by Ngan Po Shun. / Thesis (M.Phil.)--Chinese University of Hong Kong, 1998. / Includes bibliographical references (leaves 109-115). / Abstract also in Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Data Mining --- p.1 / Chapter 1.2 --- Motivation --- p.4 / Chapter 1.3 --- Contributions of the research --- p.5 / Chapter 1.4 --- Organization of the thesis --- p.6 / Chapter 2 --- Related Work in Data Mining --- p.9 / Chapter 2.1 --- Decision Tree Approach --- p.9 / Chapter 2.1.1 --- ID3 --- p.10 / Chapter 2.1.2 --- C4.5 --- p.11 / Chapter 2.2 --- Classification Rule Learning --- p.13 / Chapter 2.2.1 --- AQ algorithm --- p.13 / Chapter 2.2.2 --- CN2 --- p.14 / Chapter 2.2.3 --- C4.5RULES --- p.16 / Chapter 2.3 --- Association Rule Mining --- p.16 / Chapter 2.3.1 --- Apriori --- p.17 / Chapter 2.3.2 --- Quantitative Association Rule Mining --- p.18 / Chapter 2.4 --- Statistical Approach --- p.19 / Chapter 2.4.1 --- Chi Square Test and Bayesian Classifier --- p.19 / Chapter 2.4.2 --- FORTY-NINER --- p.21 / Chapter 2.4.3 --- EXPLORA --- p.22 / Chapter 2.5 --- Bayesian Network Learning --- p.23 / Chapter 2.5.1 --- Learning Bayesian Networks using the Minimum Descrip- tion Length (MDL) Principle --- p.24 / Chapter 2.5.2 --- Discretizating Continuous Attributes while Learning Bayesian Networks --- p.26 / Chapter 3 --- Overview of Evolutionary Computation --- p.29 / Chapter 3.1 --- Evolutionary Computation --- p.29 / Chapter 3.1.1 --- Genetic Algorithm --- p.30 / Chapter 3.1.2 --- Genetic Programming --- p.32 / Chapter 3.1.3 --- Evolutionary Programming --- p.34 / Chapter 3.1.4 --- Evolution Strategy --- p.37 / Chapter 3.1.5 --- Selection Methods --- p.38 / Chapter 3.2 --- Generic Genetic Programming --- p.39 / Chapter 3.3 --- Data mining using Evolutionary Computation --- p.43 / Chapter 4 --- Applying Generic Genetic Programming for Rule Learning --- p.45 / Chapter 4.1 --- Grammar --- p.46 / Chapter 4.2 --- Population Creation --- p.49 / Chapter 4.3 --- Genetic Operators --- p.50 / Chapter 4.4 --- Evaluation of Rules --- p.52 / Chapter 5 --- Learning Multiple Rules from Data --- p.56 / Chapter 5.1 --- Previous approaches --- p.57 / Chapter 5.1.1 --- Preselection --- p.57 / Chapter 5.1.2 --- Crowding --- p.57 / Chapter 5.1.3 --- Deterministic Crowding --- p.58 / Chapter 5.1.4 --- Fitness sharing --- p.58 / Chapter 5.2 --- Token Competition --- p.59 / Chapter 5.3 --- The Complete Rule Learning Approach --- p.61 / Chapter 5.4 --- Experiments with Machine Learning Databases --- p.64 / Chapter 5.4.1 --- Experimental results on the Iris Plant Database --- p.65 / Chapter 5.4.2 --- Experimental results on the Monk Database --- p.67 / Chapter 6 --- Bayesian Network Learning --- p.72 / Chapter 6.1 --- The MDLEP Learning Approach --- p.73 / Chapter 6.2 --- Learning of Discretization Policy by Genetic Algorithm --- p.74 / Chapter 6.2.1 --- Individual Representation --- p.76 / Chapter 6.2.2 --- Genetic Operators --- p.78 / Chapter 6.3 --- Experimental Results --- p.79 / Chapter 6.3.1 --- Experiment 1 --- p.80 / Chapter 6.3.2 --- Experiment 2 --- p.82 / Chapter 6.3.3 --- Experiment 3 --- p.83 / Chapter 6.3.4 --- Comparison between the GA approach and the greedy ap- proach --- p.91 / Chapter 7 --- Medical Data Mining System --- p.93 / Chapter 7.1 --- A Case Study on the Fracture Database --- p.95 / Chapter 7.1.1 --- Results of Causality and Structure Analysis --- p.95 / Chapter 7.1.2 --- Results of Rule Learning --- p.97 / Chapter 7.2 --- A Case Study on the Scoliosis Database --- p.100 / Chapter 7.2.1 --- Results of Causality and Structure Analysis --- p.100 / Chapter 7.2.2 --- Results of Rule Learning --- p.102 / Chapter 8 --- Conclusion and Future Work --- p.106 / Bibliography --- p.109 / Chapter A --- The Rule Sets Discovered --- p.116 / Chapter A.1 --- The Best Rule Set Learned from the Iris Database --- p.116 / Chapter A.2 --- The Best Rule Set Learned from the Monk Database --- p.116 / Chapter A.2.1 --- Monkl --- p.116 / Chapter A.2.2 --- Monk2 --- p.117 / Chapter A.2.3 --- Monk3 --- p.119 / Chapter A.3 --- The Best Rule Set Learned from the Fracture Database --- p.120 / Chapter A.3.1 --- Type I Rules: About Diagnosis --- p.120 / Chapter A.3.2 --- Type II Rules : About Operation/Surgeon --- p.120 / Chapter A.3.3 --- Type III Rules : About Stay --- p.122 / Chapter A.4 --- The Best Rule Set Learned from the Scoliosis Database --- p.123 / Chapter A.4.1 --- Rules for Classification --- p.123 / Chapter A.4.2 --- Rules for Treatment --- p.126 / Chapter B --- The Grammar used for the fracture and Scoliosis databases --- p.128 / Chapter B.1 --- The grammar for the fracture database --- p.128 / Chapter B.2 --- The grammar for the Scoliosis database --- p.128

Current cryptographic algorithms pose high standards of security yet they are susceptible to side-channel analysis (SCA). When it comes to implementation, the hardness of cryptography dangles on the weak link of side-channel information leakage. The widely adopted AES encryption algorithm, and others, can be easily broken when they are implemented without any resistance to SCA. This work applies state of the art techniques, namely Secret Sharing and Secure Multiparty Computation (SMC), on AES-128 encryption as a countermeasure to those attacks. This embedded C implementation explores multiple time-memory trade-offs for the design of its fundamental components, SMC and field arithmetic, to meet a variety of execution and storage demands. The performance and leakage assessment of this implementation for an ARM based micro-controller demonstrate the capabilities of masking schemes and prove their feasibility on embedded software.

An integral component of modern computing is the ability to outsource data and computation to powerful remote servers, for instance, in the context of cloud computing or remote file storage. While participants can benefit from this interaction, a fundamental security issue that arises is that of integrity of computation: How can the end-user be certain that the result of a computation over the outsourced data has not been tampered with (not even by a compromised or adversarial server)? Cryptographic schemes for verifiable computation address this problem by accompanying each result with a proof that can be used to check the correctness of the performed computation. Recent advances in the field have led to the first implementations of schemes that can verify arbitrary computations. However, in practice the overhead of these general-purpose constructions remains prohibitive for most applications, with proof computation times (at the server) in the order of minutes or even hours for real-world problem instances. A different approach for designing such schemes targets specific types of computation and builds custom-made protocols, sacrificing generality for efficiency. An important representative of this function-specific approach is an authenticated data structure (ADS), where a specialized protocol is designed that supports query types associated with a particular outsourced dataset. This thesis presents three novel ADS constructions for the important query types of set operations, multi-dimensional range search, and pattern matching, and proves their security under cryptographic assumptions over bilinear groups. The scheme for set operations can support nested queries (e.g., two unions followed by an intersection of the results), extending previous works that only accommodate a single operation. The range search ADS provides an exponential (in the number of attributes in the dataset) asymptotic improvement from previous schemes for storage and computation costs. Finally, the pattern matching ADS supports text pattern and XML path queries with minimal cost, e.g., the overhead at the server is less than 4% compared to simply computing the result, for all our tested settings. The experimental evaluation of all three constructions shows significant improvements in proof-computation time over general-purpose schemes.

