Department of Computer Science

Permanent URI for this community

https://hdl.handle.net/10566/51

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

Now showing 1 - 20 of 265

Grafting an ATM network onto an existing ethernet network
(Telkom, 1998) Tucker, William David; Keats, Derek
Grafting an ATM network onto an existing Ethernet network is a non-trivial exercise in network configuration. The process of mating ATM technology to an Ethernet network without tampering the underlying backbone and network configuration gives rise to a variety of networking issues including addressing, compatibility, security, efficiency, administrative effort, and scalability. Examples of actual situations serve to illustrate these issues. We have designed several scenarios to tackle the topological problems of an ATM graft. A dual IP approach works but suffers from a lack of scalability. We expect an edge routing solution, with subnetting, will be the most elegant and scalable.
Fast tracking students from disadvantaged backgrounds into main stream Computer Science
(Computer Society of South Africa, 2000) Blignaut, Renette; Venter, Isabella M.; Cranfield, D.J.
A computer-based training (CBT) system was used to teach Computer Literacy to full-time students at the University of the Western Cape. This approach was successful in creating computer literate students as well as creating an opportunity for students from educationally disadvantaged schools to enter the Computer Science course. The students experienced this new approach to learning positively. This has laid the foundation to export the computer-based education model to communities outside the university. Lifelong learning opportunities will thus be created.
A framework and toolkit for the collection and analysis of QoS statistics for voice traffic in Next Generation Networks
(Telkom, 2000) Paulse, Tania M.
The multi-service, multi-architecture nature of NGNs is so complex that the management of services, in addition to networks, emerges as a research challenge. Despite QoS limitations, VoIP (as opposed to VoATM), dominates the Internet and enterprise markets, and is evolving to handle the carrier space. This paper presents a strategy that abstracts QoS away from both VoATM and VoIP in order to manage voice QoS in an NGN environment.
An Internet paradigm approach to policy-based network management of legacy kit for VoIP services in Next Generation Networks
(Telkom, 2000) Naidoo, Vaughn; Tucker, William David
With QoS available on IP-dominant NGNs, Policy-based Network Management (PBNM) is an effective mechanism for managing services as opposed to actual devices. IP is ubiquitous, and any NGN must contend with legacy devices that do not support emerging PBNM protocols. This Work in Progress uses the common Internet notion of a proxy to enforce policies on legacy equipment. We use VoIP as a mechanism to test the validity of our intended solution.
A framework and toolkit for the collection and analysis of QoS statistics for voice traffic in Next Generation Networks
(Telkom, 2000) Paulse, Tania M.; Tucker, William David
The multi-service, multi-architecture nature of NGNs is so complex that the management of services, in addition to networks, emerges as a research challenge. Despite QoS limitations, VoIP (as opposed to VoATM), dominates the Internet and enterprise markets, and is evolving to handle the carrier space. This paper presents a strategy that abstracts QoS away from both VoATM and VoIP in order to manage voice QoS in an NGN environment.
An Interoperable signaling solution for IP-based Next Generation Networks
(Telkom, 2000) Jeffries, Michael; Tucker, William David
Current VoIP signaling protocols are interoperable with the PSTN SS7 via H.323-to-SS7 or SIP-to-SS7 gateways. As we move toward the Next Generation Network, the PSTN falls away and we work toward carrier-grade VoIP interoperability between H.323, SIP, and other future VoIP signaling protocols. This paper present a Work in Progress to design and implement a solution based on the Internet Protocol itself.
Policy-based network management of legacy equipment in Next Generation Networks
(Telkom, 2001) Naidoo, Vaughn; Tucker, William David
Next Generation Networks use policy-based network management and QoS protocols to provide voice services on IP networks. Large numbers of older equipment still push IP packets. We present several solutions that include legacy equipment into a PBNM and QoS system. A static design uses traffic shaping at the legacy edge. A dynamic solution uses a Quasi-PEP implemented over RSVP and COPS. Preliminary test results are presented for the static solution. Collected data shows that the solution decreases packet loss on the legacy side.
An interoperable signaling solution between SIP and H.323
(Telkom, 2001) Jeffries, Michael; Tucker, William David
