Haptic, or force, interaction in virtual environments can support the development of physical manipulation skills if users feel realistic forces in response to their motion in the virtual environment. The realism of the forces felt by users depends on: (i) how accurately the virtual environment simulates a real life situation such as surgery; and (ii) how faithfully the haptic controller renders the simulated interactions to users. Accurate simulations of real life situations such as surgery run at variable frequencies of the order of 20-100 Hz. However, the haptic controller needs updated stiffness and direction of contact at 1000 Hz to faithfully convey the shape and hardness of the virtual objects to the user. This thesis proposes to bridge the gap between the required fast haptic control rate and the slower virtual environment updates through a passive local model of interaction. This model comprises an approximation of the shape and stiffness of the virtual world in the area near the point of interaction. It also monitors its exchange of energy with the user to ensure its own passivity and thus, the stability of the haptic system. Lastly, the local model eliminates the spurious discontinuities that arise in contact direction at model updates by interpolating the contact normal before rendering it to the user. / Graduate

One form of model robust regression (MRR) predicts mean response as a convex combination of a parametric and a nonparametric prediction. MRR is a semiparametric method by which an incompletely or an incorrectly specified parametric model can be improved through adding an appropriate amount of a nonparametric fit. The combined predictor can have less bias than the parametric model estimate alone and less variance than the nonparametric estimate alone. Additionally, as shown in previous work for uncorrelated data with linear mean function, MRR can converge faster than the nonparametric predictor alone. We extend the MRR technique to the problem of predicting mean response for clustered non-normal data. We combine a nonparametric method based on local estimation with a global, parametric generalized estimating equations (GEE) estimate through a mixing parameter on both the mean scale and the linear predictor scale. As a special case, when data are uncorrelated, this amounts to mixing a local likelihood estimate with predictions from a global generalized linear model. Cross-validation bandwidth and optimal mixing parameter selectors are developed. The global fits and the optimal and data-driven local and mixed fits are studied under no/some/substantial model misspecification via simulation. The methods are then illustrated through application to data from a longitudinal study. / Ph. D.

This thesis presents several novel methods to address some of the real world data modelling issues through the use of local and individualised modelling approaches. A set of real world data modelling issues such as modelling evolving processes, defining unique problem subspaces, identifying and dealing with noise, outliers, missing values, imbalanced data and irrelevant features, are reviewed and their impact on the models are analysed. The thesis has made nine major contributions to information science, includes four generic modelling methods, three real world application systems that apply these methods, a comprehensive review of the real world data modelling problems and a data analysis and modelling software. Four novel methods have been developed and published in the course of this study. They are: (1) DyNFIS – Dynamic Neuro-Fuzzy Inference System, (2) MUFIS – A Fuzzy Inference System That Uses Multiple Types of Fuzzy Rules, (3) Integrated Temporal and Spatial Multi-Model System, (4) Personalised Regression Model. DyNFIS addresses the issue of unique problem subspaces by identifying them through a clustering process, creating a fuzzy inference system based on the clusters and applies supervised learning to update the fuzzy rules, both antecedent and consequent part. This puts strong emphasis on the unique problem subspaces and allows easy to understand rules to be extracted from the model, which adds knowledge to the problem. MUFIS takes DyNFIS a step further by integrating a mixture of different types of fuzzy rules together in a single fuzzy inference system. In many real world problems, some problem subspaces were found to be more suitable for one type of fuzzy rule than others and, therefore, by integrating multiple types of fuzzy rules together, a better prediction can be made. The type of fuzzy rule assigned to each unique problem subspace also provides additional understanding of its characteristics. The Integrated Temporal and Spatial Multi-Model System is a different approach to integrating two contrasting views of the problem for better results. The temporal model uses recent data and the spatial model uses historical data to make the prediction. By combining the two through a dynamic contribution adjustment function, the system is able to provide stable yet accurate prediction on real world data modelling problems that have intermittently changing patterns. The personalised regression model is designed for classification problems. With the understanding that real world data modelling problems often involve noisy or irrelevant variables and the number of input vectors in each class may be highly imbalanced, these issues make the definition of unique problem subspaces less accurate. The proposed method uses a model selection system based on an incremental feature selection method to select the best set of features. A global model is then created based on this set of features and then optimised using training input vectors in the test input vector’s vicinity. This approach focus on the definition of the problem space and put emphasis the test input vector’s residing problem subspace. The novel generic prediction methods listed above have been applied to the following three real world data modelling problems: 1. Renal function evaluation which achieved higher accuracy than all other existing methods while allowing easy to understand rules to be extracted from the model for future studies. 2. Milk volume prediction system for Fonterra achieved a 20% improvement over the method currently used by Fonterra. 3. Prognoses system for pregnancy outcome prediction (SCOPE), achieved a more stable and slightly better accuracy than traditional statistical methods. These solutions constitute a contribution to the area of applied information science. In addition to the above contributions, a data analysis software package, NeuCom, was primarily developed by the author prior and during the PhD study to facilitate some of the standard experiments and analysis on various case studies. This is a full featured data analysis and modelling software that is freely available for non-commercial purposes (see Appendix A for more details). In summary, many real world problems consist of many smaller problems. It was found beneficial to acknowledge the existence of these sub-problems and address them through the use of local or personalised models. The rules extracted from the local models also brought about the availability of new knowledge for the researchers and allowed more in-depth study of the sub-problems to be carried out in future research.

