Department of Computer Science
Permanent URI for this community
The Bridging Application and Network Gaps (BANG) group examines the
intersection of human computer interfaces, computer networks and
software engineering within the context of ICT interventions in disadvantaged communities.
The South African Sign Language (SASL) group looks at the integration of signed and verbal communication building on the South African Sign Language Translation System.
Browse
Browsing by Title
Now showing 1 - 20 of 265
Results Per Page
Sort Options
Item 3D forensic crime scene reconstruction involving immersive technology: A systematic literature review(Institute of Electrical and Electronics Engineers, 2022) Maneli, Mfundo A.; Isafiade, Omowunmi E.Recreation of 3D crime scenes is critical for law enforcement in the investigation of serious crimes for criminal justice responses. This work presents a premier systematic literature review (SLR) that offers a structured, methodical, and rigorous approach to understanding the trend of research in 3D crime scene reconstruction as well as tools, technologies, methods, and techniques employed thereof in the last 17 years. Major credible scholarly database sources, Scopus, and Google Scholar, which index journals and conferences that are promoted by entities such as IEEE, ACM, Elsevier, and SpringerLink were explored as data sources. Of the initial 17, 912 papers that resulted from the first search string, 258 were found to be relevant to our research questions after implementing the inclusion and exclusion criteria.Item 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.Item A Comparison of Machine Learning Techniques for Facial Expression Recognition(University of the Western Cape, 2018) Deaney, Mogammat Waleed; Venter, IsabellaA 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.Item Abstractions for designing and evaluating communication bridges for people in developing regions(ACM, 2010) Tucker, William David; Blake, Edwin H.This paper describes two novel abstractions that help soft- ware engineers work in developing regions to align social and technical factors when building communication systems. The abstractions extend two concepts familiar to engineers of computer networks and applications: the Open Systems Interconnect stack for design, and Quality of Service for eval- uation. The novel nature of the abstractions lies in how they help cultivate awareness of socio-cultural and technical is- sues when designing and evaluating communication bridges in the eld. Advantages of the abstractions are that they can be understood easily by software engineers, they aid communication with bene ciaries, and can therefore facili- tate collaboration. The paper makes an argument for these socially aware abstractions, describes the abstractions in de- tail, provides examples of how we used the new abstractions in the eld and then gives practical guidelines for how to use them. The simple nature of the new abstractions can help software engineers and end-users to work together to produce useful information technology based communication systems for people in developing regions.Item Adapting x264 to asynchronous video telephony for the Deaf(Telkom, 2008) Ma, Zhen Yu; Tucker, William DavidDeaf people want to communicate remotely with sign language. Sign language requires sufficient video quality to be intelligible. Internet-based real-time video tools do not provide that quality. Our approach is to use asynchronous transmission to maintain video quality. Unfortunately, this entails a corresponding increase in latency. To reduce latency as much as possible, we sought to adapt a synchronous video codec to an asynchronous video application. First we compared several video codecs with subjective and objective metrics. This paper describes the process by which we chose x264 and integrated it into a Deaf telephony video application, and experimented to configure x264 optimally for the asynchronous environment.Item 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.Item Affective gesture feedback Instant Messaging on handhelds(Institute of Electrical and Electronics Engineers, Inc., 2004) Adesemowo, A. Kayode; Tucker, William DavidMobile devices and mobile networks are becoming more data-centric (evident in Japanese I-mode) even as mobile network voice Average Revenue Per User are declining, new stream of data services are required which must take cognisance of handhelds features albeit their small screen estate and input/output limitations. A text only Instant Messaging (IM) built on the Internet Engineering Task Force open standard Session Initiation Protocol (SIP) and SIP for Instant Messaging and Presence Leveraging Extensions (SIMPLE) has been developed in line with our novel introduction of a user-defined text Hotkey feature. Given that text communication possesses expressive discourse with some presence level, we seek to show that one-click text-gesture fast-tracking enhances text communication further. For this study, we are taking a hybrid quantitative and qualitative approach. Initial results have shown that an Affective Gesture approach is more likely to improve IM chat spontaneity/response rate. Enhanced input mechanisms for handheld IM system are expected to increase co-presence