Titlebook: South African Computer Science and Information Systems Research Trends; 45th Annual Conferen Aurona Gerber Conference proceedings 2024 The

纠缠

Is Transformer-Based Attention Agnostic of the Pretraining Language and Task?ection—have similar internal patterns of attention, even when trained for different languages, in our case English, Afrikaans, Xhosa, and Zulu. This result suggests that, on a high level, the learnt role of attention is language-agnostic.

商业上

Deep Learning Classification for Encrypted Botnet Traffic: Optimising Model Performance and Resource where we evaluate the impact this has in terms of a trade-off between computational and classification performance. For botnet detection, we find that all models attain good (.0.979 accuracy) classification performance on a normal testing set; however, this performance drops fairly substantially wh

Allowance

态学

Bph773

Investigating Markov Model Accuracy in Representing Student Programming Behaviourspresented that works on AST nodes as input to emphasise structural similarity and related programming approaches. As such, the effectiveness of the Modified MinHashLSH approach is based on the clusters that make up the Markov model..The research result shows that we can successfully create a high-qu

ascetic

遗忘

Age-Related Face Recognition Using Siamese Networks and Vision Transformersl image context. This work investigates the performance of these distinct architectures in discerning age-related variations within facial data features. Performance comparisons were conducted on three established SCN models and two ViT architectures. The results revealed that the optimal SCNs prima

CHIDE

Sarcasm Detection in Political Speeches Using Recurrent Neural Networksing the clear benefit of ensemble learning. This improvement suggests that ensembles effectively combine the strengths of different models, leading to more robust and generalisable sarcasm detection in political speech. Furthermore, this research paves the way for the application of similar techniqu

Coronary

Unsupervised State Encoding in Video Sequences Using ,-Variational Autoencodersces which deviate from those seen in training. The results demonstrate that the .-VAE successfully learned to encode distinct states within the sequence, as evidenced by the visualisations. It is shown that .-VAE is capable of detecting states within a sequence. Furthermore, it is demonstrated that

贫穷地活

User Centred Design and Implementation of Useful Picture Archiving and Communication Systems for Effacilities. Semi-structured interviews were conducted with two (2) radiologists and four (4) radiographers in order to understand medical imaging workflows in public health facilities. A Picture Archiving and Communication System was designed and implemented using Dicoogle as the base platform and, s