Two stage genetic approach for bio-chemical named entity recognition

In this paper, feature subset selection from river-ice image samples for classification of river-ice types is proposed using extreme learning machine (ELM) and differential evolution feature selection (DEFS) technique called extreme learning machine-based differential evolution feature selection (ELM-DEFS). Although DEFS is a good feature selection technique, the feature weights are selected by cross over and mutation which may be trapped. So, ELM is integrated with DEFS to overcome the difficulties of selecting the weights. Feature subset selection plays the most important role to classify the river-ice types. First-and second-order statistical texture features are extracted from real river-ice images. All the original features extracted from feature extraction methods do not help in recognition of river-ice types, so it is essential to reduce the feature subset to improve classification accuracy. In this paper, experiments are conducted on real river-ice image samples with probabilistic neural network (PNN) classifier which classifies different ice types. Performances of ELM-DEFS are compared with genetic algorithm (GA) and DEFS by means of performance evaluation metrics. Experimental results show that ELM-DEFS convergence is better than both DEFS and GA in selecting top-most feature subset; ELM-DEFS-based PNN (ELM-DEFS-PNN) classifier exhibits higher performance with an accuracy of 93% which is approximately 1% higher than GA-based PNN (GA-PNN) and DEFSbased PNN (DEFS-PNN) classification.

Modeling of processes with many input variables requires selection of informative inputs in order to construct less complex models with good generalization abilities. In this paper two feature selection methods are compared: mutual information (MI) based feature selection and genetic algorithm (GA) based feature selection. As a modeling structure a hybrid linear-neural model is used. The methods are applied to a case study: modeling of an industrial antibiotic fermentation process. It is shown that both feature selection methods can lead to similar results. 8s based feature selection can be applied to problems where only few data exist and MI can not be calculated. In GA based feature selection it is possibile to adjust the objective function in order to control the propperties of the method.

This study presents a comprehensive analysis of artificial intelligence (AI) techniques to predict healthcare expenditure per capita (pcHCE) in Turkey. Well‐known AI techniques such as random forest (RF), artificial neural network (ANN), multiple linear regression (MLR), support vector regression (SVR), and relevance vector machine (RVM) were used to forecast pcHCE. Twenty‐nine years of historical data from 1990 to 2018 were used in the training and testing phases of the models. Gross domestic product per capita, life expectancy at birth, unemployment rate, crude birth rate, and the number of physicians and hospitals were used as input variables for the analysis. A genetic algorithm‐based feature selection (GAFS) method was applied to all models to select the relevant and optimal feature subset in the prediction of pcHCE. The comparative results showed that the GAFS method improved the overall performance of all base AI models. The hybrid GAFS‐RF model performed best among all AI‐based prediction methods, with a 99.86% correlation of determination (R2) value at the testing stage.

Recently, student’s academic performance prediction has become an increasingly prominent research topic in the field of Educational Data Mining (EDM). The prediction of student’s academic performance aims to explore information that is beneficial to the learning process of student. Therefore, accurate prediction of student’s academic performance provide benefits for education institutions to improve the quality of their institutions by improving the learning process of students. In predicting the student’s academic performance, the problem of high dimensional dataset is often faced in the datasets which significantly impacts the accuracy of student academic performance prediction. This paper proposed Genetic Algorithm based Feature Selection (GAFS) along with selected single classifier for classification in order to improve the accuracy in predicting student academic performance. Kaggle dataset is used in this paper and two phase of experiment have been conducted, single classifier without GAFS, and single classifier with GAFS. Results from the experiments show that, the accuracy of the proposed GAFS for classification makes an impressive performance in predicting student academic performance in terms of accuracy compare to existing techniques.

In text classification, feature selection is essential to improve the classification effectiveness. This paper provides an empirical study of a feature selection method based on genetic algorithms for different text representation methods. This feature selection algorithm can accomplish two goals: in one hand is the search of a feature subset such that the performance of classifier is best; in other hands is find a feature subset with the smallest dimensionality which achieves higher accuracy in classification. To evaluate the performance of this approach, three from the best classifiers have been selected: Naive Bayes (NB), Nearest Neighbors (KNN) and Support Vector Machines (SVMs). Our objective is to determine whether the genetic algorithms based feature selection will improve the performances in text classification with smaller size using F-measure. Experimentations were carried out on two benchmark document collections 20Newsgroups, and Reuters-21578. And the results were very interesting.