Fok Ka Ling. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 96-101). / Abstracts in English and Chinese. / Abstract --- p.1 / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Evolutionary Computation --- p.1 / Chapter 1.2 --- Graphics Processing Unit --- p.2 / Chapter 1.3 --- Objective --- p.3 / Chapter 1.4 --- Contribution --- p.4 / Chapter 1.5 --- Thesis Organization --- p.4 / Chapter 2 --- Evolutionary Computation --- p.6 / Chapter 2.1 --- Introduction --- p.6 / Chapter 2.2 --- General Framework --- p.7 / Chapter 2.3 --- Features of Evolutionary Algorithm --- p.8 / Chapter 2.3.1 --- Widely Applicable --- p.8 / Chapter 2.3.2 --- Parallelism --- p.9 / Chapter 2.3.3 --- Robust to Change --- p.9 / Chapter 2.4 --- Parallel and Distributed Evolutionary Algorithm --- p.9 / Chapter 2.4.1 --- Global Parallel Evolutionary Algorithms --- p.10 / Chapter 2.4.2 --- Fine-Grained Evolutionary Algorithms --- p.11 / Chapter 2.4.3 --- Island Distributed Evolutionary Algorithms --- p.12 / Chapter 2.5 --- Summary --- p.14 / Chapter 3 --- Graphics Processing Unit --- p.15 / Chapter 3.1 --- Introduction --- p.15 / Chapter 3.2 --- History of GPU --- p.16 / Chapter 3.2.1 --- First-Generation GPUs --- p.16 / Chapter 3.2.2 --- Second-Generation GPUs --- p.17 / Chapter 3.2.3 --- Third-Generation GPUs --- p.17 / Chapter 3.2.4 --- Fourth-Generation GPUs --- p.17 / Chapter 3.3 --- The Graphics Pipelining --- p.18 / Chapter 3.3.1 --- Standard Graphics Pipeline --- p.18 / Chapter 3.3.2 --- Programmable Graphics Pipeline --- p.18 / Chapter 3.3.3 --- Fragment Processors for Scientific Computation --- p.21 / Chapter 3.4 --- GPU-CPU Analogy --- p.23 / Chapter 3.4.1 --- Memory Architecture --- p.23 / Chapter 3.4.2 --- Processing Model --- p.24 / Chapter 3.5 --- Limitation of GPU --- p.24 / Chapter 3.5.1 --- Limited Input and Output --- p.24 / Chapter 3.5.2 --- Slow Data Readback --- p.24 / Chapter 3.5.3 --- No Random Number Generator --- p.25 / Chapter 3.6 --- Summary --- p.25 / Chapter 4 --- Evolutionary Programming on GPU --- p.26 / Chapter 4.1 --- Introduction --- p.26 / Chapter 4.2 --- Evolutionary Programming --- p.26 / Chapter 4.3 --- Data Organization --- p.29 / Chapter 4.4 --- Fitness Evaluation --- p.31 / Chapter 4.4.1 --- Introduction --- p.31 / Chapter 4.4.2 --- Different Forms of Fitness Function --- p.32 / Chapter 4.4.3 --- Parallel Fitness Function Evaluation using GPU --- p.33 / Chapter 4.5 --- Mutation --- p.34 / Chapter 4.5.1 --- Introduction --- p.34 / Chapter 4.5.2 --- Self Adaptive Mutation Operators --- p.36 / Chapter 4.5.3 --- Mutation on GPU --- p.37 / Chapter 4.6 --- Selection for Replacement --- p.39 / Chapter 4.6.1 --- Introduction --- p.39 / Chapter 4.6.2 --- Classification of Selection Operator --- p.39 / Chapter 4.6.3 --- q -Tournament Selection --- p.40 / Chapter 4.6.4 --- Median Searching --- p.41 / Chapter 4.6.5 --- Minimizing Data Transfer --- p.43 / Chapter 4.7 --- Experimental Results --- p.44 / Chapter 4.7.1 --- Visualization --- p.48 / Chapter 4.8 --- Summary --- p.49 / Chapter 5 --- Genetic Algorithm on GPU --- p.56 / Chapter 5.1 --- Introduction --- p.56 / Chapter 5.2 --- Canonical Genetic Algorithm --- p.57 / Chapter 5.2.1 --- Parent Selection --- p.57 / Chapter 5.2.2 --- Crossover and Mutation --- p.62 / Chapter 5.2.3 --- Replacement --- p.63 / Chapter 5.3 --- Experiment Results --- p.64 / Chapter 5.4 --- Summary --- p.66 / Chapter 6 --- Multi-Objective Genetic Algorithm --- p.70 / Chapter 6.1 --- Introduction --- p.70 / Chapter 6.2 --- Definitions --- p.71 / Chapter 6.2.1 --- General MOP --- p.71 / Chapter 6.2.2 --- Decision Variables --- p.71 / Chapter 6.2.3 --- Constraints --- p.71 / Chapter 6.2.4 --- Feasible Region --- p.72 / Chapter 6.2.5 --- Optimal Solution --- p.72 / Chapter 6.2.6 --- Pareto Optimum --- p.73 / Chapter 6.2.7 --- Pareto Front --- p.73 / Chapter 6.3 --- Multi-Objective Genetic Algorithm --- p.75 / Chapter 6.3.1 --- Ranking --- p.76 / Chapter 6.3.2 --- Fitness Scaling --- p.77 / Chapter 6.3.3 --- Diversity Preservation --- p.77 / Chapter 6.4 --- A Niched and Elitism Multi-Objective Genetic Algorithm on GPU --- p.79 / Chapter 6.4.1 --- Objective Values Evaluation --- p.80 / Chapter 6.4.2 --- Pairwise Pareto Dominance and Pairwise Distance --- p.81 / Chapter 6.4.3 --- Fitness Assignment --- p.85 / Chapter 6.4.4 --- Embedded Archiving Replacement --- p.87 / Chapter 6.5 --- Experiment Result --- p.89 / Chapter 6.6 --- Summary --- p.90 / Chapter 7 --- Conclusion --- p.95 / Bibliography --- p.96

Yang, Zhaojun. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2011. / Includes bibliographical references (p. 92-99). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- SDS Architecture --- p.1 / Chapter 1.2 --- Dialog Model --- p.3 / Chapter 1.3 --- SDS Evaluation --- p.4 / Chapter 1.4 --- Thesis Outline --- p.7 / Chapter 2 --- Previous Work --- p.9 / Chapter 2.1 --- Approaches to Dialog Modeling --- p.9 / Chapter 2.1.1 --- Handcrafted Dialog Modeling --- p.9 / Chapter 2.1.2 --- Statistical Dialog Modeling --- p.12 / Chapter 2.2 --- Evaluation Metrics --- p.16 / Chapter 2.2.1 --- Subjective User Judgments --- p.17 / Chapter 2.2.2 --- Interaction Metrics --- p.18 / Chapter 2.3 --- The PARADISE Framework --- p.19 / Chapter 2.4 --- Chapter Summary --- p.22 / Chapter 3 --- Implementation of a Dialog System based on POMDP --- p.23 / Chapter 3.1 --- Partially Observable Markov Decision Processes (POMDPs) --- p.24 / Chapter 3.1.1 --- Formal Definition --- p.24 / Chapter 3.1.2 --- Value Iteration --- p.26 / Chapter 3.1.3 --- Point-based Value Iteration --- p.27 / Chapter 3.1.4 --- A Toy Example of POMDP: The NaiveBusInfo System --- p.27 / Chapter 3.2 --- The SDS-POMDP Model --- p.31 / Chapter 3.3 --- Composite Summary Point-based Value Iteration (CSPBVI) --- p.33 / Chapter 3.4 --- Application of SDS-POMDP Model: The Buslnfo System --- p.35 / Chapter 3.4.1 --- System Description --- p.35 / Chapter 3.4.2 --- Demonstration Description --- p.39 / Chapter 3.5 --- Chapter Summary --- p.42 / Chapter 4 --- Collecting User Judgments on Spoken Dialogs with Crowdsourcing --- p.46 / Chapter 4.1 --- Dialog Corpus and Automatic Dialog Classification --- p.47 / Chapter 4.2 --- User Judgments Collection with Crowdsourcing --- p.50 / Chapter 4.2.1 --- HITs on Dialog Evaluation --- p.51 / Chapter 4.2.2 --- HITs on Inter-rater Agreement --- p.53 / Chapter 4.2.3 --- Approval of Ratings --- p.54 / Chapter 4.3 --- Collected Results and Analysis --- p.55 / Chapter 4.3.1 --- Approval Rates and Comments from Mturk Workers --- p.55 / Chapter 4.3.2 --- Consistency between Automatic Dialog Classification and Manual Ratings --- p.57 / Chapter 4.3.3 --- Inter-rater Agreement Among Workers --- p.60 / Chapter 4.4 --- Comparing Experts to Non-experts --- p.64 / Chapter 4.4.1 --- Inter-rater Agreement on the Let's Go! System --- p.65 / Chapter 4.4.2 --- Consistency Between Expert and Non-expert Annotations on SDC Systems --- p.66 / Chapter 4.5 --- Chapter Summary --- p.68 / Chapter 5 --- Collaborative Filtering for Performance Prediction --- p.70 / Chapter 5.1 --- Item-Based Collaborative Filtering --- p.71 / Chapter 5.2 --- CF Model for User Satisfaction Prediction --- p.72 / Chapter 5.2.1 --- ICFM for User Satisfaction Prediction --- p.72 / Chapter 5.2.2 --- Extended ICFM for User Satisfaction Prediction --- p.73 / Chapter 5.3 --- Extraction of Interaction Features --- p.74 / Chapter 5.4 --- Experimental Results and Analysis --- p.76 / Chapter 5.4.1 --- Prediction of User Satisfaction --- p.76 / Chapter 5.4.2 --- Analysis of Prediction Results --- p.79 / Chapter 5.5 --- Verifying the Generalibility of CF Model --- p.81 / Chapter 5.6 --- Evaluation of The Buslnfo System --- p.86 / Chapter 5.7 --- Chapter Summary --- p.87 / Chapter 6 --- Conclusions and Future Work --- p.89 / Chapter 6.1 --- Thesis Summary --- p.89 / Chapter 6.2 --- Future Work --- p.90 / Bibliography --- p.92

