No abstract

Feature selection (FS) is one of the important tasks of data preprocessing in data analytics. The data with a large number of features will affect the computational complexity, increase a huge amount of resource usage and time consumption for data analytics. The objective of this study is to analyze relevant and significant features of huge network traffic to be used to improve the accuracy of traffic anomaly detection and to decrease its execution time. Information Gain is the most feature selection technique used in Intrusion Detection System (IDS) research. This study uses Information Gain, ranking and grouping the features according to the minimum weight values to select relevant and significant features, and then implements Random Forest (RF), Bayes Net (BN), Random Tree (RT), Naive Bayes (NB) and J48 classifier algorithms in experiments on CICIDS-2017 dataset. The experiment results show that the number of relevant and significant features yielded by Information Gain affects significantly the improvement of detection accuracy and execution time. Specifically, the Random Forest algorithm has the highest accuracy of 99.86% using the relevant selected features of 22, whereas the J48 classifier algorithm provides an accuracy of 99.87% using 52 relevant selected features with longer execution time.

The difficulty of the intrusion detection system in heterogeneous networks is significantly affected by devices, protocols, and services, thus the network becomes complex and difficult to identify. Deep learning is one algorithm that can classify data with high accuracy. In this research, we proposed deep learning to intrusion detection system identification methods in heterogeneous networks to increase detection accuracy. In this paper, we provide an overview of the proposed algorithm, with an initial experiment of denial of services (DoS) attacks and results. The results of the evaluation showed that deep learning can improve detection accuracy in the heterogeneous internet of things (IoT).

-This study investigates the conceptual model that has been used to measure the acceptance of e-learning technology applied in higher education. We conducted literature review study by collecting the papers from reputable journals. We used recognize database journal such as Google scholar, ProQuest, EBSCOhost, and IEEE to collect the articles. E-learning conceptual model is used as a keyword to search the relevant article. The selected articles are reviewed and analyzed. The result of analysis is presented. This study reveals that a famous conceptual model by Davis, Technology Acceptance Model (TAM), is used as reference in developing e-learning acceptance conceptual models.