Indexing is a fundamental technique used by the administrator to reduce the cost of processing complex queries defined on a data warehouse. However, selecting a suitable configuration of indexes is a difficult problem to solve. The problem is classified as NP-hard. Automatic index selection has received significant attention in the databases field. Most works have focused on providing tools and algorithms to help data bases administrators in the choice of a configuration of indexes. Some of these works have been adapted for the data warehouse context. The idea, recently introduced, of using data mining techniques to resolve this problem remains a promising approach. In this paper, we propose a maximal frequent pattern based approach to generate a configuration of indexes from a given workload. The proposed approach was tested on APB-1 benchmark under Oracle. The results obtained show that the proposed approach generates indexes that improve the performance of the workload.
{"title":"Improving Star Join Queries Performance: A Maximal Frequent Pattern Based Approach for Automatic Selection of Indexes in Relational Data Warehouses","authors":"B. Ziani, Y. Ouinten","doi":"10.1109/ICICIS.2011.36","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.36","url":null,"abstract":"Indexing is a fundamental technique used by the administrator to reduce the cost of processing complex queries defined on a data warehouse. However, selecting a suitable configuration of indexes is a difficult problem to solve. The problem is classified as NP-hard. Automatic index selection has received significant attention in the databases field. Most works have focused on providing tools and algorithms to help data bases administrators in the choice of a configuration of indexes. Some of these works have been adapted for the data warehouse context. The idea, recently introduced, of using data mining techniques to resolve this problem remains a promising approach. In this paper, we propose a maximal frequent pattern based approach to generate a configuration of indexes from a given workload. The proposed approach was tested on APB-1 benchmark under Oracle. The results obtained show that the proposed approach generates indexes that improve the performance of the workload.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121288831","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}
Chen Xuemei, Gao Li, Wang Xi, Wei Zhonghua, Z. Zhenhua, Liao Zhigao
The traditional K-Means algorithm is sensitive to outliers, outliers traction and easy off-center, and overlap of classes can not very well show their classification. This paper introduces a variant of the probability distribution theory, K-Means clustering algorithm - Gaussian mixture model to part of the customer data randomly selected of Volkswagen dealer in a Beijing office in 2008, for example, and carry out empirical study based on the improved clustering algorithm model. The results showed that: data mining clustering algorithm in active demand management and market segmentation has important significance.
{"title":"The Research on the Data Mining Technology in the Active Demand Management","authors":"Chen Xuemei, Gao Li, Wang Xi, Wei Zhonghua, Z. Zhenhua, Liao Zhigao","doi":"10.1109/ICICIS.2011.125","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.125","url":null,"abstract":"The traditional K-Means algorithm is sensitive to outliers, outliers traction and easy off-center, and overlap of classes can not very well show their classification. This paper introduces a variant of the probability distribution theory, K-Means clustering algorithm - Gaussian mixture model to part of the customer data randomly selected of Volkswagen dealer in a Beijing office in 2008, for example, and carry out empirical study based on the improved clustering algorithm model. The results showed that: data mining clustering algorithm in active demand management and market segmentation has important significance.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"293 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116309945","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}
Prediction of library borrowing flow plays an important role in controlling the quality of book collection and cataloging work in library. Traditional time series prediction methods are hard to model the library borrowing flow because it is a nonlinear dynamical process and has nonstationary and stochastic character. Based on support vector machine and the theory of chaotic time series prediction, a new method is proposed to model and predict the library borrowing flow. The experiments show this method is reasonable to solve the nonlinear problem in library borrowing flow and is of certain value in both theory and practice.
{"title":"Application of Chaotic Time Series Prediction in Forecasting of Library Borrowing Flow","authors":"Mei Tian","doi":"10.1109/ICICIS.2011.147","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.147","url":null,"abstract":"Prediction of library borrowing flow plays an important role in controlling the quality of book collection and cataloging work in library. Traditional time series prediction methods are hard to model the library borrowing flow because it is a nonlinear dynamical process and has nonstationary and stochastic character. Based on support vector machine and the theory of chaotic time series prediction, a new method is proposed to model and predict the library borrowing flow. The experiments show this method is reasonable to solve the nonlinear problem in library borrowing flow and is of certain value in both theory and practice.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125465446","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}
In view of the artificial neural network weights training problem, this paper proposed a method to optimize the network's structure parameters and regularization coefficient using two-layer Particle Swarm Optimization (PSO). This algorithm was applied to train Adaline network. Compared with fixed regularization coefficient method and Sliding Mode Variable Structure optimization method, the result showed that it had the advantages of high precision and strong ability of generalization.
