Research Publications (Accounting and Informatics)

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

Browse

Now showing 1 - 19 of 19

Analysis of road traffic accidents severity using a pruned tree-based model
(International Information and Engineering Technology Association, 2023-06-30) Adeliyi, Timothy T.; Oluwadele, Deborah; Igwe, Kevin; Aroba, Oluwasegun Julius
Traffic accidents are becoming a global issue, causing enormous losses in both human and financial resources. According to a World Health Organization assessment, the severity of road accidents affects between 20 and 50 million people each year. This study intends to examine significant factors that contribute to road traffic accident severity. Seven machine learning models namely, Naive Bayes, KNN, Logistic model tree, Decision Tree, Random Tree, and Logistic Regression machine learning models were compared to the J48 pruned tree model to analyze and predict accident severity in the road traffic accident. To compare the effectiveness of the machine learning models, ten well-known performance evaluation metrics were employed. According to the experimental results, the J48 pruned tree model performed more accurately than the other seven machine learning models. According to the analysis, the number of casualties, the number of vehicles involved in the accident, the weather conditions, and the lighting conditions of the road, is the main determinant of road traffic accident severity.
Assessment of user authentication risks in a healthcare knowledge management system
(The Clute Insitute, 2015) Adekanmbi, Oluwole; Green, Paul
Risk management is a concept which has becomes very popular with a number of national and international businesses. Many companies often establish a risk management procedure in their projects for improving performance and increasing profits. Projects undertaken in the construction sector are widely complex, often having significant budgets; therefore, reducing risks associated with projects should be a priority for each project manager. Patient information security has become a matter of interest to healthcare professionals, governments and researchers worldwide. This paper proposes a comprehensive risk assessment methodology that provides a decision support tool, directed to a healthcare system, which can be utilized for evaluating risk involved during user authorization and authentication procedures. Within this context, a process technique was implemented to develop a risk assessment model, which is used to derive the relative priorities of the risk factors associated with a healthcare knowledge management system. The study showed risks involved when users are accessing a healthcare system. It proposes a model for assessing each risk occurring during the user authorization and authentication process. The results of the knowledge generated from the risk assessment provide a basis for deriving a system performance that is desirable for evaluating risk.
Assessment of user authentication risks in a healthcare knowledge management system
(The Clute Institute, 2015) Adekanmbi, Oluwole; Green, Paul
This paper proposes a comprehensive risk assessment methodology that provides a decision support tool, directed to a healthcare system, which can be utilized for evaluating risk involved during user authorization and authentication procedures. Within this context, a process technique was implemented to develop a risk assessment model, which is used to derive the relative priorities of the risk factors associated with a healthcare knowledge management system. The study showed risks involved when users are accessing a healthcare system. It proposes a model for assessing each risk occurring during the user authorization and authentication process. The results of the knowledge generated from the risk assessment provide a basis for deriving a system performance that is desirable for evaluating risk.
Change-point analysis : an effective technique for detecting abrupt change in the homicide trends in a democratic South Africa
(Hindawi Limited, 2020-04-21) Monyeki, Phirime; Naicker, N.; Obagbuwa, Ibidun Christiana
South Africa is considered the murder capital of the world. The challenge for the South African government is to attract foreign investment to boost the economy in a country plagued by homicide. In this study, a change-point analysis was used to pinpoint significant changes in the murder trends in each of the nine provinces in South Africa from 2005 to 2015. This analysis will assist authorities to gain a better understanding of the big picture view in order to mitigate against this crime. Two methods were used in the analysis, namely, CUSUM and Bootstrap. CUSUM was used to analyse data trends, and Bootstrap was used to calculate the occurrence of change points based on the confidence level. The results of the analysis clearly show the abrupt shifts in murder data across the provinces of South Africa. In addition, we used the South African population statistic dataset from 2005 to 2015 to evaluate the relationship between population of the nine provinces and contextualise the murder crime rates year to year and province to province.
