Repository logo
 

Faculty of Accounting and Informatics

Permanent URI for this communityhttp://ir-dev.dut.ac.za/handle/10321/1

Browse

Subject: search.filters.subject.Decision support systems

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Intelligent decision support system for selection of Learning Apps to promote critical thinking in first year programming students
    (2021-12-09) Singh, Kesarie; Naicker, Nalen; Rajkoomar, Mogiveny
    The disruption on higher education across the globe through adverse events such as student strikes, natural disasters and pandemics like Coronavirus Disease 2019 (Covid-19), can have catastrophic long-term effects on its sustainability unless there are significant and innovative research endeavours to mitigate this impact. Never before has the desire to keep learners motivated, engaged and successful in advancing their knowledge and perfecting their 21st century skills through student-centred, technology-rich teaching and learning practices, become so imperative across disciplines and job profiles. In particular, the problem associated with teaching programming to novice learners is further exacerbated by the complex and abstract nature of the field and the heavy reliance on 21st century skills such as critical and computational thinking. As a result, a kaleidoscope of research into programming self-efficacy, the complexity of the field, teaching methods and a variety of teaching tools, have emerged over the recent past. In response, the aim of this research was to use decision support systems to obtain student-centred preferences for learning applications to promote critical thinking in first year programming students. This study focuses on the visual programming environment and critical thinking as the gateway skill for student success in understanding programming. The extensive literature review has revealed an array of learning Apps and a multiplicity of critical thinking criteria that serve a diverse set of needs and expectations. Therefore, research to develop a multiple attribute decision-making model is needed to assist academics make quick, scientifically-proven, accurate and collective decisions about which learning App to choose from the range of available alternatives. The study used decision theory and Diane Halpern’s 4-part model for critical thinking as the theoretical frameworks for evaluating and selecting learning Apps on the basis of its capacity to promote critical thinking. As a quantitative study, it randomly selected 217 students from a population of 500 programming students to rate four learning Apps, namely, Scratch, Alice, Blockly and MIT App Inventor, against critical thinking criteria and established Scratch as the App that best promotes critical thinking among first year programming students. Consequently, its distinctiveness lies in its use of the Fuzzy TOPSIS (Technique for Order Preference by Similarity to Ideal Situation) multi-criteria decision-making algorithm to rank criteria for critical thinking, calculate their weights on the basis of informed opinion and hence scientifically deduce the best rated App among the available alternatives that promote critical thinking among first year programming students. Furthermore, the study offers useful, insightful and ranked critical thinking criteria to formulate a user-friendly, transparent and evidence-based framework for App selection among academics teaching programming in higher education institutions.
  • Thumbnail Image
    Item
    Intelligent decision support systems for managing the diffusion of social computing in school-based ubiquitous learning
    (2022-01-06) Sam, Caitlin; Naicker, Nalen; Rajkoomar, Mogiveny
    The past decade has seen an explosion in social media applications. Most adolescents in South Africa have access to social media applications despite the country’s economic inequalities. The drive for social media applications is important to enhance human connectedness. In unprecedented times social computing can be utilised in school-based learning to benefit learners. Climate change has propagated extreme weather patterns which has increased the occurrence of natural disasters and diseases. The emergence of the novel Coronavirus resulted in most countries implementing nation-wide forms of lockdown to curb the spread of infection. Consequently, these adverse phenomena across the globe are disruptive to conventional schoolbased education. Ubiquitous learning (u-learning) relates to learning that occurs at any place without time constraints. In some schools, u-learning has become a conventional learning approach and pedagogy but there are various education and technology attributes that must be addressed for the penetration of social computing in schools. Therefore, there is a need to guide learners and school-based instructors on their preferences of digital access and social media applications. The main aim of the study was to investigate social media-driven Intelligent Decision Support Systems using live data, to assist instructors and learners manage the diffusion of social computing in school-based ubiquitous learning. In pursuing this study, a quantitative research methodology was used for the collection of data from learners and instructors from the schools in the eThekwini Region, namely, Umlazi District and Pinetown District of KwaZulu-Natal Province, South Africa. A survey was conducted to elicit data from participants on their use of social computing for u-learning. The approximate target population size was 129 421 individuals with a sample size of 384 participants. There were 260 respondents with an acceptable response rate of 67,71%. The study derived attributes for ranking the social media applications and Principal Component Analysis which is an unsupervised Machine Learning algorithm reduced the dimensionality of the attributes. The multi-criteria decision-making algorithm, Fuzzy Technique of Order Preference Similarity Ideal Solution was implemented to rank the social media applications in line with the dimensionality reduced criteria based on the subjective decisions of expert decision makers. Data Envelopment Analysis, another multi-criteria analysis method was utilised to score the efficiency of the devices for u-learning. The results showed the most precise, mathematically approved social media applications and devices that can support u-learning in schools. An automated application based on research evidence using Intelligent Decision Support Systems was designed as a research output.
  • Thumbnail Image
    Item
    Development of multi-person multi-attribute matchmaking decision system
    (2017-08-23) Uko, Edidiong Idungima; Olugbara, Oludayo O.; Manish, Joshi
    This dissertation reports on the development of an algorithm based on an existing matchmaking method to solve diverse decision problems in a multi-person environment. The capacity to effectively achieve a lucrative and accurate decision making is a critical aspect of resource management. But the accuracy of a decision making process can be highly compromised because of the high subjectivity and multiple conflicting attributes that are present in human judgement. multi-person decision making is an effective approach for achieving a lucrative and accurate decision making process. The multi-person decision process has proven to be tedious mainly because the existing multi-person decision making methods are extensions of single decision making methods. This imposes additional computational resources, especially for a large number of decision makers because they aggregate the preferences of several decision makers into a unified format.This work therefore seeks to improve the multi-person decision making process using a matchmaking approach. In doing so, the Hunt ForTune matchmaking algorithm was investigated and improved for this purpose. Thus, the preferences of decision makers for each attribute are collected as an attribute description vector. The attribute, its description vector, flexibility and priority vector are compactly represented as a 4-tuple profile. The improved Hunt ForTune matchmaking algorithm is applied to different sets of multi-person decision problems and offered as an effective way of enhancing decision accuracy. The improved matchmaking decision algorithm is compared with a novel mathematical technique of Hausdorff distance. Results generally show that multi-person matchmaking algorithm is suitable and efficient for diverse decision making in the presence of multiple decision makers. The practical implication of the proposed multi-person matchmaking algorithm for decision making is that it provides a less complicated way to capture and represent the preferences of multiple decision makers irrespective of decision domain. The originality of the work reported in this dissertation is built on a matchmaking algorithm by introducing effective profile representation using vector analysis approach to capture the preferences of multiple decision makers and similarity metrics to provide an efficient and robust way to accurately perform a multi-person decision process.