Chensheng Wang, Fei Wang, Xiaochun Wang, J. Vergeest, T. Wiegers
For human being the object perception process is often conducted in a non-crisp manner, in which vagueness plays one of the pivot roles. In this paper, we propose a Fuzzy logic based approach for vision-based object perception in enhanced reality, supported by a shape repository. By means of defining the Fuzzy matching and reasoning rules, the proposed approach is capable of supporting the Fuzzy decision making process in finding the matching shape model in the repository. Experiment results confirm that the proposed method is both valid and effective in the designated application.
{"title":"A Fuzzy Approach for Vision-Based Object Perception in Robot Telecontrol","authors":"Chensheng Wang, Fei Wang, Xiaochun Wang, J. Vergeest, T. Wiegers","doi":"10.1109/HIS.2009.99","DOIUrl":"https://doi.org/10.1109/HIS.2009.99","url":null,"abstract":"For human being the object perception process is often conducted in a non-crisp manner, in which vagueness plays one of the pivot roles. In this paper, we propose a Fuzzy logic based approach for vision-based object perception in enhanced reality, supported by a shape repository. By means of defining the Fuzzy matching and reasoning rules, the proposed approach is capable of supporting the Fuzzy decision making process in finding the matching shape model in the repository. Experiment results confirm that the proposed method is both valid and effective in the designated application.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"196 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131652959","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}
Thiago T. Angelico, Thais Santos Bueno, Silvio Bortoleto, Anderson Ravanello
This article presents a case study about datamining applied in IVR’s navigation trees. Using data from a Call Center, the main objective is to discover patterns with information about the phone calls. Using a specific part from this information, it shows an analysis about the navigation tree of the offered service. With the WEKA, a data mining toolkit, which provides a lot of possibilities of data mining algorithms, were used three types of Data Mining Algorithms. After the mining process, new information about the navigation could be discovered and the data could be better understood.
{"title":"KDD on IVR Navigation Trees: Case Study","authors":"Thiago T. Angelico, Thais Santos Bueno, Silvio Bortoleto, Anderson Ravanello","doi":"10.1109/HIS.2009.305","DOIUrl":"https://doi.org/10.1109/HIS.2009.305","url":null,"abstract":"This article presents a case study about datamining applied in IVR’s navigation trees. Using data from a Call Center, the main objective is to discover patterns with information about the phone calls. Using a specific part from this information, it shows an analysis about the navigation tree of the offered service. With the WEKA, a data mining toolkit, which provides a lot of possibilities of data mining algorithms, were used three types of Data Mining Algorithms. After the mining process, new information about the navigation could be discovered and the data could be better understood.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125515962","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}
To solve fuzzy and non-linear features of mechanical equipment. A new computational intelligence method was proposed by combing based on extended T-S fuzzy model of self-adaptive disturbed PSO and BP neural network algorithm. Firstly, the T-S fuzzy model is modified, and then uses the extended T-S model to adjust the PSO parameter. Secondly, the neural network is trained by the modified PSO algorithm. Finally, a wheel disc model is optimized to check that network model, the test results show that it guarantees the performance of the wheel disc, meanwhile the wheel disc structure is obviously optimized, and the algorithm in the paper is a method of viable structure optimization.
{"title":"Optimization Algorithm Based on T-S Fuzzy Model of Self-Adaptive Disturbed Particle Swarm Optimization and Neural Network","authors":"Wang Jianfang, L. Weihua","doi":"10.1109/HIS.2009.94","DOIUrl":"https://doi.org/10.1109/HIS.2009.94","url":null,"abstract":"To solve fuzzy and non-linear features of mechanical equipment. A new computational intelligence method was proposed by combing based on extended T-S fuzzy model of self-adaptive disturbed PSO and BP neural network algorithm. Firstly, the T-S fuzzy model is modified, and then uses the extended T-S model to adjust the PSO parameter. Secondly, the neural network is trained by the modified PSO algorithm. Finally, a wheel disc model is optimized to check that network model, the test results show that it guarantees the performance of the wheel disc, meanwhile the wheel disc structure is obviously optimized, and the algorithm in the paper is a method of viable structure optimization.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126640678","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 order to improve the speaker recognition accuracy, the pitch is applied to GMM-based speaker recognition (SR). The circular average magnitude difference function (CAMDF) method is used to extract the pitch. An endpoint detection method based on the pitch is proposed. The following four features are selected as the features of the SR: the mel-frequency cepstral coefficient (MFCC) based on the pitch, the pitch contour, the pitch first-order difference and the pitch changed rate. Experimental results show that the recognition rate using proposed endpoint detection method is improved 20% than that using the conventional method. The recognition rate of the proposed system using the selected four features is improved 5% than that of the speaker recognition system using the MFCC parameters only.