between handheld users and their desktop-based counterparts while in a synchronous discussion.Item Africa 3: A continental network model to enable the African fourth industrial revolution(IEEE, 2020) Ajayi, Olasupo O; Bagula, Antoine B.; Maluleke, Hloniphani C.It is widely recognised that collaboration can help fast-track the development of countries in Africa. Leveraging on the fourth industrial revolution, Africa can achieve accelerated development in health care services, educational systems and socio-economic infrastructures. While a number of conceptual frameworks have been proposed for the African continent, many have discounted the Cloud infrastructure used for data storage and processing as well as the underlying network infrastructure upon which such frameworks would be built. This work therefore presents a continental network model for interconnecting nations in Africa through its data centres. The proposed model is based on a multilayer network engineering approach, which first groups African countries into clusters of data centers using a hybrid combination of clustering techniques; then utilizes Ant Colony Optimisation with Stench Pheromone, that is modified to support variable evaporation rates, to find ideal network path(s) across the clusters and the continent as a whole. The proposed model takes into consideration the geo-spatial location, population sizes, data centre counts and intercontinental submarine cable landings of each African country, when clustering and routing. For bench-marking purposes, the path selection algorithm was tested on both the obtained clusters and African Union’s regional clusters.Item Agent-based context-aware healthcare information retrieval using DROPT approach(International Science Press, 2012) Agbele, Kehinde K.; Adesina, Ademola Olusola; Daniel, Ekong; Seluwa, DeleAs the volume of information available on the Web information systems is growing continuously, browsing this content becomes a tedious task given the presentation of data that does meet user's aims and needs. In this paper, to satisfy user needs, an agent-based paradigm is an appropriate solution which gives outputs suitable to the user in the form of highly ranked documents. Conversely, patient care and a health condition commonly require collaboration between healthcare providers. The emergence of agent's technology motivates radical changes of how information is obtained. This paper addresses this problem by proposing a novel DROPT (Document Ranking OPTimization) measure for information retrieval results to validate the effectiveness of the information management tasks. We propose information retrieval system architecture, which main components are context aware agent’s technology to meet users' information needs.Item Amplifying positive deviance with ICT enabling community development and interdependence(Springer, 2017) Tucker, William DavidPositive deviance is a social mechanism whereby a beneficial practice that is not considered as normal gets taken up and spread within a community. This enables a community to solve its own problems aided by mentorship and facilitation. Through two long term case studies, we have identified positive deviants and are now learning how to leverage the ICT inherent in our interventions to cultivate and amplify positive change. We find both ourselves and beneficiary communities developing through various stages of dependence, independence and interdependence. We consider the latter a strong form of development. We now look at ICT4D projects as opportunities to identify positive deviants, and to amplify positive deviance with ICT. We posit that affordable, accessible and generic ICTs offer a way to do so, and that explicitly aiming to mentor and facilitate positive deviance with such ICT offers a path toward community development and interdependence.Item An authoring tool for generalised scenario creation for SignSupport(University of the Western Cape, 2016) Duma, Lindokuhle Sifso; Tucker, WilliamThis 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.Item An analysis of voice over Internet Protocol in wireless mesh networks(IEEE, 2014) Meeran, Mohammed Tariq; Tucker, William DavidThe paper focuses on analyzing the affects of wireless mesh networks with some mobile nodes on Voice over Internet Protocol service quality. Our interest is to examine this in simulation to learn how to better deploy voice services on such a network in a rural community. Wireless mesh networks' unique characteristics like multi-hop, node mobility, coverage, and medium usage cause quality of service issues for Voice over Internet Protocol implementations. This research considers three wireless mesh scenarios on 26 mesh nodes. In the first scenario all nodes are stationary. In the second, 10 nodes are mobile and 16 nodes are stationary. In a third scenario, all nodes are mobile. Nodes move at a walking speed of 1.3m per second. The analysis and results show that while node mobility can increase packet loss, delay, jitter, Voice over Internet Protocol implementations in wireless mesh networks can be successful if there is no background traffic. We recommend that Voice over Internet Protocol implementations in wireless mesh networks with some mobile nodes and background traffic be