{"title":"Neural Network Research Using Particle Swarm Optimization","authors":"Yahui Wang, Zhifeng Xia, Yifeng Huo","doi":"10.1109/ICICIS.2011.106","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.106","url":null,"abstract":"In view of the artificial neural network weights training problem, this paper proposed a method to optimize the network's structure parameters and regularization coefficient using two-layer Particle Swarm Optimization (PSO). This algorithm was applied to train Adaline network. Compared with fixed regularization coefficient method and Sliding Mode Variable Structure optimization method, the result showed that it had the advantages of high precision and strong ability of generalization.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124074688","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}
In this paper, a kind of Birkhoff type 2-Periodic trigonometric and Para trigonometric interpolation problems with equidistant nodes for 2Ĉ -periodic and antiperiodic functions are discussed. We give the necessary and sufficient conditions for the solvable case of these interpolation problems. The expressions of the interpolation basis are constructed.
{"title":"On a Kind of Birkhoff Type 2-Periodic Trigonometric and Paratrigonometric Interpolation","authors":"Jin Guoxiang, Zhang Li, Ding Yong","doi":"10.1109/ICICIS.2011.97","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.97","url":null,"abstract":"In this paper, a kind of Birkhoff type 2-Periodic trigonometric and Para trigonometric interpolation problems with equidistant nodes for 2Ĉ -periodic and antiperiodic functions are discussed. We give the necessary and sufficient conditions for the solvable case of these interpolation problems. The expressions of the interpolation basis are constructed.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127532376","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}
J. Xia, Yang Ruixia, Zhao Zhengping, Z. Zhiguo, Feng Zhihong
Based on the charge control theory, a accurate analytical model of I-V characteristics for AlGaN/GaN high electron mobility transistor (HEMT) is presented considering the relationship between self-heating effect and polarization, electron mobility, velocity saturation, conduction band discontinuity, doping concentration, channel temperature. The comparison between simulations and physical calculation shows a good agreement. The model is simple in calculations, suitable for design of microwave device and circuit.
{"title":"Analytical Model and Simulation for AlGaN/GaN High Electron Mobility Transistor","authors":"J. Xia, Yang Ruixia, Zhao Zhengping, Z. Zhiguo, Feng Zhihong","doi":"10.1109/ICICIS.2011.93","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.93","url":null,"abstract":"Based on the charge control theory, a accurate analytical model of I-V characteristics for AlGaN/GaN high electron mobility transistor (HEMT) is presented considering the relationship between self-heating effect and polarization, electron mobility, velocity saturation, conduction band discontinuity, doping concentration, channel temperature. The comparison between simulations and physical calculation shows a good agreement. The model is simple in calculations, suitable for design of microwave device and circuit.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132211850","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}
X. Zou, Zhen Shang, I. Odeh, Yizhao Chen, Jian-long Li
integration of Geographical Information System (GIS) and Remote Sensing (RS) methods is one of the most important methods for detecting LULC's change. In this study, with the support of GIS, RS technology and based on recent 10 years LULC data, the landscape pattern dynamics and regional spatio-temporal features related with the LULC change of three metropolis in Asian region, Zhangjiagang (China), Dehradun (India), and Hanoi (Vietnam) are analyzed. We mapping the LULC using supervised method with parallelepiped-maximum likelihood algorithm in ERDAS Imagine 9.1 of the study area based on three consecutive satellite images: Land sat TM, Land sat ETM+ and ASTER. The regional feature of the three cities illustrates different development direction, and the urbanization process of the cities was at different stages. Zhangjiagang was found at the highest stage of urbanization, and with the significant high per capita income level. Hanoi and Dehradun were demonstrated a moderate degree of urbanization and extensive land alternation of agricultural and non-used land to urban area. In Hanoi, Vietnam's capital city, urban agriculture is a longstanding feature, but rapid urban growth is leading to greater competition over land use. In Dehradun, urban areas increased from 96.15 ha to 150.23 ha while agricultural areas decreased from 91.59ha to 45.33ha from 2000-2009. Urban class showed an overall amount and extent of change from 28023 ha to 33215 ha while agricultural areas decrease from 45031 to 41173 during 2002-2010 in Zhangjiagang. As the result, the issue of low quality and security of food was concerned in these three areas. Government support has encouraged urban producers to modernize and invest in safer developing practices. However, in these cities, as indeed elsewhere, there is an urgent need to recognize the significance of sustainable development, agriculture and native forest area reservation in future planning strategies. This kind of strategies identifies key trends and underlying environmental and socio-economic factors, and considers the future sustainability of the practice.