The Session Initiation Protocol and H.323 dominate the Voice over IP world. These signaling protocols are responsible for call setup and call tear down by IP telephony solutions. This project analyses and discusses the underlying H.323 and SIP interoperability issues and intends to build a scalable solution for the interoperability of these protocols. The gateway maps the call sequences between the two protocols. A test scenario establishes a barrage of call setup and tear down requests to test the scalability of any H.323/SIP interoperability solution.
Web-based telephony bridges for the deaf
(Telkom, 2001) Glaser, Meryl; Tucker, William David
A Teldem provides text-based telephony services to the deaf. Despite an array of text-based communications mechanisms on the web, the Teldem is the only means of synchronous telecommunication available to a deaf person. We examine a human-assisted relay that provides a bridge between the deaf and the hearing, and then propose several additional bridges. These bridges take advantage of both standard and cutting edge technologies. We present each bridge's impact on the deaf with respect to synchrony, connectivity, independence, and the Digital Divide. It is hoped that by deploying trials for each bridge, we can eventually provide the deaf with equal access.
Telgo323: an H.323 Bridge for deaf telephony
(Telkom, 2002) Penton, Jason; Tucker, William David; Glaser, Meryl
We have developed a prototype bridge that relays text and speech between Teldem, a text telephone for the Deaf, and a standard telephone or H.323 endpoint. Telgo323 uses modified H.323 media gateways and open source Text to Speech and Speech to Text software. The approach allows for easy integration of new tools as the technologies mature. This paper presents the design of the implementation prototype, discusses Teldem tone decoding, and suggests directions for future work. The Telgo323 provides evidence that an automated relay bridge is imminently viable for the Deaf Community, and further demonstrates an attractive approach for building bridges over the Digital Divide.
SoftBridge: an architecture for building IP-based bridges over the digital divide
(Telkom, 2002) Lewis, John; Tucker, William David; Blake, Edwin H.
Users and computing equipment have varying capabilities that include the abilities to exchange text and audio, engage in high bandwidth communication, etc. As the technological options increase, e ective communication between the di erent media has be able to bridge across these options: the bridges have to take into account network quality, end-user equipment capabilities as well as user preferences and capabilities. Our research proposes a Soft- Bridge, an abstracted communications platform for the construction of applications across disparate capabilities found in various Digital Divides. We outline the architecture and the requirements that the SoftBridge has to ful ll. An approach and some initial work is described.
Policy based network management of legacy network elements in next generation networks for voice services
(University of the Western Cape, 2002) Naidoo, Vaughn; Tucker, William; Dept. of Computer Science
Telecommunication companies, service providers and large companies are now adapting converged multi-service Next Generation Networks (NGNs). Network management is shifting from managing Network Elements (NE) to managing services. This paradigm shift coincides with the rapid development of Quality of Service (QoS) protocols for IP networks. NEs and services are managed with Policy Based Network Management (PBNM) which is most concerned with managing services that require QoS using the Common Open Policy Service (COPS) Protocol. These services include Voice over IP (VoIP), video conferencing and video streaming. It follows that legacy NEs without support for QoS need to be replaced and/or excluded from the network. However, since most of these services run over IP, and legacy NEs easily supports IP, it may be unnecessary to throw away legacy NEs if it can be made to fit within a PBNM approach. Our approach enables an existing PBNM system to include legacy NEs in its management paradigm. The Proxy-Policy Enforcement Point (P-PEP) and Queuing Policy Enforcement Point (Q-PEP) can enforce some degree of traffic shaping on a gateway to the legacy portion of the network. The P-PEP utilises firewall techniques using the common legacy and contemporary NE management protocol Simple Network Management Protocol (SNMP) while the Q-PEP uses queuing techniques in the form Class Based Queuing (CBQ) and Random Early Discard (RED) for traffic control.
Using voice over IP to bridge the digital divide: a critical action research approach
(Telkom, 2003) Chetty, Marshini; Tucker, William David; Blake, Edwin H.