Data mining algorithms discover knowledge from data. The knowledge are commonly expressed as dependency relationships in various forms, like rules, decision trees and Bayesian Networks (BNs). Moreover, many real-world problems are multi-class problems, in which more than one of the variables in the data set are considered as classes. However, most of the rule learners available were proposed for single-class problems only and would produce cyclic rules if they are applied to multi-class ones. In addition, most of them produce rules with conflicts, i.e. more than one of the rules classify the same data items and different rules have different predictions. Similarly, existing decision trees learners cannot handle multi-class problems, and thus cannot detect and avoid cycles. In contrast, BNs represent acyclic dependency relationships among variables, but they can handle discrete values only. They cannot manage continuous, interval and ordinal values and cannot represent higher-order relationships. Consequently, BNs have higher network complexity and lower understandability when they are used for such problems. / This thesis has studied in depth discovering dependency relationships in various forms by Evolutionary Computation (EC). Through analysis of the reasons leading to the disadvantages of rules, decision trees and BNs, and their learners, we have proposed a sequence of EAs, a novel functional dependency network (FDN) and two techniques for dependency relationship learning and for multi-class problems. They are the multi-population Genetic Programming (GP) using backward chaining procedure and the GP employing co-operating scoring stage for acyclic rules learning. The dependency network with functions can manage all kinds of values and represent any kind of relationships among variables, the flexible and robust MDLGP to learn the novel dependency network and BN. Based on the FDN we have further developed the techniques to learn rules without conflict and acyclic decision trees for multi-class problems respectively. The new self-organizing map (SOM) with expanding force for clustering and data visualization for data preprocessing have also been given in the appendix. / Shum Wing Ho. / "May 2007." / Adviser: Kwong-Sak Leung. / Source: Dissertation Abstracts International, Volume: 69-01, Section: B, page: 0436. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2007. / Includes bibliographical references (p. 221-240). / Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Electronic reproduction. [Ann Arbor, MI] : ProQuest Information and Learning, [200-] System requirements: Adobe Acrobat Reader. Available via World Wide Web. / Abstracts in English and Chinese. / School code: 1307.

Thesis: S.M., Massachusetts Institute of Technology, Computation for Design and Optimization Program, 2017. / S.M. !c Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science 2017 / Cataloged from PDF version of thesis. / Includes bibliographical references (pages 91-94). / For an insurance company, assessing risk exposure for Property Damage (PD), and Business Interruption (BI) for large commercial clients is difficult because of the heterogeneity of that exposure, within a single client (account), and between different divisions, and regions, where the client is active. Traditional risk assessment models attempt to scale up the single location approach used in personal lines: A large amount of data is collected to profile a sample