{"title":"Comparative Analysis on Spatio-Temporal Land Use and Land Cover (LULC) Characteristics in Three Asia Cities","authors":"X. Zou, Zhen Shang, I. Odeh, Yizhao Chen, Jian-long Li","doi":"10.1109/ICICIS.2011.52","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.52","url":null,"abstract":"integration of Geographical Information System (GIS) and Remote Sensing (RS) methods is one of the most important methods for detecting LULC's change. In this study, with the support of GIS, RS technology and based on recent 10 years LULC data, the landscape pattern dynamics and regional spatio-temporal features related with the LULC change of three metropolis in Asian region, Zhangjiagang (China), Dehradun (India), and Hanoi (Vietnam) are analyzed. We mapping the LULC using supervised method with parallelepiped-maximum likelihood algorithm in ERDAS Imagine 9.1 of the study area based on three consecutive satellite images: Land sat TM, Land sat ETM+ and ASTER. The regional feature of the three cities illustrates different development direction, and the urbanization process of the cities was at different stages. Zhangjiagang was found at the highest stage of urbanization, and with the significant high per capita income level. Hanoi and Dehradun were demonstrated a moderate degree of urbanization and extensive land alternation of agricultural and non-used land to urban area. In Hanoi, Vietnam's capital city, urban agriculture is a longstanding feature, but rapid urban growth is leading to greater competition over land use. In Dehradun, urban areas increased from 96.15 ha to 150.23 ha while agricultural areas decreased from 91.59ha to 45.33ha from 2000-2009. Urban class showed an overall amount and extent of change from 28023 ha to 33215 ha while agricultural areas decrease from 45031 to 41173 during 2002-2010 in Zhangjiagang. As the result, the issue of low quality and security of food was concerned in these three areas. Government support has encouraged urban producers to modernize and invest in safer developing practices. However, in these cities, as indeed elsewhere, there is an urgent need to recognize the significance of sustainable development, agriculture and native forest area reservation in future planning strategies. This kind of strategies identifies key trends and underlying environmental and socio-economic factors, and considers the future sustainability of the practice.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"153 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134263442","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}
M. Tariquzzaman, Song-Min Gyu, Kim Jin Young, Na Seung You, M. A. Rashid
In state-of-the-art ASR technology, audio and video (AV) information based speech recognition is one of key challenges to cope with noise problem. AV fusion is one of the robust approaches for ASR. The main issues of AV fusion is where and how to integrate the two modalities' information. To enhance the AV fusion performance the paper [1] has proposed the optimum reliability fusion (ORF) and applied the ORF to AV speaker identification. In this paper we adopt the ORF based fusion in AV based speech recognition and evaluate the performance improvement in that domain. The ORF's main idea is to introduce weighting factors in score-base reliability measure (SCRM) for solving the over- or under-estimation problem in SCRM calculation. Our AV speech recognition system is implemented for Korean digit recognition using SAMSUMG AV database. Experimental results show that ORF effectively reduce the relative error rate of 42.8% in comparison with the baseline system adopt the previous AV fusion scheme [2].
