The modern electronic financial market is composed of a large amount of actors. With the surge in algorithmic trading some of these actors collectively behave in increasingly complex ways. Historically, academic research related to financial markets has been focused on areas such as asset pricing, portfolio management and financial econometrics. However, the fragmentation of the financial market has given rise to a different set of problems, namely the order allocation problem, as well as smart order routers as a tool to comply with these. In this thesis we consider price discrepancies between order books, trading the same instruments, as a proxy for order routing opportunities. A survival analysis framework for these price differences is developed. Specifically, we consider the two widely used Kaplan-Meier and Cox Proportional Hazards models, as well as the somewhat less known Random Survival Forest model, in order to investigate whether such a framework is effective for predicting the survival times of price differences. The results show that the survival models outperform random models and fixed routing decisions significantly. Thus suggesting that such models could beneficially be incorporated into existing SOR environments. Furthermore, the implementation of order book parameters as covariates in the CPH and RSF models add additional performance. / Den moderna elektroniska marknaden består av ett stort antal aktörer som, till följd av ökningen av algoritmisk handel, beter sig alltmer komplext. Historiskt sett har akademisk forskning inom finans i huvudsak fokuserat på områden som prissättning av tillgångar, portföljförvaltning och finansiell ekonometri. Fragmentering av finansiella marknader har däremot gett upphov till nya sorters problem, däribland orderplaceringsproblemet. Följdaktligen har smart order routers utvecklats som ett verktyg för att tillmötesgå detta problem. I detta examensarbete studerar vi prisskillnader mellan orderböcker som tillhandhåller handel av samma instrument. Dessa prisskillnader representerar möjligheter för order routing. Vi utvecklar ett ramverk inom överlevnadsanalys för dessa prisskillnader. Specifikt används de välkända Kaplan-Meier- och Cox Proportional Hazards-modellerna samt den något mindre kända Random Survival Forest, för att utvärdera om ett sådant ramverk kan användas för att förutspå prisskillnadernas livstider. Våra resultat visar att dessa modeller överträffar slumpmässiga modeller samt deterministiska routingstrategier med stor marginal och antyder därmed att ett sådant ramverk kan integreras i SOR-system. Resultaten visar dessutom att användning av orderboksparametrar som variabler i CPH- och RSF-modellerna ökar prestandan.

In this thesis, a novel robust estimation strategy for observing the system state variables of robotic manipulators with distributed flexibility is established. Motivation for the derived approach stems from the observation that lightweight, high speed, and large workspace robotic manipulators often suffer performance degradation because of inherent structural compliance. This flexibility often results in persistent residual vibration, which must be damped before useful work can resume. Inherent flexibility in robotic manipulators, then, increases cycle times and shortens the operational lives of the robots. Traditional compensation techniques, those which are commonly used for the control of rigid manipulators, can only approach a fraction of the open-loop system bandwidth without inducing significant excitation of the resonant dynamics. To improve the performance of these systems, the structural flexibility cannot simply be ignored, as it is when the links are significantly stiff and approximate rigid bodies. One thus needs a model to design a suitable compensator for the vibration, but any model developed to correct this problem will contain parametric error. And in the case of very lightly damped systems, like flexible robotic manipulators, this error can lead to instability of the control system for even small errors in system parameters. This work presents a systematic solution for the problem of robust state estimation for flexible manipulators in the presence of parametric modeling error. The solution includes: 1) a modeling strategy, 2) sensor selection and placement, and 3) a novel, multiple model estimator. Modeling of the FLASHMan flexible gantry manipulator is accomplished using a developed hybrid transfer matrix / assumed modes method (TMM/AMM) approach to determine an accurate low-order state space representation of the system dynamics. This model is utilized in a genetic algorithm optimization in determining the placement of MEMs accelerometers for robust estimation and observability of the system’s flexible state variables. The initial estimation method applied to the task of determining robust state estimates under conditions of parametric modeling error was of a sliding mode observer type. Evaluation of the method through analysis, simulations and experiments showed that the state estimates produced were inadequate. This led to the development of a novel, multiple model adaptive estimator. This estimator utilizes a bank of similarly designed sub-estimators and a selection algorithm to choose the true value from a given set of possible system parameter values as well as the correct state vector estimate. Simulation and experimental results are presented which demonstrate the applicability and effectiveness of the derived method for the task of state variable estimation for flexible robotic manipulators.