of the locations and based on this information the risk is then inferred and somewhat subjectively assessed for the whole account. The assumption is that the risk characteristics at the largest locations are representative of all locations, and moreover, that risk is proportional to the size of the location. This approach is both ineffective and inefficient. Thus our first goal is to build a better risk assessment model through machine learning based on clients' data from internal sources. Further, we define a new problem, to predict whether a specific contract would be profitable or unprofitable for the insurance company. This problem turns out to be an imbalance classification, which attracts the second half of our research efforts in this thesis. In Chapter 2, we first review related literature on state-of-the-art risk assessment models in the field of insurance. Later in the chapter we move to the imbalance classification problems and review some popular and effective solutions researchers have proposed. In Chapter 3, we describe the data structure, provide some preliminary analysis over certain attributes and discuss the preprocessing techniques used for feature construction. In Chapter 4, we propose a new model with the objective to develop a new risk index which represents clients' potential future risk level. We then compare the performance of our new index with the original risk index used by the insurance company and computational results show that our new index successfully captures clients' financial loss pattern, while the original risk score used by the insurance company fails to do so. In Chapter 5, we propose a multi-layer algorithm to predict whether a specific contract would be profitable or unprofitable for the insurance company. Simulation shows that we can accurately label more than 83 percent of the contracts on record and that our proposed algorithm outperforms traditional classifiers such as Support Vector Machines and Random Forests. Later in the chapter, we define a new imbalance classification problem and propose a hybrid method to improve the recall percentage and prediction accuracy of Support Vector Machines. The method incorporates unsupervised learning techniques into the classical Support Vector Machines algorithm and achieves satisfying results. In Chapter 6, we conclude the thesis and provide future research guidance. This thesis builds models and trains algorithms based on real world business data from a global leading insurance and reinsurance company. / by Ziyu Wang. / S.M. / S.M. !c Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science

This paper is based on Landau's book "Foundations of Analysis" which constitutes a development of the number system founded on the Peano axioms for natural numbers. In order to show mastery of the subject matter this paper gives a somewhat different organization of material and modified or more detailed proofs of theorems. In situations where proofs become rather routine re pet it ions of previously noted techniques the proofs are omitted. The following symbols and notation are used. Natural numbers are denoted by lower case letters such as a,b,c, ... x,y,z. Sets are denoted by upper case letters such as M, N, ... X, Y, Z. If a is an element of M, this will be written atM, The denial of this is written at M. The symbol 3 /x is read "There exists an unique x". If x and y are names for the same number we write x=y. It is assumed that the relation= is an equivalence relation; i.e., (1) x=x, (2) if x=y, then y=x, (3) u x=y and y=z, then x=z. Throughout this paper there will be no special attempt to distinguish between the name of a number and the number itself. For example, the phrase" if xis a number" will be used in place of "if x is the name of a number."