Data augmentation for deep learning algorithms that perform driver drowsiness detection
(The Science and Information Organization, 2023-01) Mohamed, Ghulam Masudh; Patel, Sulaiman Saleem; Naicker, Nalindren
Driver drowsiness is one of the main causes of driver-related motor vehicle collisions, as this impairs a person’s concentration whilst driving. With the enhancements of computer vision and deep learning (DL), driver drowsiness detection systems have been developed previously, in an attempt to improve road safety. These systems experienced performance degradation under real-world testing due to factors such as driver movement and poor lighting. This study proposed to improve the training of DL models for driver drowsiness detection by applying data augmentation (DA) techniques that model these real-world scenarios. This paper studies six DL models for driver drowsiness detection: four configurations of a Convolutional Neural Network (CNN), two custom configurations as well as the architectures designed by the Visual Geometry Group (VGG) (i.e. VGG16 and VGG19); a Generative Adversarial Network (GAN) and a Multi-Layer Perceptron (MLP). These DL models were trained using two datasets of eye images, where the state of eye (open or closed) is used in determining driver drowsiness. The performance of the DL models was measured with respect to accuracy, F1-Score, precision, negative class precision, recall and specificity. When comparing the performance of DL models trained on datasets with and without DA in aggregation, it was found that all metrics were improved. After removing outliers from the results, it was found that the average improvement in both accuracy and F1 score due to DA was +4.3%. Furthermore, it is shown that the extent to which the DA techniques improve DL model performance is correlated with the inherent model performance. For DL models with accuracy and F1-Score ≤ 90%, results show that the DA techniques studied should improve performance by at least +5%
Enhancing municipal e-procurement using inventory stock control: South African design approach
(Business Perspectives, 2015) Nzuza, Zwelihle Wiseman; Garbharran, Hari Lall
The control of stock is imperative to ensure efficiency and effectiveness of municipal e-procurement. The main purpose of this study is threefold: to identify critical factors influencing e-procurement; to assess strategies used by inventory stock control to improve successful e-procurement; and to explore significant relationships between inventory stock control and e-procurement, in the South African municipalities, with specific reference to the KwaZulu-Natal (KZN) Province. This study uses the 5Ps theoretical framework (purpose, principles, processes, people and performance). This census study was descriptive, cross-sectional and quantitative in nature with 62 questionnaires administered by members of staff at procurement of the South African municipalities. Data are analyzed with the aid of the Statistical Package for Social Sciences (SPSS) version 21.0. The results indicate that stock inspection, control strategies, organizational support, staff skills and involvement, and sustainability of the 5Ps attributes are the main promotional tools for inventory stock control to improve e-procurement in the South African municipalities. Interestingly, the hypotheses of the study are accepted and the departments reveal a significant relationship with purpose (p=.008*), people (p=.021*), principles (p=.004*), and organizational support (p=.008*). The study recommends strategic advancements in the stock control to improve e-procurement, and it also recommends that other researches to test and validate a proposed model.
Evaluation of access to finance, market and viability of small and medium-sized enterprises in South Africa
(LLC CPC Business Perspectives, 2021-03-15) Msomi, Thabiso Sthembiso; Olarewaju, Odunayo Magret
Access to finance and market has been described as a predominant challenge confronting small and medium-sized enterprises (SMEs). Hence, this paper seeks to evaluate access to finance, market access and viability of SMEs. A quantitative research method and a purposive sampling technique were used to select the participants for this study. Respondents from retail, manufacturing, construction and agricultural SMEs operating in Durban, KwaZulu-Natal, were selected to complete the structured questionnaires. 310 questionnaires were returned out of 321 distributed. The study revealed a significant effect of access to finance (absolute value 0.425) and access to market (absolute vale 0.373) on SMEs’ viability with a 5% level of significance. Thus, it was concluded that access to finance uniquely accounted for the larger proportion of the variance in the regression model. Thus, this study suggests that owners of SMEs should pay greater attention to access to finance in running their businesses, and the Government should aid SMEs to market their products and keep their businesses viable. Public loans or the government supported loans should be made available for SMEs with soften requirements in order to stimulate economic growth.
Exploring TOPSIS based algorithm for non-homogeneous alternatives in group decision making
(International Association of Engineers, 2012) Olugbara, Oludayo O.; Thiruthlall, Nepal
The purpose of this work is to explore an algorithm based on Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for non-homogeneous alternatives in group decision making. In this particular case of evaluating a set of decision alternatives, an individual expert expresses hedonic judgments for a subset of decision alternatives depending on his/her knowledge about the alternatives. The structure of the decision making problem generates a local matrix of judgmental responses for each decision alternative. Signal-to-Noise Ratio (SNR) determines the ratio of relevant information to irrelevant information in the local response matrices. The SNR vectors of all decision alternatives are aggregated into a global decision matrix and passed as argument to the TOPSIS algorithm to rank the alternatives. The attractiveness of this algorithm is that we do not have to modify the existing TOPSIS. The algorithm was used to rank 10 different sports that were evaluated by 34 respondents in a survey and the result is practically appealing. This type of non-homogeneous group decision making is particularly useful in selecting an optimal decision alternative among a large set of alternatives where opinions of a large group of stakeholders count. This is for instance in opinion polls, comparison of market products/services and Delphi process where an expert does not necessarily have to possess full knowledge about all decision alternatives or be jack of all trades.