Thesis (MSc)--University of Stellenbosch, 2007. / ENGLISH ABSTRACT: Buying and selling in financial markets are driven by demand. The demand can be quantified by the imbalance in the number of shares QB and QS transacted by buyers and sellers respectively over a given time interval t. The demand in an interval t is given by (t) = QB − QS. The local noise intensity is given by = h|aiqi − haiqii|i where i = 1, . . . ,N labels the transactions in t, qi is the number of shares traded in transaction i, ai = ±1 denotes buyer- initiated and seller- initiated trades respectively and h· · · i is the local expectation value computed from all the transactions during the interval t. In a paper [1] based on data from the New York Stock Exchange Trade and Quote database during the period 1995-1996, Plerou, Gopikrishnan and Stanley [1] reported that the analysis of the probability distribution P( | ) of demand conditioned on the local noise intensity revealed the surprising existence of a critical threshold c. For < c, the most probable value of demand is roughly zero; they interpreted this as an equilibrium phase in which neither buying nor selling predominates. For > c two most probable values emerge that are symmetrical around zero demand, corresponding to excess demand and excess supply; they interpreted this as an out-of-equilibrium phase in which the market behaviour is buying for half of the time, and selling for the other half. It was suggested [1] that the two-phase behaviour indicates a link between the dynamics of a financial market with many interacting participants and the phenomenon of phase transitions that occurs in physical systems with many interacting units. This thesis reproduces the two-phase behaviour by means of experiments using sequences of random variables. We reproduce the two-phase behaviour based on correlated and uncorrelatd data. We use a Markov modulated Bernoulli process to model the transactions and investigate a simple interpretation of the two-phase behaviour. We sample data from heavy-tailed distributions and reproduce the two-phase behaviour. Our experiments show that the results presented in [1] do not provide evidence for the presence of complex phenomena in a trading market; the results are a consequence of the sampling method employed. / AFRIKAANSE OPSOMMING: Aankope en verkope in finansi¨ele markte word deur aanvraag gedryf. Aanvraag kan gekwantifiseer word in terme van die ongebalanseerdheid in die getal aandele QB en QB soos onderskeidelik verhandel deur kopers en verkopers in ’n gegewe tyd-interval t. Die aanvraag in ’n interval t word gegee deur (t) = QB −QS. Die lokale geraasintensiteit word gegee deur = h|aiqi − haiqii|i waar i = 1, . . . ,N die transaksies in t benoem, qi die getal aandele verhandel in transaksies verwys, en h· · · i op die lokale verwagte waarde dui, bereken van al die tansaksies tydens die interval t. In ’n referaat [1] wat op data van die New York Effektebeurs se Trade and Quote databasis in die periode tussen 1995 en 1996 geskoei was, het Plerou, Gopikrishnan en Stanley [1] gerapporteer dat ’n analise van die waarskynlikheidsverspreiding P( | ) van aanvraag gekondisioneer op die lokale geraasintensiteit , die verrassende bestaan van ’n kritieke drempelwaarde c na vore bring. Vir < c is die mees waarskynlike aanvraagwaarde nagenoeg nul; hulle het dit ge¨ınterpreteer as ’n ekwilibriumfase waartydens n`og aankope n`og verkope die oormag het. Vir > c is die twee mees waarskynlike aanvraagwaardes wat te voorskyn kom simmetries rondom nul aanvraag, wat oorenstem met ’n oormaat aanvraag en ’n oormaat aanbod; hulle het dit geinterpreteer as ’n buite-ewewigfase waartydens die markgedrag die helfte van die tyd koop en die anderhelfte verkoop. Daar is voorgestel [1] dat die tweefase gedrag op ’n verband tussen die dinamiek van ’n finansiele mark met baie deelnemende partye, en die verskynsel van fase-oorgange wat in fisieke sisteme met baie wisselwerkende eenhede voorkom, dui. Hierdie tesis reproduseer die tweefase gedrag deur middel van eksperimente wat gebruik maak van reekse van lukrake veranderlikes. Ons reproduseer die tweefase gedrag gebaseer op gekorreleerde en ongekorreleerde data. Ons gebruik ’n Markov-gemoduleerde Bernoulli proses om die transaksies te moduleer en ondersoek ’n eenvoudige interpretasie van die tweefase gedrag. Ons seem steekproefdata van “heavy-tailed” verspreidings en reproduseer die tweefase gedrag. Ons ekperimente wys dat die resultate in [1] voorgested is nie bewys lewer vir die teenwoordigheid van komplekse verskynsel in’n handelsmark nie; die resultate is as gevolg van die metode wat gebruik is vir die generering van die steekproefdata.

