Email classification methods based on the content general use vector space model. The model is constructed based on the frequency of every independent word appearing in Email content. Frequency based VSM does not take the context environment of the word into account, thus the feature vectors can not accurately represent Email content, which will result in the inaccurate of classification. This paper presents a new approach to Email classification based on the concept vector space model using WordNet. In our approach, based on WordNet we extract the high-level information on categories during training process by replacing terms in the feature vector with synonymy sets and considering the hypernymy-hyponymy relation between synonymy sets. We design a Email classification system based on the concept VSM and carry on a series of experiments. The results show that our approach could improve the accuracy of Email classification especially when the size of training set is small.
{"title":"A New Approach to Email Classification Using Concept Vector Space Model","authors":"C. Zeng, Zhao Lu, J. Gu","doi":"10.1109/FGCNS.2008.7","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.7","url":null,"abstract":"Email classification methods based on the content general use vector space model. The model is constructed based on the frequency of every independent word appearing in Email content. Frequency based VSM does not take the context environment of the word into account, thus the feature vectors can not accurately represent Email content, which will result in the inaccurate of classification. This paper presents a new approach to Email classification based on the concept vector space model using WordNet. In our approach, based on WordNet we extract the high-level information on categories during training process by replacing terms in the feature vector with synonymy sets and considering the hypernymy-hyponymy relation between synonymy sets. We design a Email classification system based on the concept VSM and carry on a series of experiments. The results show that our approach could improve the accuracy of Email classification especially when the size of training set is small.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116443080","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, we propose a multi-channel audio panning method based on the MPEG surround spatial parameters for multi-view broadcasting systems. Multi-channel audio panning techniques are necessary for realistic broadcasting services based on multi-view cameras, where delivering multi-channel audio can increase realism. The proposed audio panning method is composed of two parts. The first part is an enhanced channel level difference (CLD)-based audio panning method to overcome problems of a conventional CLD based panning method. The second part is an interchannel correlation (ICC)-based audio panning method to improve the localization performance of panned audio. To evaluate the performance of the proposed methods, 5.1 channel audio samples belonging to various music genres are used. AMUSHRA test is conducted to objectively evaluate the perceptual quality and measure localization performance using a dummy head. From the experiments, it is shown that the proposed method provides better localization performance than the conventional CLD-based audio panning method.
{"title":"Parameter-Based Multi-Channel Audio Panning for Multi-View Broadcasting Systems","authors":"Yong Guk Kim, H. Kim","doi":"10.1109/FGCNS.2008.37","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.37","url":null,"abstract":"In this paper, we propose a multi-channel audio panning method based on the MPEG surround spatial parameters for multi-view broadcasting systems. Multi-channel audio panning techniques are necessary for realistic broadcasting services based on multi-view cameras, where delivering multi-channel audio can increase realism. The proposed audio panning method is composed of two parts. The first part is an enhanced channel level difference (CLD)-based audio panning method to overcome problems of a conventional CLD based panning method. The second part is an interchannel correlation (ICC)-based audio panning method to improve the localization performance of panned audio. To evaluate the performance of the proposed methods, 5.1 channel audio samples belonging to various music genres are used. AMUSHRA test is conducted to objectively evaluate the perceptual quality and measure localization performance using a dummy head. From the experiments, it is shown that the proposed method provides better localization performance than the conventional CLD-based audio panning method.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123362184","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}
Se-Kab Oh, Yangsun Lee, Heau-Jo Kang, Sung-Eon Cho
In this paper the Coefficient Tracking Synchronization Algorithm is proposed for the compensation and the suitability of the fast channel fluctuation OFDM in the WAVE (Wireless Access in Vehicular Environments) system. The in progress of standardization WAVE process, IEEE802.11's physical layer is considered on the coexistence of fading and Frequency offset of OFDM channel to find the system performance ability and the comparing examination which is taken on the proposed method of Coefficient Tracking Synchronization Algorithm and the performance efficiency. Through the simulation result we also can see that the proposed system improves the channel estimation ability and offers an extra efficiency if compared to the existing method.
{"title":"Performance Analysis for Coefficient Tracking Synchronization Algorithm of OFDM Based Vehicle Communication System in Intelligent Transportation System Environment","authors":"Se-Kab Oh, Yangsun Lee, Heau-Jo Kang, Sung-Eon Cho","doi":"10.1109/FGCNS.2008.106","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.106","url":null,"abstract":"In this paper the Coefficient Tracking Synchronization Algorithm is proposed for the compensation and the suitability of the fast channel fluctuation OFDM in the WAVE (Wireless Access in Vehicular Environments) system. The in progress of standardization WAVE process, IEEE802.11's physical layer is considered on the coexistence of fading and Frequency offset of OFDM channel to find the system performance ability and the comparing examination which is taken on the proposed method of Coefficient Tracking Synchronization Algorithm and the performance efficiency. Through the simulation result we also can see that the proposed system improves the channel estimation ability and offers an extra efficiency if compared to the existing method.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126030812","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}
Extended Kalman filter (EKF), which has long been used in the field of GPS positioning, has recently been used for indoor positioning, introduced extended Kalman filter (EKF) indoor positioning method based on Bluetooth signal strength. However, the error range of the EKF is so large when it was applied in WLAN tracking that we modified it to use K-NN method for the measurement of the EKF. Furthermore, this paper proposes an idea of improving accuracy of EKF tracking by adjusting parameter values referring to map information. Experimental results comparing our method with other previous methods are discussed.
