Full Description
This book constitutes the refereed proceedings of the 5th Southern African Conference on Artificial Intelligence Research, SACAIR 2024, held in Bloemfontein, South Africa, during December 2-6, 2024.
The 29 full papers presented in these proceedings were carefully reviewed and selected from 101 submissions. The papers are organized in the following topical sections: algorithmic and Data Driven AI; socio-technical and human-centred AI (Information Systems); responsible and Ethical AI (Philosophy, Law and Humanities); symbolic AI and Knowledge Representation and Reasoning.
Contents
.- Algorithmic and Data Driven AI.
.- Parameter-Efficient Fine-Tuning of Pre-trained Large Language Models for Financial Text Analysis.
.- Optimally traversing explainability in Bayesian networks via the graphical Lasso.
.- Assessing multilinguality of topic models on a short-text South African languages dataset.
.- Cascaded RFM-based Fuzzy Clustering Model for Dynamic Customer Segmentation in Retail Sector.
.- Automatic Assessment of Speech Impediment for South African Early Literacy Readers.
.- Automated Enhancement of isiZulu Data Collection for the African Health Research Institute.
.- AI in Education: An Analysis of Large Language Models for Twi Automatic Short Answer Grading.
.- Enhancing Credit Risk Assessment through Transformer Based Machine Learning Models.
.- Predicting and discovering weather patterns in South Africa using Spatial-Temporal Graph Neural Networks.
.- Benchmarking Political Bias Classification with In-Context Learning: Insights from GPT-3.5, GPT-4, LLaMA-3, and Gemma-2.
.- Uncovering the ANPR Performance Gap: A Commercial Systems Analysis.
.- Neural Network-based Vehicular Channel Estimation Performance: Effect of Noise in the Training Set.
.- Deep Learning-based Network Intrusion Detection Systems: A Systematic Literature Review.
.- Impact of batch normalization on convolutional network representations.
.- Does simple trump complex? Comparing strategies for adversarial robustness in DNNs.
.- A novel approach to lion re-Identification using vision transformers.
.- Assessing Data-Driven of Discriminative Deep Learning Models in Classification Task Using Synthetic Pandemic Dataset.
.- Deep Neural Network Compression for Lightweight and Accurate Fish Classification.
.- Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset.
.- Automated Fish Detection in Underwater Environments: Performance Analysis of YOLOv8 and YOLO-NAS.
.- Socio-technical and human-centred AI (Information Systems).
.- The Effect of Generative AI on Cognitive Thinking Skills in Higher Education Institutions: A Systematic Literature Review.
.- LLMs as Enablers of Accessible Business Process Modeling.
.- The role of artificial intelligence in modern language translation and its societal applications: A systematic literature review.
.- Deep Learning Forecasting of Photovoltaics Output Using Digital Twin Data.
.- Responsible and Ethical AI (Philosophy, Law and Humanities).
.- Requirements Engineering (RE) in Artificial Intelligence (AI) Systems Implementation: The Need to Emphasize Non-Functional Requirements (NFRs) for Ethical AI.
.- Democratic AI: Justification for a Broad View of Public Reason.
.- Symbolic AI and Knowledge Representation and Reasoning.
.- Towards Propositional KLM-Style Defeasible Standpoint Logics.
.- Non-monotonic Extensions to Formal Concept Analysis via Object Preferences.
.- Knowledge Compilation for KLM-Style Defeasible Reasoning.