This thesis presents several novel methods to address some of the real world data modelling issues through the use of local and individualised modelling approaches. A set of real world data modelling issues such as modelling evolving processes, defining unique problem subspaces, identifying and dealing with noise, outliers, missing values, imbalanced data and irrelevant features, are reviewed and their impact on the models are analysed. The thesis has made nine major contributions to information science, includes four generic modelling methods, three real world application systems that apply these methods, a comprehensive review of the real world data modelling problems and a data analysis and modelling software. Four novel methods have been developed and published in the course of this study. They are: (1) DyNFIS – Dynamic Neuro-Fuzzy Inference System, (2) MUFIS – A Fuzzy Inference System That Uses Multiple Types of Fuzzy Rules, (3) Integrated Temporal and Spatial Multi-Model System, (4) Personalised Regression Model. DyNFIS addresses the issue of unique problem subspaces by identifying them through a clustering process, creating a fuzzy inference system based on the clusters and applies supervised learning to update the fuzzy rules, both antecedent and consequent part. This puts strong emphasis on the unique problem subspaces and allows easy to understand rules to be extracted from the model, which adds knowledge to the problem. MUFIS takes DyNFIS a step further by integrating a mixture of different types of fuzzy rules together in a single fuzzy inference system. In many real world problems, some problem subspaces were found to be more suitable for one type of fuzzy rule than others and, therefore, by integrating multiple types of fuzzy rules together, a better prediction can be made. The type of fuzzy rule assigned to each unique problem subspace also provides additional understanding of its characteristics. The Integrated Temporal and Spatial Multi-Model System is a different approach to integrating two contrasting views of the problem for better results. The temporal model uses recent data and the spatial model uses historical data to make the prediction. By combining the two through a dynamic contribution adjustment function, the system is able to provide stable yet accurate prediction on real world data modelling problems that have intermittently changing patterns. The personalised regression model is designed for classification problems. With the understanding that real world data modelling problems often involve noisy or irrelevant variables and the number of input vectors in each class may be highly imbalanced, these issues make the definition of unique problem subspaces less accurate. The proposed method uses a model selection system based on an incremental feature selection method to select the best set of features. A global model is then created based on this set of features and then optimised using training input vectors in the test input vector’s vicinity. This approach focus on the definition of the problem space and put emphasis the test input vector’s residing problem subspace. The novel generic prediction methods listed above have been applied to the following three real world data modelling problems: 1. Renal function evaluation which achieved higher accuracy than all other existing methods while allowing easy to understand rules to be extracted from the model for future studies. 2. Milk volume prediction system for Fonterra achieved a 20% improvement over the method currently used by Fonterra. 3. Prognoses system for pregnancy outcome prediction (SCOPE), achieved a more stable and slightly better accuracy than traditional statistical methods. These solutions constitute a contribution to the area of applied information science. In addition to the above contributions, a data analysis software package, NeuCom, was primarily developed by the author prior and during the PhD study to facilitate some of the standard experiments and analysis on various case studies. This is a full featured data analysis and modelling software that is freely available for non-commercial purposes (see Appendix A for more details). In summary, many real world problems consist of many smaller problems. It was found beneficial to acknowledge the existence of these sub-problems and address them through the use of local or personalised models. The rules extracted from the local models also brought about the availability of new knowledge for the researchers and allowed more in-depth study of the sub-problems to be carried out in future research.

