Research Publications (Accounting and Informatics)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/212

Browse

Now showing 1 - 4 of 4

Experimental comparison of support vector machines with random forests for hyperspectral image land cover classiﬁcation
(Indian Academy of Sciences, 2014-06-12) Marwala, T.; Abe, B. T.; Olugbara, Oludayo O.
The performances of regular support vector machines and random forests are experimentally com-pared for hyperspectral imaging land cover classiﬁcation. Special characteristics of hyperspectral imaging dataset present diverse processing problems to be resolved under robust mathematical formalisms such as image classiﬁcation. As a result, pixel purity index algorithm is used to obtain endmember spectral responses from Indiana pine hyperspectral image dataset. The generalized reduced gradient optimiza-tion algorithm is thereafter executed on the research data to estimate fractional abundances in the hyperspectral image and thereby obtain the numeric values for land cover classiﬁcation. The Waikato environment for knowledge analysis (WEKA) data mining framework is selected as a tool to carry out the classiﬁcation process by using support vector machines and random forests classiﬁers. Results show that performance of support vector machines is comparable to that of random forests. This study makes a positive contribution to the problem of land cover classiﬁcation by exploring generalized reduced gra-dient method, support vector machines, and random forests to improve producer accuracy and overall classiﬁcation accuracy. The performance comparison of these classiﬁers is valuable for a decision maker to consider tradeoﬀs in method accuracy versus method complexity.
Exploring first-year engineering student perceptions of the engineering librarian as an IL instructor in multimodal teaching and learning environments
(Emerald, 2023-12-08) Omarsaib, Mousin
This study aims to explore first-year engineering students’ perceptions of the engineering librarian as an instructor in multimodal environments related to Information Literacy (IL) topics, teaching strategy, content evaluation, organising, planning and support. Design/methodology/approach A quantitative approach was used through a survey instrument based on an online questionnaire. Questions were adopted and modified from a lecturer evaluation survey. A simple random sampling technique was used to collect data from first-year cohorts of engineering students in 2020 and 2022. Findings Respondents perception of the engineering librarian as an instructor in multimodal learning environment was good. Findings revealed students’ learning experiences were aligned with IL instruction even though the environment changed from blended to online. However, an emerging theme that continuously appeared was a lack of access to technology. Practical implications These findings may help in developing and strengthening the teaching identity of academic librarians as instructors in multimodal learning environments. Originality/value To the best of the author’s knowledge, this study is novel in that it evaluates the teaching abilities of an academic librarian in multimodal environments through the lens of students.
Hyperspectral image classification using random forests and neural networks
(International Association of Engineers, 2012) Abe, B. T.; Olugbara, Oludayo O.; Marwala, T.
Spectral unmixing of hyperspectral images are based on the knowledge of a set of unknown endmembers. Unique characteristics of hyperspectral dataset enable different processing problems to be resolved using robust mathematical logic such as image classification. Consequently, pixel purity index is used to find endmembers from Washington DC mall hyperspectral image dataset. The generalized reduced gradient algorithm is used to estimate fractional abundances in the hyperspectral image dataset. The WEKA data mining tool is selected to construct random forests and neural networks classifiers from the set of fractional abundances. The performances of these classifiers are experimentally compared for hyperspectral data land cover classification. Results show that random forests give better classification accuracy when compared to neural networks. The study proffers solution to the problem associated with land cover classification by exploring generalized reduced gradient approach with learning classifiers to improve overall classification accuracy. The classification accuracy comparison of classifiers is important for decision maker to consider tradeoffs in accuracy and complexity of methods.
An implementation of SAP enterprise resource planning : a case study of the South African revenue services and taxation sectors
(Informa UK Limited, 2023) Aroba, Oluwasegun Julius; Abayomi, Abdultaofeek
A SAP enterprise resource planning (ERP) is a software system that assists organizations in automating and managing fundamental business processes for ideal performance. This research study aims to ameliorate the business operation problems of the South African Revenue Services (SARS) and Taxation sectors. Involving tax sectors in the preliminary stages of SAP ERP design and implementation saves SARS’ clients some resources such as money and time while also allowing various departments to improve their tax technology ecosystem. To address the associated financial, operational, technical, and compliance challenges, an ERP implementation requiring significant support from strategy execution is suggested. This proposed model for designing and implementing an ERP with a case study of the South African Revenue Services (SARS) and other taxation sectors, the benefits of ERP system within the taxation sector, implementation challenges, and proposed solutions are presented in this article while utilising data from a survey that was conducted for 50 SARS employees and taxpayers outside the organization. The proposed ERP system will enhance the connectivity of all operations within the SARS with a central access to all departments rather than having silos of business operations. From our analysis, the Cronbach report of 0.85 obtained, which is greater than 0.7 minimum, shows that it fits the proposed solution of a SAP ERP mobile app for inclusivity in the operational processes for both SARS employees and other taxpayers.