Repository logo
 

Research Publications (Engineering and Built Environment)

Permanent URI for this collectionhttp://ir-dev.dut.ac.za/handle/10321/215

Browse

Filters

2022 - 20232

Settings

Author: search.filters.author.Pillay, NelendranSubject: search.filters.subject.MATLAB

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    An evaluation of digital and artificial intelligent tools in an electronic and computer engineering curriculum at a university of technology in South Africa
    (2023-12-08) Maharaj, Shaveen; Pillay, Nelendran
    Digital tools have become integral to higher education, offering a wide array of opportunities for improving the learning experience. This study explores the adoption and impact of digital tools in engineering education. The study employed a mixed-methods approach, utilizing quantitative data and qualitative data collection. Participants included both staff and students in a comprehensive analysis. The integration of technology in higher education has witnessed significant growth, encompassing educational software, learning management systems (LMS), and online platforms. In engineering education, tools like Moodle, MATLAB, Turnitin, Simulink, and MS Teams have gained prominence (Joksimović & Milosavljević, 2016). However, their effectiveness in achieving educational goals remains to be fully evaluated. One key advantage of digital tools is personalized learning. Advancements in technology, including artificial intelligence (AI), enable adaptive learning software like ChatGPT to tailor lesson plans based on individual needs. Furthermore, digital tools expand students' access to resources, such as online lectures, readings, and simulations, supplementing traditional teaching methods. They also facilitate collaborative learning and group projects through platforms like Moodle and Blackboard, enabling effective communication, document sharing, and teamwork. The findings of this study shed light on the current landscape of digital tools in engineering education. A SWOT analysis is applied to inform future strategies. The study emphasizes the need for a comprehensive evaluation of the effectiveness of these tools and their potential to transform engineering education. This research contributes to the ongoing dialogue on optimizing digital tools for personalized learning and collaborative education in engineering programs. It underscores the importance of evaluating their impact and tailoring their use to enhance the overall educational experience.
  • Thumbnail Image
    Item
    Machine learning classifiers based on HoG features extracted from locomotive neutral section images
    (IEEE, 2022-10-27) Mcineka, Christopher Thembinkosi; Pillay, Nelendran
    This paper presents a comparative study on machine learning algorithms for neutral section image classification. The classifiers are trained by employing the Histogram of Oriented Gradient features that are extracted from the neutral section dataset [1]. A neutral section is a phase break that is used on the Transnet freight rail system to separate the single-phase supply from the 25kV three-phase overhead traction supply. The 25kV is a stepped-down voltage from an 88kV three-phase supply coming from the national grid. While the main purpose of the neutral section is to separate phase voltages, electric locomotives can traverse through these phases by switching On and Off. This auto-switching is possible through induction magnets installed in between the rails and with magnet detection sensors installed underneath the locomotives. However, a computer vision model has been developed, trained, and tested with a neutral section dataset containing images having open and close markers [1]. This paper, therefore, utilises this dataset to provide performance comparison on several machine learning classification algorithms viz. Decision Tree, Discriminant Analysis, Support Vector Machine, K-Nearest Neighbors, Ensemble, Naïve Bayes, and Convolutional Neural Network. A confusion matrix, F1- measure and computation time are employed to measure the performance of each classifier. The MATLAB Classification Learner application was used to obtain the results. The results show that the Linear Support Vector Machine performs best when considering performance and prediction speed. The Linear Support Vector Machine achieved a training accuracy of 93.40% with a test accuracy reaching 94% at a prediction speed of 75 objects per second (computation time).