MicroRNAs (miRNAs) are a group of small noncoding RNA (ncRNA) molecules that play an important role in biological functions. This paper proposes a microRNA prediction application, which is based on the multi-layer hierarchical MapReduce framework and provides four prediction workflows for four different datasets: miRNA-like sequences, miRNA cluster sequences, unknown miRNA sequences and the next generation sequencing (NGS) sequences. These workflows include four core procedures for finding the genome location, applying the biological filtering criteria and a genetic algorithm based pre-miRNA classifier. Each procedure works as a MapReduce task and uses JSON format to translate the MapReduce output to the next MapReduce procedure. Experimental results show that the proposed miRNA predictor not only achieves high sensitivity and accuracy, but also has ability to process more than million sequences in acceptable time by relying on the multi-layer hierarchical MapReduce framework.

In this paper, the Multiple Trajectory Search (MTS) is presented for single objective constrained real-parameter optimization problems. The MTS uses multiple agents to search the solution space concurrently. Each agent does an iterated region search using one of three candidate region search methods. By choosing a region search method that best fits the landscape of a solution's neighborhood, an agent may find its way to a local optimum or the global optimum. We applied the MTS to the eighteen benchmark problems designed for the CEC 2010 Competition on Single Objective Constrained Real-Parameter Optimization. The results are quite promising.

For some difficult problems, artificial neural network (ANN) ensemble classifiers, instead of a single ANN classifier, are considered. The ensemble usually has better generalization performance than any individual network for classification problems. But, it is not easy to construct the ANN ensemble. In the previous study, the authors presented the systematic trajectory search algorithm (STSA) to train the ANN and the experimental results revealed the performance of the STSA is good. Based on the STSA, an evolutionary algorithm for variable-sized ANN ensemble construction, called the VSEC, is proposed in this paper. A penalty term is added to the error function in order to guarantee the diversity of the ensemble. Besides, a variable-sized ANN ensemble construction method, based on three operations, is proposed to update the ensemble members. The performance of the proposed algorithm is evaluated by applying it to train a class of feedforward neural networks to solve the large n-bit parity problems. By comparing with the previous studies, the experimental results revealed that the neural network ensemble classifiers trained by the VSEC have very good classification ability.

Many real-world optimization problems involve multiple conflicting objectives. Therefore, multi-objective optimization has attracted much attention of researchers and many algorithms have been developed for solving multi-objective optimization problems in the last decade. In this paper the multiple trajectory search (MTS) is presented and successfully applied to thirteen unconstrained and ten constrained multi-objective optimization problems. These problems constitute a test suite provided for competition in the special session & competition on performance assessment of constrained/bound constrained multi-objective optimization algorithms in CEC 2009. In the multiple trajectory search, a set of uniformly distributed solutions is first generated. These solutions will be separated into foreground solutions and background solutions. The search is focuses mainly on foreground solutions and partly on background solutions. The MTS chooses and applies one of the three local search methods on solutions iteratively. The three local search methods begin their search in a very large ldquoneighborhoodrdquo. Then the neighborhood contracts step by step until it reaches a pre-defined tiny size, after then, it is reset to its original size. By utilizing such size-varied neighborhood searches, the MTS effectively solves the multi-objective optimization problems.

The location problems are important problems in the business world and have been widely studied. The p-median problem is one of the location problems. In this study, we propose an orthogonal array based swap method to solve the p-median problem. A local search method called the OA-interchange is designed. It utilizes the OA array and the Taguchi method to generate a set of solutions, and among this set of solutions, it finds the best one. The proposed OA-based swap method consists of iterative applications of the OA-interchange. Moreover, the proposed method has a scheme to control the strength of diversification and the strength of intensification. Testing of the OA-based swap method on the OR-Library and the fl1400 benchmarks reveals that the proposed method is competitive with other state-of-the-art methods reported in the literature.

