Thesis (MSc)--University of Stellenbosch, 2007. / ENGLISH ABSTRACT: Machine translation, especially machine translation for sign languages, remains an active research area. Sign language machine translation presents unique challenges to the whole machine translation process. In this thesis a prototype machine translation system is presented. This system is designed to translate English text into a gloss based representation of South African Sign Language (SASL). In order to perform the machine translation, a transfer based approach was taken. English text is parsed into an intermediate representation. Translation rules are then applied to this intermediate representation to transform it into an equivalent intermediate representation for the SASL glosses. For both these intermediate representations, a tree adjoining grammar (TAG) formalism is used. As part of the prototype machine translation system, a TAG parser was implemented. The translation rules used by the system were derived from a SASL phrase book. This phrase book was also used to create a small gloss based SASL TAG grammar. Lastly, some additional tools, for the editing of TAG trees, were also added to the prototype system. / AFRIKAANSE OPSOMMING: Masjienvertaling, veral masjienvertaling vir gebaretale, bly ’n aktiewe navorsingsgebied. Masjienvertaling vir gebaretale bied unieke uitdagings tot die hele masjienvertalingproses. In hierdie tesis bied ons ’n prototipe masjienvertalingstelsel aan. Hierdie stelsel is ontwerp om Engelse teks te vertaal na ’n glos gebaseerde voorstelling van Suid-Afrikaanse Gebaretaal (SAG). Ons vertalingstelsel maak gebruik van ’n oorplasingsbenadering tot masjienvertaling. Engelse teks word ontleed na ’n intermediˆere vorm. Vertalingre¨els word toegepas op hierdie intermediˆere vorm om dit te transformeer na ’n ekwivalente intermediˆere vorm vir die SAG glosse. Vir beide hierdie intermediˆere vorms word boomkoppelingsgrammatikas (BKGs) gebruik. As deel van die prototipe masjienvertalingstelsel, is ’n BKG sintaksontleder ge¨ımplementeer. Die vertalingre¨els wat gebruik word deur die stelsel, is afgelei vanaf ’n SAG fraseboek. Hierdie fraseboek was ook gebruik om ’n klein BKG vir SAG glosse te ontwikkel. Laastens was addisionele nutsfasiliteite, vir die redigering van BKG bome, ontwikkel.

Thesis (MSc)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: see full text for abstract / AFRIKAANSE OPSOMMING: sien volteks vir opsomming

Thesis (MSc)--Stellenbosch University, 2012. / ENGLISH ABSTRACT: In this thesis we describe the creation of an embodied conversational agent which exhibits the behavioural traits of a child who has Asperger Syndrome. The agent is rule-based, rather than arti cially intelligent, for which we give justi cation. We then describe the design and implementation of the agent, and pay particular attention to the interaction between emotion, personality and social context. A 3D demonstration program shows the typical output to conform to Asperger-like answers, with corresponding emotional responses. / AFRIKAANSE OPSOMMING: In hierdie tesis beskryf ons die ontwerp en implementasie van 'n gestaltegespreksagent wat die gedrag van 'n kind met Asperger se sindroom uitbeeld. Ons regverdig die besluit dat die agent reël-gebaseerd is, eerder as 'n ware skynintelligensie implementasie. Volgende beskryf ons die wisselwerking tussen emosies, persoonlikheid en sosiale konteks en hoe dit inskakel by die ontwerp en implementasie van die agent. 'n 3D demonstrasieprogram toon tipiese ooreenstemmende Asperger-agtige antwoorde op vrae, met gepaardgaande emosionele reaksies.

