International Journal of Computational Intelligence and Applications

In this paper, a method that uses RBF-BP neural network to generate fingerprint database (FD) is proposed to improve the quality. The reference points in the database present regular tetrahedron distribution in three-dimensional space. To improve the accuracy of selecting which points are considered to locate currently and estimating their weights, two positioning algorithms based on signal strength difference values (SSDV) are proposed through analyzing the characteristic of difference values between mobile receiver and reference points. The first one is fuzzy logic algorithm (FLA). It uses different fuzzy logic models to calculate the weights of considered points. The second one is RBF-BP neural network algorithm (NNA). It uses different neural network models to estimate the spatial distances between mobile receiver and reference points. The points which have small sum of distances are considered. Their weights are calculated by a newly proposed method. The proposed algorithms use more than one weight to describe the distance to one considered point, which is more accurate. The test results demonstrate the improvement and effectiveness of proposed methods by comparing with other existing methods.

In this paper, we present a parallel hybrid metaheuristic that combines the strengths of the particle swarm optimization (PSO) and the genetic algorithm (GA) to produce an improved path-planner algorithm for fixed wing unmanned aerial vehicles (UAVs). The proposed solution uses a multi-objective cost function we developed and generates in real-time feasible and quasi-optimal trajectories in complex 3D environments. Our parallel hybrid algorithm simulates multiple GA populations and PSO swarms in parallel while allowing migration of solutions. This collaboration between the GA and the PSO leads to an algorithm that exhibits the strengths of both optimization methods and produces superior solutions. Moreover, by using the "single-program, multiple-data" parallel programming paradigm, we maximize the use of today's multicore CPU and significantly reduce the execution time of the parallel program compared to a sequential implementation. We observed a quasi-linear speedup of 10.7 times faster on a 12-core shared memory system resulting in an execution time of 5 s which allows in-flight planning. Finally, we show with statistical significance that our parallel hybrid algorithm produces superior trajectories to the parallel GA or the parallel PSO we previously developed.

Feature selection is a multi-objective problem, where the two main objectives are to maximize the classification accuracy and minimize the number of features. However, most of the existing algorithms belong to single objective, wrapper approaches. In this work, we investigate the use of binary particle swarm optimization (BPSO) and probabilistic rough set (PRS) for multi-objective feature selection. We use PRS to propose a new measure for the number of features based on which a new filter based single objective algorithm (PSOPRSE) is developed. Then a new filter-based multi-objective algorithm (MORSE) is proposed, which aims to maximize a measure for the classification performance and minimize the new measure for the number of features. MORSE is examined and compared with PSOPRSE, two existing PSO-based single objective algorithms, two traditional methods, and the only existing BPSO and PRS-based multi-objective algorithm (MORSN). Experiments have been conducted on six commonly used discrete datasets with a relative small number of features and six continuous datasets with a large number of features. The classification performance of the selected feature subsets are evaluated by three classification algorithms (decision trees, Naïve Bayes, and k-nearest neighbors). The results show that the proposed algorithms can automatically select a smaller number of features and achieve similar or better classification performance than using all features. PSOPRSE achieves better performance than the other two PSO-based single objective algorithms and the two traditional methods. MORSN and MORSE outperform all these five single objective algorithms in terms of both the classification performance and the number of features. MORSE achieves better classification performance than MORSN. These filter algorithms are general to the three different classification algorithms.

The Artificial Bee Colony (ABC) algorithm is a recently introduced swarm intelligence algorithm that has been successfully applied on numerous and diverse optimization problems. However, one major problem with ABC is its premature convergence to local optima, which often originates from its insufficient degree of explorative search capability. This paper introduces ABC with Improved Explorations (ABC-IX), a novel algorithm that modifies both the selection and perturbation operations of the basic ABC algorithm in an explorative way. First, an explorative selection scheme based on simulated annealing allows ABC-IX to probabilistically accept both better and worse candidate solutions, whereas the basic ABC can accept better solutions only. Second, a self-adaptive strategy enables ABC-IX to automatically adapt the perturbation rate, separately for each candidate solution, to customize the degree of explorations and exploitations around it. ABC-IX is evaluated on several benchmark numerical optimization problems and results are compared with a number of state-of-the-art evolutionary and swarm intelligence algorithms. Results show that ABC-IX often performs better optimization than most other algorithms in comparison on most of the problems.

Portfolio selection is a vital research field in modern finance. Multi-objective portfolio optimization problem is the portfolio selection process that results in the highest expected return rate and the lowest identified risk among the various financial assets. This paper proposes a model that can efficiently suggest a portfolio that is worth investing. First, a cluster analysis model is introduced in order to categorize a huge amount of stock data into several groups based on their associated return rate and the risk. Several validity indexes are used to select the optimal number of clusters/stocks to be included in the portfolio. Finally, the multi-objective genetic algorithm is used to build portfolio optimization with highest return rate and lowest risk. The proposed model is tested on the data obtained from the Stock Exchange of Thailand.

A big deal for current research on automatic speaker recognition is the effectiveness of the speaker modeling techniques for the talkers, because they have their own speaking style, depending on their specific accents and dialects. This paper investigates on the influence of the dialect and the size of database on the text independent speaker verification task using the SVM and the hybrid GMM/SVM speaker modeling. The Principal Component Analysis (PCA) technique is used in the front-end part of the speaker recognition system, in order to extract the most representative features. Experimental results show that the size of database has an important impact on the SVM and GMM/SVM based speaker verification performances, while the dialect has no significant effect. Applying PCA dimensionality reduction improves the recognition accuracy for both SVM and GMM/SVM based recognition systems. However, it did not give an obvious observation about the dialect effect.