Academic Support

Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/210

Browse

Now showing 1 - 4 of 4

Analysing factors influencing women unemployment using a random forest model
(2022-12-30) Adeliyi, Timothy; Oyewusi, Lawrence; Epizitone, Ayogeboh; Oyewusi, Damilola
The unemployment crisis has been a persistent issue for both development countries, resulting in an economic indicator deficit. Women are at a disadvantage and continue to encounter significant obstacles to gaining employment. Nigeria, like many other developing countries with high unemployment rates, has a 33% unemployment rate. Consequently, there has been minimal research on the factors that affect women's unemployment. As a result, the purpose of this study investigates the factors women's unemployment in Nigeria. Although the Random Forest model has been widely applied to classification issues, there is a gap in the literature's use of the random forest as a predictor for analyzing factors influencing women's unemployment. The random forest model was employed in this study because of its characteristics such as strong learning ability, robustness, and feasibility of the hypothesis space. As a result, the Random forest prediction model was benchmarked with seven different cutting-edge classical machine learning prediction models, which include the J48 pruned tree, Support Vector Machine, AdaBoost, Logistic Regression, Naive Bayes, Logistic Model Tree, Bagging and Random Forest. The experimental results demonstrate that Random Forest outperformed the other seven machine learning classifier models using ten commonly used performance evaluation metrics. According to the study's findings, age groups, ethnicity, marital status, and religion were the essential factors affecting women's unemployment in Nigeria.
Ecological functionality of the Upper and Middle Vaal Water Management areas
(2012-12-05) Dzwairo, Bloodless; Otieno, Fredrick Alfred O.; Ochieng, George M.
A harmonised in-stream water quality guideline was constructed for the Upper and Middle Vaal Water Management Areas (WMAs) using ideal catchment background values for the sub-catchments; Vaal dam, Vaal barrage, Klip River and Blesbokspruit/Suikerbosrant Rivers. Data for years 2003 to 2009 was interpolated to a daily time-step for 2526 days at 21 monitoring sites covering both WMAs. Conductivity was used as a surrogate to capture the variability in water quality. This provided an ecological functionality model of the study area, coded for ranges 10-18, 19-45, 46-80, 80< and 81-100 mS/m. The Upper and Middle Vaal basin is currently extremely vulnerable to changes in water quality, uncertainty about changes which it can tolerate, and the fact that there are very limited options for mitigating effects of poor water quality in the basin, overall. Thus a precautionary approach is being proposed in this paper, in order to protect the ecological functionality of the aquatic ecosystem. The proposed harmonised guideline presents a crucial model to pre-determine the ecological functionality for any water point in the study area, in order to provide upstream-downstream pollution trading and other decision support processes towards sustainable basin management
A split-then-join lightweight hybrid majority vote classifier
(Springer International Publishing, 2022) Gadebe, Moses L.; Ojo, Sunday O.; Kogeda, Okuthe P.
Classification of human activities using smallest dataset is achievable with tree-oriented (C4.5, Random Forest, Bagging) algorithms. However, the KNN and Gaussian Naïve Bayes (GNB) achieve higher accuracy only with largest dataset. Of interest KNN is challenged with minor feature problem, where two similar features are predictable far from each other because of limited number of classification features. In this paper the split-then-join combiner strategy is employed to split classification features into first and secondary (KNN and GNB) classifier based on integral conditionality function. Therefore, top K prediction voting list of both classifier are joined for final voting. We simulated our combined algorithm and compared it with other classification algorithms (Support Vector Machine, C4.5, K NN, and Naïve Bayes, Random Forest) using R programming language with Caret, Rweka and e1071 libraries using 3 selected datasets with 27 combined human activities. The result of the study indicates that our combined classifier is effective and reliable than its predecessor Naïve Bayes and KNN. The results of study shows that our proposed algorithm is compatible with C4.5, Boosted Trees and Random Forest and other ensemble algorithms with accuracy and precision reaching 100% in most of 27 human activities.
What happens in the forest? Memory, trauma, repression and resilience amongst Congolese Refugees living in Durban, South Africa
(CS SALL Publishers, 2015) Tschudin, Alain Jean-Paul Charles
A project entitled ‘Dialogics and the pursuit of solidarity’ brings together Congolese refugees and Zulu street traders and students who reside in the inner city of Durban, South Africa. The first phase was referred to as ‘Voices’ and allowed participants to share their unique life-stories with us. Our adult female Congolese participants reported having suffered experiences of violence, most extreme, before leaving the Democratic Republic of Congo (DRC). Several of the men referred to traumatic incidents that were endured ‘in the forest’, but one of these, an elderly gentleman, referred to these as ‘unspeakable’. What happens in the forest, and why are these memories so unbearable? Is it a case of what transpires in the forest remains in the forest? Or is it that these experiences remain repressed in the mind; geographically remote from the forest, but embodied as an ever-present menace if revealed or exposed? Despite the immense trauma that has been lived by our participants, our study indicates a tremendous resilience on their part and an adaptability to life contexts that remain hostile, and at best uncertain.