Thesis (MSc (Mathematical Sciences)--University of Stellenbosch, 2010. / ENGLISH ABSTRACT: Binary Decision Diagrams (BDDs) are data structures that have been used to solve various problems in different aspects of computer aided design and formal verification. The large memory and time requirements of BDD applications are the major constraints that usually prevent the use of BDDs since there is a limited amount of memory available on a machine. One way of overcoming this resource limitation problem is to utilize the memory available on a network of workstations (NOW). This requires the distribution of the computation and memory requirements involved in the manipulation of BDDs over a NOW. In this thesis, an algorithm for manipulating BDDs on a NOW is presented. The algorithm makes use of the breadth-first technique to manipulate BDDs so that various BDD operations can be started concurrently on the different workstations on the NOW. The design and implementation details of the distributed BDD package are described. The various approaches considered in order to optimize the performance of the algorithm are also discussed. Experimental results demonstrating the performance and capabilities of the distributed package and the benefits of the different optimization approaches are given. / AFRIKAANSE OPSOMMING: Binêre besluitnemingsbome (BBBs) is data strukture wat gebruik word om probleme in verskillende areas van Rekenaarwetenskap, soos by voorbeeld rekenaargesteunde ontwerp en formele verifikasie, op te los. Die tyd- en spasiekoste van BBB-gebaseerde toepassings is die hoofrede waarom BBBs nie altyd gebruik kan word nie; die geheue van ’n enkele is ongelukkig te beperkend. Een manier om hierdie hulpbronprobleem te omseil, is om die gedeelde geheue van die werkstasies in ’n netwerk van werkstasies (Engels: “network of workstations”, oftewel, ’n NOW) te benut. Dit is dus nodig om die berekening en geheuevoorvereistes van die BBB bewerking oor die NOW te versprei. Hierdie tesis bied ’n algoritme aan om BBBs op ’n NOW te hanteer. Die algoritme gebruik die breedte-eerste soektegniek, sodat BBB operasies gelyklopend kan uitvoer. Die details van die ontwerp en implementasie van die verspreide BBB bilbioteek word beskryf. Verskeie benaderings om die gedrag van die biblioteek te optimeer word ook aangespreek. Empiriese resultate wat die werkverrigting en kapasiteit van die biblioteek meet, en wat die uitwerking van die onderskeie optimerings aantoon, word verskaf.

Thesis (MSc)--University of Stellenbosch, 2004. / ENGLISH ABSTRACT: We present a system that uses statistical machine learning to identify and extract bibliography information from scientific literature. Techniques for finding and gathering useful information from the ever growing volume of knowledge on the World Wide Web (WWW), are investigated. We use hidden Markov models both for recognition of bibliography styles and extraction of bibliographic information with an accuracy of up to 97%. The accuracy with which we are able to extract this information allows us to present a case study in which we apply methods of citation analysis to information extracted from three areas of machine learning. We use this information to identify core sets of papers that have made significant contributions to the fields of hidden Markov models, neural networks and recurrent neural networks. / AFRIKAANSE OPSOMMING: Ons bied 'n sisteem aan wat gebruik maak van statistiese masjiene wat leer om bibliografiese inligting uit wetenskaplikke literatuur te identifiseer en ontgin. Tegnieke wat aangewend word vir die verkenning en insameling van nuttige inligting vanaf die snel groeiende kennisbron van die WWW, word ondersoek. Ons gebruik verskuilde Markov modelle vir die herkenning van verwysingsstyl en ontginning van verwysingsinligting met 'n akuraatheidspeil van to 97%. Hierdie hoë ontginningsakuraatheid stelons in staat om 'n toepassing van die tegniek op die veld van masjiene wat leer toe te pas. Ons rapporteer hoe ons die tegnieke gebruik het om literatuur wat beduidende bydraes in die velde van verskuilde Markov modelle, neurale netwerke en terugkerende neurale netwerke, te identifiseer.

Thesis (MSc)--Stellenbosch University, 2004. / ENGLISH ABSTRACT: It is possible to improve on the accuracy of a single neural network by using an ensemble of diverse and accurate networks. This thesis explores diversity in ensembles and looks at the underlying theory and mechanisms employed to generate and combine ensemble members. Bagging and boosting are studied in detail and I explain their success in terms of well-known theoretical instruments. An empirical evaluation of their performance is conducted and I compare them to a single classifier and to each other in terms of accuracy and diversity. / AFRIKAANSE OPSOMMING: Dit is moontlik om op die akkuraatheid van 'n enkele neurale netwerk te verbeter deur 'n ensemble van diverse en akkurate netwerke te gebruik. Hierdie tesis ondersoek diversiteit in ensembles, asook die meganismes waardeur lede van 'n ensemble geskep en gekombineer kan word. Die algoritmes "bagging" en "boosting" word in diepte bestudeer en hulle sukses word aan die hand van bekende teoretiese instrumente verduidelik. Die prestasie van hierdie twee algoritmes word eksperimenteel gemeet en hulle akkuraatheid en diversiteit word met 'n enkele netwerk vergelyk.

