The study of convenient methods of information dissemination has been a vital research area for years. Mobile ad hoc networks (MANET) have revolutionized our society due to their self-configuring, infrastructure-less decentralized modes of communication and thus researchers have focused on finding better and better ways to fully utilize the potential of MANETs. The recent advent of modern machine learning techniques has made it possible to apply artificial intelligence to develop better protocols for this purpose. In this paper, we expand our previous work which developed a clustering algorithm that used weight-based parameters to select cluster heads and use Artificial Neural Network to train a model to accurately predict the scale of the weights required for different network topologies.

Malware poses one of the most serious threats to computer information systems. The current detection technology of malware has several inherent constraints. Because signature-based traditional techniques embedded in commercial antiviruses are not capable of detecting new and obfuscated malware, machine learning algorithms are applied in identifing patterns of malware behavior through features extracted from programs. There, a method is presented for detecting malware based on the features extracted from the PE header and section table PE files. The packed files are detected and then unpacke them. The PE file features are extracted and their static features are selected from PE header and section tables through forward selection method. The files are classified into malware files and clean files throughs different classification methods. The best results are obtained through DT classifier with an accuracy of 98.26%. The results of the experiments consist of 971 executable files containing 761 malware and 210 clean files with an accuracy of 98.26%.

Traditional database system forces all data to adhere to an explicitly specified, rigid schema and most of the limitations of traditional database may be overcome by semi-structured database. Whereas a traditional transaction system guarantee that either all modifications are done or none of these i.e. the database must be atomic (either occurs all or occurs nothing) in nature. In this paper transaction is treating as a mapping from its environment to compensable programs and provides a transaction refinement calculus. The motivation of the Transactional Calculus for Semi Structured Database System (TCSS) is-finally, on a highly distributed network, it is desirable to provide some amount of fault tolerance. The paper proposes a mathematical framework for transactions where a transaction is treated as a mapping from its environment to compensable programs and also provides a transaction refinement calculus. It proposes to show that most of the semi structured transaction can be converted to a calculus based model which is simply consists of a forward activity and a compensation module of CAP (consistency, availability, and partition tolerance) [12] and BASE (basic availability, soft state and eventually consistent) [45] theorem. It proposes to show that most of the semi-structured transaction can be converted to a calculus based model which is simply consists of a forward activity and a compensation module of CAP and BASE theorem. It is important that the service still perform as expected if some nodes crash or communication links fail, Verification of several useful properties of the proposed TCSS includes in this article. Moreover, a detailed comparative analysis has been providing towards evaluation of the proposed TCSS.

The exponent increase in the use of online information systems triggered the demand of secure networks so that any intrusion can be detected and aborted. Intrusion detection is considered as one of the emerging research areas now days. This paper presents a machine learning based classification framework to detect the Denial of Service (DoS) attacks. The framework consists of five stages, including: 1) selection of the relevant Dataset, 2) Data pre-processing, 3) Feature Selection, 4) Detection, and 5) reflection of Results. The feature selection stage incudes the Decision Tree (DT) classifier as subset evaluator with four well known selection techniques including: Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Best First (BF), and Rank Search (RS). Moreover, for detection, Decision Tree (DT) is used with bagging technique. Proposed framework is compared with 10 widely used classification techniques including Naïve Bayes (NB), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (kNN), Decision Tree (DT), Radial Basis Function (RBF), One Rule (OneR), PART, Bayesian Network (BN) and Random Tree (RT). A part of NSL-KDD dataset related to Denial of Service attack is used for experiments and performance is evaluated by using various accuracy measures including: Precision, Recall, F measure, FP rate, Accuracy, MCC, and ROC. The results reflected that the proposed framework outperformed all other classifiers.