{"title":"How to read the web in portuguese using the never-ending language learner's principles","authors":"M. Duarte, Estevam Hruschka","doi":"10.1109/ISDA.2014.7066260","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066260","url":null,"abstract":"An alternative to the traditional single function approximation method is the never-ending learning (NEL) approach i.e., a learning paradigm in which, the learner, in an autonomous way, manages to constantly, incrementally and continuously evolve with time. But, most important than just keep evolving, in this new paradigm acquired knowledge can, in a dynamic way, be used to expand the scope and improve the performance of the learning task as a whole. The first Never-Ending Learning system reported in the literature, which is called NELL (Never-Ending Language Learner), is applied to the task of autonomously building a knowledge base as a result of reading the web. Results reported so far reveal that very good results have been achieved when NELL is reading the web in English. When trying, however, to perform the same Machine Reading task (the task of reading the web) applied to web pages written in Portuguese, the previous reported approaches could not keep up with the good performance achieved in English. In this paper we describe an approach, different from previously proposed in the literature, and we present empirical results that corroborate the hypothesis that working on the preprocessing task of a sufficiently big corpus can be key to allow us to use the very same architecture proposed in NELL, but applied to the idea of reading the web in Portuguese (reading, and extracting knowledge from web pages written in Portuguese).","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"13 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116647607","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 Hyper-heuristic approach towards mitigating Premature Convergence caused by the objective fitness function in GP","authors":"Anisa W. Ragalo, N. Pillay","doi":"10.1109/ISDA.2014.7066272","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066272","url":null,"abstract":"This manuscript proposes a hyper-heuristic approach towards mitigating Premature Convergence caused by objective fitness in Genetic Programming (GP). The objective fitness function used in standard GP has the potential to profoundly exacerbate Premature Convergence in the algorithm. Accordingly several alternative fitness measures have been proposed in GP literature. These alternative fitness measures replace the objective function, with the specific aim of mitigating this type of Premature Convergence. However each alternative fitness measure is found to have its own intrinsic limitations. To this end the proposed approach automates the selection of distinct fitness measures during the progression of GP. The power of this methodology lies in the ability to compensate for the weaknesses of each fitness measure by automating the selection of the best alternative fitness measure. Our hyper-heuristic approach is found to achieve generality in the alleviation of Premature Convergence caused by objective fitness. Vitally the approach is unprecedented and highlights a new paradigm in the design of GP systems.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124588692","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":"The weighted Support Vector Machines for the stock turning point prediction","authors":"P. Chang, Jheng-Long Wu","doi":"10.1109/ISDA.2014.7066264","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066264","url":null,"abstract":"This research treats the stock turning point prediction as the imbalanced data classification problems and proposes the evolving weighted support vector machines (EW-SVM) system that leads to superior predictions upon the direction-of-change of the market. However, many parameters of the w-SVM model have to be decided by the user beforehand. Therefore, the EW-SVM system combining both w-SVM with GA is applied to forecast stock turning points. In the experimental results, the EW-SVM system is used to predict stock turning points and is compared to other prediction models including the SVM, DT, NB and k-NN models. These experimental results show that our EW-SVM system has the better performance among all the different approaches.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114821934","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":"Dimension reduction methods in graph drawing problem","authors":"Lukás Zaorálek, T. Buriánek, V. Snás̃el","doi":"10.1109/ISDA.2014.7066252","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066252","url":null,"abstract":"Graph is a standard data structures mainly used to impose relations in a connected network of objects. Graphs are drawn mostly in ℝ2 space with vertices as points and edges as straight lines connecting vertices. Methods for reduction of dimension are intended for projecting high-dimensional data to a new representation in low-dimensional space. Objective of this work is to use selected dimension reduction methods as a main step in construction of a graph drawing. Graph drawings by selected methods are compared to each other and also to the classical approach presented by Kamada and Kawai.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126465167","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 novel evolutionary algorithm with indirect representation and extended nearest neighbor constructive procedure for solving routing problems","authors":"Jiří Kubalík, Michal Snizek","doi":"10.1109/ISDA.2014.7066254","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066254","url":null,"abstract":"This paper presents a novel evolutionary algorithm for solving routing and sequencing problems. It builds directly on the observation that the optimal solution is composed mostly of short and low-cost links. It uses an indirect representation and an extended nearest neighbor constructive procedure. The representation scheme is redundant making it possible to have multiple attractors in the search space representing the same optimal solution. The order-based crossover is used that allows for combining partial solutions contained in parental individuals. Further, an adaptive iterated scheme is used to allow for escaping from a region of attraction of a local optimum. Proof-of-concept experiments have been carried out on the classical TSP with data sets ranging from 100 to 2392 nodes. The proposed algorithm was compared with two other relevant EAs. The achieved results clearly show the proposed method is competitive to and better than the compared EAs.