Four-dimensional variational data assimilation (4D-Var) provides an estimate to the state of a dynamical system through the minimization of a cost functional that measures the distance to a prior state (background) estimate and observations over a time window. The analysis fit to each information input component is determined by the specification of the error covariance matrices in the data assimilation system (DAS). Weak-constraint 4D-Var (w4D-Var) provides a theoretical framework to account for modeling errors in the analysis scheme. In addition to the specification of the background error covariance matrix, the w4D-Var formulation requires information on the model error statistics and specification of the model error covariance. Up to now, the increased computational cost associated with w4D-Var has prevented its practical implementation. Various simplifications to reduce the computational burden have been considered, including writing the model error covariance as a scalar multiple of the background error covariance and modeling the model error. In this thesis, the main objective is the development of computationally feasible techniques for the improved representation of the model error statistics in a data assimilation system. Three new approaches are considered. A Monte Carlo method that uses an ensemble of w4D-Var systems to obtain flow-dependent estimates to the model error statistics. The evaluation of statistical diagnostic equations involving observation residuals to estimate the model error covariance matrix. An adaptive tuning procedure based on the sensitivity of a short-range forecast error measure to the model error DAS parametrization. The validity and benefits of these approaches are shown in two stages of numerical experiments. A proof-of-concept is shown using the Lorenz multi-scale model and the shallow water equations for a one-dimensional domain. The results show the potential of these methodologies to produce improved state estimates, as compared to other approaches in data assimilation. It is expected that the techniques presented will find an extended range of applications to assess and improve the performance of a w4D-Var system.

Traditional techniques for the design of robots require human engineers to plan every aspect of the system, from body to controller. In contrast, the field of evolu- tionary robotics uses evolutionary algorithms to create optimized morphologies and neural controllers with minimal human intervention. In order to expand the capability of an evolved agent, it must be exposed to a variety of conditions and environments. This thesis investigates the design and benefits of virtual robots which can reflect the structure and modularity in the world around them. I show that when a robot’s morphology and controller enable it to perceive each environment as a collection of independent components, rather than a monolithic entity, evolution only needs to optimize on a subset of environments in order to maintain performance in the overall larger environmental space. I explore previously unused methods in evolutionary robotics to aid in the evolution of modularity, including using morphological and neurological cost. I utilize a tree morphology which makes my results generalizable to other mor- phologies while also allowing in depth theoretical analysis about the properties rel- evant to modularity in embodied agents. In order to better frame the question of modularity in an embodied context, I provide novel definitions of morphological and neurological modularity as well as create the sub-goal interference metric which mea- sures how much independence a robot exhibits with regards to environmental stimu- lus. My work extends beyond evolutionary robotics and can be applied to the opti- mization of embodied systems in general as well as provides insight into the evolution of form in biological organisms.