Current Issue : January - March Volume : 2013 Issue Number : 1 Articles : 5 Articles
We have developed a method for spatiotemporally integrating databases of shop and company information, such as from a digital\r\ntelephone directory, spatiotemporally, in order to monitor dynamic urban transformations in a detailed manner. To realize this,\r\nan additional method is necessary to verify the identicalness of different instances of Japanese shop and company names that\r\nmight contain fluctuations of description. In this paper, we discuss a method that utilizes an n-gram model for comparing and\r\nidentifying Japanese words. The processing accuracy was improved through developing various kinds of libraries for frequently\r\nappearing words, and using these libraries to clean shop and company names. In addition, the accuracy was greatly and novelty\r\nimproved through the detection of those frequently appearing words that appear eccentrically across both space and time. By\r\nutilizing natural language processing (NLP), our method incorporates a novel technique for the advanced processing of spatial\r\nand temporal data....
Evolutionary methods are well-known techniques for solving nonlinear constrained optimization problems. Due to the exploration\r\npower of evolution-based optimizers, population usually converges to a region around global optimum after several generations.\r\nAlthough this convergence can be efficiently used to reduce search space, in most of the existing optimization methods,\r\nsearch is still continued over original space and considerable time is wasted for searching ineffective regions. This paper proposes\r\na simple and general approach based on search space reduction to improve the exploitation power of the existing evolutionary\r\nmethods without adding any significant computational complexity. After a number of generations when enough exploration\r\nis performed, search space is reduced to a small subspace around the best individual, and then search is continued over this\r\nreduced space. If the space reduction parameters (red gen and red factor) are adjusted properly, reduced space will include global\r\noptimum. The proposed scheme can help the existing evolutionary methods to find better near-optimal solutions in a shorter\r\ntime. To demonstrate the power of the new approach, it is applied to a set of benchmark constrained optimization problems and\r\nthe results are compared with a previous work in the literature....
Two artificial intelligence techniques, namely artificial neural network (ANN)\r\nand genetic algorithm (GA) were combined to be used as a tool for optimizing the covalent\r\nimmobilization of cellulase on a smart polymer, Eudragit L-100. 1-Ethyl-3-(3-\r\ndimethyllaminopropyl) carbodiimide (EDC) concentration, N-hydroxysuccinimide (NHS)\r\nconcentration and coupling time were taken as independent variables, and immobilization\r\nefficiency was taken as the response. The data of the central composite design were used to\r\ntrain ANN by back-propagation algorithm, and the result showed that the trained ANN\r\nfitted the data accurately (correlation coefficient R2 = 0.99). Then a maximum\r\nimmobilization efficiency of 88.76% was searched by genetic algorithm at a EDC\r\nconcentration of 0.44%, NHS concentration of 0.37% and a coupling time of 2.22 h, where\r\nthe experimental value was 87.97 �± 6.45%. The application of ANN based optimization by\r\nGA is quite successful....
Biometric pattern recognition emerged as one of the predominant research directions in modern security systems. It plays a crucial\r\nrole in authentication of both real-world and virtual reality entities to allow system to make an informed decision on granting\r\naccess privileges or providing specialized services. The major issues tackled by the researchers are arising from the ever-growing\r\ndemands on precision and performance of security systems and at the same time increasing complexity of data and/or behavioral\r\npatterns to be recognized. In this paper, we propose to deal with both issues by introducing the new approach to biometric pattern\r\nrecognition, based on chaotic neural network (CNN). The proposed method allows learning the complex data patterns easily while\r\nconcentrating on the most important for correct authentication features and employs a unique method to train different classifiers\r\nbased on each feature set. The aggregation result depicts the final decision over the recognized identity. In order to train accurate\r\nset of classifiers, the subspace clustering method has been used to overcome the problem of high dimensionality of the feature\r\nspace. The experimental results show the superior performance of the proposed method....
This paper focuses on designing a tool for guiding a group of people out of a public building when they are faced with dangerous\r\nsituations that require immediate evacuation. Despite architectural attempts to produce safe floor plans and exit door placements,\r\npeople will still commit to fatal route decisions. Since they have access to global views, we believe supervisory people in the control\r\nroom can use our simulation tools to determine the best courses of action for people. Accordingly, supervisors can guide people\r\nto safety. In this paper, we combine Coulomb�s electrical law, graph theory, and convex and centroid concepts to demonstrate\r\na computer-generated evacuation scenario that divides the environment into different safe boundaries around the locations\r\nof each exit door in order to guide people through exit doors safely and in the most expedient time frame. Our mechanism\r\ncontinually updates the safe boundaries at each moment based on the latest location of individuals who are present inside the\r\nenvironment. Guiding people toward exit doors depends on the momentary situations in the environment, which in turn rely on\r\nthe specifications of each exit door. Our mechanism rapidly adapts to changes in the environment in terms of moving agents and\r\nchanges in the environmental layout that might be caused by explosions or falling walls....
Loading....