The algorithms based on classical Multidimensional Scaling (MDS) only need 3 or 4 anchor nodes and can provide higher accuracy than other schemes. But it's high computational complexity and large energy consumption cause its shorter lifecycle, so an improved positioning algorithm for Wireless Sensor Networks (WSN) is presented in the paper. It reduces distance matrix involved and fully uses nodes with ranging capability. We conduct simulation studies under square shaped topologies with different communication radius, different connectivity levels and different number of anchors. Simulation results show that improved MDS provides a lower position estimation error than classical MDS and have less running time. In the end, some parameters are suggested, which can make WSN get the optimal network performance.
{"title":"Perfomance Research of Improved MDS-MAP Algorithm in Wireless Sensor Networks Localization","authors":"Xiaoling Sun, Tao Chen, Weiqin Li, Mian Zheng","doi":"10.1109/ICCSEE.2012.290","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.290","url":null,"abstract":"The algorithms based on classical Multidimensional Scaling (MDS) only need 3 or 4 anchor nodes and can provide higher accuracy than other schemes. But it's high computational complexity and large energy consumption cause its shorter lifecycle, so an improved positioning algorithm for Wireless Sensor Networks (WSN) is presented in the paper. It reduces distance matrix involved and fully uses nodes with ranging capability. We conduct simulation studies under square shaped topologies with different communication radius, different connectivity levels and different number of anchors. Simulation results show that improved MDS provides a lower position estimation error than classical MDS and have less running time. In the end, some parameters are suggested, which can make WSN get the optimal network performance.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126800800","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}
Traditional machine learning and data mining have achieved significant success in many knowledge engineering areas including classification, regression clustering and so on, but a major assumption in them is that the training and test data must be in the same feature space and follow the same distribution. However, in real applications, this assumption couldn't be satisfied for ever. In this case, the role of transfer learning can be highlight, because transfer learning does not make the same distributional assumptions as the traditional machine learning, and reduces the dependencies of the target task and training data, has a wider migration of knowledge. In this paper we will propose a transfer learning algorithm for document categorization based on clustering. We describe the main idea and the step of the algorithm. Then use experiment to test the algorithm and compare the algorithm with no-transfer algorithm. the experiment demonstrate that the algorithm we proposed in this paper is better than the others in some extent.
{"title":"A Transfer Learning Algorithm for Document Categorization Based on Clustering","authors":"Wei Sun, Qian Xu","doi":"10.1109/ICCSEE.2012.132","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.132","url":null,"abstract":"Traditional machine learning and data mining have achieved significant success in many knowledge engineering areas including classification, regression clustering and so on, but a major assumption in them is that the training and test data must be in the same feature space and follow the same distribution. However, in real applications, this assumption couldn't be satisfied for ever. In this case, the role of transfer learning can be highlight, because transfer learning does not make the same distributional assumptions as the traditional machine learning, and reduces the dependencies of the target task and training data, has a wider migration of knowledge. In this paper we will propose a transfer learning algorithm for document categorization based on clustering. We describe the main idea and the step of the algorithm. Then use experiment to test the algorithm and compare the algorithm with no-transfer algorithm. the experiment demonstrate that the algorithm we proposed in this paper is better than the others in some extent.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121261308","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}
With the rapid development of the Computer Science and Technology, It has become a major problem for the users that how to quickly find useful or needed information. Text categorization can help people to solve this question. The feature selection method has become one of the most critical techniques in the field of the text automatic categorization. A new method of the text feature selection based on Information Gain and Genetic Algorithm is proposed in this paper. This method chooses the feature based on information gain with the frequency of items. Meanwhile, for the information filtering systems, this method has been improved fitness function to fully consider the characteristics of weight, text and vector similarity dimension, etc. The experiment has proved that the method can reduce the dimension of text vector and improve the precision of text classification.
{"title":"A Feature Selection Method Based on Information Gain and Genetic Algorithm","authors":"S. Lei","doi":"10.1109/ICCSEE.2012.97","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.97","url":null,"abstract":"With the rapid development of the Computer Science and Technology, It has become a major problem for the users that how to quickly find useful or needed information. Text categorization can help people to solve this question. The feature selection method has become one of the most critical techniques in the field of the text automatic categorization. A new method of the text feature selection based on Information Gain and Genetic Algorithm is proposed in this paper. This method chooses the feature based on information gain with the frequency of items. Meanwhile, for the information filtering systems, this method has been improved fitness function to fully consider the characteristics of weight, text and vector similarity dimension, etc. The experiment has proved that the method can reduce the dimension of text vector and improve the precision of text classification.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121683277","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 low-frequency magnetic communication (LFMC) wireless communication system based on MCP2030 is designed in this paper. The article presented the system design method, gived the hardware and software system design and test validation after analyzing the working principle of LFMC. Be a technology's turn to have very high application value in automobile electron field.