Despite the great benefits accruable from the debut of computer and the internet, efforts are constantly being put up by fraudulent and mischievous individuals to compromise the integrity, confidentiality or availability of electronic information systems. In Cyber-security parlance, this is termed ‘intrusion’. Hence, this has necessitated the introduction of Intrusion Detection Systems (IDS) to help detect and curb different types of attack. However, based on the high volume of data traffic involved in a network system, effects of redundant and irrelevant data should be minimized if a qualitative intrusion detection mechanism is genuinely desirous. Several attempts, especially feature subset selection approach using Bee Algorithm (BA), Linear Genetic Programming (LGP), Support Vector Decision Function Ranking (SVDF), Rough, Rough-DPSO, and Mutivariate Regression Splines (MARS) have been advanced in the past to measure the dependability and quality of a typical IDS. The observed problem among these approaches has to do with their general performance. This has therefore motivated this research work. We hereby propose a new but robust algorithm called membrane algorithm to improve the Bee Algorithm based feature subset selection technique. This Membrane computing paradigm is a class of parallel computing devices. Data used were taken from KDD-Cup 99 Dataset which is the acceptable standard benchmark for intrusion detection. When the final results were compared to those of the existing approaches, using the three standard IDS measurements-Attack Detection, False Alarm and Classification Accuracy Rates, it was discovered that Bee Algorithm-Membrane Computing (BA-MC) approach is a better technique. This is because our approach produced very high attack detection rate of 89.11%, classification accuracy of 95.60% and also generated a reasonable decrease in false alarm rate of 0.004. Receiver Operating Characteristic (ROC) curve was used for results interpretation.

In many pattern recognition applications feature selection and instance selection can be used as two data preprocessing methods that aim at reducing the computational cost of the learning process. Moreover, in some cases, feature subset selection can improve the classification performance. Feature selection and instance selection can be interesting since the choice of features and instances greatly influence the performance of the learnt models as well as their training costs. In the past, unifying both problems was carried out by solving a global optimization problem using meta-heuristics. This paradigm not only does not exploit the manifold structure of data but can be computationally expensive. To the best of our knowledge, the joint use of sparse modeling representative and feature subset relevance have not been exploited by the joint feature and selection methods. In this paper, we target the joint feature and instance selection by adopting feature subset relevance and sparse modeling representative selection. More precisely, we propose three schemes for the joint feature and instance selection. The first is a wrapper technique while the two remaining ones are filter approaches. In the filter approaches, the search process adopts a genetic algorithm in which the evaluation is mainly given by a score that quantify the goodness of the features and instances. An efficient instance selection technique is used and integrated in the search process in order to adapt the instances to the candidate feature subset. We evaluate the performance of the proposed schemes using image classification where classifiers are the nearest neighbor classifier and support vector machine classifier. The study is conducted on five public image datasets. These experiments show the superiority of the proposed schemes over various baselines. The results confirm that the filter approaches leads to promising improvement on classification accuracy when both feature selection and instance selection are adopted.

Genetic algorithm-based feature selection in high-resolution NMR spectra

BackgroundWe consider both univariate- and multivariate-based feature selection for the problem of binary classification with microarray data. The idea is to determine whether the more sophisticated multivariate approach leads to better misclassification error rates because of the potential to consider jointly significant subsets of genes (but without overfitting the data).MethodsWe present an empirical study in which 10-fold cross-validation is applied externally to both a univariate-based and two multivariate- (genetic algorithm (GA)-) based feature selection processes. These procedures are applied with respect to three supervised learning algorithms and six published two-class microarray datasets.ResultsConsidering all datasets, and learning algorithms, the average 10-fold external cross-validation error rates for the univariate-, single-stage GA-, and two-stage GA-based processes are 14.2%, 14.6%, and 14.2%, respectively. We also find that the optimism bias estimates from the GA analyses were half that of the univariate approach, but the selection bias estimates from the GA analyses were 2.5 times that of the univariate results.ConclusionsWe find that the 10-fold external cross-validation misclassification error rates were very comparable. Further, we find that a two-stage GA approach did not demonstrate a significant advantage over a 1-stage approach. We also find that the univariate approach had higher optimism bias and lower selection bias compared to both GA approaches.

