DNA microarray gene-expression data has been widely used to identify cancerous gene signatures. Microarray can increase the accuracy of cancer diagnosis and prognosis. However, analyzing the large amount of gene expression data from microarray chips pose a challenge for current machine learning researches. One of the challenges lie within classification of healthy and cancerous tissues is high dimensionality of gene expressions. High dimensionality decreases the accuracy of the classification. This research aims to apply a hybrid model of Genetic Algorithm and Neural Network to overcome the problem during subset selection of informative genes. Whereby, a Genetic Algorithm (GA) reduced dimensionality during feature selection and then a Multi-Layer perceptron Neural Network (MLP) is applied to classify selected genes. The performance evaluated by considering to the accuracy and the number of selected genes. Experimental results show the proposed method suggested high accuracy and minimum number of selected genes in comparison with other machine learning algorithms.

There exist many similar services by different service providers available within the cloud environment. When the service offerings are packaged with similar functionalities, service consumers will be having a difficult time in evaluating the most relevant services that fit to their individual requirement. To address this issue, this paper proposes an effective services classification in cloud environment, which will classify the equivalent services based on their quality of service (QoS). The attribute selection method is based genetic algorithms (GA) and is designed to rank the cloud services before the attributes are being fed into a multi-layer perceptron (MLP) classification system. The results have shown a considerably high performance of 98.5%.

Social Engineering (SE) has emerged as one of the most familiar problem concerning organizational security and computer users. At present, the performance deterioration of phishing and spam detection systems are attributed to high feature dimensionality as well as the computational cost during feature selection. This consequently reduces the classification accuracy or detection rate and increases the False Positive Rate (FPR). This research is set to introduce a novel feature selection method called the New Binary Particle Swarm Optimization (NBPSO) to choose a set of optimal features in spam and phishing emails. The proposed feature selection method was tested in a classification experiments using the Support Vector Machine (SVM) to classify emails according to the various features as input. The results obtained by experimenting on two phishing and spam emails showed a reasonable performance to the phishing detection system.

E-mail is efficient and common communication method these days, but flooding spam or unsolicited e-mail messages have become uncontrollable. Most spams benefit from the commercial advertising. From the literature review only the accuracy identify the classification process in spam detection. Infrequently, false positive is identified as measurement methods of detection system. Based on the proposed detection system of this study, for the first time Binary Quantum Particle Swarm Optimization (BQPSO) as feature selection method decrease the number of irrelevant features in order to increase classifier performance and decrease dimensionality that influence reliability of detection system. The Multi-Layer Perceptron (MLP) classifier is applied in this research to detect spam emails based on selected relevant features. The experiments are showed on two datasets, namely Ling Spam and Spam Assassin to indicate BOPS based on MLP classifier not only reduce high dimensionality but achieves the accuracy near to 100% with less false positive rate in spam detection system.

Due to control different infrastructures of networked computers in cyber security, intrusion detection system has been an important task essentially. Today, an effective intrusion detection system utilizes computational methods as machine learning techniques to improve detection rate with lowest false positive rate; however large number of irrelevant features as an optimization problem decrease this rate. This study using Binary Search Gravitational Algorithm (BGSA) as a feature selection method decreases irrelevant features in KDD 99 intrusion detection data set in order to improve Multi-layer perceptron performance. Results show that significant and relevant features increase performance of intrusion detection system near to 100% with lowest computational cost.

The difficulties of email spam detection system associated with high dimensionality in feature selection process and low accuracy of spam email classification. However, in machine learning, Feature selection (FS) as a global optimization problem decreases irrelevant and redundant data and creates a set of acceptable results with high accuracy. This paper presents a feature selection algorithm based on particle swarm optimization (PSO), which decreases dimensionality and improves the accuracy of spam email classification. PSO as a computational model fallows the social behavior of bird flocking or fish schooling. The proposed PSO-based feature selection algorithm searches the feature space for the best feature subsets. The evolution of feature selected is determined by a fitness function. The classifier performance and the length of selected feature vector as a classifier input are considered for performance evaluation using Ling-Spam and SpamAssassin databases. Experimental results show that the PSO-based feature selection algorithm was presented to generate excellent feature selection results with the minimal set of selected features to be caused by a high accuracy of spam email classification based on Multi-Layer Perceptron (MLP) classifier.

Spam has created a significant security problem for computer users everywhere. Spammers take an advantage of defrauds to cover parts of messages that can be used for identification of spam. For instance, a spammer does not need to consume much cost and bandwidth for sending junk mails even more than one hundred emails. On the other hand, from the feature selection perspective, one of the specific problems that decrease accuracy of spam and non-spam emails classification is high data dimensionality. Therefore, the reduction of dimensionality is related to decrease the number of irrelevant features. In this paper, a genetic algorithm (GA) is applied during feature selection in effort to decrease the number of useless features in a collection of high-dimensional email body and subject. Next, a Multi-Layer Perceptron (MLP) is employed to classify features that have been selected by the GA. Using LingSpam benchmark corpora as the dataset, the experimental results showed that a GA feature selector with the MLP classifier does not only decrease the data dimensionality but increase the spam detection rate as compared against other classifiers such as SVM and Naïve Bayes.