Catálogo de publicaciones - libros

Geographical Information Systems (GIS) technology plays an increasingly important role in Location-Based Services (LBS), which include applications such as car navigation, tour guide information, route-guide information, and tracking systems. Most GIS applications focus on showing the stored information on a map, not providing user-oriented map services to register user’s preferred information. We propose an ontology-based approach to register and to search personal information on maps. We also implement a GIS search prototype considering user preferences using favorite food information and having a connection function to Web sites on the map using our digital map format. Our contribution is to provide a personalized service by connecting LBS/GIS services and ontology technology.

We present a filtered retrieval technique for structural information on internet-scale knowledge such as large-scale XML data in the Web. The technique evaluates XML standard queries on heterogeneous XML documents using information retrieval technique based on the relational tables in relational database management systems. The XML standard queries, XPath queries, in their general form are partial match queries, and these queries are particularly useful for searching documents of heterogeneous schemas. Thus, our technique is geared for partial match queries expressed as the queries. This indexes the elements in label paths, which are sequences of node labels, like keywords in texts, and finds the label paths matching a given query.

In this paper, we describe a rough sets approach to classification and attribute extraction of a lymphoma cancer dataset. We verify the classification accuracy of the results obtained from rough sets with a two artificial neural network based classifiers (ANNs). Our primary goal was to produce a classifier and a set of rules that could be used in a predictive manner. The dataset consisted of a number of relevant clinical variables obtained from patients that were suspected of having some form of blood based cancer (lymphoma or leukaemia). Of the 18 attributes that were collected for this patient cohort, seven were useful with respect to outcome prediction. In addition, this study was able to predict with a high degree of accuracy whether or not the disease would undergo metastases.

We present the packet wavelet coder implemented with Cellular Neural Network architecture as an example of the applications of cellular neural networks. This paper also demonstrates how the cellular neural universal machine (CNNUM) architecture can be extended to image compression. The packet wavelet coder performs the operation of image compression, aided by CNN architecture. It uses the highly parallel nature of the CNN structure and its speed outperforms traditional digital computers. In packet wavelet coder, an image signal can be analyzed by passing it through an analysis filter banks followed by a decimation process, according to the rules of packet wavelets. The Simulation results indicate that the quality of the reconstructed image is improvised by using packet wavelet coding scheme.

The major goal of this paper is to develop a practically implemental radial basis function neural network based multi-user detector for direct sequence code division in multiple access systems. This work is expected to provide an efficient solution by quickly setting up the proper number of radial basis function centers and their locations required in training. The basic idea in this research is to select all the possible radial basis function centers by using supervised -means clustering technique, select the only centers which locate near seemingly decision boundary, and reduce them further by grouping some of the centers adjacent to each other. Therefore, it reduces the computational burden for finding the proper number of radial basis function centers and their locations in the existing radial basis function based multi-user detector, and ultimately, make its implementation practical.

Environmental impact assessment of products has been a key area of research and development for sustainable product development. Many companies copy these trends and they consider environmental criteria into the product design process. Life Cycle Assessment (LCA) is used to support the decision-making for product design and the best alternative can be selected by its estimated environmental impacts and benefits. The need for analytical LCA has resulted in the development of approximate LCA. This paper presents an optimization strategy for approximate LCA using a hybrid approach which incorporate genetic algorithms (GAs) and neural networks (NNs). In this study, GAs are employed to select feature subsets to eliminate irrelevant factors and determine the number of hidden nodes and processing elements. In addition, GAs will optimize the connection weights between layers of NN simultaneously. Experimental results show that a hybrid GA and NN approach outperforms the conventional backpropagation neural network and verify the effectiveness of the proposed approach.

This paper presents a Nash genetic algorithm (Nash GA) as a solution for a network design problem, formulated as a bi-level programming model and designs a backbone topology in a hierarchical Link-State (LS) routing domain. Given that the sound backbone topology structure has a great impact on the overall routing performance in a hierarchical LS domain, the importance of this research is evident. The proposed decision model will find an optimal configuration that consists of backbone router for Backbone Provider (BP), router for Internet Service Provider (ISP), and connection link properly meeting two-pronged engineering goals: i.e., average message delay and connection costs. It is also presumed that there are decision makers for BP and the decision makers for ISP join in the decision making process in order to optimize the own objective function. The experiment results clearly indicates that it is essential to the effective operations of hierarchical LS routing domain to consider not only the engineering aspects but also specific benefits from systematical layout of backbone network, which presents the validity of the decision model and Nash GA.

The local governments of major cities in Korea are giving focus on public transportation to reduce congestion and improve accessibility in city areas. In this regards, the proper measurement of accessibility is now a key policy requirement for reorganizing the public transport network. However, Public transport routing problems are considered to be highly complicated since a multi-mode travel generates different combinations of accessibility. While most of the previous research efforts on measuring transport accessibility are found at zone-levels, an alternative approach at a finer scale such as bus links and stops is presented in this study. We propose a method to compute the optimal route choice of origin-destination pairs and measure the accessibility of the chosen mode combination based on topological configuration. The genetic algorithm is used for the computation of the journey paths, whereas the space syntax theory is used for the accessibility. The resulting accessibilities of bus stops are calibrated by O-D survey data and the proposed process is tested on a CBD of Seoul using the city GIS network data.

There are several search algorithms for the shortest path problem: the Dijkstra algorithm and Bellman-Ford algorithm, to name a few. These algorithms are not effective for dynamic traffic network involving rapidly changing travel time. The evolution program is useful for practical purposes to obtain approximate solutions for dynamic route guidance systems (DRGS). The objective of this paper is to propose an adaptive routing algorithm using evolution program (ARAEP) that is to find the multiple shortest paths within limited time when the complexity of traffic network including turn-restrictions, U-turns, and P-turns exceeds a predefined threshold.

Task scheduling is one of the core steps to effectively exploit the capabilities of cooperative control of multiple uninhabited combat aerial vehicles(UCAVs) team. The main function of multi-UCAV cooperative task scheduling is to allocate tasks which should be implemented by vehicles, and arrange the sequence of these tasks to be carried out for each vehicle simultaneously, while optimizing the team objective and satisfying various constrains of vehicles and tasks. By analyzing the characters of tasks and UCAVs, we presented a general mathematical model based on a combinatorial optimization. By defining a suitable particle structure, the Particle Swarm Optimization (PSO) algorithm was applied to solve this problem. Adaptive weight values and stochastic turbulence strategies were added to the algorithm. Simulation results indicate that the PSO algorithm proposed in this paper is a feasible and efficient approach for task scheduling in multi-UCAV cooperative control.