This thesis presents the design and evaluation of an approach to concatenative speech synthesis using the Titne-Domain Pitch-Synchronous OverLap-Add (I'D-PSOLA) signal processing algorithm. Concatenative synthesis systems make use of pre-recorded speech segments stored in a speech corpus. At synthesis time, the `best' segments available to synthesise the new utterances are chosen from the corpus using a process known as unit selection. During the synthesis process, the pitch and duration of these segments may be modified to generate the desired prosody. The TD-PSOLA algorithm provides an efficient and essentially successful solution to perform these modifications, although some perceptible distortion, in the form of `buzzyness', may be introduced into the speech signal. Despite the popularity of the TD-PSOLA algorithm, little formal research has been undertaken to address this recognised problem of distortion. The approach in the thesis has been developed towards reducing the perceived distortion that is introduced when TD-PSOLA is applied to speech. To investigate the occurrence of this distortion, a psychoacoustic evaluation of the effect of pitch modification using the TD-PSOLA algorithm is presented. Subjective experiments in the form of a set of listening tests were undertaken using word-level stimuli that had been manipulated using TD-PSOLA. The data collected from these experiments were analysed for patterns of co- occurrence or correlations to investigate where this distortion may occur. From this, parameters were identified which may have contributed to increased distortion. These parameters were concerned with the relationship between the spectral content of individual phonemes, the extent of pitch manipulation, and aspects of the original recordings. Based on these results, a framework was designed for use in conjunction with TD-PSOLA to minimise the possible causes of distortion. The framework consisted of a novel speech corpus design, a signal processing distortion measure, and a selection process for especially problematic phonemes. Rather than phonetically balanced, the corpus is balanced to the needs of the signal processing algorithm, containing more of the adversely affected phonemes. The aim is to reduce the potential extent of pitch modification of such segments, and hence produce synthetic speech with less perceptible distortion. The signal processingdistortion measure was developed to allow the prediction of perceptible distortion in pitch-modified speech. Different weightings were estimated for individual phonemes,trained using the experimental data collected during the listening tests.The potential benefit of such a measure for existing unit selection processes in a corpus-based system using TD-PSOLA is illustrated. Finally, the special-case selection process was developed for highly problematic voiced fricative phonemes to minimise the occurrence of perceived distortion in these segments. The success of the framework, in terms of generating synthetic speech with reduced distortion, was evaluated. A listening test showed that the TD-PSOLA balanced speech corpus may be capable of generating pitch-modified synthetic sentences with significantly less distortion than those generated using a typical phonetically balanced corpus. The voiced fricative selection process was also shown to produce pitch-modified versions of these phonemes with less perceived distortion than a standard selection process. The listening test then indicated that the signal processing distortion measure was able to predict the resulting amount of distortion at the sentence-level after the application of TD-PSOLA, suggesting that it may be beneficial to include such a measure in existing unit selection processes. The framework was found to be capable of producing speech with reduced perceptible distortion in certain situations, although the effects seen at the sentence-level were less than those seen in the previous investigative experiments that made use of word-level stimuli. This suggeststhat the effect of the TD-PSOLA algorithm cannot always be easily anticipated due to the highly dynamic nature of speech, and that the reduction of perceptible distortion in TD-PSOLA-modified speech remains a challenge to the speech community.