{"title":"Utilizing Map Information for WLAN-Based Kalman Filter Indoor Tracking","authors":"J. Yim, Seunghwan Jeong, Jaehun Joo, Chansik Park","doi":"10.1109/FGCNS.2008.148","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.148","url":null,"abstract":"Extended Kalman filter (EKF), which has long been used in the field of GPS positioning, has recently been used for indoor positioning, introduced extended Kalman filter (EKF) indoor positioning method based on Bluetooth signal strength. However, the error range of the EKF is so large when it was applied in WLAN tracking that we modified it to use K-NN method for the measurement of the EKF. Furthermore, this paper proposes an idea of improving accuracy of EKF tracking by adjusting parameter values referring to map information. Experimental results comparing our method with other previous methods are discussed.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127336095","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}
Aiming at the problem of lower accuracy of vibration fault diagnosis system for turbo-generator set, a new diagnosis method based on self-organized fuzzy neural network is proposed and a self-organized fuzzy neural network system is structured for diagnosing faults of large-scale turbo-generator set in this paper by associating the fuzzy set theory with neural network technology. Especially, an effective fuzzy self-organized method for training samples of neural network is presented and the standard sample database for diagnosis neural network is established. Finally, supported by the 108DAI detecting system, a vibration fault diagnosis system of 600MW turbo-generator set is designed and realized by the proposed system structure, its running results in a thermal power plant of Guangdong Province show that this new diagnosis system can satisfy fault diagnosis requirement of large turbo-generator set. Its accuracy varies from 92 percent to 98 percent.
{"title":"Fault Diagnosis System for Turbo-Generator Set Based on Self-Organized Fuzzy Neural Network","authors":"Ping Yang, Zhen Zhang","doi":"10.1109/FGCNS.2008.124","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.124","url":null,"abstract":"Aiming at the problem of lower accuracy of vibration fault diagnosis system for turbo-generator set, a new diagnosis method based on self-organized fuzzy neural network is proposed and a self-organized fuzzy neural network system is structured for diagnosing faults of large-scale turbo-generator set in this paper by associating the fuzzy set theory with neural network technology. Especially, an effective fuzzy self-organized method for training samples of neural network is presented and the standard sample database for diagnosis neural network is established. Finally, supported by the 108DAI detecting system, a vibration fault diagnosis system of 600MW turbo-generator set is designed and realized by the proposed system structure, its running results in a thermal power plant of Guangdong Province show that this new diagnosis system can satisfy fault diagnosis requirement of large turbo-generator set. Its accuracy varies from 92 percent to 98 percent.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125904057","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}
An accurate prediction of queue length at the intersection has been one of the key issues in implementation of the adaptive signal control systems as well as the bus signal priority systems (BSP). Because of the analytical queueing modelspsila nature, most prediction models have limited in predicting the queue length for longer time interval. This paper develops a multi-time step queue prediction model based on DTPP to forecast multi time steps using the delay between the time vehicle is detected and the time vehicle arrived at the end of queue. The test on simple one-way network provided a fairly accurate result in queue prediction, less than 1 vehicle in average. For practical application to the traffic signal system in operation, it is required to improve further the model being able to consider left-turn and right-turn traffic at the intersection.
{"title":"Multi-time Step Traffic Queue Prediction Model Based on Discrete Time Point Process (DTPP)","authors":"W. Kim, B. Park","doi":"10.1109/FGCNS.2008.134","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.134","url":null,"abstract":"An accurate prediction of queue length at the intersection has been one of the key issues in implementation of the adaptive signal control systems as well as the bus signal priority systems (BSP). Because of the analytical queueing modelspsila nature, most prediction models have limited in predicting the queue length for longer time interval. This paper develops a multi-time step queue prediction model based on DTPP to forecast multi time steps using the delay between the time vehicle is detected and the time vehicle arrived at the end of queue. The test on simple one-way network provided a fairly accurate result in queue prediction, less than 1 vehicle in average. For practical application to the traffic signal system in operation, it is required to improve further the model being able to consider left-turn and right-turn traffic at the intersection.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"13 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116774276","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 the H.264/AVC video codec, a rate-distortion optimization method for mode decision provides high coding efficiency. However, it increases encoding time significantly due to its high complexity. In this paper, we propose a fast algorithm for inter mode decision using motion cost during motion estimation to reduce the number of candidate modes. The proposed approach makes early 16 times 16 mode decision and early inactive P8 times 8 mode decision. Its encoding performance is similar to that of the fast inter mode decision in the H.264/AVC JM reference software; however, its encoding time is reduced by 30.95% on average. Especially, when quantization parameter (QP) is larger, we obtained better results.