Thesis (PhD)-- Stellenbosch University, 2013. / ENGLISH ABSTRACT: This dissertation considers automatic segmentation of the left cardiac ventricle in short axis magnetic resonance images. The presence of papillary muscles near the endocardium border makes simple threshold based segmentation difficult. The endo- and epicardium are modelled as two series of radii which are inter-related using features describing shape and motion. Image features are derived from edge information from human annotated images. The features are combined within a Conditional Random Field (CRF) – a discriminatively trained probabilistic model. Loopy belief propagation is used to infer segmentations when an unsegmented video sequence is given. Powell’s method is applied to find CRF parameters by minimising the difference between ground truth annotations and the inferred contours. We also describe how the endocardium centre points are calculated from a single human-provided centre point in the first frame, through minimisation of frame alignment error. We present and analyse the results of segmentation. The algorithm exhibits robustness against inclusion of the papillary muscles by integrating shape and motion information. Possible future improvements are identified. / AFRIKAANSE OPSOMMING: Hierdie proefskrif bespreek die outomatiese segmentasie van die linkerhartkamer in kortas snit magnetiese resonansie beelde. Die teenwoordigheid van die papillêre spiere naby die endokardium grens maak eenvoudige drumpel gebaseerde segmentering moeilik. Die endo- en epikardium word gemodelleer as twee reekse van die radiusse wat beperk word deur eienskappe wat vorm en beweging beskryf. Beeld eienskappe word afgelei van die rand inligting van mens-geannoteerde beelde. Die funksies word gekombineer binne ’n CRF (Conditional Random Field) – ’n diskriminatief afgerigte waarskynlikheidsverdeling. “Loopy belief propagation” word gebruik om segmentasies af te lei wanneer ’n ongesegmenteerde video verskaf word. Powell se metode word toegepas om CRF parameters te vind deur die minimering van die verskil tussen mens geannoteerde segmentasies en die afgeleide kontoere. Ons beskryf ook hoe die endokardium se middelpunte bereken word vanaf ’n enkele mens-verskafte middelpunt in die eerste raam, deur die minimering van ’n raambelyningsfout. Ons analiseer die resultate van segmentering. Die algoritme vertoon robuustheid teen die insluiting van die papillêre spiere deur die integrasie van inligting oor die vorm en die beweging. Moontlike toekomstige verbeterings word geïdentifiseer.

No description available.

Atsitiktinių dydžių transformacijas, naudojančias normalų dėsnį, kone pirmieji išnagrinėjo E. A. Korniš ir R. A. Fišer [5]. Jie savo straipsnyje pasiūlė funkcijų ir formalų skleidimą eilute. Šios eilutės (tiksliau, jų dalinės sumos) yra plačiai naudojamos matematinėje statistikoje, jos vadinamos Korniš – Fišer skleidiniais. Šio darbo tikslas yra išnagrinėti, kaip Grigelionio GZD ( , , , , ) bei ( , , , ) pasiskirstymams taikomas asimptotinis Edžvorto skleidinys (daugianaris). Nagrinėjome kaip užsirašo minėtas skleidinys keičiantis parametrams. Edžvorto skleidinį išreiškėme apytiksliai. Nes naujieji semiinvariantai, gauti po to, kai centravom bei normavom Grigelionio GZD ( , , , , ) ir ( , , , ) atsitiktinį dydį, užrašyti apytiksliai. Semiinvariantų išreiškimui buvo naudojamas tik pirmas narys funkcijos , kuri užrašyta, naudojantis Eulerio – Makloreno sumavimo formule. / Cornish and Fisher were the firsts scholars who have analysed transformations of the random variables are associated with normal distribution. They suggested formal expansions of the functions x(y) and y(x). These expansions are widely spread in the statistics, they are called Cornish – Fisher expansions. The research is investigated the normal approximations for other distributions. The research is investigated how Edgeworth expansions applied for Br. Grigelionis distributions GZD ( , , , , ) and ( , , , ).

