Search

Text classification reduces the time complexity and space complexity by dividing the complete task into the different classes. The main problem with text classification is a vast number of features extracted from the textual data. Pre-processed dataset have many features, some of which are not desirable and act only like noise. In this paper, a novel approach for optimal text classification based on nature-inspired algorithm and ensemble classifier is proposed. In the proposed model, feature selection was performed with Biogeography Based Optimization (BBO) algorithm along with ensemble classifiers (Bagging). The use of ensemble classifiers for classification delivers better performance for optimal text classification as compared to an individual classifier, and hence, improving the accuracy. Ensemble classifiers combines the weakness of individual classifiers. The individual classifiers are unable to improve the classification results when compared to ensemble classifier. The selected features, after feature selection using BBO algorithm, are classified into various classes using six machine learning classifier. The experimental results are computed on ten text classification datasets taken from UCI repository and one real-time dataset of an airlines. The four different measures namely; Accuracy, Precision, Recall and F- measure are used to validate performance of our model with ten-fold cross-validation. For feature selection process, a comparison is performed among state-of-the-art algorithms available in the literature. Results shows that BBO for feature selection outperforms the other similar nature-based optimization techniques. Our proposed approach of BBO with ensemble classifier is also compared with techniques proposed by other researchers and we analyzed the results quantitatively and qualitatively. [ABSTRACT FROM AUTHOR]

Feature selection is used as a preprocessing step in the resolution of many problems using machine learning. It aims to improve the classification accuracy, speed up the model generation process, reduce the model complexity and reduce the required storage space. Feature selection is an NP-hard combinatorial optimization problem. It is the process of selecting a subset of relevant, non-redundant features from the original ones. Among the works that are proposed to solve this problem, few are dedicated for intrusion detection. This paper presents a new feature selection approach for intrusion detection, using the Biogeography Based Optimization (BBO) algorithm. The approach which is named Guided Adaptive Binary Biogeography Based Optimization (GAB-BBO) uses the evolutionary state estimation (ESE) approach and a new migration and mutation operators. The ESE approach we propose in this paper uses the Hamming distance between the binary solutions to calculate an evolutionary factor f which determines the population diversity. During this process, fuzzy logic is used through a fuzzy classification method, to perform the transition between the numerical f value and four evolutionary states which are : convergence, exploration, exploitation and jumping out. According to the state identified, GAB-BBO adapts the algorithm behavior using a new adaptive strategy. The performances of GAB-BBO are evaluated on benchmark functions and the Kdd’99 intrusion detection dataset. In addition, we use other different datasets for further validation. Comparative study with other algorithms is performed and the results show the effectiveness of the proposed approach.

Biomarker discovery from high-dimensional data is a complex task in the development of efficient cancer diagnoses and classification. However, these data are usually redundant and noisy, and only a subset of them present distinct profiles for different classes of samples. Thus, selecting high discriminative genes from gene expression data has become increasingly interesting in the field of bioinformatics. In this paper, a discrete biogeography based optimization is proposed to select the good subset of informative gene relevant to the classification. In the proposed algorithm, firstly, the fisher-markov selector is used to choose fixed number of gene data. Secondly, to make biogeography based optimization suitable for the feature selection problem; discrete migration model and discrete mutation model are proposed to balance the exploration and exploitation ability. Then, discrete biogeography based optimization, as we called DBBO, is proposed by integrating discrete migration model and discrete mutation model. Finally, the DBBO method is used for feature selection, and three classifiers are used as the classifier with the 10 fold cross-validation method. In order to show the effective and efficiency of the algorithm, the proposed algorithm is tested on four breast cancer dataset benchmarks. Comparison with genetic algorithm, particle swarm optimization, differential evolution algorithm and hybrid biogeography based optimization, experimental results demonstrate that the proposed method is better or at least comparable with previous method from literature when considering the quality of the solutions obtained. [ABSTRACT FROM AUTHOR]

Abstract: Accurate detection of peptides binding to specific Major Histocompatibility Complex Class I (MHC-I) molecules is extremely important for understanding the underlying process of the immune system, as well as for effective vaccine design and developing immunotherapies. Development of learning algorithms and their application for binding predictions have thus speeded up the state-of-the-art in immunological research, in a cost-effective manner. In this work, we propose the application of a hybrid filter-wrapper algorithm employing concepts from the recently developed biogeography based optimization algorithm, in conjunction with SVM and Random Forests for identification of MHC-I binding peptides. In the process, we demonstrate the effectiveness of this evolutionary technique, coupled with weighted heuristics, for the construction of improved prediction models. The experiments have been carried out for the CoEPrA competition datasets (accessible online at: http://www.coepra.org) and the results show a marked improvement over the winner results in some situations and comparably good with regard to others .We thus hope to initiate further research on the application of this new bio-inspired methodology for immunological research. [Copyright &y& Elsevier]