No abstract

No abstract

No abstract

The quality of higher education is of particular importance for the development and progress of modern society. Modern higher education institutions aim to improve their services, and establish a system of continuous quality assurance. Within the framework of the European Standards and Guidelines for Quality Assurance, Standard 1.6 requires the implementation of information systems for efficient management of study programs and other activities. During the phase of problem analysis and objectives, in regard to the application of information systems at the University "Dzemal Bijedic", the existence of heterogeneous internal and external data sources was established. In modern management, data is considered a key resource necessary for the survival and development of the institution. Accordingly, the research focus is on the development of models of business intelligence systems that will be based on existing data sources. This system would primarily be used to support internal quality assurance at the University, as well as management support for timely and optimal decision making process. This paper presents the tools and technology of business intelligence, and through practical example demonstrates the possibilities of the system.

This paper investigates anomalies such as worms, power outages, and routing table leak (RTL) events occurring in Border Gateway Protocol (BGP) that can cause connectivity and data loss issues. Ensemble learning is a machine learning model employing multiple classifiers in order to reliably identify network anomalies. We use bagging, boosting, and random forests ensemble models trained on network anomaly datasets for classification improvement. Models were compared with respect to the following performance metrics: F-measure, Matthews correlation coefficient (MCC), Receiver operating characteristic (ROC) curve, precision-recall (PR) curves and model execution time. We observed improvement in performance measures when ensemble classifiers realized in Python were used in comparison to our previously reported results on single classifiers. Further improvement in most performance measures was observed by using sampling techniques (oversampling and undersampling) on anomalous datasets. This approach increases model execution time which is not favorable for real-time anomaly detection models.Index Terms-BGP, bagging, boosting, random forest.