Šioje santraukoje trumpai aprašoma V. Kurausko disertacija. Pristatomos abi disertacijos dalys, įvedami atsitiktinių sankirtų grafų ir digrafų modeliai, apibrėžiamos minorinės grafų klasės, suformuluojami sprendžiami uždaviniai bei pateikiami pagrindiniai rezultatai. / This paper summarizes (in Lithuanian) the doctoral dissertation "On two models of random graphs" (in English) by V. Kurauskas. We introduce the random graph models (random intersection graphs, graphs with disjoint excluded minors) studied in the thesis, overview the problems and state the main results.

The dissertation consists of two parts. In the first part several asymptotic properties of random intersection graphs are studied. They include birth thresholds for small complete subgraphs in the binomial random intersection graph, the clique number in sparse random intersection graphs and the chromatic index of random uniform hypergraphs. Several new methods and theoretically and practically relevant algorithms are proposed. Some results are illustrated with data from real-world networks. The second part deals with asymptotic enumeration and properties of graphs from minor-closed classes in the case when the excluded minors are disjoint. The class of graphs without k+1 (vertex-)disjoint cycles and more general classes of graphs without k+1 disjoint excluded minors (satisfying a condition related to fans) are considered. Typical graphs in such classes are shown to have a simple “k apex vertex” structure. Other asymptotic properties (connectivity, number of components, chromatic number, vertex degrees) are also determined. Finally, it is shown that typical graphs without k+1 disjoint minors K4 have a more complicated “2k+1 apex vertex” structure, and properties of such graphs are investigated. Part of the results is proved in greater generality. A variety of methods from computer science, graph theory, combinatorics and the theory of generating functions are applied. / Disertacijoje yra dvi pagrindinės dalys. Pirmojoje dalyje gaunami keli nauji rezultatai uždaviniams, susijusiems su atsitiktiniais sankirtų grafais. Nagrinėjamas pilnojo pografio gimimo slenkstis binominiame atsitiktiniame sankirtų grafe, didžiausios klikos eilė atsitiktiniame retame sankirtų grafe ir chromatinio indekso eilė atsitiktiniame reguliariajame hipergrafe. Sprendimams pasiūloma keletas naujų metodų, taip pat pateikiami teoriškai ir praktiškai svarbūs algoritmai. Kai kurie rezultatai iliustruojami duomenimis iš realių tinklų. Antrojoje dalyje pristatomi rezultatai grafų su uždraustaisiais minorais tematikoje, nagrinėjamas atvejis kai uždraustieji minorai yra nejungūs. Čia tiriamas asimptotinis grafų, neturinčių k+1 nepriklausomų ciklų, skaičius, rezultatai apibendrinami grafų, neturinčių k+1 uždraustųjų minorų, tačiau tenkinančių tam tikrą „vėduoklės“ apribojimą, klasėms. Įrodoma, kad tipiniai tokių klasių grafai turi paprastą „k dydžio blokatoriaus“ struktūrą, nustatomos kitos tokių grafų asimptotinės savybės (jungumas, komponenčių skaičius, viršūnių laipsniai). Galiausiai parodoma, kad tipiniai grafai, neturintys k+1 nepriklausomų minorų K4 turi sudėtingesnę „2k+1 dydžio blokatoriaus“ struktūrą ir ištiriamos kitos jų savybės. Dalis šių rezultatų įrodoma daug bendresniu atveju. Darbe pasitelkiami įvairūs informatikos, kombinatorikos, grafų, tikimybių ir generuojančiųjų funkcijų teorijos metodai.

