3. Electronic Theses and Dissertations (ETDs) - All submissions
Permanent URI for this communityhttps://wiredspace.wits.ac.za/handle/10539/45
Browse
4 results
Search Results
Item Partially automated grading of short free-text responses in computer science through sentence embedding and clustering(2024) Philip, SheenaA significant portion of educators‘ time is spent marking assessments, which could be better utilized for teaching and research to enhance the overall education experience. To assess higher-order thinking, questions that require short text answers are necessary. However, automatically grading these questions is much more complex since computers need to understand the underlying semantic meaning of the text. Furthermore, the dataset available for grading is limited to a few hundred responses due to the smaller size of lecture classes, which is not sufficient for evaluating most NLP and machine learning methods. To address this, this research aims to partially automate the grading of short free-text responses in computer science by grouping similar responses and manually marking specific submissions that best represent the group. It will explore various sentence embedding techniques, clustering techniques, and sampling techniques, and evaluate the Enhancement of Clustering by Iterative Classification (ECIC) algorithm, which improves cluster quality. The study found that Agglomerative clustering combined with Universal Sentence Encoder (USE) and a sampling strategy that marks submissions based on their distance to the center of the cluster produced the best results, balancing time saved and meeting the performance criteria. This combination resulted in a 65% reduction in the time it takes to grade a question. However, the ECIC algorithm was not effective on datasets that comprises a few hundred data points.Item Automated parking space detection(2018) Nyambal, Julien CedricParking space management is a problem that most big cities encounter. Without parking space management strategies, the traffic can become anarchic. Compared to physical sensors around the parking lot, a camera monitoring it can send images to be processed for vacancy detection. This dissertation implements a system to automatically detect and classify spaces (vacant or occupied) in images of a parking lot. Detection is done using the Region based Convolutional Neural Networks (RCNN). It reduces the amount of time that would otherwise be spent manually mapping out a parking lot. After the spaces are detected, they are classified as either vacant or occupied. It is accomplished using the Histograms of Oriented Gradients (HOG) with the Linear and Radial Basis Function (RBF) Support Vector Machines (SVM), Convolutional Neural Networks (CNN) and a Hybrid approach. The classifiers are trained, tested and validated using data collected for this research. We compared the results of the Hybrid classifier against CNN and SVMs. The Hybrid classifier performed better than all the other ones with an accuracy of 89.36% and a precision of 82.54%, which is the best score obtained from all the other classifiers used. Novel contributions of this work include the new labeled database, the use of the RCNN for bay detection, and the classification of bays using the hybrid CNN and SVM.Item Object oriented development a logical approach to control system software design(2016-08-26) Bricker, R IAutomation is currently being used to an ever increasing degree in industrial plants. However most of these applications require only a few basic control concepts repeated for each piece of equipment. There is often a fair amount of interaction between pieces of equipment in terms of safety interlocking and sequencing. Despite this each piece of software remains an autonomous entity receiving the necessary external data it requires. The principles of OBJECT ORIENTED DESIGN are suited to the development of this type of software. This dissertation will demonstrate that object oriented development has distinct benefits over more classical design techniques. Generalized software for controlling a minerals processing plant will be conceptually designed, using techniques implemented in C++ to demonstrate the basic hypothesis. This will attempt to encompass all the available design techniques of object oriented design into an area that has traditionally developed its own software development paradigm.Item A polarographic and potentiometric study of metal-ligand equilibria: Instrumentation and investigations of systems with non-reversible electrode reactions(2006-11-13T13:05:09Z) Mkwizu, Tumaini Samuel PeterNew possibilities in collection of polarographic and potentiometric experimental data in studies of metal–ligand systems by automated instrumental methods, and subsequent treatment of the polarographic data, whereby the degree of reversibility of the electrode processes varies, have been investigated in this work. An automated instrumental set–up was developed for applications in studies of metal–ligand solution equilibria by potentiometry and sampled Direct Current Polarography (DCP). The new set–up was designed based on virtual instrumentation principles whereby several commercially– available hardware units as well as custom–built electronic components, were interfaced to a personal computer that was equipped with appropriate hardware and control programs. The instrumental set–up was tested and validated by studying the protonation equilibria of the ligand glycine by Glass Electrode Potentiometry (GEP) as well as the complexation of the ligand glycine with Cd2+ by GEP and DCP. The new set–up provides increased versatility, accuracy and convenience in obtaining large numbers of experimental points in solution equilibria studies by DCP and GEP as opposed to the use of tedious and time–consuming manual methods. Nonlinear curve–fitting procedures, based on closed–form models that were derived here from suitable theoretical equations identified from literature, have been investigated in this work for applications in analysis of DC curves recorded on metal–ligand systems with variation in electrochemical reversibility. The applicability and limitations of the curve–fitting procedures developed have been tested in analysis of the DCP data collected on several metal–ligand systems involving Cd2+, Pb2+, Zn2+ and the ligands glycine and sarcosine, whereby the DCP studies of these systems exhibited reversible, quasi–reversible or irreversible electrochemical processes. Information on applicability and limitations of the proposed methods investigated in this work was derived by comparison of the results obtained from DCP, using the proposed methods, with either reported literature data and/or results obtained in this work by the independent analytical technique of GEP, which was deployed wherever it was found to be applicable to study the metal–ligand systems considered.