{"title":"Design of the LFMC Wireless Communication System Based on MCP2030","authors":"Shi Jianfeng, Luo Bo, E. Aijun","doi":"10.1109/ICCSEE.2012.212","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.212","url":null,"abstract":"A low-frequency magnetic communication (LFMC) wireless communication system based on MCP2030 is designed in this paper. The article presented the system design method, gived the hardware and software system design and test validation after analyzing the working principle of LFMC. Be a technology's turn to have very high application value in automobile electron field.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123842957","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 principle of SVPWM (Space Vector Pulse Width Modulation) was analyzed and its algorithm and realization method are discussed in detail. Set up elevator door motor control system based on TMS3202407. Structure of hardware for generating PWM and design method of software are provided. Experiment results show that system has low power device switching losses and high DC voltage utilization efficiency. The effects of system actual operation represent the good performance of this algorithm.
{"title":"Algorithm Analysis and Realization Method of SVPWM Based on TMS320LF2407","authors":"Hongqiu Teng","doi":"10.1109/ICCSEE.2012.141","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.141","url":null,"abstract":"The principle of SVPWM (Space Vector Pulse Width Modulation) was analyzed and its algorithm and realization method are discussed in detail. Set up elevator door motor control system based on TMS3202407. Structure of hardware for generating PWM and design method of software are provided. Experiment results show that system has low power device switching losses and high DC voltage utilization efficiency. The effects of system actual operation represent the good performance of this algorithm.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124974259","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 topic detection and tracking method combining semantic analysis with Suffix Tree Clustering (STC) algorithm is presented. A feature selection using NLP algorithm was introduced to select the noun, verb and name entity as the input of STC. Focusing on the topic drifting, we formed the VSM of cluster by the key words extracted from the nodes of suffix tree by mutual information algorithm. After the similarity computing of clusters and topic detection and tracking, a semantic analysis was introduced to filter the words with same meaning and analyze the semantic structure of words in label of cluster. Finally a content-relevant description was generated for each topic. The experiments showed that this method can detect and track the topics from the news articles effectively.
{"title":"A Topic Detection and Tracking Method Combining NLP with Suffix Tree Clustering","authors":"Yaohong Jin","doi":"10.1109/ICCSEE.2012.131","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.131","url":null,"abstract":"A topic detection and tracking method combining semantic analysis with Suffix Tree Clustering (STC) algorithm is presented. A feature selection using NLP algorithm was introduced to select the noun, verb and name entity as the input of STC. Focusing on the topic drifting, we formed the VSM of cluster by the key words extracted from the nodes of suffix tree by mutual information algorithm. After the similarity computing of clusters and topic detection and tracking, a semantic analysis was introduced to filter the words with same meaning and analyze the semantic structure of words in label of cluster. Finally a content-relevant description was generated for each topic. The experiments showed that this method can detect and track the topics from the news articles effectively.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115831485","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, the factors of steel balls' wear were studied by Discrete Element Method (DEM). Firstly models of steel balls' motion were established by Particle Flow Code in 3 Dimensions (PFC 3D) according to experimental condition. Then the motion regions of steel balls were simplified into grinding regions and throwing regions based on characteristics of steel balls' motion, then the quantity of steel balls in the two regions were counted. Void rate in grinding region and quality of steel balls in throwing region were calculated by data processing, and they were used respectively as criterion of grinding wear and impact wear of steel balls. The influence laws of grading scheme, rotary speed rate of mill and ball filling rate on void rate and throwing balls' quality were studied. The results showed that void rate and throwing balls' quality of three grading scheme had the same tendencies that was Grading>;Grading>;Gradingó when ball filling rate and rotary speed rate of mill were constant. Void rate and throwing balls' quality both increased firstly, then decreased with the rising rotary speed rate of mill at the same ball filling rate and grading scheme. When rotary speed rate of mill remained unchanged, void rate decreased but throwing balls' quality increased with ball filling rate increasing.
{"title":"Research on Wear of Grading Steel Balls by Discrete Element Method","authors":"P. Zhou, J. Du, Xixiang Duan","doi":"10.1109/ICCSEE.2012.365","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.365","url":null,"abstract":"In this paper, the factors of steel balls' wear were studied by Discrete Element Method (DEM). Firstly models of steel balls' motion were established by Particle Flow Code in 3 Dimensions (PFC 3D) according to experimental condition. Then the motion regions of steel balls were simplified into grinding regions and throwing regions based on characteristics of steel balls' motion, then the quantity of steel balls in the two regions were counted. Void rate in grinding region and quality of steel balls in throwing region were calculated by data processing, and they were used respectively as criterion of grinding wear and impact wear of steel balls. The influence laws of grading scheme, rotary speed rate of mill and ball filling rate on void rate and throwing balls' quality were studied. The results showed that void rate and throwing balls' quality of three grading scheme had the same tendencies that was Grading>;Grading>;Gradingó when ball filling rate and rotary speed rate of mill were constant. Void rate and throwing balls' quality both increased firstly, then decreased with the rising rotary speed rate of mill at the same ball filling rate and grading scheme. When rotary speed rate of mill remained unchanged, void rate decreased but throwing balls' quality increased with ball filling rate increasing.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122750695","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 article, a self-similar river networks model was put forward, which use strings code to identify the original unit and the generator unit of RSN (Random Self-similar river Network). This strings code is consist of four parameters: the river networks price, the node number in generator unit, the angle between adjacent chains, and the probability of replacement of generator unit. Set the basic part of limit distribution of water system as the generator unit, and then use the Width Function (WF) of RSN to construct a Geomorphologic Instantaneous Unit Hydrograph (GIUH) based on WF, which was used to simulate hydrological response.
