{"title":"Improving English-Vietnamese Word Alignment Using Translation Model","authors":"Giang Nguyen, Dinh Dien","doi":"10.1109/rivf.2012.6169841","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169841","url":null,"abstract":"Word alignment for a parallel corpus is the connection between the words/phrases in source language and the words/phrases in target language. The alignment result is an important input for many natural language processing applications. In this paper, we propose an approach to improve the English-Vietnamese word alignment result by using the alignment frequency that is presented in the translation model of SMT (Statistical Machine Translation). We also indicate 5 common error types of English-Vietnamese word alignment and propose the heuristic patterns to discover the alignment errors. The experimental results show the improvement compared to the result of GIZA++.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129658314","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}
{"title":"Unsupervised and Semi-Supervised Clustering for Large Image Database Indexing and Retrieval","authors":"Hien Phuong Lai, M. Visani, A. Boucher, J. Ogier","doi":"10.1109/rivf.2012.6169869","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169869","url":null,"abstract":"The feature space structuring methods play a very important role in finding information in large image databases. They organize indexed images in order to facilitate, accelerate and improve the results of further retrieval. Clustering, one kind of feature space structuring, may organize the dataset into groups of similar objects without prior knowledge (unsupervised clustering) or with a limited amount of prior knowledge (semi- supervised clustering). In this paper, we present both formal and experimental comparisons of different unsupervised clustering methods for structuring large image databases. We use different image databases of increasing sizes (Wang, PascalVoc2006, Caltech101, Core130k) to study the scalability of the different approaches. Moreover, a summary of semi-supervised clustering methods is presented and an interactive semi-supervised clustering model using the HMRF-kmeans is experimented on the Wang image database in order to analyse the improvement of the clustering results when user feedbacks are provided.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127273895","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}
{"title":"Rough Set Methods for Large and Spare Data in EAV Format","authors":"Wojciech Swieboda, H. Nguyen","doi":"10.1109/rivf.2012.6169830","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169830","url":null,"abstract":"In this article we discuss a computationally effective method for computing approximate decision reducts of large data sets. We consider the EAV (entity-attribute-value) which efficiently stores sparse data sets and we propose new implementations of Maximum Discernibility heuristic for data sets represented in this format.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128811897","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}
{"title":"Higher Order Conditional Random Field for Multi-Label Interactive Image Segmentation","authors":"T. Nguyen, N. Pham, Trung-Thien Tran, H. Le","doi":"10.1109/rivf.2012.6169870","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169870","url":null,"abstract":"In this paper, we propose the efficient approach to tackle the multi-label interactive image segmentation issue by applying the higher order Conditional Random Fields model which associates superpixel as higher order energy. People did take advantage of CRF model for unsupervised segmentation for years, but it requires training set for providing neccessary information. Therefore, unsupervised strategy is fairly restrictive for the variety of image contexts and categorizations. For this reason, the user interaction seems inevitable to help us address the multi- label segmentation's riddle in accordance with exploiting CRF perspectives. The promising experiments are conducted in MSRC and Berkeley dataset comparing with the original Conditional Random Fields framework.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126722072","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}
{"title":"An Approximation-Based Abstract Interpretation Framework for Formal Verification of Floating-Point Programs","authors":"Vinh D. Thai, T. Quan, Tien V. Le, B. Ngo","doi":"10.1109/rivf.2012.6169864","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169864","url":null,"abstract":"Formal verification of programs involved with floating-point data type still remains a tough problem nowadays. One of the major problems faced in this area is how to reflect the rounding error caused by IEEE standard floating-point processing for verification. In this paper we present an approximation approach which basically converts all floating-point data objects into corresponding integer values. It is carried by some scale operations, which are shown equivalent to a consistent Abstract Interpretation. We have also developed a Web-based verification system to check programming works submitted by students. Experimental results show that the learning interests of students have been significantly improved since floating-point programming problems were supported in the system.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123263180","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}