Thesis (MSc) -- Stellenbosch University, 2004. / ENGLISH ABSTRACT: The Internet is fast evolving into a commercial platform that carries a mixture of narrow- and broadband applications such as voice, video, and data. Users expect a certain level of guaranteed service from their service providers and consequently the need exists for efficient Internet traffic engineering to enable better Quality of Service (QoS) capabilities. Multi-protocol Label Switching (MPLS) is a label switching protocol that has emerged as an enabling technology to achieve efficient traffic engineering for QoS management in IP networks. The ability of the MPLS protocol to create explicit virtual connections called Label Switched Paths (LSPs) to carry network traffic significantly enhances the traffic engineering capabilities of communication networks. The MPLS protocol supports two options for explicit LSP selection: offline LSP computation using an optimization method and dynamic route selection where a single node makes use of current available network state information in order to compute an explicit LSP online. This thesis investigates various methods for the selection of explicit bandwidth guaranteed LSPs through dynamic route selection. We address the problem of computing a sequence of optimal LSPs where each LSP can carry a specific traffic demand and we assume that no prior information regarding the future traffic demands are available and that the arrival sequence of LSP requests to the network is unknown. Furthermore, we investigate the rerouting abilities of the online LSP selection methods to perform MPLS failure restoration upon link failure. We propose a new online routing framework known as Least Interference Optimization (LIO) that utilizes the current bandwidth availability and traffic flow distribution to achieve efficient traffic engineering. We present the Least Interference Optimization Algorithm (LIOA) that reduces the interference among competing network flows by balancing the number and quantity of flows carried by a link for the setup of bandwidth guaranteed LSPs in MPLS networks. The LIOA routing strategy is evaluated and compared against well-known routing strategies such as the Minimum Hop Algorithm (MHA), Minimum Interference Routing Algorithm (MIRA), Open Shortest Path First (OSPF) and Constraint Shortest Path First (CSPF) by means of simulation. Simulation results revealed that, for the network topologies under consideration, the routing strategies that employed dynamic network state information in their routing decisions (LIOA, CSPF and MIRA) generally outperformed the routing strategies that only rely on static network information (OSPF and MHA). In most simulation experiments the best performance was achieved by the LIOA routing strategy while the MHA performed the worse. Furthermore we observed that the computational complexity of the MIRA routing strategy does not translate into equivalent performance gains. We employed the online routing strategies for MPLS failure recovery upon link failure. In particular we investigated two aspects to determine the efficiency of the routing strategies for MPLS rerouting: the suitability of the LSP configuration that results due to the establishment of LSPs prior to link failure and the ability of the online routing strategy to reroute failed LSPs upon link failure. Simulation results revealed similar rerouting performance for all online routing strategies under investigation, but a LSP configuration most suitable for online rerouting was observed for the LIOA routing strategy. / AFRIKAANSE OPSOMMING:Die Internet is voordurend besig om te evoleer in 'n medium wat 'n wye reeks moderne kommunikasietegnologiee ondersteun, insluitende telefoon, video en data. Internet gebruikers verwag gewaarborgde diens van hul diensverskaffers en daar bestaan dus 'n vraag na doeltreffende televerkeerbeheer vir gewaarborgde Internet diensgehalte. Multiprotokol Etiketskakeling (MPLS) is 'n etiketskakeling protokol wat doeltreffende televerkeerbeheer en diensgehalte moontlik maak deur die eksplisiete seleksie van virtuele konneksies vir die transmissie van netwerkverkeer in Internetprotokol (IP) netwerke. Hierdie virtuele konneksies staan bekend as etiketgeskakelde paaie. Die MPLS protokol ondersteun tans