For the last decade it has become commonplace to evaluate machine learning techniques for network based intrusion detection on the KDD Cup '99 data set. This data set has served well to demonstrate that machine learning can be useful in intrusion detection. However, it has undergone some criticism in the literature, and it is out of date. Therefore, some researchers question the validity of the findings reported based on this data set. Furthermore, as identified in this thesis, there are also discrepancies in the findings reported in the literature. In some cases the results are contradictory. Consequently, it is difficult to analyse the current body of research to determine the value in the findings. This thesis reports on an empirical investigation to determine the underlying causes of the discrepancies. Several methodological factors, such as choice of data subset, validation method and data preprocessing, are identified and are found to affect the results significantly. These findings have also enabled a better interpretation of the current body of research. Furthermore, the criticisms in the literature are addressed and future use of the data set is discussed, which is important since researchers continue to use it due to a lack of better publicly available alternatives. Due to the nature of the intrusion detection domain, there is an extreme imbalance among the classes in the KDD Cup '99 data set, which poses a significant challenge to machine learning. In other domains, researchers have demonstrated that well known techniques such as Artificial Neural Networks (ANNs) and Decision Trees (DTs) often fail to learn the minor class(es) due to class imbalance. However, this has not been recognized as an issue in intrusion detection previously. This thesis reports on an empirical investigation that demonstrates that it is the class imbalance that causes the poor detection of some classes of intrusion reported in the literature. An alternative approach to training ANNs is proposed in this thesis, using Genetic Algorithms (GAs) to evolve the weights of the ANNs, referred to as an Evolutionary Neural Network (ENN). When employing evaluation functions that calculate the fitness proportionally to the instances of each class, thereby avoiding a bias towards the major class(es) in the data set, significantly improved true positive rates are obtained whilst maintaining a low false positive rate. These findings demonstrate that the issues of learning from imbalanced data are not due to limitations of the ANNs; rather the training algorithm. Moreover, the ENN is capable of detecting a class of intrusion that has been reported in the literature to be undetectable by ANNs. One limitation of the ENN is a lack of control of the classification trade-off the ANNs obtain. This is identified as a general issue with current approaches to creating classifiers. Striving to create a single best classifier that obtains the highest accuracy may give an unfruitful classification trade-off, which is demonstrated clearly in this thesis. Therefore, an extension of the ENN is proposed, using a Multi-Objective GA (MOGA), which treats the classification rate on each class as a separate objective. This approach produces a Pareto front of non-dominated solutions that exhibit different classification trade-offs, from which the user can select one with the desired properties. The multi-objective approach is also utilised to evolve classifier ensembles, which yields an improved Pareto front of solutions. Furthermore, the selection of classifier members for the ensembles is investigated, demonstrating how this affects the performance of the resultant ensembles. This is a key to explaining why some classifier combinations fail to give fruitful solutions.

Traditionally building of predictive models is perceived as a combination of both science and art. Although the designer of a predictive system effectively follows a prescribed procedure, his domain knowledge as well as expertise and intuition in the field of machine learning are often irreplaceable. However, in many practical situations it is possible to build well–performing predictive systems by following a rigorous methodology and offsetting not only the lack of domain knowledge but also partial lack of expertise and intuition, by computational power. The generalised predictive model development cycle discussed in this thesis is an example of such methodology, which despite being computationally expensive, has been successfully applied to real–world problems. The proposed predictive system design cycle is a purely data–driven approach. The quality of data used to build the system is thus of crucial importance. In practice however, the data is rarely perfect. Common problems include missing values, high dimensionality or very limited amount of labelled exemplars. In order to address these issues, this work investigated and exploited inspirations coming from physics. The novel use of well–established physical models in the form of potential fields, has resulted in derivation of a comprehensive Electrostatic Field Classification Framework for supervised and semi–supervised learning from incomplete data. Although the computational power constantly becomes cheaper and more accessible, it is not infinite. Therefore efficient techniques able to exploit finite amount of predictive information content of the data and limit the computational requirements of the resource–hungry predictive system design procedure are very desirable. In designing such techniques this work once again investigated and exploited inspirations coming from physics. By using an analogy with a set of interacting particles and the resulting Information Theoretic Learning framework, the Density Preserving Sampling technique has been derived. This technique acts as a computationally efficient alternative for cross–validation, which fits well within the proposed methodology. All methods derived in this thesis have been thoroughly tested on a number of benchmark datasets. The proposed generalised predictive model design cycle has been successfully applied to two real–world environmental problems, in which a comparative study of Density Preserving Sampling and cross–validation has also been performed confirming great potential of the proposed methods.

Two intensive, longitudinal case studies were conducted at IBM Hursley Park. There were several objectives to these case studies: first, to investigate the actual behaviour of the two projects in depth; second, to develop conceptual structures relating the lower-level processes of each project to the higher-level processes; third, to relate the lower-level and higher-level processes to project duration; fourth, to test a conjecture forwarded by Bradac et al i. e. that waiting is more prevalent during the end of a project than during the middle of a project. A large volume of qualitative and quantitative evidence was collected and analysed for each project. This evidence included minutes of status meetings, interviews, project schedules, and information from feedback workshops (which were conducted several months after the completion of the projects). The analysis generated three models and numerous insights into software project behaviour. The models concerned software project schedule behaviour, capability and an integration of schedule behaviour and capability. The insights concerned characteristics of a project (i. e. the actual progress of phases and milestones, the amount of workload on the project, the degree of capability of the project, tactics of management, and the sociotechnical aspects of a project) and characteristics of process areas within a project (i. e. waiting, poor progress and outstanding work). Support for the models and the insights was sought, with some success, from previous research. Despite the approach taken in this investigation (i. e. the collection of a large volume of evidence and the analyses of a wide variety of factors using a very broad perspective), this investigation has been unable to pinpoint definite causes to explain why a project will or will not complete according to its original plan. One `hint' of an explanation are the differences between the socio-technical contexts of the two projects and, related to this, the fact that tactics of management may be constrained by a project's socio-technical context. Furthermore, while the concept of a project as a distinct entity seems reasonable, the actual boundaries of a project in an organisation's `space-time' are ambiguous and very difficult to properly define. Therefore, it may be that those things that make a project difficult to distinguish from its surrounding organisation are interwoven with the socio-technical contexts of a project, and may be precisely those things that explain the progress of that project. Recommendations, based on the models, the insights and the conclusions, are provided for industry and research.