{"title":"Simulation of Salinity Intrusion in the Context of the Mekong Delta Region (Viet Nam)","authors":"H. Hoang, H. Huynh, T. Nguyen","doi":"10.1109/rivf.2012.6169854","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169854","url":null,"abstract":"In this paper, we constructed a simulation model the salinity intrusion status in the past and salinity intrusion scenarios for the future in Mekong Delta, piloting in Bac Lieu province. The salinity intrusion process was simulated on river/channel system and on the area of Bac Lieu (designed from the GIS) that runs on the simulation GAMA tool. Simulation results will show the salinity contours, saline area, statistics of the average salinity between the regions, the statistics of salinity intrusion through the period 2000-2010 and 2010-2020.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115220750","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}
Thi Ngoc Anh Nguyen, Jean-Daniel Zucker, M. Nguyen, A. Drogoul, Hong-Phuong Nguyen
{"title":"Simulation of Emergency Evacuation of Pedestrians along the Road Networks in Nhatrang City","authors":"Thi Ngoc Anh Nguyen, Jean-Daniel Zucker, M. Nguyen, A. Drogoul, Hong-Phuong Nguyen","doi":"10.1109/rivf.2012.6169853","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169853","url":null,"abstract":"Evaluation and early warning for Tsunami disasters in coastal areas and islands need to research to save people and mitigate damages. This paper addresses the simulation of pedestrians evacuating along the road network in city. In a developing country, the coastal city often has a complicated roads network and the devices to support an evacuation are simple and shortage so the alert signs are the good devices. We assume that there is a given alert signs system in the city, pedestrians facing a Tsunami have difference behaviors with the signs. The simulations's result help us to estimate the number of survivors and the global amount of rescue time. Agent based model is used to build the evacuation of pedestrians with details behaviors of them. The simulation of pedestrians evacuation in this article using the heterogeneous environment Geographic Information Systems(GIS) supporting realistic simulations. In addition, the simulation is applied for road networks in Nhatrang city.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122779559","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}
{"title":"An Effective 3D Geometric Relational Feature Descriptor for Human Action Recognition","authors":"L. Hoang, T. V. Pham, Jenq-Neng Hwang","doi":"10.1109/rivf.2012.6169868","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169868","url":null,"abstract":"This paper presents an effective feature descriptor for recognizing human actions from three-dimension (3D) motion capture video sequences. The proposed feature descriptor is extended from the Boolean features which have been successfully used in computer animation. We first transform 3D coordinates of specified human points, as provided by the motion capture data system, into corresponding 3D points as defined in an articulated 3D human model. We then derive novel 3D geometric relational features, a numeric (continuous-valued) version of the Boolean features, to represent the geometric relations among body points of a pose. Finally, the proposed feature descriptor is applied in human action classification using the hidden Markov model. The simulation results indicate the effectiveness of the proposed feature descriptor as evidenced by the high recognition rate.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131874971","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}
{"title":"Combining Statistical Machine Learning with Transformation Rule Learning for Vietnamese Word Sense Disambiguation","authors":"Phu-Hung Dinh, Ngoc-Khuong Nguyen, Anh-Cuong Le","doi":"10.1109/rivf.2012.6169827","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169827","url":null,"abstract":"Word Sense Disambiguation (WSD) is the task of determining the right sense of a word depending on the context it appears. Among various approaches developed for this task, statistical machine learning methods have been showing their advantages in comparison with others. However, there are some cases which cannot be solved by a general statistical model. This paper proposes a novel framework, in which we use the rules generated by transformation based learning (TBL) to improve the performance of a statistical machine learning model. This framework can be considered as a combination of a rule-based method and statistical based method. We have developed this method for the problem of Vietnamese WSD and achieved some promising results.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116100830","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}
Tho Hoan Pham, T. Ho, Q. Nguyen, D. Tran, Van Hoang Nguyen
{"title":"Multivariate Mutual Information Measures for Discovering Biological Networks","authors":"Tho Hoan Pham, T. Ho, Q. Nguyen, D. Tran, Van Hoang Nguyen","doi":"10.1109/rivf.2012.6169834","DOIUrl":"https://doi.org/10.1109/rivf.2012.6169834","url":null,"abstract":"Most studies on biological networks until now focus only on pairwise interactions/relationships. However interactions/relationships involving more than two molecules are popular in biology. In this paper, we introduce multivariate mutual information measures to reconstruct multivariate interactions/relationships in biological networks.","PeriodicalId":115212,"journal":{"name":"2012 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123995716","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}