Magister Scientiae - MSc (Computer Science)

Permanent URI for this collection

https://hdl.handle.net/10566/14793

Browse

Now showing 1 - 20 of 99

5G wireless network support using umanned aerial vehicles for rural and low-Income areas
(University of the Western Cape, 2020) Maluleke, Hloniphani; Bagula, B.A.
The fifth-generation mobile network (5G) is a new global wireless standard that enables state-of-the-art mobile networks with enhanced cellular broadband services that support a diversity of devices. Even with the current worldwide advanced state of broadband connectivity, most rural and low-income settings lack minimum Internet connectivity because there are no economic incentives from telecommunication providers to deploy wireless communication systems in these areas. Using a team of Unmanned Aerial Vehicles (UAVs) to extend or solely supply the 5G coverage is a great opportunity for these zones to benefit from the advantages promised by this new communication technology. However, the deployment and applications of innovative technology in rural locations need extensive research.
A Comparison of Machine Learning Techniques for Facial Expression Recognition
(University of the Western Cape, 2018) Deaney, Mogammat Waleed; Venter, Isabella
A machine translation system that can convert South African Sign Language (SASL) video to audio or text and vice versa would be bene cial to people who use SASL to communicate. Five fundamental parameters are associated with sign language gestures, these are: hand location; hand orientation; hand shape; hand movement and facial expressions. The aim of this research is to recognise facial expressions and to compare both feature descriptors and machine learning techniques. This research used the Design Science Research (DSR) methodology. A DSR artefact was built which consisted of two phases. The rst phase compared local binary patterns (LBP), compound local binary patterns (CLBP) and histogram of oriented gradients (HOG) using support vector machines (SVM). The second phase compared the SVM to arti cial neural networks (ANN) and random forests (RF) using the most promising feature descriptor|HOG|from the rst phase. The performance was evaluated in terms of accuracy, robustness to classes, robustness to subjects and ability to generalise on both the Binghamton University 3D facial expression (BU-3DFE) and Cohn Kanade (CK) datasets. The evaluation rst phase showed HOG to be the best feature descriptor followed by CLBP and LBP. The second showed ANN to be the best choice of machine learning technique closely followed by the SVM and RF.
Advanced computational techniques for pipe burst detection and localisation in water distribution networks
(University of the Western Cape, 2025) Mzembegwa, Takudzwa Sikumbuzo
Pipe bursts cause a considerable loss of treated water, increase the risks of environmental contamination and are a health hazard for the end-user as they can create a passage for contaminants to enter water distribution networks (WDN). Identifying pipe burst locations will help water service providers repair pipe bursts in a timely manner. Given the ever-increasing importance of water, a great number of methods to locate pipe bursts have been proposed. But none have proved to produce results accurate enough for water service providers to heavily rely on. Therefore, this thesis presents a comprehensive investigation addressing two critical challenges in pipe burst localisation: optimising fully-linear deep learning (FL-DL) architectures for accurate detection and developing real-time localisation methods using Change point detection (CPD) algorithms. The research is structured in two main phases to tackle these challenges. The first phase conducts a comparative analysis of hyperparameter optimisation techniques, Particle Swarm Optimisation (PSO) and Population-Based Training (PBT), for FL-DL architectures. This investigation addresses the limitations of traditional detection methods, which are often costly, labour-intensive, and limited in scalability. Results demonstrate PSO’s superior performance, with PSO-optimised models consistently achieving higher accuracy and lower variance compared to PBT implementations. Notably, PSOFL-ResNet achieved a mean accuracy of 98.92% and PSOFL- DenseNet reached 98.78%, significantly outperforming their PBT counterparts at 96.70% and 97.22% respectively.
Adversarial deep reinforcement learning for autonomous cyber defense in software defined networks
(University of the Western Cape, 2024) Borchjes, Luke David
The rapid advancement of technologies such as IoT devices, Internet-based AI systems, and 5G networks has significantly heightened the demand for robust cybersecurity solutions. Traditional network architectures face challenges in scalability, security, and manageability, leading to the adoption of software-defined networking (SDN) as a flexible and secure alternative. However, the dynamic nature of tra!c patterns in SDN necessitates frequent reconfiguration, highlighting the importance of autonomous decision-making tools. Reinforcement learning (RL), and its deep learning extension, deep reinforcement learning (DRL), have proven e”ective in addressing these challenges. Nevertheless, DRL algorithms are susceptible to adversarial attacks, underscoring the need for research into more resilient algorithms, such as NEC2DQN and DDQN, for both defensive and o”ensive applications in SDN environments. The evolution of network security has shifted from rule-based systems to autonomous solutions, with Deep Reinforcement Learning (DRL) emerging as a leading approach. Algorithms such as Deep Q-Network (DQN), Double Deep Q-Network (DDQN), and Neural Episodic Control to Deep Q-Network (NEC2DQN) have advanced the field, but their adaptability has introduced vulnerabilities to adversarial attacks, necessitating ongoing testing and improvement to ensure robust, adaptive models.