Health information system and health care applications performance in the healthcare arena : a bibliometric analysis
(MDPI AG, 2022-11-12) Epizitone, Ayogeboh; Moyane, Smangele Pretty; Agbehadji, Israel Edem
There have been several studies centred on health information systems with many insights provided to enhance health care applications globally. These studies have provided theoretical schemes for fortifying the enactment and utilisation of the Health Information System (HIS). In addition, these research studies contribute greatly to the development of HIS in alignment with major stakeholders such as health practitioners and recipients of health care. Conversely, there has been trepidation about HIS' sustainability and resilience for healthcare applications in the era of digitalization and globalization. Hence, this paper investigates research on HIS with a primary focus on health care applications to ascertain its sustainability and resilience amidst the transformation of the global healthcare space. Therefore, using a bibliometric approach, this paper measures the performance of health information systems and healthcare for health care applications using bibliometric data from the web of science database. The findings reveal solid evidence of the constructive transformation of health information systems and health care applications in the healthcare arena, providing ample evidence of the adaptation of HIS and health care applications within the healthcare arena to the fourth industrial revolution and, additionally, revealing the resilient alignment of health care applications and health information systems.
A hybridized framework for designing and evaluating e-learning students’ performance in medical education
(IEEE, 2022-10-27) Oluwadele, Deborah; Singh, Yashik; Adeliyi, Timothy T.
The COVID-19 pandemic resulted in the hurried adoption of e-learning with no proper need analysis to inform the design and subsequent evaluation of students’ performance in e-learning in medical education. Consequently, several studies evaluating performance in e-learning in medical education do so by conducting pre-test and post-test with no defined framework or model to guide the evaluation. This makes the findings from these studies subjective and biased since factors that possibly impact students’ performance were neither considered in the design of the course nor measured and reported in the evaluation studies. We, therefore, introduce an essential pedagogical e-learning concept by developing a framework to inform the design and evaluation of students’ performance in e-learning in medical education via the thoughtful fusion of the Task-Technology Fit Model and the Kirkpatrick Evaluation Model. Our hybrid framework was piloted at the University of KwaZulu-Natal, Durban, South Africa and findings emphasize the need for alignment between learning tasks, technology infrastructures, individual traits, and contextual limitations of students as key factors in determining how well students perform in the classroom and their clinical practices at work. This study advances the body of knowledge by providing a well-brainstormed and intricately designed framework to guide the design of courses and evaluation of student’s performance in an e-learning context in medical education.
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.
Lung cancer prediction using neural network ensemble with histogram of oriented gradient genomic features
(Hindawi Publishing Corporation, 2015) Adetiba, Emmanuel; Olugbara, Oludayo O.
This paper reports an experimental comparison of artificial neural network (ANN) and support vector machine (SVM) ensembles and their “nonensemble” variants for lung cancer prediction. These machine learning classifiers were trained to predict lung cancer using samples of patient nucleotides with mutations in the epidermal growth factor receptor, Kirsten rat sarcoma viral oncogene, and tumor suppressor p53 genomes collected as biomarkers from the IGDB.NSCLC corpus. The Voss DNA encoding was used to map the nucleotide sequences of mutated and normal genomes to obtain the equivalent numerical genomic sequences for training the selected classifiers. The histogram of oriented gradient (HOG) and local binary pattern (LBP) state-of-the-art feature extraction schemes were applied to extract representative genomic features from the encoded sequences of nucleotides. The ANN ensemble and HOG best fit the training dataset of this study with an accuracy of 95.90% and mean square error of 0.0159. The result of the ANN ensemble and HOG genomic features is promising for automated screening and early detection of lung cancer. This will hopefully assist pathologists in administering targeted molecular therapy and offering counsel to early stage lung cancer patients and persons in at risk populations.