{"title":"Pitch in Speaker Recognition","authors":"Jian-wei Zhu, Shuifa Sun, Xiao-li Liu, B. Lei","doi":"10.1109/HIS.2009.14","DOIUrl":"https://doi.org/10.1109/HIS.2009.14","url":null,"abstract":"In order to improve the speaker recognition accuracy, the pitch is applied to GMM-based speaker recognition (SR). The circular average magnitude difference function (CAMDF) method is used to extract the pitch. An endpoint detection method based on the pitch is proposed. The following four features are selected as the features of the SR: the mel-frequency cepstral coefficient (MFCC) based on the pitch, the pitch contour, the pitch first-order difference and the pitch changed rate. Experimental results show that the recognition rate using proposed endpoint detection method is improved 20% than that using the conventional method. The recognition rate of the proposed system using the selected four features is improved 5% than that of the speaker recognition system using the MFCC parameters only.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122183365","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}
Jing Chen, Jie Jia, Yingyou Wen, Dazhe Zhao, Jiren Liu
Multi-channel communication in a Wireless Mesh Network with routers having multiple radio interfaces significantly enhances the network capacity. Efficient channel assignment is critical for realization of optimal throughput in such networks. This paper addresses the channel assignment problem for multi-channel multi-interface (radio) wireless mesh networks. We focus on static wireless mesh networks where multiple non-overlapping channels are available for each wireless interface. In this network environment, our objective is to find a fixed channel assignment which maximizes the number of bidirectional links that can be activated simultaneously, subject to interference constraints. We present a mixed integer linear programming models for solving the fixed channel assignment problem with multiple radios. Detailed computational results are presented and discussed to validate the algorithm.
{"title":"Optimization of Resource Allocation in Multi-radio Multi-channel Wireless Mesh Networks","authors":"Jing Chen, Jie Jia, Yingyou Wen, Dazhe Zhao, Jiren Liu","doi":"10.1109/HIS.2009.159","DOIUrl":"https://doi.org/10.1109/HIS.2009.159","url":null,"abstract":"Multi-channel communication in a Wireless Mesh Network with routers having multiple radio interfaces significantly enhances the network capacity. Efficient channel assignment is critical for realization of optimal throughput in such networks. This paper addresses the channel assignment problem for multi-channel multi-interface (radio) wireless mesh networks. We focus on static wireless mesh networks where multiple non-overlapping channels are available for each wireless interface. In this network environment, our objective is to find a fixed channel assignment which maximizes the number of bidirectional links that can be activated simultaneously, subject to interference constraints. We present a mixed integer linear programming models for solving the fixed channel assignment problem with multiple radios. Detailed computational results are presented and discussed to validate the algorithm.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120966897","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}
Session Initiation Protocol (SIP) standardized by IETF provides a way to establish the sessions between Internet telephony devices, but this protocol can’t work with Network Address Translator (NAT). Therefore how to make SIP NAT friendly becomes a worthy topic. This paper proposes an efficient approach P2P-Grid architecture model based ICE which uses Simple Traversal of User Datagram Protocol (STUN) and TURN synthetically at the beginning of Interactive Connectivity Establishment (ICE) process (establishing the multimedia sessions) ¿the agents ignore their own NAT topologies. In the process of establishing sessions, agents explore the NAT topology by a request / response interaction, and a smart sorting algorithm is also used to find and select the optimal path for media streams to traverse NAT. The program was tested on Linux platform. The result shows that the media streams can traversal various NAT efficiently.
{"title":"A P2P-Grid Model for Traversing NAT in SIP Communication","authors":"Qinghui Wang, Lifeng Wei, Danmei Liu","doi":"10.1109/HIS.2009.217","DOIUrl":"https://doi.org/10.1109/HIS.2009.217","url":null,"abstract":"Session Initiation Protocol (SIP) standardized by IETF provides a way to establish the sessions between Internet telephony devices, but this protocol can’t work with Network Address Translator (NAT). Therefore how to make SIP NAT friendly becomes a worthy topic. This paper proposes an efficient approach P2P-Grid architecture model based ICE which uses Simple Traversal of User Datagram Protocol (STUN) and TURN synthetically at the beginning of Interactive Connectivity Establishment (ICE) process (establishing the multimedia sessions) ¿the agents ignore their own NAT topologies. In the process of establishing sessions, agents explore the NAT topology by a request / response interaction, and a smart sorting algorithm is also used to find and select the optimal path for media streams to traverse NAT. The program was tested on Linux platform. The result shows that the media streams can traversal various NAT efficiently.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120999200","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 study, we applied ensemble machine learning to evaluate credit scoring. With decision tree as the baseline algorithm, two popular ensemble learning methods, bagging and boosting, were evaluated across different experiment conditions: using all 14 features, using selected 6 features on Australian credit data form UCI data set. Results showed that in experiments with all features improved performance was achieved by ensemble learning. The best result was obtained in adaboost CART with 14 features, in which the overall correct rate increases from 83.25% to 85.86%.