Many clustering algorithms have been developed and improved over the years to cater for large scale data clustering. However, much of this work has been in developing numeric based algorithms that use efficient summarisations to scale to large data sets. There is a growing need for scalable categorical clustering algorithms as, although numeric based algorithms can be adapted to categorical data, they do not always produce good results. This thesis presents a categorical conceptual clustering algorithm that can scale to large data sets using appropriate data summarisations. Data mining is distinguished from machine learning by the use of larger data sets that are often stored in database management systems (DBMSs). Many clustering algorithms require data to be extracted from the DBMS and reformatted for input to the algorithm. This thesis presents an approach that integrates conceptual clustering with a DBMS. The presented approach makes the algorithm main memory independent and supports on-line data mining.

The Model Driven Architecture (MDA) is offered as one way forward in software systems modelling to connect software design with the business domain. The general focus of the MDA is the development of software systems by performing transformations between software design models, and the automatic generation of application code from those models. Software systems are provided by developers, whose experience and models are not always in line with those of other stakeholders, which presents a challenge for the community. From reviewing the available literature, it is found that whilst many models and notations are available, those that are significantly supported by the MDA may not be best for use by non technical stakeholders. In addition, the MDA does not explicitly consider requirements and specification. This research begins by investigating the adequacy of the MDA requirements phase and examining the feasibility of incorporating a requirements definition, specifically focusing upon model transformations. MDA artefacts were found to serve better the software community and requirements were not appropriately integrated within the MDA, with significant extension upstream being required in order to sufficiently accommodate the business user in terms of a requirements definition. Therefore, an extension to the MDA framework is offered that directly addresses Requirements Engineering (RE), including the distinction of analysis from design, highlighting the importance of specification. This extension is suggested to further the utility of the MDA by making it accessible to a wider audience upstream, enabling specification to be a direct output from business user involvement in the requirements phase of the MDA. To demonstrate applicability, this research illustrates the framework extension with the provision of a method and discusses the use of the approach in both academic and commercial settings. The results suggest that such an extension is academically viable in facilitating the move from analysis into the design of software systems, accessible for business use and beneficial in industry by allowing for the involvement of the client in producing models sufficient enough for use in the development of software systems using MDA tools and techniques.

Time series forecasting has a long track record in many application areas. In forecasting research, it has been illustrated that finding an individual algorithm that works best for all possible scenarios is hopeless. Therefore, instead of striving to design a single superior algorithm, current research efforts have shifted towards gaining a deeper understanding of the reasons a forecasting method may perform well in some conditions whilst it may fail in others. This thesis provides a number of contributions to this matter. Traditional empirical evaluations are discussed from a novel point of view, questioning the benefit of using sophisticated forecasting methods without domain knowledge. An own empirical study focusing on relevant off-the shelf forecasting and forecast combination methods underlines the competitiveness of relatively simple methods in practical applications. Furthermore, meta-features of time series are extracted to automatically find and exploit a link between application specific data characteristics and forecasting performance using meta-learning. Finally, the approach of extending the set of input forecasts by diversifying functional approaches, parameter sets and data aggregation level used for learning is discussed, relating characteristics of the resulting forecasts to different error decompositions for both individual methods and combinations. Advanced combination structures are investigated in order to take advantage of the knowledge on the forecast generation processes. Forecasting is a crucial factor in airline revenue management; forecasting of the anticipated booking, cancellation and no-show numbers has a direct impact on general planning of routes and schedules, capacity control for fareclasses and overbooking limits. In a collaboration with Lufthansa Systems in Berlin, experiments in the thesis are conducted on an airline data set with the objective of improving the current net booking forecast by modifying one of its components, the cancellation forecast. To also compare results achieved of the methods investigated here with the current state-of-the-art in forecasting research, some experiments also use data sets of two recent forecasting competitions, thus being able to provide a link between academic research and industrial practice.