{"title":"Performance Improvement of Audio-Visual Speech Recognition with Optimal Reliability Fusion","authors":"M. Tariquzzaman, Song-Min Gyu, Kim Jin Young, Na Seung You, M. A. Rashid","doi":"10.1109/ICICIS.2011.58","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.58","url":null,"abstract":"In state-of-the-art ASR technology, audio and video (AV) information based speech recognition is one of key challenges to cope with noise problem. AV fusion is one of the robust approaches for ASR. The main issues of AV fusion is where and how to integrate the two modalities' information. To enhance the AV fusion performance the paper [1] has proposed the optimum reliability fusion (ORF) and applied the ORF to AV speaker identification. In this paper we adopt the ORF based fusion in AV based speech recognition and evaluate the performance improvement in that domain. The ORF's main idea is to introduce weighting factors in score-base reliability measure (SCRM) for solving the over- or under-estimation problem in SCRM calculation. Our AV speech recognition system is implemented for Korean digit recognition using SAMSUMG AV database. Experimental results show that ORF effectively reduce the relative error rate of 42.8% in comparison with the baseline system adopt the previous AV fusion scheme [2].","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134518747","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}
Querying k nearest neighbors of query point from data set in high dimensional space is one of important operations in spatial database. The classic nearest neighbor query algorithms are based on R-tree. However, R-tree exits overlapping problem of minimum bounding rectangles. This causes its time complexity exponentially depends on the dimensionality of the space. So, the reduction of the dimensionality is the key point. Hilbert curve fills high dimensional space linearly, divides the space into equal-size grids and maps points lying in grids into linear space. Using the quality of reducing dimensionality of Hilbert curve, the paper presents an approximate k nearest neighbor query algorithm AKNN, and analyzes the quality of k nearest neighbors in theory. According to the experimental result, the execution time of algorithm AKNN is shorter than the nearest neighbor query algorithm based on R-tree in high dimensional space, and the quality of approximate k nearest neighbors satisfies the need of real applications.
{"title":"An Approximate Nearest Neighbor Query Algorithm Based on Hilbert Curve","authors":"Hongbo Xu","doi":"10.1109/ICICIS.2011.134","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.134","url":null,"abstract":"Querying k nearest neighbors of query point from data set in high dimensional space is one of important operations in spatial database. The classic nearest neighbor query algorithms are based on R-tree. However, R-tree exits overlapping problem of minimum bounding rectangles. This causes its time complexity exponentially depends on the dimensionality of the space. So, the reduction of the dimensionality is the key point. Hilbert curve fills high dimensional space linearly, divides the space into equal-size grids and maps points lying in grids into linear space. Using the quality of reducing dimensionality of Hilbert curve, the paper presents an approximate k nearest neighbor query algorithm AKNN, and analyzes the quality of k nearest neighbors in theory. According to the experimental result, the execution time of algorithm AKNN is shorter than the nearest neighbor query algorithm based on R-tree in high dimensional space, and the quality of approximate k nearest neighbors satisfies the need of real applications.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133084394","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}
In [1] the decision feedback equalizer (DFE) based on constant modulus algorithm (CMA) and decision directed (DD) adaptive algorithm was proposed. It has been proved that it is much more effective than the conventional DFEs such as DFE based on CMA and DFE based on DD. However when Doppler frequency shift occurs in the communication channel, which can result in carrier phase rotation, the decisions precision is very low which degrades the performance of these DFEs. Consequently based on the DFE in [1] a new DFE with phase-looked loop (PLL) is proposed. The PLL works in CMA part which can offer correct decision for DD, so the proposed method can obtain lower steady state MSE and compensate phase rotations. The efficiency of the method is proved by computer simulation.
{"title":"New DFE with Phase-Locked Loop","authors":"Wei Rao, Huijuan Gao, B. Zou, Wen-qun Tan","doi":"10.1109/ICICIS.2011.150","DOIUrl":"https://doi.org/10.1109/ICICIS.2011.150","url":null,"abstract":"In [1] the decision feedback equalizer (DFE) based on constant modulus algorithm (CMA) and decision directed (DD) adaptive algorithm was proposed. It has been proved that it is much more effective than the conventional DFEs such as DFE based on CMA and DFE based on DD. However when Doppler frequency shift occurs in the communication channel, which can result in carrier phase rotation, the decisions precision is very low which degrades the performance of these DFEs. Consequently based on the DFE in [1] a new DFE with phase-looked loop (PLL) is proposed. The PLL works in CMA part which can offer correct decision for DD, so the proposed method can obtain lower steady state MSE and compensate phase rotations. The efficiency of the method is proved by computer simulation.","PeriodicalId":255291,"journal":{"name":"2011 International Conference on Internet Computing and Information Services","volume":"31 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2011-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133165551","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：