In this paper, the resource-constrained project scheduling problem with multiple execution modes for each activity is explored. This paper aims to find a schedule of activities such that the makespan of the schedule is minimized subject to the precedence and resource constraints. We present a two-phase genetic local search algorithm that combines the genetic algorithm and the local search method to solve this problem. The first phase aims to search globally for promising areas, and the second phase aims to search more thoroughly in these promising areas. A set of elite solutions is collected during the first phase, and this set, which acts as the indication of promising areas, is utilized to construct the initial population of the second phase. By suitable applications of the mutation with a large mutation rate, the restart of the genetic local search algorithm, and the collection of good solutions in the elite set, the strength of intensification and diversification can be properly adapted and the search ability retained in a long term. Computational experiments were conducted on the standard sets of project instances, and the experimental results revealed that the proposed algorithm was effective for both the short-term (with 5000 schedules being evaluated) and the long-term (with 50000 schedules being evaluated) search in solving this problem.

In this paper, the multiple trajectory search (MTS) is presented for large scale global optimization. The MTS uses multiple agents to search the solution space concurrently. Each agent does an iterated local search using one of three candidate local search methods. By choosing a local search method that best fits the landscape of a solutionpsilas neighborhood, an agent may find its way to a local optimum or the global optimum. We applied the MTS to the seven benchmark problems designed for the CEC 2008 Special Session and Competition on large scale global optimization.

In recent years, many algorithms for solving multiobjective (MO) optimization problems were proposed. Some studies on the design of multiobjective test problems and the performance evaluation of algorithms were also suggested. In this paper, we proposed a novel searching algorithm called the multiple trajectory search (MTS). The MTS uses multiple agents to search the solution space concurrently. Each agent does an iterated local search using one of four candidate local search methods. By choosing a local search method that best fits the landscape of a solution's neighborhood, an agent may find its way to a local optimum or the global optimum. We applied the MTS to the multiobjective optimization and tested it on the 13 benchmark problems provided for competition in the Special Session & Competition on Performance Assessment of Multi-Objective Optimization Algorithms in CEC2007.

In this work, the systematic trajectory search algorithm (STSA) is proposed to train the connection weights of the feedforward neural networks. The STSA utilizes the orthogonal array (OA) to uniformly generate the initial population in order to globally explore the solution space, then it applies a novel trajectory search method that can exploit the promising area thoroughly. The performance of the proposed STSA is evaluated by applying it to train a class of feedforward neural networks to solve the n-bit parity problem and the classification problem on two medical datasets from the UCI machine learning repository. By comparing with the previous studies, the experimental results revealed that the neural networks trained by the STSA have very good classification ability.

In this work, a two-phase genetic local search algorithm is proposed to train the connection weights of the feedforward neural networks. Various evolutionary algorithms including evolution strategies, evolutionary programming, and genetic algorithms had been proposed to train the weights and/or architectures of neural networks. But, most of them did not have an effective crossover operator. In the proposed algorithm, an effective orthogonal array crossover operator was used. Two classes of architectures were adopted and the classification capability of these two neural network architectures trained by the proposed two-phase genetic local search algorithm was shown by applying them to the n-bit parity problem.

New technologies are continuously being applied to high-speed networks such as distribution systems, on-line video-services, and some other applications. These services must ensure stable QoS (quality of service) and provide acceptable link costs, time delay, bandwidth and pack loss constraints, essentially a multicast routing problem. Computing such multicast routing problems is an NP-complete problem. In this paper, we propose a genetic algorithm using fuzzy selection (GFS) to address the problem of QoS under delay constraints. The GFS algorithm finds a multicast tree with minimum cost under delay constraints..

