Hector Diez-Rodriguez, Guillermo Morales-Luna, J. O. Olmedo-Aguirre
{"title":"Ontology-Based Knowledge Retrieval","authors":"Hector Diez-Rodriguez, Guillermo Morales-Luna, J. O. Olmedo-Aguirre","doi":"10.1109/MICAI.2008.25","DOIUrl":"https://doi.org/10.1109/MICAI.2008.25","url":null,"abstract":"We deal with knowledge retrieval within the context of Virtual Learning Environment (VLE). A good VLE should deliver relevant learning materials to the learner at the most appropriate time to facilitate knowledge acquisition by Problem-Based Learning (PBL). In PBL, students should retrieve information about a problem by working in small groups with the guidance of a learning facilitator providing materials required through the problem solving process. The use of ontologies to represent domain knowledge improves the information management in a VLE because it enables automatic reasoning and facilitates the processes of knowledge searching and retrieving needed to promote the interest in problem solving. We propose an ontology-based for searching, discovering and publishing relevant learning materials as Learning Objects to help students in the PBL approach.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116904944","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":"A Vectorial Approach on Flock Traffic Navigation","authors":"C. Astengo-Noguez, L.M.G. Velzquez","doi":"10.1109/MICAI.2008.56","DOIUrl":"https://doi.org/10.1109/MICAI.2008.56","url":null,"abstract":"In a city where vehicles will travel without the aid of traffic lights finding partners to make a flock will be a very important issue. Flock Traffic Navigation assumes that vehicles can communicate with each other in order to negotiate a common bone-structure using their actual positions and destinations. In this paper we present an original method based on vector analysis to determine possible best-partners. The cross product is used to determine direction meanwhile the dot product can be used to discriminate among neighbors choosing for travel partners. The meeting and the splitting point are founded using centroids.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131513929","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. Ramos-Arreguín, J. Ortega, E. Gorrostieta, R. de Jesus Romero-Troncoso
{"title":"Artificial Intelligence Applied into Pneumatic Flexible Manipulator","authors":"J. Ramos-Arreguín, J. Ortega, E. Gorrostieta, R. de Jesus Romero-Troncoso","doi":"10.1109/MICAI.2008.76","DOIUrl":"https://doi.org/10.1109/MICAI.2008.76","url":null,"abstract":"Several researches with flexible manipulator robot had been developed using an electrical actuator while other research works deal with pneumatic control, but both investigation lines had been used in separate way. Our goal is simulate the control position angle for the flexible arm, limited to one degree of freedom. We propose an interaction between the pneumatic control and the flexible manipulator robot, being this, the original part of the present work. In this proposal, a speed feedback is used for control position, taken from the pneumatic actuator displacement. We use a fuzzy logic algorithm to adjust the control values, getting a fuzzy algorithm with better results than classic control PID. The project is focused to the engineering application in pneumatic control and flexible manipulators. Result shows a soft movement behavior when speed feedback is used, combined with fuzzy logic, let us to get better results than the classic control approach.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126371425","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":"On the Estimation of the Pareto Optimal Set Using an Evolutionary Parameter Adjustment of the Normal Distribution Function","authors":"L. Torres-Treviño","doi":"10.1109/MICAI.2008.20","DOIUrl":"https://doi.org/10.1109/MICAI.2008.20","url":null,"abstract":"In multi-objective evolutionary optimization it is desirable to obtain a set of solutions usually called the Pareto optimal set. In this paper, some preliminary results are presented to approximate a Pareto optimal set considering an evolutionary adjustment of the parameters of a normal distribution function. The univariable and multivariable normal distribution functions are considered. Four test functions are used considering two forms of evaluation. Results indicate a novel way to represent the Pareto front and suggest different ideas for this area of optimization.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126372094","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":"Natural Language Processing Techniques for the Extraction of Semantic Information in Web Services","authors":"Maricela Bravo, Azucena Montes, Alejandro Reyes","doi":"10.1109/MICAI.2008.50","DOIUrl":"https://doi.org/10.1109/MICAI.2008.50","url":null,"abstract":"With the increase in the number of Web services and the value they are taking, discovery of services that meet the criteria of users becomes a major challenge. Currently the discovery process lacks of well-defined semantics, therefore it is difficult to obtain the non explicit meaning of services, such as functionality. In order to provide an accurate solution to the problem described above, in this paper we evaluate two natural language processing (NLP) techniques to extract semantic information from textual descriptions of Web services: linguistic patterns and extraction rules. Both techniques are implemented and compared in order to select the best alternative to our problem. This information will be useful for enhancing semantically the discovery process of services. We implemented a simulation environment for experimentation, and designed a set of experiments to show the applicability of our solution approach. Results of the tests show that the linguistic patterns are better than extraction rules.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131621941","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. Kundu, A. R. Pal, Tanay Sarkar, M. Banerjee, S. Mandal, R. Dattagupta, Debajyoti Mukhopadhyay