{"title":"Efficient Selection of Candidates for Fast Inter Mode Decision in H.264","authors":"Woo-seok Jang, Jin Heo, Yo-Sung Ho","doi":"10.1109/FGCNS.2008.43","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.43","url":null,"abstract":"In the H.264/AVC video codec, a rate-distortion optimization method for mode decision provides high coding efficiency. However, it increases encoding time significantly due to its high complexity. In this paper, we propose a fast algorithm for inter mode decision using motion cost during motion estimation to reduce the number of candidate modes. The proposed approach makes early 16 times 16 mode decision and early inactive P8 times 8 mode decision. Its encoding performance is similar to that of the fast inter mode decision in the H.264/AVC JM reference software; however, its encoding time is reduced by 30.95% on average. Especially, when quantization parameter (QP) is larger, we obtained better results.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114707727","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}
Many approaches have been proposed for mining frequent pattern. However, either the search space or memory space is huge, such that the performance for the previous approach degrades when the database is massive or the threshold for mining frequent patterns is low. In this paper, we propose an algorithm for mining frequent patterns. Our algorithm only needs to construct a FP-tree and traverse each subtree of the FP-tree to generate all the frequent patterns for an item without constructing any other subtrees. After traversing a subtree for an item, our approach merges and removes the subtree to reduce the FP-tree smaller and smaller. By this way, only a subtree of the reduced FP-tree needs to be traversed to generate frequent patterns for the other item. Since there is no extra trees constructed and the frequent patterns generated for an item only need to traverse a subtree, our approach is much more efficient than FP-Growth algorithm. The experimental results also show that our approach outperforms FP-Growth algorithm.
{"title":"The Combinations of Frequent Pattern Tree and Candidate Generation for Mining Frequent Patterns","authors":"Show-Jane Yen, Yue-Shi Lee, Chiu-Kuang Wang, Jung-Wei Wu","doi":"10.1109/FGCNS.2008.68","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.68","url":null,"abstract":"Many approaches have been proposed for mining frequent pattern. However, either the search space or memory space is huge, such that the performance for the previous approach degrades when the database is massive or the threshold for mining frequent patterns is low. In this paper, we propose an algorithm for mining frequent patterns. Our algorithm only needs to construct a FP-tree and traverse each subtree of the FP-tree to generate all the frequent patterns for an item without constructing any other subtrees. After traversing a subtree for an item, our approach merges and removes the subtree to reduce the FP-tree smaller and smaller. By this way, only a subtree of the reduced FP-tree needs to be traversed to generate frequent patterns for the other item. Since there is no extra trees constructed and the frequent patterns generated for an item only need to traverse a subtree, our approach is much more efficient than FP-Growth algorithm. The experimental results also show that our approach outperforms FP-Growth algorithm.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126755976","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 presents an image formation model of a digital camera with consideration of both optical and the Bayer color filter array (CFA) degradations. Based on the proposed model, a regularized iterative image restoration algorithm is presented to deconvolve the space-variant image degradation. The spatially adaptive version further improves the restoration quality. Hardware implementation issues are briefly summarized, and future modification plan is presented.
{"title":"Regularized Iterative Restoration of Combined Optical and Color Filter Array Degradation","authors":"Yoonjong Yoo, Sinyoung Jun, Jeongho Shin, J. Paik","doi":"10.1109/FGCNS.2008.12","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.12","url":null,"abstract":"This paper presents an image formation model of a digital camera with consideration of both optical and the Bayer color filter array (CFA) degradations. Based on the proposed model, a regularized iterative image restoration algorithm is presented to deconvolve the space-variant image degradation. The spatially adaptive version further improves the restoration quality. Hardware implementation issues are briefly summarized, and future modification plan is presented.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125740212","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 a method of transforming RDF (resource description framework) model into a CPN (colored Petri net) model. The method represents the semantics of the RDF model in the CPN model by mapping the classes and properties of RDF model to CPN places and representing the relationships between classes and properties as token transitions on the CPN. In order to represent a RDF statement on the CPN, the method introduces a transition which produces a token consisting of two ordered tokens, one is corresponding to the subject and the other is corresponding to the object of the statement. Applying the proposed method, we built an example CPN model for a RDF model. We also perform simulations on the model to answer to RDF queries.
{"title":"Colored Petri Net Representation of RDF Models","authors":"J. Yim, Seunghwan Jeong, Jaehun Joo","doi":"10.1109/FGCNS.2008.149","DOIUrl":"https://doi.org/10.1109/FGCNS.2008.149","url":null,"abstract":"This paper proposes a method of transforming RDF (resource description framework) model into a CPN (colored Petri net) model. The method represents the semantics of the RDF model in the CPN model by mapping the classes and properties of RDF model to CPN places and representing the relationships between classes and properties as token transitions on the CPN. In order to represent a RDF statement on the CPN, the method introduces a transition which produces a token consisting of two ordered tokens, one is corresponding to the subject and the other is corresponding to the object of the statement. Applying the proposed method, we built an example CPN model for a RDF model. We also perform simulations on the model to answer to RDF queries.","PeriodicalId":370780,"journal":{"name":"2008 Second International Conference on Future Generation Communication and Networking Symposia","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117353304","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：