Affective gesture fast-track feedback instant messaging (AGFIM)
(University of Western Cape, 2005) Adesemowo, A. Kayode; Tucker, William D.
Text communication is often perceived as lacking some components of communication that are essential in sustaining interaction or conversation. This interaction incoherency tends to make text communication plastic. It is traditionally devoid of intonation, pitch, gesture, facial expression and visual or auditory cues. Nevertheless, Instant Messaging (IM), a form of text communication is on the upward uptake both on PCs and on mobile handhelds. There is a need to rubberise this plastic text messaging to improve co-presence for text communications thereby improving synchronous textual discussion, especially on handheld devices. One element of interaction is gesture, seen as a natural way of conversing. Attaining some level of interaction naturalism requires improving synchronous communication spontaneity, partly achieved by enhancing input mechanisms. To enhance input mechanisms for interactive text-based chat on mobile devices, there is a need to facilitate gesture input. Enhancement is achievable in a number of ways, such as input mechanism redesigning and input offering adaptation. This thesis explores affective gesture mode on interface redesign as an input offering adaptation. This is done without a major physical reconstruction of handheld devices. This thesis presents a text only IM system built on Session Initiation Protocol (SIP) and SIP for Instant Messaging and Presence Leveraging Extensions (SIMPLE). It was developed with a novel user-defined hotkey implemented as a one-click context menu to "fast-track" text-gestures and emoticons. A hybrid quantitative and qualitative approach was taken to enable data triangulation. Results from experimental trials show that an Affective Gesture (AG) approach improved IM chat spontaneity/response. Feedback from the user trials affirms that AG hotkey improves chat responsiveness, thus enhancing chat spontaneity.
An authoring tool for generalised scenario creation for SignSupport
(University of the Western Cape, 2016) Duma, Lindokuhle Sifso; Tucker, William
This thesis describes the development cycles of an authoring tool that generalises scenario creation for SignSupport. SignSupport is a mobile communication tool for Deaf people that currently runs on an Android smartphone. The authoring tool is computer-based software that helps a domain expert, with little or no programming skills, design and populate a limited domain conversation scenario between a Deaf person and a hearing person, e.g., when a Deaf patient collects medication at a hospital pharmacy or when a Deaf learner is taking a computer literacy course. SignSupport provides instructions to the Deaf person in signed language videos on a mobile device. The authoring tool enables the creation and population of such scenarios on a computer for subsequent 'playback' on a mobile device. The output of this authoring tool is an XML script, alongside a repository of media les that can be used to render the SignSupport mobile app on any platform. Our concern was to iteratively develop the user interface for the authoring tool, focusing on the domain experts who create the overall flow and content for a given scenario. We had four development iterations, where the rst three were evaluated for usability; for both pharmacy and ICDL course scenarios with purposive sampling. The fourth iteration focused on using the authoring tool to design an ICDL practise mobile app, recording the necessary SASL videos and using an XML parser to render the designs XML script into an Android app. The research conducted herein leveraged multiple approaches to content authoring and generalisation; and further that software generalisation can improve accessibility and a ordability for the ultimate end users. The thesis concludes with a summary of recommendations and lessons learnt.
An analysis of voice over internet protocol in wireless mesh networks
(University of the Western Cape, 2012) Meeran, Mohammad Tariq; Tucker, William; Dept. of Computer Science
This thesis presents an analysis of the impact of node mobility on the quality of service for voice over Internet Protocol in wireless mesh networks. Voice traffic was simulated on such a mesh network to analyze the following performance metrics: delay, jitter, packet loss and throughput. Wireless mesh networks present interesting characteristics such as multi-hop routing, node mobility, and variable coverage that can impact on quality of service. A reasonable deployment scenario for a small organizational network, for either urban or rural deployment, is considered with three wireless mesh network scenarios, each with 26 mesh nodes. In the first scenario, all mesh nodes are stationary. In the second scenario, 10 nodes are mobile and 16 nodes are stationary. Finally, in the third scenario, all mesh nodes are mobile. The mesh nodes are simulated to move at a walking speed of 1.3m per second. The results show that node mobility can increase packet loss, delay, and jitter. However, the results also show that wireless mesh networks can provide acceptable quality of service, providing that there is little or no background traffic generated by other applications. In particular, the results demonstrate that jitter across all scenarios remains within humanacceptable tolerances. It is therefore recommended that voice over Internet Protocol implementations on wireless mesh networks with background traffic be supported by quality of service standards; otherwise they can lead to service delivery failures. On the other hand, voice-only esh networks, even with mobile nodes, offer an attractive alternative voice over Internet Protocol platform.