In the Cloud computing platform, several technologies are practiced to manage the huge amount of information and also afford the comfort of routine. In this state, every cloud-based application plays an extensive role in the real-time applications. To avail efficient facilities to the patients, this paper presents an optimal feature selection based data classification model particularly for cloud platform. The presented model is based on two stages namely genetic algorithm based feature selection (GA-FS) and neural network (NN) based data classification. The presented GA-NN model is applied to diagnose the diseases and its various stages. The experimentations have been directed by the benchmark dataset and the real-time medicinal data that is gathered from numerous medical organizations. The simulation outcomes demonstrate that the efficiency of the GA-NN method beats the prevailing methods to predict diseases.

Functional Magnetic Resonance Imaging (fMRI) is a neuroimaging technique used to capture images of brain activity. These images have high spatial resolution and hence are very high dimensional. Each scan consists of more than one hundred thousand voxels. All of the scanned voxels are not activated for every stimulus. Therefore, finding the informative voxels with respect to stimulus becomes a prerequisite for any machine learning solution using fMRI data. The specific problem attempted to be solved in this paper is that of decoding cognitive states from multiple-subject fMRI data. Decoding multiple-subject data is challenging owing to the difference in the shape and size of the brain of different subjects. A Genetic algorithm based technique is proposed here for selection of voxels that capture commonality across subjects. Some popular feature selection techniques are compared against Genetic algorithms. It is observed that feature selection using Genetic algorithms perform consistently and predictably better than other techniques.

Brain hemorrhage is a type of stroke which is caused by a ruptured artery, resulting in localized bleeding in or around the brain tissues. Among a variety of imaging tests, a computerized tomography (CT) scan of the brain enables the accurate detection and diagnosis of a brain hemorrhage. In this work, we developed a practical approach to detect the existence and type of brain hemorrhage in a CT scan image of the brain, called Accurate Identification of Brain Hemorrhage, abbreviated as AIBH. The steps of the proposed method consist of image preprocessing, image segmentation, feature extraction, feature selection, and design of an advanced classification framework. The image preprocessing and segmentation steps involve removing the skull region from the image and finding out the region of interest (ROI) using Otsu’s method, respectively. Subsequently, feature extraction includes the collection of a comprehensive set of features from the ROI, such as the size of the ROI, centroid of the ROI, perimeter of the ROI, the distance between the ROI and the skull, and more. Furthermore, a genetic algorithm (GA)-based feature selection algorithm is utilized to select relevant features for improved performance. These features are then used to train the stacking-based machine learning framework to predict different types of a brain hemorrhage. Finally, the evaluation results indicate that the proposed predictor achieves a 10-fold cross-validation (CV) accuracy (ACC), precision (PR), Recall, F1-score, and Matthews correlation coefficient (MCC) of 99.5%, 99%, 98.9%, 0.989, and 0.986, respectively, on the benchmark CT scan dataset. While comparing AIBH with the existing state-of-the-art classification method of the brain hemorrhage type, AIBH provides an improvement of 7.03%, 7.27%, and 7.38% based on PR, Recall, and F1-score, respectively. Therefore, the proposed approach considerably outperforms the existing brain hemorrhage classification approach and can be useful for the effective prediction of brain hemorrhage types from CT scan images (The code and data can be found here: http://cs.uno.edu/~tamjid/Software/AIBH/code_data.zip).

