Timothy A. Chadza

TL;DR: It is shown that it is possible to develop a robust, fully-automated, solar powered, and low cost IMS to suit the socio-economic conditions of small scale farmers in developing countries.

TL;DR: This paper critically analyses the detection and prediction accuracy of a wide range of training and initialisation algorithms including the expectation–maximisation, spectral, Baum–Welch, differential evolution, K-means, and segmental K-Means for determining computer systems under a Multi-Stage Network Attack.

TL;DR: Results show that the BW and VT count-based initialisation techniques perform better than uniform and random initialisation when detecting AS and CS, and for NS prediction, uniform andrandom initialisations techniques performbetter than BW andVT count- based approaches.

TL;DR: A transfer learning (TL) approach that exploits already learned knowledge, gained from a labelled source dataset, and adapts it on a different, unlabelled target dataset is proposed and evaluated against conventional machine learning approaches.

TL;DR: This work proposes a new approach towards addressing this challenging type of cyber-attacks by employing external sources of information, beyond the conventional use of signatures and monitored network data, and proves that the use of contextual information improves the efficiency of the IDS by enhancing the Detection Rate (DR) of MSAs by almost 50%.