Application of Several Time Series Methods to Three Important Financial Time Series
(University of the Western Cape, 2007) O'Connell, Bryan; Koean, C
This study is concerned with three different financial time series over an eight year period, namely: the government repurchase rate, the Rand-Dollar exchange rate and the Allshare Index. The aim is to better understand the statistical nature of the time series. The theory employed will be discussed briefly and then the results will be reported. Different methods are employed to model the different time series. The following topics are discussed: unit root tests, autoregressive integrated moving average models, outlier tests, transformations, generalised autoregressive conditional heteroscedasticity models, cointegration, transfer function models and vector autoregressive models.
Articulated structure from motion
(University of the Western Cape, 2004) Scheffler, Carl; Omlin, Christian W.P.; Dept. of Computer Science; Faculty of Science
The structure from motion (SfM) problem is that of determining 3-dimensional (3D) information of a scene from sequences of 2-dimensional (2D) images [59]. This information consists of object shape and motion and relative camera motion. In general, objects may undergo complex non-rigid motion and may be occluded by other objects or themselves. These aspects make the general SfM problem under-constrained and the solution subject to missing or incomplete data.
Automated detection of race condition vulnerabilities in binary programs using symbolic execution
(University of the Western Cape, 2025) Makan, Keith
Identifying race conditions in binary programs is challenging due to limited research on the subject and the lack of thoroughly evaluated methods, especially those applied to consumer-grade, off-the-shelf binary programs without requiring source code. Symbolic execution is a static analysis technique that significantly enhances vulnerability identi- fication, especially in fuzzing-driven security analysis. However, its scalability is often restricted by the computational demands of constraint solving, high memory consump-tion, and the state explosion problem—the rapid increase in the number of states caused by program structures. To overcome these challenges, many vulnerability analysis meth-ds incorporate techniques to manage state explosion, enabling the analysis of more complex programs. The approach presented by this thesis employs symbolic vulnerability analysis for bi-naries by introducing a novel approach called "Xegmap" which uses Directed Symbolic Execution to strategically guide the exploration of program states. Xegmap is designed to prioritise the detection of Global Memory Access Points, operating on the premise that identifying these points facilitates the detection of potentially race-prone threadinteractions. It accomplishes this through a two-phase process: a naive symbolic execu-tion phase, Negmap, followed by a directed phase, Degmap. Degmap directs symbolic execution toward global memory access points and evaluates memory interactions using a hybrid lock-set and happens-before analysis. Experimentation demonstrates Xegmap’s enhanced capacity to increase code coverage in consumer-grade, off-the-shelf binaries and to detect race conditions in binaries of varying complexity, including those with intricate input constraints and numerous threads, all without the need for source code.
Automatic real-time facial expression recognition for signed language translation
(University of the Western Cape, 2006) Whitehill, Jacob Richard; Omlin, Christian W
We investigated two computer vision techniques designed to increase both the recognition accuracy and computational efficiency of automatic facial expression recognition. In particular, we compared a local segmentation of the face around the mouth, eyes, and brows to a global segmentation of the whole face. Our results indicated that, surprisingly, classifying features from the whole face yields greater accuracy despite the additional noise that the global data may contain. We attribute this in part to correlation effects within the Cohn-Kanade database. We also developed a system for detecting FACS action units based on Haar features and the Adaboost boosting algorithm. This method achieves equally high recognition accuracy for certain AUs but operates two orders of magnitude more quickly than the Gabor+SVM approach. Finally, we developed a software prototype of a real-time, automatic signed language recognition system using FACS as an intermediary framework.
