La compréhension automatique de la parole est au confluent des deux grands domaines que sont la reconnaissance automatique de la parole et l'apprentissage automatique. Un des problèmes majeurs dans ce domaine est l'obtention d'un corpus de données conséquent afin d'obtenir des modèles statistiques performants. Les corpus de parole pour entraîner des modèles de compréhension nécessitent une intervention humaine importante, notamment dans les tâches de transcription et d'annotation sémantique. Leur coût de production est élevé et c'est la raison pour laquelle ils sont disponibles en quantité limitée.Cette thèse vise principalement à réduire ce besoin d'intervention humaine de deux façons : d'une part en réduisant la quantité de corpus annoté nécessaire à l'obtention d'un modèle grâce à des techniques d'apprentissage semi-supervisé (Self-Training, Co-Training et Active-Learning) ; et d'autre part en tirant parti des réponses de l'utilisateur du système pour améliorer le modèle de compréhension.Ce dernier point touche à un second problème rencontré par les systèmes de compréhension automatique de la parole et adressé par cette thèse : le besoin d'adapter régulièrement leurs modèles aux variations de comportement des utilisateurs ou aux modifications de l'offre de services du système

Student Number : 9811923K - PhD thesis - School of Mechanical Engineering - Faculty of Engineering and the Built Environment / Methods are presented for obtaining models used for predicting welded sample resistance and effective weld current (RMS) for desired weld diameter (weld quality) in the resistance spot welding process. These models were used to design predictive controllers for the welding process. A suitable process model forms an important step in the development and design of process controllers for achieving good weld quality with good reproducibility. Effective current, dynamic resistance and applied electrode force are identified as important input parameters necessary to predict the output weld diameter. These input parameters are used for the process model and design of a predictive controller. A three parameter empirical model with dependent and independent variables was used for curve fitting the nonlinear halfwave dynamic resistance. The estimates of the parameters were used to develop charts for determining overall resistance of samples for any desired weld diameter. Estimating resistance for samples welded in the machines from which dataset obtained were used to plot the chart yielded accurate results. However using these charts to estimate sample resistance for new and unknown machines yielded high estimation error. To improve the prediction accuracy the same set of data generated from the model were used to train four different neural network types. These were the Generalised Feed Forward (GFF) neural network, Multilayer Perceptron (MLP) network, Radial Basis Function (RBF) and Recurrent neural network (RNN). Of the four network types trained, the MLP had the least mean square error for training and cross validation of 0.00037 and 0.00039 respectively with linear correlation coefficient in testing of 0.999 and maximum estimation error range from 0.1% to 3%. A prediction accuracy of about 97% to 99.9%. This model was selected for the design and implementation of the controller for predicting overall sample resistance. Using this predicted overall sample resistance, and applied electrode force, a second model was developed for predicting required effective weld current for any desired weld diameter. The prediction accuracy of this model was in the range of 94% to 99%. The neural network predictive controller was designed using the MLP neural network models. The controller outputs effective current for any desired weld diameter and is observed to track the desired output accurately with same prediction accuracy of the model used which was about 94% to 99%. The controller works by utilizing the neural network output embedded in Microsoft Excel as a digital link library and is able to generate outputs for given inputs on activating the process by the push of a command button.

Classificação automática de modulação digital de sinais de comunicações é um importante problema de processamento de sinais no campo das comunicações. É um passo intermediário entre a interceptação do sinal e a recuperação da informação, no qual um classificador identifica automaticamente o tipo de modulação do sinal recebido para posterior demodulação e demais tarefas. A técnica de reconhecimento de padrões pode ser utilizada neste problema de classificação. Neste caso, na classificação é necessária a seleção e extração de características relevantes do sinal recebido. Neste trabalho, foram utilizados três tipos de características relevantes: espectrais, estatísticas e uma combinação dos dois tipos. Dois classificadores foram desenvolvidos nesta pesquisa: o primeiro, baseado em Redes Neurais Artificiais, utilizando o Perceptron Multicamadas (MLP); e o segundo, baseado em Máquinas de Vetores de Suporte (SVM). Estes dois classificadores foram usados para classificar as seguintes modulações digitais: Chaveadas em Amplitude (ASK2, ASK4), Chaveadas em Freqüência (FSK2, FSK4, FSK8), e Chaveadas em Fase (PSK2, PSK4, PSK8). Foi verificado, por meio de simulações em MATLAB 7, que o classificador com a abordagem SVM, utilizando uma combinação de características relevantes espectrais e estatísticas, obteve excelente resultados nos testes.