本文提出了一种自相似河网模型，该模型使用字符串编码来识别RSN (Random self-similar river Network，随机自相似河网)的原始单元和生成单元。该串代码由四个参数组成:河网价格、发电机组节点数、相邻链间夹角、机组更换概率。以水系极限分布的基本部分为发电机组，利用RSN的宽度函数(WF)构建基于WF的地貌瞬时单元水文曲线(GIUH)，用于模拟水文响应。
{"title":"RSN Code and Its Application Style","authors":"Xinglong Gong, Zhenxiang Xing, Xiao-fang Rui, Ling Zhe","doi":"10.1109/ICCSEE.2012.370","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.370","url":null,"abstract":"In This article, a self-similar river networks model was put forward, which use strings code to identify the original unit and the generator unit of RSN (Random Self-similar river Network). This strings code is consist of four parameters: the river networks price, the node number in generator unit, the angle between adjacent chains, and the probability of replacement of generator unit. Set the basic part of limit distribution of water system as the generator unit, and then use the Width Function (WF) of RSN to construct a Geomorphologic Instantaneous Unit Hydrograph (GIUH) based on WF, which was used to simulate hydrological response.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131223182","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 described a novel speech emotion recognition approach aiming at improving speech emotion recognition rate. Seven discrete emotional states (anger, disgust, fear, joy, neutral, sadness, surprise) are classified throughout the work. Firstly, series preprocessing of speech signals are done. Secondly, extracting features are done, and then we consider incorporating Canonical Correlation Based on Compensation (CCBC) to cope with the mismatch between training and test set. The mismatch between training and test conditions can be simply clustered into three classes: differences of speakers, changes of recording channel and effects of noisy environment. Finally, we evaluated the system using Back-propagation Neural Networks (BPNN). Results are given using the Chinese Corpus of emotional speech synthesis database, recognition experiments show that the method is effective and high speech for emotion recognition.
{"title":"A Study on Speech Emotion Recognition Based on CCBC and Neural Network","authors":"Zhiyan Han, Shuxian Lun, Jian Wang","doi":"10.1109/ICCSEE.2012.128","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.128","url":null,"abstract":"This paper described a novel speech emotion recognition approach aiming at improving speech emotion recognition rate. Seven discrete emotional states (anger, disgust, fear, joy, neutral, sadness, surprise) are classified throughout the work. Firstly, series preprocessing of speech signals are done. Secondly, extracting features are done, and then we consider incorporating Canonical Correlation Based on Compensation (CCBC) to cope with the mismatch between training and test set. The mismatch between training and test conditions can be simply clustered into three classes: differences of speakers, changes of recording channel and effects of noisy environment. Finally, we evaluated the system using Back-propagation Neural Networks (BPNN). Results are given using the Chinese Corpus of emotional speech synthesis database, recognition experiments show that the method is effective and high speech for emotion recognition.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"70 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131747884","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}
Aimed at satisfying the demand of complex path programming for industrial robot, a computer-aided programming system based on DXF file is developed. By analyzing storage information of the graphic elements in DXF file, we develop a method to extract lines, arcs and circles, and then come up with a connect algorithm, which rearranges and connects the original isolated graphic elements in drawing order to some continuous paths. Guaranteeing assigned working paths, this system can not only raise working efficiency by reducing spare travels, but also avoid position error in one continuous path between graphic elements caused by relocation. The paths after rearrangement can be converted into robot's working file directly, hence increasing the programming efficiency. The results of both simulation and field experiment prove the system's feasibility in cutting, gelatinizing, arc welding, grinding and etc.
{"title":"An Optimized Path Planning Method for Off-Line Programming of a Industrial Robot","authors":"Xianlun Wang, Dongsheng Liu, Yiwei Tao, Yuxia Cui","doi":"10.1109/ICCSEE.2012.159","DOIUrl":"https://doi.org/10.1109/ICCSEE.2012.159","url":null,"abstract":"Aimed at satisfying the demand of complex path programming for industrial robot, a computer-aided programming system based on DXF file is developed. By analyzing storage information of the graphic elements in DXF file, we develop a method to extract lines, arcs and circles, and then come up with a connect algorithm, which rearranges and connects the original isolated graphic elements in drawing order to some continuous paths. Guaranteeing assigned working paths, this system can not only raise working efficiency by reducing spare travels, but also avoid position error in one continuous path between graphic elements caused by relocation. The paths after rearrangement can be converted into robot's working file directly, hence increasing the programming efficiency. The results of both simulation and field experiment prove the system's feasibility in cutting, gelatinizing, arc welding, grinding and etc.","PeriodicalId":132465,"journal":{"name":"2012 International Conference on Computer Science and Electronics Engineering","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115155134","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：