No abstract

Machine learning (ML) and Deep Learning (DL) methods are being adopted rapidly, especially in computer network security, such as fraud detection, network anomaly detection, intrusion detection, and much more. However, the lack of transparency of ML and DL based models is a major obstacle to their implementation and criticized due to its black-box nature, even with such tremendous results. Explainable Artificial Intelligence (XAI) is a promising area that can improve the trustworthiness of these models by giving explanations and interpreting its output. If the internal working of the ML and DL based models is understandable, then it can further help to improve its performance. The objective of this paper is to show that how XAI can be used to interpret the results of the DL model, the autoencoder in this case. And, based on the interpretation, we improved its performance for computer network anomaly detection. The kernel SHAP method, which is based on the shapley values, is used as a novel feature selection technique. This method is used to identify only those features that are actually causing the anomalous behaviour of the set of attack/anomaly instances. Later, these feature sets are used to train and validate the autoencoderbut on benign data only. Finally, the built SHAP_Model outperformed the other two models proposed based on the feature selection method. This whole experiment is conducted on the subset of the latest CICIDS2017 network dataset. The overall accuracy and AUC of SHAP_Model is 94% and 0.969, respectively.

Nowadays, many organizations are concerned with how successfully they can formulate an information system (IS) strategy. Have them adopted enterprise architecture, they are concerned of how to activate the business and IS decisions. From a functional perspective, enterprise architecture demonstrates how all information technology elements in an organization, systems, processes and people work together as a whole. Hence, enterprise architecture is an approach of aligning the business area of an organization with the IT area. It has become widely recognized that an enterprise architecture plays a key role in influencing the IS strategy formulation. Strategy formulation in enterprises is a continuous process and it is considered an implicit process that is influenced by a set of factors in which enterprise architecture is a major one. In this paper, we discuss that role that an enterprise architecture plays in influencing the IS strategy formulation.

This paper outlines the design and development of an intelligent tutoring technique to personalize the navigation of individual users in the course content and generate advice to students. Based on that, a framework for adaptive e-learning, the e-Learning Guide system (eLGuide), is implemented and an empirical evaluation of the prototype is conducted to assess the possibility of its integration with web-based learning systems. The system is tested in a real setting with the SQL-A Database Language course comprising postgraduate students of the computer science program, all new to database systems. The evaluation study shows a positive impact on learning outcomes. The results of the experimental study allowed us to conclude that eLGuide is a useful framework, which can be employed in a web-based learning environment to support students as well as teachers in a better way. ß 2015 Wiley Periodicals, Inc. Comput Appl Eng Educ 23:542-555, 2015; View this article online at wileyonlinelibrary.com/journal/cae;

No abstract