Although the side-match vector quantizer (SMVQ) reduces the bit rate, the image coding quality by SMVQ generally degenerates as the gray level transition across the boundaries of the neighboring blocks is increasing or decreasing. This study presents a smooth side-match method to select a state codebook according to the smoothness of the gray levels between neighboring blocks. This method achieves a higher PSNR and better visual perception than SMVQ does for the same bit rate. Moreover, to design codebooks, a genetic clustering algorithm that automatically finds the appropriate number of clusters is proposed. The proposed smooth side-match classified vector quantizer (SSM-CVQ) is thus a combination of three techniques: the classified vector quantization, the variable block size segmentation and the smooth side-match method. Experimental results indicate that SSM-CVQ has a higher PSNR and a lower bit rate than other methods. Furthermore, the Lena image can be coded by SSM-CVQ with 0.172 bpp and 32.49 dB in PSNR.

The full-search vector quantization suffers from spending much time searching the whole codebook sequentially. Several tree-structured vector quantizers had been proposed. But almost all trees used are binary trees and hence the training samples contained in each node are forced to be divided into two clusters artificially. We present a general-tree-structured vector quantizer that is based on a genetic clustering algorithm. This genetic clustering algorithm can divide the training samples contained in each node into more natural clusters. A distortion threshold is used to guarantee the quality of coding. Also, Huffman coding is used to achieve the optimal bit rate after the general-tree-structured coder was constructed. An experiment on speech coding was conducted. A comparison of the performance of this vector quantizer and the other two tree-structured vector quantizers is also given.

Almost all form documents contain line segments. We propose an efficient method to recognize the form document that contains at least one line segment. Our method is based on an efficient representation model of the form. The representation model uses three types of line segments to represent a form. All line segments are normalized and sorted after they are extracted. The normalization and sorting not only solve the problems of magnification and contraction but also provide a unified and efficient way of matching between forms. To make the recognition method more robust, fuzzy matching is used. Experimental results show the effectiveness and efficiency of the method.

A new approach is proposed to segment off-line handwritten Chinese characters. Many papers have been published on the off-line recognition of Chinese characters, and almost all of them focus on the recognition of isolated Chinese characters. The segmentation of text into characters was rarely discussed. The segmentation is an important preprocess of the off-line Chinese character recognition because correct recognition of characters relies on correct segmentation of characters. In handwritten Chinese characters, characters may be written to touch each other or to overlap with each other, therefore, the segmentation problem is not an easy one. In this paper, we present a novel method which uses strokes to build stroke bounding boxes first. Then, the knowledge-based merging operations are used to merge those stroke bounding boxes and finally, a dynamic programming method is applied to find the best segmentation boundaries. A series of experiments show that our method is very effective for off-line handwritten Chinese character segmentation.

A heuristic algorithm for the recognition of printed Chinese characters is presented. Preprocessing consists of identifying individual straight line primitive strokes of a Chinese character, and then identifying the sequence of occurrence of these primitive strokes in the course of two orthogonal and one diagonal scans. The results of the three scans are three ordered sets of primitive strokes that can be binary encoded. These three types of codes are called feature codes. The feature codes are used in the training phase and recognition phase by hashing. An experiment that trained on 13053 characters of a single font shows that only six pairs of characters have coincident feature codes. The recognition speed of this experiment is 44.4 milliseconds of 80386 CPU time per character (1,350 characters per minute excluding disk I/O time). The recognition rate is from 97.22% to 98.4%.>

We describe a new method for representation of an image pattern, which we call the reduced special interval graph (RSIG). Any binary image pattern can be easily converted into a RSIG. Based on the RSIG, we can enlarge the scope of vision and process a much greater zone of the image. This helps us properly extract the feature of the image and identify the image pattern. We apply the RSIG to help us extract the strokes of Chinese characters by incorporating some knowledge about the structure of Chinese characters. We found this method can not only heuristically extract strokes but also heuristically eliminate noises including those added to strokes for the artistic sake. Experimental results reveal that the method based on the RSIG can extract the strokes of Chinese characters effectively and efficiently. Moreover, the RSIG can be applied to many other application areas, and it is an effective representation method in pattern recognition and image processing.>