{"title":"Credit Scoring Using Ensemble Machine Learning","authors":"Ping Yao","doi":"10.1109/HIS.2009.264","DOIUrl":"https://doi.org/10.1109/HIS.2009.264","url":null,"abstract":"In this study, we applied ensemble machine learning to evaluate credit scoring. With decision tree as the baseline algorithm, two popular ensemble learning methods, bagging and boosting, were evaluated across different experiment conditions: using all 14 features, using selected 6 features on Australian credit data form UCI data set. Results showed that in experiments with all features improved performance was achieved by ensemble learning. The best result was obtained in adaboost CART with 14 features, in which the overall correct rate increases from 83.25% to 85.86%.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116621643","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 nonlinear characteristic of an LED (light emitting diode) imposes limitations on the performance of indoor optical wireless (OW) systems when using intensity modulation in combination with OFDM (orthogonal frequency division multiplexing). First, the impact of the nonlinear characteristic on bit-error performance is analyzed using a commercially available LED (OSRAM, SFH 4230). Second, the paper proposes a predistorter to overcome the nonlinearities. Key features of the predistorter reside in the use of the LED inverse characteristics as nonlinear distortion compensator. A DC biased optical OFDM (DCO-OFDM) system is considered and the performance without compensation and after compensation is analyzed via simulations in an AWGN (additive white Gaussian noise) environment. In this context, the bit-error performance is determined for different bias points and power back-off values applied to the OFDM signal modulating the LED intensity. It is shown that LED nonlinearity can significantly degrade the performance. However, it is demonstrated that this degradation can greatly be mitigated by using the proposed predistortion technique.
{"title":"Predistortion in Optical Wireless Transmission Using OFDM","authors":"H. Elgala, R. Mesleh, H. Haas","doi":"10.1109/HIS.2009.321","DOIUrl":"https://doi.org/10.1109/HIS.2009.321","url":null,"abstract":"The nonlinear characteristic of an LED (light emitting diode) imposes limitations on the performance of indoor optical wireless (OW) systems when using intensity modulation in combination with OFDM (orthogonal frequency division multiplexing). First, the impact of the nonlinear characteristic on bit-error performance is analyzed using a commercially available LED (OSRAM, SFH 4230). Second, the paper proposes a predistorter to overcome the nonlinearities. Key features of the predistorter reside in the use of the LED inverse characteristics as nonlinear distortion compensator. A DC biased optical OFDM (DCO-OFDM) system is considered and the performance without compensation and after compensation is analyzed via simulations in an AWGN (additive white Gaussian noise) environment. In this context, the bit-error performance is determined for different bias points and power back-off values applied to the OFDM signal modulating the LED intensity. It is shown that LED nonlinearity can significantly degrade the performance. However, it is demonstrated that this degradation can greatly be mitigated by using the proposed predistortion technique.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131754750","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}
Discovered gene regulation networks are very helpful to predict unknown gene functions. Microarray gene expression data reveals activation and deactivation relations among genes. There are evidences showing that multiple time units delay exist in a gene regulation process. Association rule mining technique is very suitable for finding regulation relations among genes. However, current association rule mining techniques can not handle temporally ordered transactions. We propose a modified association rule mining technique for efficiently discovering time-delayed regulation relationships among genes.
{"title":"Finding Time-Delayed Gene Regulation Patterns from Microarray Data","authors":"Huang-Cheng Kuo, Pei-Cheng Tsai, Jen-peng Huang","doi":"10.1109/HIS.2009.31","DOIUrl":"https://doi.org/10.1109/HIS.2009.31","url":null,"abstract":"Discovered gene regulation networks are very helpful to predict unknown gene functions. Microarray gene expression data reveals activation and deactivation relations among genes. There are evidences showing that multiple time units delay exist in a gene regulation process. Association rule mining technique is very suitable for finding regulation relations among genes. However, current association rule mining techniques can not handle temporally ordered transactions. We propose a modified association rule mining technique for efficiently discovering time-delayed regulation relationships among genes.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128056951","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}
On the analysis of the characteristic of the data in cement enterprise, it brings forward structure in MES based on data integration platform. In this thesis, the key technologies in data integration are analyzed, and the strategy and method of system implementation in a cement enterprise are introduced. Design practice and method of cement enterprise MES information integration are significantly researched. Finally a successful realization case is given.
{"title":"MES Based on Data Integration in Cement Enterprise","authors":"Shaohong Jing, Xiaohong Wang","doi":"10.1109/HIS.2009.320","DOIUrl":"https://doi.org/10.1109/HIS.2009.320","url":null,"abstract":"On the analysis of the characteristic of the data in cement enterprise, it brings forward structure in MES based on data integration platform. In this thesis, the key technologies in data integration are analyzed, and the strategy and method of system implementation in a cement enterprise are introduced. Design practice and method of cement enterprise MES information integration are significantly researched. Finally a successful realization case is given.","PeriodicalId":414085,"journal":{"name":"2009 Ninth International Conference on Hybrid Intelligent Systems","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-08-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132712537","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：