There is a great disparity between those who have access to Information and Communication Technologies (ICTs) and those that do not. This phenomenon forms part of the Digital Divide. Many ICTs may be used to help overcome this divide if they are applied in a useful way, providing locally applicable content and services. Critical Action Research (CAR) is an approach used to develop such applications. CAR aims to empower people by involving them in the development process. Using CAR, this project investigates how Voice over IP (VoIP) may be applied in a productive way in an underserviced community. VoIP is an ICT used for sending voice over packet switched networks using Internet Protocol. It can be used to integrate data and voice to produce multimedia applications. In South Africa (SA), VoIP may only be provided by Telkom, the Second National Operator and the Under-Serviced Area Licensees. Using CAR and VoIP, an application is being developed to service a specific need of a particular rural community. The application will either provide a service to a small rural business or aid the provision of healthcare in rural areas. The project evaluates how well CAR integrates with a normal Software Development Lifecycle and makes policy recommendations for the use of VoIP in rural SA.
Handheld fast-track feedback instant messaging
(Telkom, 2003) Adesemowo, A. Kayode; Tucker, William David
As mobile devices and networks become more data-centric, text messaging requires an extension of co-presence capabilities for better interactive discussion between input/output handicapped handheld users and their free form desktop counterparts. Given some degree of co-presence (online presence and awareness) in text-based Instant Messaging, we hope to increase this co-presence on a handheld with fast-track feedback (FF) mechanisms. These are user-defined gestures, such as emoticons, and prioritised messages. We are building a system that facilitates gesture input within an interactive text-based chat over a wireless network running Session Initiation Protocol (SIP). The chat bridges a robust desktop environment and a small number of handhelds. This work in progress looks into the SIP Instant Messaging and Presence Leveraging Extensions as a platform to provide fast-track interactive and co-presence feedback. The aim is to rubberise a hitherto plastic and limited instant messaging conversation. We shall measure co-presence levels between FF and standard IM environments in and without desktop and handhelds by engaging two groups of users in chats session. We expect to demonstrate that there exists high co-presence notion in open (work by Sun Research Awarenex Group and AT&T Hubbubme in similar domain were in closed systems) FF text messaging open environment as we would like to show that this higher presence brings a much more enhanced interactive discourse. The envisaged results are intended to extrapolate to online aware co-presence in the up and coming smart phones on 3G packet networks.
Floor control arbitration for a hybrid voice/text web-board
(Telkom, 2003) Benjamin, Anita; Tucker, William David
We have built a hybrid voice/text web–board that utilizes floor control for handling resources such as microphone and interface events. The aim of this research is to determine the most appropriate floor control mechanism for a hybrid communication tool that allows conventional text and audio users to communicate with one another using a common interface. Research on floor control mechanisms provides many implementations for arbitration that are application-specific. Myers proposes a categorical explanation of the most widely used mechanisms for providing floor control and discusses these different dimensions with respect to a project called Pebbles. We have chosen to model our arbitration policies along these categories. The application will be implemented as a Java applet and gives users a view of both the text and audio aspects of the exchange. To facilitate the multi-modality of the system we will provide media conversion, using the Nuance system’s Java API. Our hypothesis is that well–known multi-tasking arbitration protocols such as FCFS, Round Robin, Token – based, and many more can be adapted to create a conferencing floor control policy for the interface of a hybrid communication environment so as to facilitate free–flowing multi-modal conversation. Measurements to determine which floor control implementation provides the best arbitration in terms of user interaction with the system will be calculated using RPT, ORT and usage tests based on the Kirkpatrick Model. We hope to show that users benefit more from an implicit arbitration mechanism than they do from an explicit one.
SoftBridge in action: the first Deaf telephony pilot
(Telkom, 2003) Tucker, William David; Glaser, Meryl; Lewis, John