Yes / This paper introduces a hybrid dynamic modelling approach for the prediction of NOx emissions for a Diesel engine, based on a multi-physics simulation platform coupling a 1-D air path model (GT-Suite) with in-cylinder combustion model (CMCL Stochastic Reactor Model Engine Suite). The key motivation for this research was the requirement to establish a real time stochastic simulation capability for emissions predictions early in engine development, which required the replacement of the slow combustion chemistry solver (SRM) with an appropriate surrogate model. The novelty of the approach in this research is the introduction of a hybrid approach to metamodeling that combines dynamic experiments for the gas path model with a zonal optimal space-filling design of experiments (DoEs) for the combustion model. The dynamic experiments run on the virtual Diesel engine model (GT- Suite) was used to fit a dynamic model for the parameters required as input to the SRM. Optimal Latin Hypercubes (OLH) DoE run on the SRM model was used to fit a response surface model for the NOx emissions. This surrogate NOx model was then used to replace the computationally expensive SRM simulation, enabling real time simulations of transient drive cycles to be executed. The performance of the proposed approach was validated on a simulated NEDC drive cycle against experimental data collected for the engine case study, which proved the capability of methodology to capture the transient trends for the NOx emissions. The significance of this work is that it provided an efficient approach to the development of a global model with real time transient modelling capability based on the integration of dynamic and local DoE metamodeling experiments.

Dans cette thèse, nous étudions la mauvaise réduction de variétés de Shimura. Plus précisément, nous construisons un modèle local des schémas de Hilbert-Siegel de niveau Г₁(p) sur Spec Zq lorsque p est non-ramifié dans le corps totalement réel, où q est le cardinal résiduel au-dessus de p. Notre outil principal est une variante sur le petit topos de Zariski du complexe de Lie anneau-équivariant Aℓv_G défini par Illusie dans sa thèse, où A est un anneau commutatif et G est un schéma en A-modules.Nous montrons aussi une compatibilité entre le complexe de Lie de G équivariant par l’anneau A, et celui équivariant par le monoïde multiplicatif sous-jacent de A.Ce complexe nous permet de calculer le complexe de Lie Fq-équivariant d’un schéma en groupes de Raynaud, donc de relier le modèle entier et le modèle local. / In this thesis, we study the bad reduction of Shimura varieties. More precisely, we construct a local model of Hilbert-Siegel moduli schemes in level Г₁(p) over Spec Zq when p is unramified in the totally real field, where q is the residue cardinality over p. Our main tool is a variant over the small Zariski topos of the ring-equivariant Lie complex Aℓv_G defined by Illusie in his thesis, where A is a commutative ringand G is a scheme of A-modules. We also prove a compatibility result between thering-equivariant Lie complex and the Lie complex equivariant by the multiplicative monoid underlying this ring. With this complex, we calculate the Fq-equivariant Lie complex of a Raynaud group scheme, then relate the integral model and the local model.

