataset shows that the proposed model can solve the cold starting problem in effect and remarkably improve the accuracy of traditional model and lower time consuming level.
{"title":"A Novel Nearest Neighborhood Algorithm for Recommender Systems","authors":"Lei Xiong, Yang-Li Xiang, Qi Zhang, Lili Lin","doi":"10.1109/GCIS.2012.58","DOIUrl":"https://doi.org/10.1109/GCIS.2012.58","url":null,"abstract":"Traditional k-nearest neighborhood (KNN) model is being widely used in the recommender systems. However, it behaves badly without enough history records for new users, called the cold starting problem. Both time and space complexity are huge for computing all pair wise similarities among items or users. A mixed neighborhood algorithm is proposed for treating new users and old users separately. For new users, this paper takes into account users' characteristics. For old users, combined with Singular Value Decomposition (SVD), we reduce the time and space complexity efficiently. Experiment on Movie Lens dataset shows that the proposed model can solve the cold starting problem in effect and remarkably improve the accuracy of traditional model and lower time consuming level.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122929465","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}
A new heuristic algorithm based on simple blocks is proposed in this paper to pack to solve three-dimensional packing problems(3DPP), and a self-adaptive genetic algorithm is used to optimize the packing sequence and direction of the constraint sequence in order to find an approximate optimal solution of the problem. In the heuristic algorithm, the simple block selected each time must not only to be packed into the current residual space, but also to be the most appropriate one, the packing sequence is a permutation of the types of boxes. An experimental study over the LN computational example shows that the algorithm is an effective method to solve the packing problems.
{"title":"A Self-Adaptive Hybrid Genetic Algorithm for 3D Packing Problem","authors":"Jinshan Jiang, Shi Yin","doi":"10.1109/GCIS.2012.34","DOIUrl":"https://doi.org/10.1109/GCIS.2012.34","url":null,"abstract":"A new heuristic algorithm based on simple blocks is proposed in this paper to pack to solve three-dimensional packing problems(3DPP), and a self-adaptive genetic algorithm is used to optimize the packing sequence and direction of the constraint sequence in order to find an approximate optimal solution of the problem. In the heuristic algorithm, the simple block selected each time must not only to be packed into the current residual space, but also to be the most appropriate one, the packing sequence is a permutation of the types of boxes. An experimental study over the LN computational example shows that the algorithm is an effective method to solve the packing problems.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125902932","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}
Based on the thought of “to be expert in one aspect and good at many”, a new training method of modular neural network (MNN) is presented. The key point of this method is a subnet learns the neighbor data sets while fulfiling its main task : learning the objective data set. Both methodology and empirical study of this new method are presented. Two examples (static approximation and nonlinear dynamic system prediction) are tested to show the new method's effectiveness: average testing error is dramatically decreased compared to original algorithm..
{"title":"A New MNN's Training Method with Empirical Study","authors":"Jiasen Wang, Pan Wang","doi":"10.1109/GCIS.2012.35","DOIUrl":"https://doi.org/10.1109/GCIS.2012.35","url":null,"abstract":"Based on the thought of “to be expert in one aspect and good at many”, a new training method of modular neural network (MNN) is presented. The key point of this method is a subnet learns the neighbor data sets while fulfiling its main task : learning the objective data set. Both methodology and empirical study of this new method are presented. Two examples (static approximation and nonlinear dynamic system prediction) are tested to show the new method's effectiveness: average testing error is dramatically decreased compared to original algorithm..","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133173121","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 ability of energy harvesting has enhanced sustainability of mobile networks. However, the energy harvesting capability and possibility of nodes are quite different. Namely, energy consumption and harvesting is still not balanced. In this paper, we follow the concept of energy sharing, and bring forward three necessary protocols. Distinguished from other works, we propose two kinds of power cord connection structures. We consider the leakage nature of ultra-capacitors and propose sender initialized method. We also describe energy routing protocol under the condition of NON DC/DC module. We evaluate our methods using a test platform.
{"title":"Design and Implementation of Energy Sharing System for MANETs","authors":"Xiuzhi Zhao","doi":"10.1109/GCIS.2012.101","DOIUrl":"https://doi.org/10.1109/GCIS.2012.101","url":null,"abstract":"The ability of energy harvesting has enhanced sustainability of mobile networks. However, the energy harvesting capability and possibility of nodes are quite different. Namely, energy consumption and harvesting is still not balanced. In this paper, we follow the concept of energy sharing, and bring forward three necessary protocols. Distinguished from other works, we propose two kinds of power cord connection structures. We consider the leakage nature of ultra-capacitors and propose sender initialized method. We also describe energy routing protocol under the condition of NON DC/DC module. We evaluate our methods using a test platform.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130518353","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}
Multivariate time series (MTS) are used in very broad areas such as finance, medicine, multimedia and speech recognition. Most of existing approaches for MTS classification are not designed for preserving the within-class local structure of the MTS dataset. The within-class local structure is important when a classifier is used for classification. In this paper, a new feature extraction method for MTS classification based on supervised Isomap and generalized regression network is proposed. MTS samples in training dataset are projected into a low dimensional space by using the supervised Isomap, its mapping function can be learned by generalized regression network. Experimental results performed on six real-world datasets demonstrate the effectiveness of our proposed approach for MTS classification.