twee moontlikhede vir eksplisiete seleksie van etiketgeskakelde paaie: aflyn padberekening met behulp van optimeringsmetodes en dinamiese aanlyn padseleksie waar 'n gekose node 'n eksplisiete pad bereken deur die huidige stand van die netwerk in ag te neem. In hierdie tesis word verskeie padseleksiemetodes vir die seleksie van eksplisiete bandwydte-gewaarborgde etiketgeskakelde paaie deur mid del van dinamiese padseleksie ondersoek. Die probleem om 'n reeks optimale etiketgeskakelde paaie te bereken wat elk 'n gespesifeerde verkeersaanvraag kan akkommodeer word aangespreek. Daar word aanvaar dat geen informasie in verband met die toekomstige verkeersaanvraag bekend is nie en dat die aankomsvolgorde van etiketgeskakelde pad verso eke onbekend is. Ons ondersoek verder die herroeteringsmoontlikhede van die aanlyn padseleksiemetodes vir MPLS foutrestorasie in die geval van skakelonderbreking. Vir hierdie doel word 'n nuwe aanlyn roeteringsraamwerk naamlik Laagste Inwerking Optimering (LIO) voorgestel. LIO benut die huidige beskikbare bandwydte en verkeersvloeidistribusie van die netwerk om doeltreffende televerkeerbeheer moontlik te maak. Ons beskryf 'n Laagste Inwerking Optimering Algoritme (LIOA) wat die inwerking tussen kompeterende verkeersvloei verminder deur 'n balans te handhaaf tussen die aantal en kwantiteit van die verkeersvloeistrome wat gedra word deur elke netwerkskakel. Die LIOA roeteringstrategie word geevalueer met behulp van simulasie en die resultate word vergelyk met ander bekende roeteringstrategiee insluitende die Minimum Node Algorithme (MHA), die Minimum Inwerking Algoritme (MIRA), die Wydste Kortste Pad Eerste Algoritme (OSPF) en die Beperkte Kortste Pad Eerste Algoritme (CSPF). Die resultate van die simulasie-eksperimente to on dat, vir die netwerk topologiee onder eksperimentasie, die roeteringstratgiee wat roeteringsbesluite op dinamiese netwerk informasie baseer (LIOA, MIRA, CSPF) oor die algemeen beter vaar as die wat slegs staatmaak op statiese netwerkinformasie (MHA, OSPF). In die meeste simulasie-eksperimente vaar die LIOA roeteringstrategie die beste en die MHA roeteringstrategie die slegste. Daar word verder waargeneem dat die komputasiekomplesiteit van die MIRA roeteringstrategie nie noodwendig weerspieel word in die sukses van roeteringsuitkoms nie. In die geval waar die aanlyn roeteringstrategiee aangewend word vir MPLS foutrestorasie, toon die resultate van simulasie-eksperimente dat al die roeteringstrategiee min of meer dieselfde uitkoms lewer ten opsigte van herroetering van onderbreekte verkeersvloei. Die konfigurasie van etiketgeskakelde paaie deur die LIOA roeteringstrategie voor skakelonderbreking is egter die geskikste vir televerkeer herroetering na skakelonderbreking

Thesis (MSc)--University of Stellenbosch, 2005. / ENGLISH ABSTRACT: Sign Language is a fully-fledged natural language possessing its own syntax and grammar; a fact which implies that the problem of machine translation from a spoken source language to Sign Language is at least as difficult as machine translation between two spoken languages. Sign Language, however, is communicated in a modality fundamentally different from all spoken languages. Machine translation to Sign Language is therefore burdened not only by a mapping from one syntax and grammar to another, but also, by a non-trivial transformation from one communicational modality to another. With regards to the computer visualization of Sign Language; what is required is a three dimensional, temporally accurate, visualization of signs including both the manual and nonmanual components which can be viewed from arbitrary perspectives making accurate understanding and imitation more feasible. Moreover, given that facial expressions and movements represent a fundamental basis for the majority of non-manual signs, any system concerned with the accurate visualization of Sign Language must rely heavily on a facial animation component capable of representing a well-defined set of emotional expressions as well as a set of arbitrary facial movements. This thesis investigates the development of such a computer facial animation system. We address the problem of delivering coordinated, temporally constrained, facial animation sequences in an online environment using