International Journal of Computational Intelligence and Applications

This paper presents a study on the application of a hybrid genetic algorithm (HGA) to an extended instance of the Vehicle Routing Problem. The actual problem is a complex real-life vehicle routing problem regarding the distribution of products to customers. A non homogenous fleet of vehicles with limited capacity and allowed travel time is available to satisfy the stochastic demand of a set of different types of customers with earliest and latest time for servicing. The objective is to minimize distribution costs respecting the imposed constraints (vehicle capacity, customer time windows, driver working hours and so on). The approach for solving the problem was based on a "cluster and route" HGA. Several genetic operators, selection and replacement methods were tested until the HGA became efficient for optimization of a multi-extrema search space system (multi-modal optimization). Finally, High Performance Computing (HPC) has been applied in order to provide near-optimal solutions in a sensible amount of time.

In this paper, the effectiveness of three different operating strategies applied to the Fuzzy ARTMAP (FAM) neural network in pattern classification tasks is analyzed and compared. Three types of FAM, namely average FAM, voting FAM, and ordered FAM, are formed for experimentation. In average FAM, a pool of the FAM networks is trained using random sequences of input patterns, and the performance metrics from multiple networks are averaged. In voting FAM, predictions from a number of FAM networks are combined using the majority-voting scheme to reach a final output. In ordered FAM, a pre-processing procedure known as the ordering algorithm is employed to identify a fixed sequence of input patterns for training the FAM network. Three medical data sets are employed to evaluate the performances of these three types of FAM. The results are analyzed and compared with those from other learning systems. Bootstrapping has also been used to analyze and quantify the results statistically.

Generating high quality code for embedded processors is made difficult by irregular architectures and highly encoded parallel instructions. Rather than dealing with the target machine at every stage of the compilation, a promising new methodology employs generic algorithms to optimize code for an idealized abstraction of the true target machine. This code, called reference code, is then mapped to the real instruction set by enhanced genetic algorithms. One perturbs the original schedule to find a number of alternative (parallel) instruction sequences, and the other evolves feasible register assignments, if possible, for each sequence. This paper describes the strategy for mapping idealized code into actual code. The COGEN(T) system employs this methodology to produce good code for different commercial DSPs and ASIPs.

A typical biometric system has three distinct phases. These are biometric data acquisition, feature extraction, and decision-making. The first step, the acquisition phase, is extremely important. If high quality images are not obtained, the next phase cannot operate reliably. Fingerprint recognition remains as one of the most prominent biometric identification methods. In this paper, we develop a prototype optical-based fingerprints data acquisition system using a CCD digital still camera to capture a complete impression of finger area required for accurately identifying an individual and present an image-based approach for online fingerprint recognition with the objective to increase the overall matching performance. The fingerprint images are matched based on features extracted with an adaptive learning vector quantization (LVQ) neural network to yield peak recognition of 98.6% for a random set of 300 test prints (100 fingers × 3 images). This system can be adopted as a multi-modal biometrics where two or more fingers are matched.

A heuristic, automatic facial feature extraction approach is presented in this paper. The method is based on the edge density distribution of the image, containing non-occluded, nearly frontal view of one or more faces. In the preprocessing stage, a face is approximated to an ellipse, and genetic algorithm is applied to search for the best ellipse region match. In the feature extraction stage, genetic algorithm is applied to extract the facial features, such as the eyes (with eyebrows), nose and mouth, in the predefined subregions. The simulation results validates that the proposed method is capable of automatically extracting features from various video images effectively under natural lighting environments and in the presence of complex backgrounds, certain amount of artificial noise and of multi-face oriented with angles. This preliminary study advanced from a rich literature provides robust facial feature detection under certain variations in lighting conditions and backgrounds.

This paper shows how deliberative agents can be built by means of a case-based reasoning system. The concept of deliberative agent is introduced and the case-based reasoning model is presented. Once the advantages and disadvantages of such agents have been discussed, it will be shown how to solve some of their inconveniences, especially those related to their implementation and adaptation. The World Wide Web has emerged as one of the most popular vehicle for disseminating and sharing information through computer networks; a distributed agent-based solution for e-business, in which such agents have been used, is also presented and evaluated in this paper.

This paper proposes a novel application of fuzzy logic to web data mining for two basic problems of a website: popularity and satisfaction. Popularity means that people will visit the website while satisfaction refers to the usefulness of the site. We will illustrate that the popularity of a website is a fuzzy logic problem. It is an important characteristic of a website in order to survive in Internet commerce. The satisfaction of a website is also a fuzzy logic problem that represents the degree of success in the application of information technology to the business. We propose a framework of fuzzy logic for the representation of these two problems based on web data mining techniques to fuzzify the attributes of a website.