{"title":"Classification of Multivariate Time Series Using Supervised Isomap","authors":"Xiaoqing Weng, Shimin Qin","doi":"10.1109/GCIS.2012.31","DOIUrl":"https://doi.org/10.1109/GCIS.2012.31","url":null,"abstract":"Multivariate time series (MTS) are used in very broad areas such as finance, medicine, multimedia and speech recognition. Most of existing approaches for MTS classification are not designed for preserving the within-class local structure of the MTS dataset. The within-class local structure is important when a classifier is used for classification. In this paper, a new feature extraction method for MTS classification based on supervised Isomap and generalized regression network is proposed. MTS samples in training dataset are projected into a low dimensional space by using the supervised Isomap, its mapping function can be learned by generalized regression network. Experimental results performed on six real-world datasets demonstrate the effectiveness of our proposed approach for MTS classification.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130061895","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}
Kernels in a SVM-based text-independent speaker verification system determine the performance. One of the main difficulties in designing a kernel arises from the unequal length of cepstral vector sequences. To simplify the above problem, time information is discarded and each speaker is presumed to have a unique probability density distribution. Gaussian mixture models (GMMs) are often used to estimate the probability density distribution from the train cepstral vector sequence. The methods of constructing SVM kernels by adapted GMMs become an open and key question in a GMM-SVM system. In this paper, we introduce a novel way of measuring the similarity between adapted GMMs and propose a log-likelihood kernel. We demonstrate that the presented kernel has an excellent performance on the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) 2008 tel-tel English corpus.
{"title":"Log-Likelihood Kernels Based on Adapted GMMs for Speaker Verification","authors":"Liang He, Yi Yang, Jia Liu","doi":"10.1109/GCIS.2012.100","DOIUrl":"https://doi.org/10.1109/GCIS.2012.100","url":null,"abstract":"Kernels in a SVM-based text-independent speaker verification system determine the performance. One of the main difficulties in designing a kernel arises from the unequal length of cepstral vector sequences. To simplify the above problem, time information is discarded and each speaker is presumed to have a unique probability density distribution. Gaussian mixture models (GMMs) are often used to estimate the probability density distribution from the train cepstral vector sequence. The methods of constructing SVM kernels by adapted GMMs become an open and key question in a GMM-SVM system. In this paper, we introduce a novel way of measuring the similarity between adapted GMMs and propose a log-likelihood kernel. We demonstrate that the presented kernel has an excellent performance on the National Institute of Standards and Technology (NIST) speaker recognition evaluation (SRE) 2008 tel-tel English corpus.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"639 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133501233","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}
Shaohua Liu, Changqing Du, Yan Fuwu, Wang Jun, Li Zheng, Luo Yuan
This paper focuses on the analysis of energy management for hybrid electric vehicle of BSG type. A well designed control strategy is a significant factor for obtaining lower fuel consumption, less emission as well as satisfying drivability. To ensure engine operating in the optimal fuel consumption region and coordinate the power split between electrical and mechanical energy sources, an adaptive power splitting algorithm is presented and discussed here on the basis of a new BSG hybrid electric vehicle equipped with both a battery of higher capacity and a motor of higher peak power. Also a smart regenerative braking method is proposed to realize the maximum energy saving purpose. The proposed hybrid electric vehicle (HEV) algorithm simulation results are compared with those of a conventional vehicle with similar configuration as HEV. And the simulation results show that the overall dynamic performance, fuel consumption and emission are all greatly improved.
{"title":"A Rule-Based Energy Management Strategy for a New BSG Hybrid Electric Vehicle","authors":"Shaohua Liu, Changqing Du, Yan Fuwu, Wang Jun, Li Zheng, Luo Yuan","doi":"10.1109/GCIS.2012.63","DOIUrl":"https://doi.org/10.1109/GCIS.2012.63","url":null,"abstract":"This paper focuses on the analysis of energy management for hybrid electric vehicle of BSG type. A well designed control strategy is a significant factor for obtaining lower fuel consumption, less emission as well as satisfying drivability. To ensure engine operating in the optimal fuel consumption region and coordinate the power split between electrical and mechanical energy sources, an adaptive power splitting algorithm is presented and discussed here on the basis of a new BSG hybrid electric vehicle equipped with both a battery of higher capacity and a motor of higher peak power. Also a smart regenerative braking method is proposed to realize the maximum energy saving purpose. The proposed hybrid electric vehicle (HEV) algorithm simulation results are compared with those of a conventional vehicle with similar configuration as HEV. And the simulation results show that the overall dynamic performance, fuel consumption and emission are all greatly improved.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"10 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114518168","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 an effective particle swarm optimization algorithm with social weight (ESWPSO) to solve economic dispatch problem in power system. Many nonlinear characteristics of cost function and operational constraints are all considered for practical operation. The extremum disturbance operator in ESWPSO effectively contributes to finding better solutions by generating random points in promising area. The penalty strategy is adopted to help particles satisfy the dynamic power balance constraints. The effectiveness and feasibility of ESWPSO are demonstrated by two power system cases. Compared with previous literature, the experiment results show ESWPSO can fast find higher quality solutions.