A meta-analysis of the economic impact of carbon emissions in Africa
(LLC CPC Business Perspectives, 2022-11-09) Rajkoomar, Mogiveny; Marimuthu, Ferina; Naicker, Nalindren; Damascene Mvunabandi, Jean
The economic impact of carbon emissions in Africa is gaining traction in the extant literature. This study adopted Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) to concomitantly track data on carbon emissions versus economic growth in Africa from 2018 to 2022 providing evidence from a meta-analysis. Through database searches, 591 publications were identified. A machine learning algorithm called Latent Dirichlet Allocation (LDA) was used as a visualization technique for reporting trends in the eleven papers selected for the analysis. Identifying, evaluating, and summarizing the findings of all relevant individual studies conducted in Africa on the impact of economic growth on carbon emissions contributes to the existing body of knowledge. This study fills a critical gap by surveying the studies conducted in Africa in the last five years, implying that economic growth negatively and significantly triggers CO2 emissions in Africa. The debate on the economic impact of CO2 emissions in Africa, the most vulnerable continent to climate change, is elucidated. The findings tracked sources of data for carbon emissions in Africa. The results showed that although some studies reported a positive correlation (and some a negative correlation) between economic growth and carbon emissions, most studies concur that the economic impact of carbon emissions over a timeline can be explained by the Environmental Kuznets Curve (EKC) hypothesis. Therefore, there is a dire need for African countries to strengthen economic growth without deteriorating their environment or having ecological footprint. Future research must assess whether this trend on the economic impact of carbon emissions in Africa continues. AcknowledgmentThe authors express their appreciation to the Durban University of Technology for providing the resources to conduct this study.
Node localization in wireless sensor networks using a hyper-heuristic DEEC-Gaussian gradient distance algorithm
(Elsevier BV, 2023-03) Aroba, Oluwasegun Julius; Naicker, Nalindren; Adeliyi, Timothy T.
In the recent age of technological advancements, wireless sensor networks are an important application for smart modernized environments. In WSNs, node localization has been an issue for over a decade in the research community. One of the goals of localization in a wireless sensor network is to localize sensor nodes in a two-dimensional plane. Localization in wireless sensor networks helps to supply information to aid decision-making from the aggregated data that are sent from packets to base stations. Internet of Things with the use of Global Positioning Systems for tracking sensor zones is not a cost-effective means of solution. In the extant literature, there have been a variety of algorithms to identify unknown sensor locations in wireless sensor networks. This research paper aims to address the problem of determining the location of the sensor node at the base station with minimum localization error when the data between the nodes is transmitted wirelessly. To detect the location of an unknown sensor node packets sent to the destinations, the total number of anchor nodes, location error and distance estimation error were considered. The DEEC-Gauss Gradient Distance Algorithm has a lower localization error than the Weighted Centroid Localizations algorithm, Compensation Coefficient algorithm, DV-Hop algorithm, Weighted Hyperbolic algorithm and Weighted Centroid algorithm for the same ratio of anchor nodes and WSN configuration. According to the study's findings, the DGGDEA has an average localization error of 11% for anchor nodes (20-80), and an average localization error of 11.3% for anchor nodes 200-450. Hence, the DEEC-Gaussian Gradient Distance Elimination Algorithm (DGGDEA) showed higher accuracy with comparison to the modern-day approaches.
A review : the bibliometric analysis of emerging node localization in wireless sensor network
(2023-07-31) Aroba, Oluwasegun Julius; Nalindren, Naicker; Timothy, Adeliyi; Avintha, Gupthar; Khadija, Karodia
As research in Node localization in WSN becomes ubiquitous, there is a dire need to interpret and map the increasing scientific knowledge and evolutionary trends so that a firm foundation can be laid for identifying knowledge gaps and advancing the domain. There is a critical need to interpret and map the expanding body of scientific knowledge and evolutionary trends as Node localization research in WSN spreads widely to establish a solid foundation for identifying knowledge gaps and developing the domain. Hence, this study aims to undertake a bibliometric analysis of node localization approaches. The Scopus central assemblage database was searched for titles that included "node localization", "wireless sensor network," and "WSN". A total of 1618 documents were published within the nineteen-study period (2003 - 2022). Microsoft Excel 365, R Bibliometric and Biblioshiny packages were implored for statistical analysis of approved published research articles. This study highlights the trends and current state of node localization research in WSN. It can aid researchers in gaining a thorough understanding of the most recent node localization techniques used in WSN
The role of forensic auditing techniques in preventing nongovernment organisations’ financial statement fraud in South Africa using a proactive approach
(2022-12-28) Mvunabandi, Jean Damascene; Nomlala, Bomi; Prof Othmar, Lehner
This study is designed to investigate the role of proactive forensic auditing techniques in preventing fraudulent activities among NGOs in the eThekwini region. The population of this study comprised 87 knowledgeable staff in the field of fraud risk management and auditing selected from 30 NGOs. Primary data was gathered using an online questionnaire and semistructured interviews. Quantitative data were analysed with the aid of SPSS version 27, while NVivo12 assisted in thematically analysing all interview questions. Analysis of movement Structures (AMOS version 27) was also used to estimate statistical models. Empirical findings proved that a proactive approach to forensic auditing techniques could hugely assist in preventing fraudulent activities among non-government organisations in the eThekwini region, South Africa. Relying on these empirical findings, this study proposes a model for proactively preventing financial and economic crimes in NGOs. This study contributes to the current body of knowledge and further contributes to fraud risk management in NGOs. This study has also provided a very robust plan for future researchers