The construction of realistic characters has become increasingly important to the production of blockbuster films, TV series and computer games. The outfit of character plays an important role in the application of virtual characters. It is one of the key elements reflects the personality of character. Virtual clothing refers to the process that constructs outfits for virtual characters, and currently, it is widely used in mainly two areas, fashion industry and computer animation. In fashion industry, virtual clothing technology is an effective tool which creates, edits and pre-visualises cloth design patterns efficiently. However, using this method requires lots of tailoring expertises. In computer animation, geometric modelling methods are widely used for cloth modelling due to their simplicity and intuitiveness. However, because of the shortage of tailoring knowledge among animation artists, current existing cloth design patterns can not be used directly by animation artists, and the appearance of cloth depends heavily on the skill of artists. Moreover, geometric modelling methods requires lots of manual operations. This tediousness is worsen by modelling same style cloth for different characters with different body shapes and proportions. This thesis addresses this problem and presents a new virtual clothing method which includes automatic character measuring, automatic cloth pattern adjustment, and cloth patterns assembling. There are two main contributions in this research. Firstly, a geodesic curvature flow based geodesic computation scheme is presented for acquiring length measurements from character. Due to the fast growing demand on usage of high resolution character model in animation production, the increasing number of characters need to be handled simultaneously as well as improving the reusability of 3D model in film production, the efficiency of modelling cloth for multiple high resolution character is very important. In order to improve the efficiency of measuring character for cloth fitting, a fast geodesic algorithm that has linear time complexity with a small bounded error is also presented. Secondly, a cloth pattern adjusting genetic algorithm is developed for automatic cloth fitting and retargeting. For the reason that that body shapes and proportions vary largely in character design, fitting and transferring cloth to a different character is a challenging task. This thesis considers the cloth fitting process as an optimization procedure. It optimizes both the shape and size of each cloth pattern automatically, the integrity, design and size of each cloth pattern are evaluated in order to create 3D cloth for any character with different body shapes and proportions while preserve the original cloth design. By automating the cloth modelling process, it empowers the creativity of animation artists and improves their productivity by allowing them to use a large amount of existing cloth design patterns in fashion industry to create various clothes and to transfer same design cloth to characters with different body shapes and proportions with ease.

Over the past decade, Genetic Programming (GP) has been the subject of a significant amount of research, but this has resulted in the solution of few complex real -world problems. In this work, I propose that, for some relatively simple, non safety -critical embedded control applications, GP can be used as a practical alternative to software developed by humans. Embedded control software has become a branch of software engineering with distinct temporal, interface and resource constraints and requirements. This results in a characteristic software structure, and by examining this, the effective decomposition of an overall problem into a number of smaller, simpler problems is performed. It is this type of problem amelioration that is suggested as a method whereby certain real -world problems may be rendered into a soluble form suitable for GP. In the course of this research, the body of published GP literature was examined and the most important changes to the original GP technique of Koza are noted; particular focus is made upon GP techniques involving an element of concurrency -which is central to this work. This search highlighted few applications of GP for the creation of software for complex, real -world problems -this was especially true in the case of multi thread, multi output solutions. To demonstrate this Idea, a concurrent Linear GP (LGP) system was built that creates a multiple input -multiple output solution using a custom low -level evolutionary language set, combining both continuous and Boolean data types. The system uses a multi -tasking model to evolve and execute the required LGP code for each system output using separate populations: Two example problems -a simple fridge controller and a more complex washing machine controller are described, and the problems encountered and overcome during the successful solution of these problems, are detailed. The operation of the complete, evolved washing machine controller is simulated using a graphical LabVIEWapplication. The aim of this research is to propose a general purpose system for the automatic creation of control software for use in a range of problems from the target problem class -without requiring any system tuning: In order to assess the system search performance sensitivity, experiments were performed using various population and LGP string sizes; the experimental data collected was also used to examine the utility of abandoning stalled searches and restarting. This work is significant because it identifies a realistic application of GP that can ease the burden of finite human software design resources, whilst capitalising on accelerating computing potential.