Autonomous facial expression recognition using the facial action coding system
(University of the Western Cape, 2016) de la Cruz, Nathan; Ghaziasgar, Mehrdad; Connan, James
The South African Sign Language research group at the University of the Western Cape is in the process of creating a fully-edged machine translation system to automatically translate between South African Sign Language and English. A major component of the system is the ability to accurately recognise facial expressions, which are used to convey emphasis, tone and mood within South African Sign Language sentences. Traditionally, facial expression recognition research has taken one of two paths: either recognising whole facial expressions of which there are six i.e. anger, disgust, fear, happiness, sadness, surprise, as well as the neutral expression; or recognising the fundamental components of facial expressions as defined by the Facial Action Coding System in the form of Action Units. Action Units are directly related to the motion of specific muscles in the face, combinations of which are used to form any facial expression. This research investigates enhanced recognition of whole facial expressions by means of a hybrid approach that combines traditional whole facial expression recognition with Action Unit recognition to achieve an enhanced classification approach.
Avatar animation from SignWriting notation
(University of the Western Cape, 2015) Abrahams, Kenzo; Ghaziasgar, Mehrdad; Connan, James
The SASL project at the University of the Western Cape is in the process of developing a machine translation system that can translate fully-fledged phrases between South African Sign Language (SASL) and English in real-time.To visualise sign language,the system aims to make use of a 3D humanoid avatar created by van Wyk. Moemedi used this avatar to create an animation system that visualises a small set of simple Phrases from very simple SignWriting notation input. This research aims to achieve an animation system that can render full sign language sentences given complex SignWriting notation glyphs with multiple sections. The specific focus of the research is achieving animations that are accurate representations of the SignWriting input in terms of the five fundamental parameters of sign language, namely, hand motion, location, orientation and shape, as well as non-manual features such as facial expressions. An experiment Was carried out to determine the accuracy of the proposed system on a set of 20 SASL phrases annotated with SignWriting notation. It was found that the proposed system is highly accurate, achieving an average accuracy of 81.6%.
Browser-based and mobile video communication alternatives for Deaf people
(University of the Western Cape, 2011) Wang, Yuanyuan; Tucker, William D; Dept. of Computer Science; Faculty of Science
This thesis offers some prototypes to provide browser-based and mobile video communication services for Deaf people and evaluates these prototypes. The aim of this research is to identify an acceptable video communication technology for Deaf people by designing and evaluating several prototypes. The goal is to find one that Deaf people would like to use in their day-to-day life. The thesis focuses on two technologies | browser-based systems and mobile applications. Several challenges emerged, for example, specific Deaf user requirements are difficult to obtain, the technical details must be hidden from end users, and evaluation of prototypes includes both technical and social aspects. This thesis describes work to provide South African Sign Language communication for Deaf users in a disadvantaged Deaf community in Cape Town. We posit an experimental design to evaluate browser-based and mobile technologies in order to learn what constitutes acceptable video communication for Deaf users. Two browser-based prototypes and two mobile prototypes were built to this effect. Both qualitative data and quantitative data are collected with user tests to evaluate the prototypes. The video quality of Android satisfies Deaf people, and the portable asynchronous communication is convenient for Deaf users. The server performance is low on bandwidth, and will therefore cost less than other alternatives, although Deaf people feel the handset is costly.
Carrier grade adaptation for an IP-based multimodal application server: moving the softbridge into SLEE
(University of the Western Cape, 2004) Sun, Tao; Tucker, William; Dept. of Computer Science
Providing carrier grade characteristics for Internet Protocol (IP) communication applications is a significant problem for IP application providers in order to offer integrated services that span IP and telecommunication networks. This thesis addresses the provision of life-cycle management, which is only one carrier grade characteristic, for a SoftBridge application, which is an example of IP communication applications. A SoftBridge provides semi-synchronous multi-modal IP-based communication. The work related to IP-Telecommunication integrated services and the SoftBridge is analyzed with respect to life-cycle management in a literature review. It is suggested to use an Application Server in a Next Generation Network (NGN) to provide life-cyclemanagement functionality for IP-Telecommunication applications. In this thesis, the Application Server is represented by a JAIN Service Logic Execution Environment(JSLEE), in which a SoftBridge application can be deployed, activated, deactivated, uninstalled and upgraded online.Two methodologies are applied in this research: exploratory prototyping, which evolves the development of a SoftBridge