The data-driven models used for the design of powertrain controllers are typically based on the data obtained from steady-state experiments. However, they are only valid under stable conditions and do not provide any information on the dynamic behaviour of the system. In order to capture this behaviour, dynamic modelling techniques are intensively studied to generate alternative solutions for engine mapping and calibration problem, aiming to address the need to increase productivity (reduce development time) and to develop better models for the actual behaviour of the engine under real-world conditions. In this thesis, a dynamic modelling approach is presented undertaken for the prediction of NOx emissions for a 2.0 litre Diesel engine, based on a coupled pre-validated virtual Diesel engine model (GT- Suite ® 1-D air path model) and in-cylinder combustion model (CMCL ® Stochastic Reactor Model Engine Suite). In the context of the considered Engine Simulation Framework, GT Suite + Stochastic Reactor Model (SRM), one fundamental problem is to establish a real time stochastic simulation capability. This problem can be addressed by replacing the slow combustion chemistry solver (SRM) with an appropriate NOx surrogate model. The approach taken in this research for the development of this surrogate model was based on a combination of design of dynamic experiments run on the virtual diesel engine model (GT- Suite), with a dynamic model fitted for the parameters required as input to the SRM, with a zonal design of experiments (DoEs), using Optimal Latin Hypercubes (OLH), run on the SRM model. A response surface model was fitted on the predicted NOx from the SRM OLH DoE data. This surrogate NOx model was then used to replace the computationally expensive SRM simulation, enabling real-time simulations of transient drive cycles to be executed. The performance of the approach was validated on a simulated NEDC drive cycle, against experimental data collected for the engine case study. The capability of methodology to capture the transient trends of the system shows promising results and will be used for the development of global surrogate prediction models for engine-out emissions.

La teoría de vigas de Timoshenko TBT y una teoría de alto orden IFSDT son formuladas utilizando las ecuaciones constitutivas no locales de Eringen. Se utilizaron ecuaciones constitutivas en 3D en el modelo IFSDT. Se utilizó una variación del material con el uso de materiales funcionalmente graduados a lo largo del peralte de una viga de sección rectangular. El principio de trabajos virtuales utilizado y ejemplos numéricos fueron presentados para comparar ambas teorías de vigas. / Timoshenko Beam Theory (TBT) and an Improved First Shear Deformation Theory (IFSDT) are reformulated using Eringen’s non-local constitutive equations. The use of 3D constitutive equation is presented in IFSDT. A material variation is made by the introduction of FGM power law in the elasticity modulus through the height of a rectangular section beam. The virtual work statement and numerical results are presented in order to compare both beam theories. / Tesis

Aquesta tesi està inspirada en els agents naturals per tal de planificar de manera dinàmica la navegació d'un robot diferencial de dues rodes. Les dades dels sistemes de percepció són integrades dins una graella d'ocupació de l'entorn local del robot. La planificació de les trajectòries es fa considerant la configuració desitjada del robot, així com els vértexs més significatius dels obstacles més propers. En el seguiment de les trajectòries s'utilitzen tècniques locals de control predictiu basades en el model, amb horitzons de predicció inferiors a un segon. La metodologia emprada és validada mitjançant nombrosos experiments. / In this thesis are used natural agents for dinamic navigation of a differential driven wheeled mobile robot. The perception data are integrated on a local occupancy grid framework where planar floor model is assumed. The path-planning is done by considering the local desired configuration, as well as the meaningful local obstacle vertexes. The trajectory-tracking is implemented by using LMPC (local model predictive control) techniques, with prediction horizons of less than one second. Many experiments are tested in order to report the validity of the prosed methodology.

Student Number : 8315331 - MSc dissertation - School of Electrical and Information Engineering - Faculty of Engineering and the Built Environment / In this dissertation an efficient algorithm to calculate the differential of the network output with respect to its inputs is derived for axis orthogonal Local Model (LMN) and Radial Basis Function (RBF) Networks. A new recursive Singular Value Decomposition (SVD) adaptation algorithm, which attempts to circumvent many of the problems found in existing recursive adaptation algorithms, is also derived. Code listings and simulations are presented to demonstrate how the algorithms may be used in on-line adaptive neurocontrol systems. Specifically, the control techniques known as series inverse neural control and instantaneous linearization are highlighted. The presented material illustrates how the approach enhances the flexibility of LMN networks making them suitable for use in both direct and indirect adaptive control methods. By incorporating this ability into LMN networks an important characteristic of Multi Layer Perceptron (MLP) networks is obtained whilst retaining the desirable properties of the RBF and LMN approach.