{"title":"An Effective Particle Swarm Optimization Algorithm with Social Weight in Solving Economic Dispatch Problem Considering Network Losses","authors":"Jinglei Guo, C. Jin, Wei Liu, W. Zhou","doi":"10.1109/GCIS.2012.83","DOIUrl":"https://doi.org/10.1109/GCIS.2012.83","url":null,"abstract":"This paper proposes an effective particle swarm optimization algorithm with social weight (ESWPSO) to solve economic dispatch problem in power system. Many nonlinear characteristics of cost function and operational constraints are all considered for practical operation. The extremum disturbance operator in ESWPSO effectively contributes to finding better solutions by generating random points in promising area. The penalty strategy is adopted to help particles satisfy the dynamic power balance constraints. The effectiveness and feasibility of ESWPSO are demonstrated by two power system cases. Compared with previous literature, the experiment results show ESWPSO can fast find higher quality solutions.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131526530","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}
Jaweria Manzoor, Saara Asif, Maryum Masud, Malik Jahan Khan
Case-Based Reasoning (CBR) has been employed as a problem-solving technique to solve numerous real-world applications. At the core of a successful CBR system is a high-quality case-base. Generating a quality case-base with minimal human intervention is a significant challenge which has not been given considerable attention in the past. In this paper, we propose a methodology for automatic generation of a quality case-base using genetic algorithm (GA). GA has been effectively used to evaluate quality of cases using predefined criteria as part of the fitness function. The performance and efficiency of the proposed approach has been evaluated and presented on the examination scheduling problem.
{"title":"Automatic Case Generation for Case-Based Reasoning Systems Using Genetic Algorithms","authors":"Jaweria Manzoor, Saara Asif, Maryum Masud, Malik Jahan Khan","doi":"10.1109/GCIS.2012.89","DOIUrl":"https://doi.org/10.1109/GCIS.2012.89","url":null,"abstract":"Case-Based Reasoning (CBR) has been employed as a problem-solving technique to solve numerous real-world applications. At the core of a successful CBR system is a high-quality case-base. Generating a quality case-base with minimal human intervention is a significant challenge which has not been given considerable attention in the past. In this paper, we propose a methodology for automatic generation of a quality case-base using genetic algorithm (GA). GA has been effectively used to evaluate quality of cases using predefined criteria as part of the fitness function. The performance and efficiency of the proposed approach has been evaluated and presented on the examination scheduling problem.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"120 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128486692","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}
Jinyong Wu, Yong Zhao, Yule Yuan, Xing Zhang, Yike Wang
Since that the surveillance video is an unstructured media, it is not beneficial for the video intelligent retrieval and mining. An approach that is based on Gaussian mixture model and support vector machine has been put forward in this paper, which can make the video of surveillance scene structured. First, it constructs Gaussian background modeling to video scene, and isolates the motion object layer. Second, the visual perceptive information from moving object can be extracted by the angular point detecting method. Third, the multi-granularity perceptive feature of the object can be extracted by the object centroid-centred. Last, a 2-level SVM classifier should be build. By this classifier the semantics can be labeled to the moving objects, and then the structured description of the scenes can be obtained. The experimental results show that the presented method can avoid the interference caused by luminance changes and the motion of the leaves effectively. It is suitable for the video of surveillance scene in structured analysis application and can be a technical support for the intelligent retrieval and mining of video contents.
{"title":"A Method of Surveillance Video Structured Based on Gaussian Mixture Model and Support Vector Machine","authors":"Jinyong Wu, Yong Zhao, Yule Yuan, Xing Zhang, Yike Wang","doi":"10.1109/GCIS.2012.26","DOIUrl":"https://doi.org/10.1109/GCIS.2012.26","url":null,"abstract":"Since that the surveillance video is an unstructured media, it is not beneficial for the video intelligent retrieval and mining. An approach that is based on Gaussian mixture model and support vector machine has been put forward in this paper, which can make the video of surveillance scene structured. First, it constructs Gaussian background modeling to video scene, and isolates the motion object layer. Second, the visual perceptive information from moving object can be extracted by the angular point detecting method. Third, the multi-granularity perceptive feature of the object can be extracted by the object centroid-centred. Last, a 2-level SVM classifier should be build. By this classifier the semantics can be labeled to the moving objects, and then the structured description of the scenes can be obtained. The experimental results show that the presented method can avoid the interference caused by luminance changes and the motion of the leaves effectively. It is suitable for the video of surveillance scene in structured analysis application and can be a technical support for the intelligent retrieval and mining of video contents.","PeriodicalId":337629,"journal":{"name":"2012 Third Global Congress on Intelligent Systems","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128612719","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：