VRML. Furthermore, we investigate the animation, using a muscle model process, of arbitrary three-dimensional facial models consisting of multiple aligned NURBS surfaces of varying refinement. Our results showed that this approach is capable of representing and manipulating high fidelity three-dimensional facial models in such a manner that localized distortions of the models result in the recognizable and realistic display of human facial expressions and that these facial expressions can be displayed in a coordinated, synchronous manner. / AFRIKAANSE OPSOMMING: Gebaretaal is 'n volwaardige natuurlike taal wat oor sy eie sintaks en grammatika beskik. Hierdie feit impliseer dat die probleem rakende masjienvertaling vanuit 'n gesproke taal na Gebaretaal net so moeilik is as masjienvertaling tussen twee gesproke tale. Gebaretaal word egter in 'n modaliteit gekommunikeer wat in wese van alle gesproke tale verskil. Masjienvertaling in Gebaretaal word daarom nie net belas deur 'n afbeelding van een sintaks en grammatika op 'n ander nie, maar ook deur beduidende omvorming van een kommunikasiemodaliteit na 'n ander. Wat die gerekenariseerde visualisering van Gebaretaal betref, vereis dit 'n driedimensionele, tyds-akkurate visualisering van gebare, insluitend komponente wat met en sonder die gebruik van die hande uitgevoer word, en wat vanuit arbitrêre perspektiewe beskou kan word ten einde die uitvoerbaarheid van akkurate begrip en nabootsing te verhoog. Aangesien gesigsuitdrukkings en -bewegings die fundamentele grondslag van die meeste gebare wat nie met die hand gemaak word nie, verteenwoordig, moet enige stelsel wat te make het met die akkurate visualisering van Gebaretaal boonop sterk steun op 'n gesigsanimasiekomponent wat daartoe in staat is om 'n goed gedefinieerde stel emosionele uitdrukkings sowel as 'n stel arbitrre gesigbewegings voor te stel. Hierdie tesis ondersoek die ontwikkeling van so 'n gerekenariseerde gesigsanimasiestelsel. Die probleem rakende die lewering van gekordineerde, tydsbegrensde gesigsanimasiesekwensies in 'n intydse omgewing, wat gebruik maak van VRML, word aangeroer. Voorts word ondersoek ingestel na die animasie (hier word van 'n spiermodelproses gebruik gemaak) van arbitrre driedimensionele gesigsmodelle bestaande uit veelvoudige, opgestelde NURBS-oppervlakke waarvan die verfyning wissel. Die resultate toon dat hierdie benadering daartoe in staat is om hoë kwaliteit driedimensionele gesigsmodelle só voor te stel en te manipuleer dat gelokaliseerde vervormings van die modelle die herkenbare en realistiese tentoonstelling van menslike gesigsuitdrukkings tot gevolg het en dat hierdie gesigsuitdrukkings op 'n gekordineerde, sinchroniese wyse uitgebeeld kan word.

Thesis (MSc)--Stellenbosch University, 2002. / ENGLISH ABSTRACT: The Internet is evolving into a commercial platform requiring enhanced protocols and an expanded physical infrastructure allowing a better delivery from IP. Multi-protocol Label Switching (MPLS) is a technology enabling traffic engineering and virtual private network (VPN) provisioning. MPLS achieves traffic engineering by carrying the traffic over virtual connections called Label Switched Paths (LSPs) which are engineered based on QoS requirements such as delay, jitter and packet loss minimization or throughput maximization. This thesis proposes path finding and traffic distribution methods to be deployed in MPLS networks for traffic engineering LSPs. A flow optimization model based on a pre-planned routing approach separating path finding and traffic distribution is presented. This model is augmented by a threshold routing approach which routes the traffic based on thresholds expressing the maximum load level reached by network links. This routing approach moves the traffic away from thresholdmarked links to achieve low-utilized links/paths. The performance and routing capabilities of these methods are evaluated through designed software. A routing architecture implementing a two-layer signalling model for MPLS network is proposed and evaluated through simulation. v / AFRIKAANSE OPSOMMING:Die verandering van die Internet in 'n kommersiele platform met verbeterde protokolle en 'n uitgebreide fisieke infrastruktuur stel die internetprotokol (IP) in staat tot beter lewering. Multiprotokol- etiketskakeling (MPLS), is 'n tegnologie vir die voorsiening van televerkeerbeheer en virtuele privaatnetwerke (VPN). MPLS verskaf televerkeerbeheer deur die verkeer te dra oar virtuele konneksies, wat bekend staan as etiketgeskakelde paaie, waarvan die ontwerp gebaseer is op vereistes vir diensgehalte soos vertraging, ritteling en die minimering van pakketverlies of maksimering van deurvoer. Hierdie tesis stel nuwe padvind- en verkeerdistribusiemetodes voor wat aangewend word in MPLSnetwerke om etiketgeskakelde paaie te beheer. 