An SAP enterprise resource planning implementation using a case study of hospital management system for inclusion of digital transformation
(2023-07-31) Aroba, Oluwasegun Julius; Adefemi Oluwaniyi, Owoputi; Temitayo, Mathew Fagbola
Enterprise resource planning (ERP) system implementation necessitates substantial organizational and technological changes. These will have an impact on system stakeholders with various viewpoints and interests. It is crucial to analyze stakeholders in these situations and others like them to comprehend their attitudes and expectations toward the system. This experience report discusses problems with a medical institution's regular SAP ERP setup. This report includes insights and suggestions based on traditional system experience regarding a project to adopt SAP ERP at a healthcare facility. It ought to be a beneficial resource for all parties participating in the ERP installation process in the public healthcare sector. Many hospitals struggle to implement system analysis programs (SAP) and enterprise system programs (ERP) to assist in their business processes. The SAP ERP System is an integrated and consolidated way of easily flowing information within the organization's department. The authors identified hospitals' failure to implement a suitable SAP ERP system that works under their operations, leading to inefficiencies in their supply chain management process. This study addresses significant operational issues and productivity of the hospital management processes by administering 50 questionnaires and using Cronbach's alpha to analyze the responses. The Cronbach alpha is considered acceptable if the result is above 0.70. Our Cronbach result is 0.77. The benefits and difficulties of using SAP ERP provide a comprehensive review of the operations of Hospital and Healthcare Centre SAP ERP system digital transformations in supply chain management. Furthermore, the authors developed a framework to assist in choosing the proper tracking and transferring of information within the hospital technology that we named hospitec
Smart face masks for COVID-19 pandemic management : a concise review of emerging architectures, challenges and future research directions
(Institute of Electrical and Electronics Engineers (IEEE), 2023-01-15) Fagbola, Temitayo Matthew; Fagbola, Funmilola Ikeolu; Aroba, Oluwasegun Julius; Doshi, Ruchi; Hiran, Kamal Kant; Thakur, Surendra Colin
Smart sensing technology has been playing tremendous roles in digital healthcare management over time with great impacts. Lately, smart sensing has awoken the world by the advent of smart face masks (SFMs) in the global fight against the deadly Coronavirus (Covid-19) pandemic. In turn, a number of research studies on innovative SFM architectures and designs are emerging. However, there is currently no study that has systematically been conducted to identify and comparatively analyze the emerging architectures and designs of SFMs, their contributions, socio-technological implications, and current challenges. In this article, we investigate the emerging SFMs in response to Covid-19 pandemic and provide a concise review of their key features and characteristics, design, smart technologies, and architectures. We also highlight and discuss the socio-technological opportunities posed by the use of SFMs and finally present directions for future research. Our findings reveal four key features that can be used to evaluate SFMs to include reusability, self-power generation ability, energy awareness and aerosol filtration efficiency. We discover that SFM has potential for effective use in human tracking, contact tracing, disease detection and diagnosis or in monitoring asymptotic populations in future pandemics. Some SFMs have also been carefully designed to provide comfort and safety when used by patients with other respiratory diseases or comorbidities. However, some identified challenges include standards and quality control, ethical, security and privacy concerns.
Using cloud computing to mitigate rural e-learning sustainability and challenges
(International Association of Engineers, 2012) Odunaike, S. A.; Olugbara, Oludayo O.; Ojo, Sunday O.
The Internet Technology is at forefront of transforming education and opportunities around the globe by allowing different kind of interaction and innovation among various educational institutes and students alike, all participating in the global online innovations. In particular, educators have realized that technology enhanced learning, offers flexible and powerful way of accomplishing wide range of opportunities that have been important and resourceful in schools, such as gaining access to universal information resources that relieve academic staff of their work load leaving time for professional development and time to improve on their studies and research output which have been so elusive for sometime now. Extending this novelty and gain to the rural settings raises lot of concerns and challenges that threaten its sustainability to its core implementation. Cloud computing brings wide ranges of computing power, innovations and shifts in paradigms of Information Technology. This paper will probe whether the promise of cloud computing could be employ to enhance or mitigate the challenges poised to e- learning implementation and sustainability in the rural setting using descriptive research approach. The paper will inform stakeholders of any gains or prospect of using cloud computing to downgrade the e-learning sustainability problems that have plagued the implementation of e-learning in the rural setting as unviable future instructional offering.