Thesis (MScEng) -- Stellenbosch University, 2014. / ENGLISH ABSTRACT: The increasing popularity of microblogging services such as Twitter means that more and more unstructured data is available for analysis. The informal language usage in these media presents a problem for traditional text mining and natural language processing tools. We develop a pre-processor to normalise this noisy text so that useful information can be extracted with standard tools. A system consisting of a tokeniser, out-of-vocabulary token identifier, correct candidate generator, and N-gram language model is proposed. We compare the performance of generative and discriminative probabilistic models for these different modules. The effect of normalising the training and testing data on the performance of a tweet sentiment classifier is investigated. A linear-chain conditional random field, which is a discriminative model, is found to work better than its generative counterpart for the tokenisation module, achieving a 0.76% character error rate compared to 1.41% for the finite state automaton. For the candidate generation module, however, the generative weighted finite state transducer works better, getting the correct clean version of a word right 36% of the time on the first guess, while the discriminatively trained hidden alignment conditional random field only achieves 6%. The use of a normaliser as a pre-processing step does not significantly affect the performance of the sentiment classifier. / AFRIKAANSE OPSOMMING: Mikro-webjoernale soos Twitter word al hoe meer gewild, en die hoeveelheid ongestruktureerde data wat beskikbaar is vir analise groei daarom soos nooit tevore nie. Die informele taalgebruik in hierdie media maak dit egter moeilik om tradisionele tegnieke en bestaande dataverwerkingsgereedskap toe te pas. ’n Stelsel wat hierdie ruiserige teks normaliseer word ontwikkel sodat bestaande pakkette gebruik kan word om die teks verder te verwerk. Die stelsel bestaan uit ’n module wat die teks in woordeenhede opdeel, ’n module wat woorde identifiseer wat gekorrigeer moet word, ’n module wat dan kandidaat korreksies voorstel, en ’n module wat ’n taalmodel toepas om die mees waarskynlike skoon teks te vind. Die verrigting van diskriminatiewe en generatiewe modelle vir ’n paar van hierdie modules word vergelyk en die invloed wat so ’n normaliseerder op die akkuraatheid van ’n sentimentklassifiseerder het word ondersoek. Ons bevind dat ’n lineêre-ketting voorwaardelike toevalsveld—’n diskriminatiewe model — beter werk as sy generatiewe eweknie vir tekssegmentering. Die voorwaardelike toevalsveld-model behaal ’n karakterfoutkoers van 0.76%, terwyl die toestandsmasjien-model 1.41% behaal. Die toestantsmasjien-model werk weer beter om kandidaat woorde te genereer as die verskuilde belyningsmodel wat ons geïmplementeer het. Die toestandsmasjien kry 36% van die tyd die regte weergawe van ’n woord met die eerste raaiskoot, terwyl die diskriminatiewe model dit slegs 6% van die tyd kan doen. Laastens het ons bevind dat die vooraf normalisering van Twitter boodskappe nie ’n beduidende effek op die akkuraatheid van ’n sentiment klassifiseerder het nie.

Made available in DSpace on 2015-04-14T14:50:03Z (GMT). No. of bitstreams: 1 449231.pdf: 1860025 bytes, checksum: 1ace09799e27fa64938e802d2d91d1af (MD5) Previous issue date: 2012-08-31 / In the Data Mining area experiments have been carried out using Ensemble Classifiers. We experimented Random Forests to evaluate the performance when randomness is applied. The results of this experiment showed us that the impact of randomness is much more relevant in Random Forests when compared with other algorithms, e.g., Bagging and Boosting. The main purpose of this work is to decrease the effect of randomness in Random Forests. To achieve the main purpose we implemented an extension of this method named Stochastic Random Forests and specified the strategy to increase the performance and stability combining the results. At the end of this work the improvements achieved are presented / Na ?rea de Minera??o de Dados, experimentos vem sendo realizados utilizando Conjuntos de Classificadores. Estes experimentos s?o baseados em compara??es emp?ricas que sofrem com a falta de cuidados no que diz respeito ? quest?es de aleatoriedade destes m?todos. Experimentamos o Random Forests para avaliar a efici?ncia do algoritmo quando submetido a estas quest?es. Estudos sobre os resultados mostram que a sensibilidade do Random Forests ? significativamente maior quando comparado com a de outros m?todos encontrados na literatura, como Bagging e Boosting. O proposito desta disserta??o ? diminuir a sensibilidade do Random Forests quando submetido a aleatoriedade. Para alcan?ar este objetivo, implementamos uma extens?o do m?todo, que chamamos de Random Forests Estoc?stico. Logo especificamos como podem ser alcan?adas melhorias no problema encontrado no algoritmo combinando seus resultados. Por ?ltimo, um estudo ? apresentado mostrando as melhorias atingidas no problema de sensibilidade