application, and empirical comparison, which is concerned with the empirical evaluation of a SoftBridge application in terms of carriergrade capabilities. A SoftBridge application called SIMBA provides a Deaf Telephony service similar to aprevious Deaf Telephony SoftBridge, However, SIMBA’s SoftBridge design and implementation are unique to this thesis. In order to test the life-cycle management ability of SIMBA, an empirical evaluation is carried out including the experiments oflife-cycle management and call-processing performance. The final experimental results of the evaluation show that a JSLEE is able to provide life-cycle management for SIMBA without causing a significant decrease in performance. In conclusion, the life-cycle management can be provided or a SoftBridge application by using an Application Server such as a JSLEE. Futhermore, the results indicate that approach of using Application Server (JSLEE) integration should be sufficiently general to provide life cycle management, and indeed other carrier grade capabilities, for other IP communication applications. This allows IP communication applications to be integrated into an NGN.Providing carrier grade characteristics for Internet Protocol (IP) communication applications is a significant problem for IP application providers in order to offer integrated services that span IP and telecommunication networks. This thesis addresses the provision of life-cycle management, which is only one carrier grade characteristic, for a SoftBridge application, which is an example of IP communication applications. A SoftBridge provides semi-synchronous multi-modal IP-based communication. The work related to IP-Telecommunication integrated services and the SoftBridge is analyzed with respect to life-cycle management in a literature review. It is suggested to use an Application Server in a Next Generation Network (NGN) to provide life-cyclemanagement functionality for IP-Telecommunication applications. In this thesis, the Application Server is represented by a JAIN Service Logic Execution Environment(JSLEE), in which a SoftBridge application can be deployed, activated, deactivated, uninstalled and upgraded online.Two methodologies are applied in this research: exploratory prototyping, which evolves the development of a SoftBridge application, and empirical comparison, which is concerned with the empirical evaluation of a SoftBridge application in terms of carriergrade capabilities. A SoftBridge application called SIMBA provides a Deaf Telephony service similar to aprevious Deaf Telephony SoftBridge, However, SIMBA’s SoftBridge design and implementation are unique to this thesis. In order to test the life-cycle management ability of SIMBA, an empirical evaluation is carried out including the experiments oflife-cycle management and call-processing performance. The final experimental results of the evaluation show that a JSLEE is able to provide life-cycle management for SIMBA without causing a significant decrease in performance. In conclusion, the life-cycle management can be provided or a SoftBridge application by using an Application Server such as a JSLEE. Futhermore, the results indicate that approach of using Application Server (JSLEE) integration should be sufficiently general to provide life cycle management, and indeed other carrier grade capabilities, for other IP communication applications. This allows IP communication applications to be integrated into an NGN.
Chereme- Based Recognition of Isolated, Dynamic Gestures from South African Sign Language with Hidden Markov Models
(University of the Western Cape, 2006) Rajah, Christopher; Omlin, Christian
Much work has been done in building systems that can recognise gestures, e.g. as a component of sign language recognition systems. These systems typically use whole gestures as the smallest unit for recognition. Although high recognition rates have been reported, these systems do not scale well and are computationally intensive. The reason why these systems generally scale poorly is that they recognize gestures by building individual models for each separate gesture; as the number of gestures grows, so does the required number of models. Beyond a certain threshold number of gestures to be recognized, this approach becomes infeasible. This work proposes that similarly good recognition rates can be achieved by building models for subcomponents of whole gestures, so-called cheremes. Instead of building models for entire gestures, we build models for cheremes and recognize gestures as sequences of such cheremes. The assumption is that many gestures share cheremes and that the number of cheremes necessary to describe gestures is much smaller than the number of gestures. This small number of cheremes then makes it possible to recognize a large number of gestures with a small number of chereme models. This approach is akin to phoneme-based speech recognition systems where utterances are recognized as phonemes which in turn are combined into words. We attempt to recognise and classify cheremes found in South African Sign Language (SASL). We introduce a method for the automatic discovery of cheremes in dynamic signs. We design, train and use hidden Markov models (HMMs) for chereme recognition. Our results show that this approach is feasible in that it not only scales well, but it also generalizes well. We are able to recognize cheremes in signs that were not used for training HMMs; this generalization ability is a basic necessity for chemere-based gesture recognition. Our approach can thus lay the foundation for building a SASL dynamic gesture recognition system.