supported by quality of service standards; else it can lead to service level delivery failures.Item 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 ScienceThis 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.Item ANCAEE: A novel clustering algorithm for energy efficiency in wireless sensor networks(Scientific Research Publishing, 2011) Abidoye, Ademola P.; Azeez, Nureni A.; Adesina, Ademola Olusola; Agbele, Kehinde K.One of the major constraints of wireless sensor networks is limited energy available to sensor nodes because of the small size of the batteries they use as source of power. Clustering is one of the routing techniques that have been using to minimize sensor nodes’ energy consumption during operation. In this paper, A Novel Clustering Algorithm for Energy Efficiency in Wireless Sensor Networks (ANCAEE) has been proposed. The algorithm achieves good performance in terms of minimizing energy consumption during data transmis-sion and energy consumptions are distributed uniformly among all nodes. ANCAEE uses a new method of clusters formation and election of cluster heads. The algorithm ensures that a node transmits its data to the cluster head with a single hop transmission and cluster heads forward their data to the base station with multi-hop transmissions. Simulation results show that our approach consumes less energy and effectively extends network utilization.Item Application of Several Time Series Methods to Three Important Financial Time Series(University of the Western Cape, 2007) O'Connell, Bryan; Koean, CThis 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.Item Article comparing three countries’ higher education students’ cyber related perceptions and behaviours during COVID-19(MPDI, 2021) Tick, Andrea; Cranfield, Desireé J.; Renaud, Karen V.: In 2020, a global pandemic led to lockdowns, and subsequent social and business restrictions. These required overnight implementation of emergency measures to permit continued functioning of vital industries. Digital technologies and platforms made this switch feasible, but it also introduced several cyber related vulnerabilities, which students might not have known how to mitigate. For this study, the Global Cyber Security Index and the Cyber Risk literacy and education index were used to provide a cyber security context for each country. This research project—an international, cross-university, comparative, quantitative project—aimed to explore the risk attitudes and concerns, as well as protective behaviours adopted by, students at a South African, a Welsh and a Hungarian University, during the pandemic. This study’s findings align with the relative rankings of the Oliver Wyman Risk Literacy and Education Index for the countries in which the universities reside. This study revealed significant differences between the student behaviours of students within these universities.Item Articulated structure from motion(University of the Western Cape, 2004) Scheffler, Carl; Omlin, Christian W.P.; Dept. of Computer Science; Faculty of ScienceThe 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.Item Asynchronous video telephony for the Deaf(Telkom, 2007) Ma, Zhen Yu; Tucker, William DavidThe South African Deaf community has very limited telephony options. They prefer to communicate in sign language, a visual medium. Realtime video over Internet Protocol is a promising option, but in reality, the quality is often not enough for the Deaf to be able to understand each other’s sign language. Furthermore, these applications were not design specifically for the Deaf. This paper introduces an asynchronous video chat system to provide better quality video at the expense of increased latency. It determined a codec/transmission protocol combination in the laboratory environment and tested it out with actual Deaf users. This paper will address the results based on comparison between different codecs, transmission protocol on asynchronous video communication for the Deaf.Item Automatic real-time facial expression recognition for signed language translation(University of the Western Cape, 2006) Whitehill, Jacob Richard; Omlin, Christian WWe 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.Item Automatic voice relay with open source Kiara(Telkom, 2009) Yi, Long; Tucker, William DavidOne way for Deaf people to communicate with hearing people over the telephone is to use a voice relay. The service is often provided with a human relay operator that relays text into voice, and vice versa, on behalf of the Deaf and hearing users. In developed countries, voice relay is frequently subsidised by governments or service providers. There is no such service in South Africa. We have built several automatic voice relay systems for a disadvantaged Deaf community in Cape Town. This paper describes how we augmented a general-purpose communication system for voice relay. Kiara is a fully open source Instant Messaging, voice and video over Internet Protocol communication system based on the Session Initiation Protocol. We integrated automatic speech recognition and text-to-speech technologies into Kiara to provide real-time automatic voice relay for relayed communication. As it stands, Kiara can also be used for standard voice and video relay with a human operator.