'n Model vir vloei-optimering-gebaseer op voorafbeplande roetering wat padvinding en verkeerdistribusie skei-word aangebied. Hierdie model word uitgebrei deur 'n benadering van drempelroetering wat die verkeer roeteer en gebaseer is op drempels wat die maksimum ladingsvlak voorstel wat bereik kan word deur netwerkskakels. Hierdie roeteringsbenadering skuif die verkeer weg van drempelgemerkte skakels en bereik daardeur laaggebruikte skakelsjpaaie. Die prestasie en roeteringsvaardigheid van hierdie metodes word gevalueer deur selfontwikkelde programmatuur. 'n Argitektuur vir roetering wat 'n dubbellaagseinmodel implementeer vir 'n MPLS-netwerk, word aangebied en gevalueer met simulasie.

Thesis (MSc) -- Stellenbosch University , 2003. / ENGLISH ABSTRACT: The integration of symbolic knowledge with artificial neural networks is becoming an increasingly popular paradigm for solving real-world problems. This paradigm named knowledge-based neurocomputing, provides means for using prior knowledge to determine the network architecture, to program a subset of weights to induce a learning bias which guides network training, and to extract refined knowledge from trained neural networks. The role of neural networks then becomes that of knowledge refinement. It thus provides a methodology for dealing with uncertainty in the initial domain theory. In this thesis, we address several advantages of this paradigm and propose a solution for the open question of determining the strength of this learning, or inductive, bias. We develop a heuristic for determining the strength of the inductive bias that takes the network architecture, the prior knowledge, the learning method, and the training data into consideration. We apply this heuristic to well-known synthetic problems as well as published difficult real-world problems in the domain of molecular biology and medical diagnoses. We found that, not only do the networks trained with this adaptive inductive bias show superior performance over networks trained with the standard method of determining the strength of the inductive bias, but that the extracted refined knowledge from these trained networks deliver more concise and accurate domain theories. / AFRIKAANSE OPSOMMING: Die integrasie van simboliese kennis met kunsmatige neurale netwerke word 'n toenemende gewilde paradigma om reelewereldse probleme op te los. Hierdie paradigma genoem, kennis-gebaseerde neurokomputasie, verskaf die vermoe om vooraf kennis te gebruik om die netwerkargitektuur te bepaal, om a subversameling van gewigte te programeer om 'n leersydigheid te induseer wat netwerkopleiding lei, en om verfynde kennis van geleerde netwerke te kan ontsluit. Die rol van neurale netwerke word dan die van kennisverfyning. Dit verskaf dus 'n metodologie vir die behandeling van onsekerheid in die aanvangsdomeinteorie. In hierdie tesis adresseer ons verskeie voordele wat bevat is in hierdie paradigma en stel ons 'n oplossing voor vir die oop vraag om die gewig van hierdie leer-, of induktiewe sydigheid te bepaal. Ons ontwikkel 'n heuristiek vir die bepaling van die induktiewe sydigheid wat die netwerkargitektuur, die aanvangskennis, die leermetode, en die data vir die leer proses in ag neem. Ons pas hierdie heuristiek toe op bekende sintetiese probleme so weI as op gepubliseerde moeilike reelewereldse probleme in die gebied van molekulere biologie en mediese diagnostiek. Ons bevind dat, nie alleenlik vertoon die netwerke wat geleer is met die adaptiewe induktiewe sydigheid superieure verrigting bo die netwerke wat geleer is met die standaardmetode om die gewig van die induktiewe sydigheid te bepaal nie, maar ook dat die verfynde kennis wat ontsluit is uit hierdie geleerde netwerke meer bondige en akkurate domeinteorie lewer.