The limitations of speech output technology emphasise the need for exploratory psychological research to maximise the effectiveness of speech as a display medium in human-computer interaction. Stage 1 of this study reviewed speech implementation research, focusing on general issues for tasks, users and environments. An analysis of design issues was conducted, related to the differing methodologies for synthesised and digitised message production. A selection of ergonomic guidelines were developed to enhance effective speech interface design. Stage 2 addressed the negative reactions of users to synthetic speech in spite of elegant dialogue structure and appropriate functional assignment. Synthetic speech interfaces have been consistently rejected by their users in a wide variety of application domains because of their poor quality. Indeed the literature repeatedly emphasises quality as being the most important contributor to implementation acceptance. In order to investigate this, a converging operations approach was adopted. This consisted of a series of five experiments (and associated pilot studies) which homed in on the specific characteristics of synthetic speech that determine the listeners varying perceptions of its qualities, and how these might be manipulated to improve its aesthetics. A flexible and reliable ratings interface was designed to display DECtalk speech variations and record listeners perceptions. In experiment one, 40 participants used this to evaluate synthetic speech variations on a wide range of perceptual scales. Factor analysis revealed two main factors: "listenability" accounting for 44.7% of the variance and correlating with the DECtalk "smoothness" parameter to . 57 (p<0.005) and "richness" to . 53 (p<0.005); "assurance" accounting for 12.6% of the variance and correlating with "average pitch" to . 42 (p<0.005) and "head size" to. 42 (p<0.005). Complimentary experiments were then required in order to address appropriate voice design for enhanced listenability and assurance perceptions. With a standard male voice set, 20 participants rated enhanced smoothness and attenuated richness as contributing significantly to speech listenability (p<0.001). Experiment three using a female voice set yielded comparable results, suggesting that further refinements of the technique were necessary in order to develop an effective methodology for speech quality optimization. At this stage it became essential to focus directly on the parameter modifications that are associated with the the aesthetically pleasing characteristics of synthetic speech. If a reliable technique could be developed to enhance perceived speech quality, then synthesis systems based on the commonly used DECtalk model might assume some of their considerable yet unfulfilled potential. In experiment four, 20 subjects rated a wide range of voices modified across the two main parameters associated with perceived listenability, smoothness and richness. The results clearly revealed a linear relationship between enhanced smoothness and attenuated richness and significant improvements in perceived listenability (p<0.001 in both cases). Planned comparisons conducted were between the different levels of the parameters and revealed significant listenability enhancements as smoothness was increased, and a similar pattern as richness decreased. Statistical analysis also revealed a significant interaction between the two parameters (p<0.001) and a more comprehensive picture was constructed. In order to expand the focus of and enhance the generality of the research, it was now necessary to assess the effects of synthetic speech modifications whilst subjects were undertaking a more realistic task. Passively rating the voices independent of processing for meaning is arguably an artificial task which rarely, if ever, would occur in 'real-world' settings. In order to investigate perceived quality in a more realistic task scenario, experiment five introduced two levels of information processing load. The purpose of this experiment was firstly to see if a comprehension load modified the pattern of listenability enhancements, and secondly to see if that pattern differed between high and and low load. Techniques for introducing cognitive load were investigated and comprehension load was selected as the most appropriate method in this case. A pilot study distinguished two levels of comprehension load from a set of 150 true/false sentences and these were recorded across the full range of parameter modifications. Twenty subjects then rated the voices using the established listenability scales as before but also performing the additional task of processing each spoken stimuli for meaning and determining the authenticity of the statements. Results indicated that listenability enhancements did indeed occur at both levels of processing although at the higher level variations in the pattern occured. A significant difference was revealed between optimal parameter modifications for conditions of high and low cognitive load (p<0.05). The results showed that subjects perceived the synthetic voices in the high cognitive load condition to be significantly less listenable than those same voices in the low cognitive load condition. The analysis also revealed that this effect was independent of the number of errors made. This result may be of general value because conclusions drawn from this findings are independent of any particular parameter modifications that may be exclusively available to DECtalk users. Overall, the study presents a detailed analysis of the research domain combined with a systematic experimental program of synthetic speech quality assessment. The experiments reported establish a reliable and replicable procedure for optimising the aesthetically pleasing characteristics of DECtalk speech, but the implications of the research extend beyond the boundaries of a particular synthesiser. Results from the experimental program lead to a number of conclusions, the most salient being that not only does the synthetic speech designer have to overcome the general rejection of synthetic voices based on their poor quality by sophisticated customisation of synthetic voice parameters, but that he or she needs to take into account the cognitive load of the task being undertaken. The interaction between cognitive load and optimal settings for synthesis requires direct consideration if synthetic speech systems are going to realise and maximise their potential in human computer interaction.