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"488 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132246263","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":"Transferring knowledge between learning systems","authors":"A. Paplinski, William M. Mount","doi":"10.1109/ISDA.2014.7066287","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066287","url":null,"abstract":"We consider a pair of multimodal integration systems, a teacher and a learner and demonstrate how the knowledge is transferred from the teacher to the learner in an incremental fashion. By combining effectors to a perceptual integration network influenced by hypothesised endogenous “action thoughts”, we present a simplified model of how a universal or common coding scheme can be used to represent dual auditory and visual sensory pathways and integrate these with articulatory and gestural forms of motor control. As an example the system learns visual representation of Chinese characters and their related Mandarin pronunciation.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131669307","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":"Ensemble relations for resource allocation tasks","authors":"M. Köppen, K. Ohnishi, M. Tsuru","doi":"10.1109/ISDA.2014.7066256","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066256","url":null,"abstract":"In general resource allocation problems there are usually different notions of optimality. While these usually refer to extreme elements of a binary relation, there are no further means to prefer the choice of one relation over the other. Here we consider a combined approach, called ensemble relations, where for a number of relations the larger count of domain element x being in relation to y than vice versa gives another specification of a binary relation. Extreme values of that relation are considered as combined solutions to the allocation problem at hand. While ensemble relations will not be cycle-free in the general case, in practical circumstances cycles are either rare or absent. The approach is demonstrated on the wireless channel allocation problem with an ensemble relation composed of maximal minimum, maximal product and maximal sum. As a result of simulations it can be seen that the selection of the ensemble relations is strongly specified and tends to equal the selection by product maximization.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124743758","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 optimal line search algorithm for the conjugate gradient method","authors":"Toru Yamazato","doi":"10.1109/ISDA.2014.7066265","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066265","url":null,"abstract":"A new line search technique for the conjugate gradient (CG) method, critical point approximation (CPA), is introduced. The CPA is an elaborately revised version of the parabolic interpolation (PI). The new algorithm evaluates the function and gradient at just one point for each line search, while the conventional PI requires two points. Although the CG usually evaluates the gradient at each critical point found in the iteration, the CG with CPA approximates the gradient, using information obtained for the line search. The new algorithm is implemented in an artificial neural network program for experiment and comparison. The results show that the CG method with the new algorithm converges significantly faster than that with the conventional PI. Under an optimistic assumption, the author explains that the CPA is an optimal line search algorithm for the CG method. Issues regarding the precision and computation time of the line search are discussed.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127222044","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":"Heart rate estimation based on camera image","authors":"T. Kitajima, SangOn Choi, E. Murakami","doi":"10.1109/ISDA.2014.7066275","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066275","url":null,"abstract":"The remote measurement of the heart rate while the user is watching TV can bring many promising applications to our home such as user's preference estimation, automatic digest edition and fitness. We developed a non-contact heart rate measurement method using camera image so that users can measure the heart rate without any attachments. We focused attention on the blood oxygenated hemoglobin which absorbs the green light and measures the heart rate by detecting the variation of the green color intensity of a person's face image. In previous research, it was not possible to measure the heart rate with precision when a person was in movement. In this proposed method, we can expect that it will be applied to various applications since we can accurately measure the heart rate even while moving the face. The results showed a performance of detection error smaller than 3 bpm for lightning conditions over 500 lux and distances up to 6.0 m.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132944941","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":"Extraction of arbitrary text in natural scene image based on stroke width transform","authors":"J. Jameson, S. Abdullah","doi":"10.1109/ISDA.2014.7066257","DOIUrl":"https://doi.org/10.1109/ISDA.2014.7066257","url":null,"abstract":"Text extraction plays an important role in numerous applications. Research on its method still need to be improved in order to achieve better performance, to increase the reliability of text extraction system and to deal with complex cases of text extraction. The majority of the text extraction methods are focusing on horizontal and near horizontal text lines; however, text in natural scene might be in arbitrary line in real time. Thus, this paper aims to solve the issue of extracting the arbitrary oriented text by suggesting a method for text detection and localization based on the Stroke Width Transform. The proposed method is tested on an arbitrary text dataset and ICDAR dataset. The result of the experiment shows that the proposed method adapts well to the arbitrary text.","PeriodicalId":328479,"journal":{"name":"2014 14th International Conference on Intelligent Systems Design and Applications","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123301786","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}