Yanxin Huang

SVM Learning from Imbalanced Data by GA Sampling for Protein Domain Prediction

The performance of support vector machines (SVM) drops significantly while facing imbalanced datasets, though it has been extensively studied and has shown remarkable success in many applications. Some researchers have pointed out that it is difficult to avoid such decrease when trying to improve the efficient of SVM on imbalanced datasets by modifying the algorithm itself only. Therefore, as the pretreatment of data, sampling is a popular strategy to handle the class imbalance problem since it re-balances the dataset directly. In this paper, we proposed a novel sampling method based on genetic algorithms (GA) to rebalance the imbalanced training dataset for SVM. In order to evaluating the final classifiers more impartiality, AUC (area under ROC curve) is employed as the fitness function in GA. The experimental results show that the sampling strategy based on GA outperforms the random sampling method. And our method is prior to individual SVM for imbalanced protein domain boundary prediction. The accuracy of the prediction is about 70% with the AUC value 0.905.

A novel quantum swarm evolutionary algorithm for solving 0-1 knapsack problem

A novel quantum swarm evolutionary algorithm is presented based on quantum-inspired evolutionary algorithm in this article. The proposed algorithm adopts quantum angle to express Q-bit and improved particle swarm optimization to update automatically. The simulated effectiveness is examined in solving 0-1 knapsack problem.

Analysis of gene expression data: application of quantum-inspired evolutionary algorithm to minimum sum-of-squares clustering

Microarray experiments have produced a huge amount of gene expression data. So it becomes necessary to develop effective clustering techniques to extract the fundamental patterns inherent in the data. In this paper, we propose a novel evolutionary algorithm so called quantum-inspired evolutionary algorithm (QEA) for minimum sum-of-squares clustering. We use a new representation form and add an additional mutation operation in QEA. Experiment results show that the proposed algorithm has better global search ability and is superior to some conventional clustering algorithms such as k-means and self-organizing maps.

Inferring gene regulatory networks by singular value decomposition and gravitation field algorithm.

Reconstruction of gene regulatory networks (GRNs) is of utmost interest and has become a challenge computational problem in system biology. However, every existing inference algorithm from gene expression profiles has its own advantages and disadvantages. In particular, the effectiveness and efficiency of every previous algorithm is not high enough. In this work, we proposed a novel inference algorithm from gene expression data based on differential equation model. In this algorithm, two methods were included for inferring GRNs. Before reconstructing GRNs, singular value decomposition method was used to decompose gene expression data, determine the algorithm solution space, and get all candidate solutions of GRNs. In these generated family of candidate solutions, gravitation field algorithm was modified to infer GRNs, used to optimize the criteria of differential equation model, and search the best network structure result. The proposed algorithm is validated on both the simulated scale-free network and real benchmark gene regulatory network in networks database. Both the Bayesian method and the traditional differential equation model were also used to infer GRNs, and the results were used to compare with the proposed algorithm in our work. And genetic algorithm and simulated annealing were also used to evaluate gravitation field algorithm. The cross-validation results confirmed the effectiveness of our algorithm, which outperforms significantly other previous algorithms.

Identification of transcription factor binding sites using hybrid particle swarm optimization

Transcription factors are key regulatory elements that control gene expression. Recognition of transcription factor binding sites (TFBS) motif from the upstream region of genes remains a highly important and unsolved problem particularly in higher eukaryotic genomes. In this paper, we present a new approach for studying this challenging issue. We first formulate the binding sites motif identification problem as a combinatorial optimization problem. Then hybrid particle swarm optimization (HPSO) is proposed for solving such a problem in upstream regions of genes regulated by octamer binding factor. We have developed two local search operators and one recombination mutation operator in HPSO. Experiment results show that the proposed algorithm is effective in obtaining known TFBS motif and can produce some putative binding sites motif. The results are highly encouraging.

A Novel Method for Prediction of Protein Domain Using Distance-Based Maximal Entropy

Detecting the boundaries of protein domains has been an important and challenging problem in experimental and computational structural biology. In this paper the domain detection is first taken as an imbalanced data learning problem. A novel undersampling method using distance-based maximal entropy in the feature space of SVMs is proposed. On multiple sequence alignments that are derived from a database search, multiple measures are defined to quantify the domain information content of each position along the sequence. The overall accuracy is about 87% together with high sensitivity and specificity. Simulation results demonstrate that the utility of the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general imbalanced datasets.

A BOUNDARY METHOD TO SPEED UP TRAINING SUPPORT VECTOR MACHINES

Inthispaper,weproposeaboundarymethodtospeedupconstructingtheoptimal hyperplane of support vector machines. The boundary, called key vector set, is an approximate small superset of support vector set which is extracted by Parzen window density estimation in the feature space. Experimental results on Checkboard data set show that the proposed method is more efficient than some conventional methods and requires much less memory.

A fuzzy neural network system based on generalized class cover and particle swarm optimization

A voting-mechanism-based fuzzy neural network system is proposed in this paper. When constructing the network structure, a generalized class cover problem is presented and its two solving algorithm, an improved greedy algorithm and a binary particle swarm optimization algorithm, are proposed to get the class covers with relatively even radii, which are used to partition fuzzy input space and extract fewer robust fuzzy IF-THEN rules. Meanwhile, a weighted Mamdani inference mechanism is adopted to improve the efficiency of the system output and a real-valued particle swarm optimization-based algorithm is used to refine the system parameters. Experimental results show that the system is feasible and effective.

A Rough-Set-Based Fuzzy-Neural-Network System for Taste Signal Identification

A voting-mechanism-based fuzzy neural network model for identifying 11 kinds of mineral waters by its taste signals is proposed. In the model, A classification rule extracting algorithm based on discretization methods in rough sets is developed to extract fewer but robust classification rules, which are ease to be translated to fuzzy if-then rules to construct a fuzzy neural network system. Finally, the particle swarm optimization is adopted to refine network parameters. Experimental results show that the system is feasible and effective.

Training minimal uncertainty neural networks by Bayesian theorem and particle swarm optimization

A new model of minimal uncertainty neural networks (MUNN) is proposed in this article. The model is based on the Minimal Uncertainty Adjudgment to construct the structure, and it combines with Bayesian Theorem and Particle Swarm Optimization (PSO) for training. The model can determine the parameters of neural networks rapidly and efficiently. The effectiveness of the algorithm is demonstrated through the classification of the taste signals of 10 kinds of tea. The simulated results show its feasibility and validity.