Chereme-based recognition of isolated, dynamic gestures from South African sign language with Hidden Markov Models
(University of the Western Cape, 2006) Rajah, Christopher; Omlin, Christian W.P.; Dept. of Computer Science; Faculty of Science
Much work has been done in building systems that can recognize gestures, e.g. as a component of sign language recognition systems. These systems typically use whole gestures as the smallest unit for recognition. Although high recognition rates have been reported, these systems do not scale well and are computationally intensive. The reason why these systems generally scale poorly is that they recognize gestures by building individual models for each separate gesture; as the number of gestures grows, so does the required number of models. Beyond a certain threshold number of gestures to be recognized, this approach become infeasible. This work proposed that similarly good recognition rates can be achieved by building models for subcomponents of whole gestures, so-called cheremes. Instead of building models for entire gestures, we build models for cheremes and recognize gestures as sequences of such cheremes. The assumption is that many gestures share cheremes and that the number of cheremes necessary to describe gestures is much smaller than the number of gestures. This small number of cheremes then makes it possible to recognized a large number of gestures with a small number of chereme models. This approach is akin to phoneme-based speech recognition systems where utterances are recognized as phonemes which in turn are combined into words.
A comparative evaluation of 3d and spatio-temporal deep learning techniques for crime classification and prediction
(University of Western Cape, 2021) Matereke, Tawanda Lloyd; Ghaziasgar, Mehrdad
This research is on a comparative evaluation of 3D and spatio-temporal deep learning methods for crime classification and prediction using the Chicago crime dataset, which has 7.29 million records, collected from 2001 to 2020. In this study, crime classification experiments are carried out using two 3D deep learning algorithms, i.e., 3D Convolutional Neural Network and the 3D Residual Network. The crime classification models are evaluated using accuracy, F1 score, Area Under Receiver Operator Curve (AUROC), and Area Under Curve - Precision-Recall (AUCPR). The effectiveness of spatial grid resolutions on the performance of the classification models is also evaluated during training, validation and testing.
A comparative evaluation of population-based optimization algorithms for workflow scheduling in cloud-fog environments
(University of the Western Cape, 2022) Subramoney, Dineshan; Nyirenda, Clement
Scientific workflows are denoted by interdependent tasks and computations that are aimed at achieving some scientific objectives. The scheduling of these workflows involve the allocation of the tasks to particular computational resources, traditionally on the cloud infrastructure. This process is, however, very challenging. It is associated with high computation and communication costs because scientific workflows are data-intensive and computationally complex. In recent years, there has been overwhelming interest in using population-based optimization algorithms such as Particle Swarm Optimization (PSO) and Genetic Algorithms (GA) for scientific workflow scheduling, predominantly, in the cloud environments.
Comparison and evaluation of mass video notification methods used to assist Deaf people
(University of the Western Cape, 2012) Hoorn, Ryno; Venter, I.M.; Tucker, William D.; Dept. of Computer Science
In South Africa, Deaf people communicate with one another and the broader community by means of South African Sign Language. The majority of Deaf people who have access to a mobile phone (cell phone) use Short Message Service (SMS) to communicate and share information with hearing people, but seldom use it among themselves. It is assumed that video messaging will be more accessible to Deaf people, since their level of literacy may prevent them from making effective use of information that is disseminated via texting/SMS. The principal objective of the esearch was to explore a cost-effective and efficient mass multimedia messaging system. The intention was to adapt a successful text-based mass notification system, developed by a local nongovernmental organization (NGO), to accommodate efficient and affordable video mass messaging for Deaf people. The questions that underpin this research are: How should video- streaming mass-messaging methods be compared and evaluated to find the most suitable method to deliver an affordable and acceptable service to Deaf people? What transport vehicles should be considered: Multimedia Message Service (MMS), the web, electronic mail, or a cell phone resident push/pullapplication? Which is the most cost effective? And, finally: How does the video quality of the various transport vehicles differ in terms of the clarity of the sign language as perceived by the Deaf? The soft-systems methodology and a mixed-methods methodology were used to address the research questions. The soft-systems methodology was followed to manage the research process and the mixed-methods research methodology was followed to collect data. Data was collected by means of experiments and semi-structured interviews. A prototype for mobile phone usage was developed and evaluated with Deaf members the NGO Deaf Community of Cape Town. The technology and internet usage of the Deaf participants provided background information. The Statistical Package for Social Science (SPSS) was used to analyse the quantitative data, and content analysis was used to analyse the documents and interviews. All of the Deaf participants used their mobile phones for SMS and the majority (81.25%) used English to type messages; however, all indicated that they would have preferred to use South Africa sign language on their mobile phones if it were available. And they were quite willing to pay between 75c and 80c per message for using such a video-messaging service.Of the transport vehicles demonstrated, most Deaf people indic indicated that they preferred to use the SMS prototype (with a web link to the video) rather than the MMS prototype with the video attached. They were, however, very concerned about the cost of using the system, as well as the quality of the sign language videos.

Browse

Browsing by Title

Results Per Page

Sort Options