{"title":"An Alternate Downloading Methodology of Webpages","authors":"A. Kundu, A. R. Pal, Tanay Sarkar, M. Banerjee, S. Mandal, R. Dattagupta, Debajyoti Mukhopadhyay","doi":"10.1109/MICAI.2008.13","DOIUrl":"https://doi.org/10.1109/MICAI.2008.13","url":null,"abstract":"We propose an advanced method for downloading Webpages from the Internet. In this technique, the whole system is considered as a bundle of crawlers which have been created dynamically at execution time. Numbers of crawlers are used depending on the requirement of downloading Webpages. The software module which interacts with WWW to search one or more Webpages is known as crawler. The numbers of crawlers are generated using the hierarchy structure of the Web server from which the data would be downloaded. Webpage downloader is an important issue for downloading Web documents from the Internet to facilitate a Web user in terms of knowledge gathering. This type of downloaders are very popular in the 'Information Technology' field. All kinds of public data, accessible throughout the world without any authentication, can be retrieved any time from any geographic location using the downloading methodology. Typically, a downloading technique has been utilized to accumulate Webpages of different domains within a single computer machine one at a time. So, our aim in this paper is to show an advanced technique for downloading a lot of related Webpages with a minimum effort and time using hierarchical downloader consisting of several dynamic crawlers.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134459337","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":"Integrating Subjective Knowledge Bases through an Extended Belief Game Model","authors":"E. Bagheri, A. Ghorbani","doi":"10.1109/MICAI.2008.37","DOIUrl":"https://doi.org/10.1109/MICAI.2008.37","url":null,"abstract":"Belief merging is concerned with the integration of several not necessarily consistent belief bases such that a coherent belief base is developed as a result. Various belief merging models often consist of two key functions, namely: negotiation, and weakening. A negotiation function finds the weakest belief bases among the available belief bases, and then the selected belief bases concede based on a weakening function. This process is iteratively repeated until a consistent belief base is developed. In this paper, we extend the existing belief merging models by introducing the extended belief game model. The extended belief game model operates over a subjective belief profile, which consists of belief bases with subjectively annotated formulae. The subjective information attached to each formula enables the proposed model to prioritize the formulae in the merging process. We provide several instantiations of the merging model by introducing suitable functions.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123127948","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":"Improving the Accuracy and Reliability of Wireless Location Systems: A Case Study","authors":"Russell Beale","doi":"10.1109/MICAI.2008.32","DOIUrl":"https://doi.org/10.1109/MICAI.2008.32","url":null,"abstract":"Wireless location is of increasing importance in context-aware systems. We have developed a wireless location positioning system that can use multiple algorithms for providing estimates of device location, and we present a case study of the system in use with a building. We show that combining two algorithms allows us to provide improved accuracy over one algorithm alone, and draw some general purpose conclusions regarding location determination in real-world environments.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124522639","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}
O. F. Reyes-Galaviz, S. D. Cano-Ortiz, C. Reyes-García
{"title":"Evolutionary-Neural System to Classify Infant Cry Units for Pathologies Identification in Recently Born Babies","authors":"O. F. Reyes-Galaviz, S. D. Cano-Ortiz, C. Reyes-García","doi":"10.1109/MICAI.2008.73","DOIUrl":"https://doi.org/10.1109/MICAI.2008.73","url":null,"abstract":"This work presents an infant cry automatic recognizer development, with the objective of classifying two kinds of infant cries, normal and pathological, from recently born babies. Extraction of acoustic features is used such as MFCC (Mel Frequency Cepstral Coefficients), obtained from Infant Cry Units sound waves, and a genetic feature selection system combined with a feed forward input delay neural network, trained by adaptive learning rate back-propagation. For the experiments, recordings from Cuban and Mexican babies are used, classifying normal and pathological cry in three different experiments; Cuban babies, Mexican Babies, and Cuban & Mexican babies. It is also shown a comparison between a simple traditional feed-forward neural network and another complemented with the proposed genetic feature selection system, to reduce the feature input vectors. In this paper the whole process is described; in which the acoustic features extraction is included, the hybrid system design, implementation, training and testing. The results from some experiments are also shown, in which the infant cry recognition rate obtained is of up to 100% using our genetic system.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131146234","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":"Exploring Unknown Environments with Multiple Robots","authors":"L. A. Sanchez, P. A. Toriz, M.A. Osorio L","doi":"10.1109/MICAI.2008.21","DOIUrl":"https://doi.org/10.1109/MICAI.2008.21","url":null,"abstract":"There are numerous studies to find efficient ways for exploring and generating maps for unknown environments. Unfortunately, most of the studies deal with single robots. In this paper, we propose a cooperative exploration strategy for mobile robots. The extension of the SRT method to the case of multiple robots is essentially a parallelization of the basic method. To this simple extension, the following functionalities were added to it: cooperation to increase the efficiency, coordination to avoid conflicts and communication to cooperate and to coordinate. We present simulation results to show the performance of this proposed technique.","PeriodicalId":301028,"journal":{"name":"2008 Seventh Mexican International Conference on Artificial Intelligence","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-10-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133338029","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}