Following on several partial prototypes, we built an automated Deaf Telephony bridging application with the SoftBridge platform. The SoftBridge performs multi-modal bridging in real-time using Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) utilities accessed via web services. To perform Action Research with the Deaf community in Cape Town, we invited a Deaf user (DU) to participate in a pilot study. We conducted three tests varying the input/output modalities of the hearing user (HU). The DU had a standard text in/text out Instant Messaging client. The HU client used the following specific modality combinations: Text & TTS in/Text out, TTS in/Text out and TTS in/Text & ASR out. The SoftBridge logged the conversations for subsequent analysis. The trial showed a largely successful conversation. Success factors include a) a text and computer literate DU who is familiar with research practise, b) using the system to explain the research as we conducted it and c) that the multi-modal bridging capabilities overcame the expected shortcomings of TTS and especially ASR. The lessons learned from this trial will be applied to the next trial once the necessary modifications have been implemented.
SoftBridge: a multimodal instant messaging bridging system
(Telkom, 2003) Lewis, John; Tucker, William David; Blake, Edwin H.
Instant Messaging is traditionally a text only a air. However, there are instances when it would be useful to bridge to other types of media, like speech. The SoftBridge is an application framework that enables this kind of communications bridging using instant messages. Its use of protocols like the Jabber Instant Messaging Protocol and the Simple Object Access Protocol makes it simple, open and extensible. It also allows bridging to non IP communications infrastructure, like the telephone network. We describe the design and architecture of the system, protocol and extensibility mechanism. Finally we describe our experimental methodology and discuss the results of our initial experiments.
Long short-term memory recurrent neural networks for signature verification
(UWC, 2003) Tiflin, C; Omlin, C
Handwritten signature verification is defined as the classification process that strives to learn the manner in which an individual makes use of the muscular memory of their hands, fingers, and wrist to reproduce a signature. A handwritten signature is captured by a pen input device and sampled at a high frequency which results in time series with several hundred data points. A novel recurrent neural network architecture known as long short-term memory was designed for modeling such a long-time series. This research investigates the suitability of long short-term memory recurrent neural networks for the task of online signature verification. We design and experiment with various network architectures to determine if this model can be trained to discriminate between authentic and fraudulent signatures. We further determine whether the complexity of a signature impacts the performance level of the network when applied to fraudulent signatures. We also investigate the performance level of the network when varying the number of signature features.
Affective gesture feedback Instant Messaging on handhelds
(Institute of Electrical and Electronics Engineers, Inc., 2004) Adesemowo, A. Kayode; Tucker, William David
Mobile 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.
Preparation of Deaf end-users and the softbridge for semi-automated relay trials
(Telkom, 2004) Glaser, Meryl; Tucker, William David; Mashao, Daniel
Following on the development of several prototypes, we have built a semi-automated Deaf Telephony prototype on the SoftBridge platform. This prototype relays text and speech between Deaf users on the Internet and hearing users on the telephone system. Previous work with a pilot trial in the laboratory revealed several opportunities for enhancement. We added a Wizard of Oz (WoOz) to replace the poorly performing automatic speech recognition functionality as well as H.323 breakout, more extensive logging and advanced call initiation functionality. In order to trial the current prototype, we initiated an Information and Communication Technology (ICT) training programme with the Deaf Community of Cape Town. Twenty Deaf users participated in the training. In addition to the training, much baseline user data was collected to give an indication of how Deaf users communicate with hearing users as well as how familiar they are with ICT devices and services. The work for the rest of this year requires us to recruit and train a WoOz operator. Subsequent trials will essentially consist of monthly cycles of prototype introduction, training, automated metric and log collection, user feedback and then feature enhancement. Linguistic analyses of the text output of the Deaf users will be analyzed. We hope to refine the SoftBridge prototype to fit the needs of the Deaf and hearing users, from both technical and social viewpoints. We expect that these iterative cycles will continue for some time and will teach us many lessons regarding multi-modal semi-synchronous IP-based communications systems.

Browse

Browsing by Issue Date

Results Per Page

Sort Options