Thanks to our daily available open source characteristics, Android Platform has the largest Market Share. Android has gathered most of the attentions of cybercriminals as it’s the most popular Operating System in the world, they operate through wide distributed malicious application. This article approaches a Machine learning-based Malware detection of Android using Genetic Algorithms-based feature selection. Genetic Algorithm is used to detect malwares by training selected feature to ML classifiers and to check the identification capacity before and after feature selection. This experiment showed that genetic algorithm produces the most optimized feature result and helps in reducing the feature dimension to half of the original feature. After feature selection and maintaining the post-feature selection of ML classifiers, 97% accuracy is gained, while working on reduced dimension, thereby a positive impact on computational complexity is gained.KeywordsAndroidMalwareCyber crimeGeneticNeural networkAISVM

In this paper we propose a modified differential evolution (MDE) based feature selection and ensemble learning algorithms for biochemical entity recognizer. Identification and classification of chemical entities are relatively more complex and challenging compared to the other related tasks. As chemical entities we focus on IUPAC and IUPAC related entities. The algorithm performs feature selection within the framework of a robust machine learning algorithm, namely Conditional Random Field. Features are identified and implemented mostly without using any domain specific knowledge and/or resources. In this paper we modify traditional differential evolution to perform two tasks, viz. determining relevant set of features as well as determining proper voting weights for constructing an ensemble. The feature selection technique produces a set of potential solutions on the final population. We develop many models of CRF using these feature combinations. In order to further improve the performance the outputs of these classifiers are combined together using a classifier ensemble technique based on modified DE. Our experiments with the benchmark datasets yield the recall, precision and F-measure values of 82.34%, 88.26% and 85.20%, respectively.KeywordsModified Differential Evolution (MDE)Conditional Random Field (CRF)Feature SelectionEnsembleBiochemical Named Entity

<p>Classification problems often have a large number of features, but not all of them are useful for classification. Irrelevant and redundant features may even reduce the classification accuracy. Feature selection is a process of selecting a subset of relevant features, which can decrease the dimensionality, shorten the running time, and/or improve the classification accuracy. There are two types of feature selection approaches, i.e. wrapper and filter approaches. Their main difference is that wrappers use a classification algorithm to evaluate the goodness of the features during the feature selection process while filters are independent of any classification algorithm. Feature selection is a difficult task because of feature interactions and the large search space. Existing feature selection methods suffer from different problems, such as stagnation in local optima and high computational cost. Evolutionary computation (EC) techniques are well-known global search algorithms. Particle swarm optimisation (PSO) is an EC technique that is computationally less expensive and can converge faster than other methods. PSO has been successfully applied to many areas, but its potential for feature selection has not been fully investigated. The overall goal of this thesis is to investigate and improve the capability of PSO for feature selection to select a smaller number of features and achieve similar or better classification performance than using all features. This thesis investigates the use of PSO for both wrapper and filter, and for both single objective and multi-objective feature selection, and also investigates the differences between wrappers and filters. This thesis proposes a new PSO based wrapper, single objective feature selection approach by developing new initialisation and updating mechanisms. The results show that by considering the number of features in the initialisation and updating procedures, the new algorithm can improve the classification performance, reduce the number of features and decrease computational time. This thesis develops the first PSO based wrapper multi-objective feature selection approach, which aims to maximise the classification accuracy and simultaneously minimise the number of features. The results show that the proposed multi-objective algorithm can obtain more and better feature subsets than single objective algorithms, and outperform other well-known EC based multi-objective feature selection algorithms. This thesis develops a filter, single objective feature selection approach based on PSO and information theory. Two measures are proposed to evaluate the relevance of the selected features based on each pair of features and a group of features, respectively. The results show that PSO and information based algorithms can successfully address feature selection tasks. The group based method achieves higher classification accuracies, but the pair based method is faster and selects smaller feature subsets. This thesis proposes the first PSO based multi-objective filter feature selection approach using information based measures. This work is also the first work using other two well-known multi-objective EC algorithms in filter feature selection, which are also used to compare the performance of the PSO based approach. The results show that the PSO based multiobjective filter approach can successfully address feature selection problems, outperform single objective filter algorithms and achieve better classification performance than other multi-objective algorithms. This thesis investigates the difference between wrapper and filter approaches in terms of the classification performance and computational time, and also examines the generality of wrappers. The results show that wrappers generally achieve better or similar classification performance than filters, but do not always need longer computational time than filters. The results also show that wrappers built with simple classification algorithms can be general to other classification algorithms.</p>