Recommender systems are an advanced form of software applications, more specifically decision-support systems, that efficiently assist the users in finding items of their interest. Recommender systems have been applied to many domains from music to e-commerce, movies to software services delivery and tourism to news by exploiting available information to predict and provide recommendations to end user. The suggestions generated by recommender systems tend to narrow down the list of items which a user may overlook due to the huge variety of similar items or users’ lack of experience in the particular domain of interest. While the performance of traditional recommender systems, which rely on relatively simpler information such as content and users’ filters, is widely accepted, their predictive capability perfomrs poorly when local context of the user and situated actions have significant role in the final decision. Therefore, acceptance and incorporation of context of the user as a significant feature and development of recommender systems utilising the premise becomes an active area of research requiring further investigation of the underlying algorithms and methodology. This thesis focuses on categorisation of contextual and non-contextual features within the domain of context-aware recommender system and their respective evaluation. Further, application of the Multilayer Perceptron Model (MLP) for generating predictions and ratings from the contextual and non-contextual features for contextual recommendations is presented with support from relevant literature and empirical evaluation. An evaluation of specifically employing artificial neural networks (ANNs) in the proposed methodology is also presented. The work emphasizes on both algorithms and methodology with three points of consideration: contextual features and ratings of particular items/movies are exploited in several representations to improve the accuracy of recommendation process using artificial neural networks (ANNs), context features are combined with user-features to further improve the accuracy of a context-aware recommender system and lastly, a combination of the item/movie features are investigated within the recommendation process. The proposed approach is evaluated on the LDOS-CoMoDa dataset and the results are compared with state-of-the-art approaches from relevant published literature.

<p>Die trainingswissenschaftliche Diagnostik in den Kernbereichen Training, Wettkampf und Leistungsfähigkeit ist durch einen hohen Praxisbezug, eine ausgeprägte strukturelle Komplexität und vielseitige Wechselwirkungen der sportwissenschaftlichen Teilgebiete geprägt. Diese Eigenschaften haben in der Vergangenheit dazu geführt, dass zentrale Fragestellungen, wie beispielsweise die Maximierung der sportlichen Leistungsfähigkeit, eine ökonomische Trainingsgestaltung, eine effektive Talentauswahl und -sichtung oder die Modellbildung noch nicht vollständig gelöst werden konnten. Neben den bereits vorhandenen linearen Lösungsansätzen werden in dieser Arbeit Methoden aus dem Bereich der Neuronalen Netzwerke eingesetzt. Diese nichtlinearen Diagnoseverfahren sind besonders geeignet für die Analyse von Prozessabläufen, wie sie beispielsweise im Training vorliegen.</p> <p>Im theoretischen Teil werden zunächst Gemeinsamkeiten, Abhängigkeiten und Unterschiede in den Bereichen Training, Wettkampf und Leistungsfähigkeit untersucht sowie die Brücke zwischen trainingswissenschaftlicher Diagnostik und nichtlinearen Verfahren über die Begriffe der Interdisziplinarität und Integrativität geschlagen. Angelehnt an die Theorie der Neuronalen Netze werden anschließend die Grundlagenmodelle Perzeptron, Multilayer-Perzeptron und Selbstorganisierende Karten theoretisch erläutert. Im empirischen Teil stehen dann die nichtlineare Analyse von personalen Anforderungsstrukturen, Zustände der sportlichen Form und die Prognose sportlichen Talents - allesamt bei jugendlichen Leistungsschwimmerinnen und -schwimmern - im Mittelpunkt. Die nichtlinearen Methoden werden dabei einerseits auf ihre wissenschaftliche Aussagekraft überprüft, andererseits untereinander sowie mit linearen Verfahren verglichen.</p> / <p>The diagnostic methods in training science concentrate on the core areas of training, competition, and performance. The methods commonly used are characterized by a high degree of practical applicability and distinct structural complexity. These characteristics have led to the question which scientific methods fit best for resolving problems like, for example, the optimization of athletic performance, efficient planning and monitoring of training processes, effective talent screening, selection and development, or the formation of analytical models. All these questions have not yet been answered sufficiently.</p> <p>Aside from the traditional mathematical approaches on the basis of the linear model, nonlinear methods in the field of neural networks are used in this dissertation. These nonlinear diagnostic methods are especially suitable for the analysis of coherent patterns in time series such as training processes.</p> <p>In the theoretical part of the dissertation, common aspects, mutual dependencies, and differences between training, competition, and performance are examined. In this context, a bridge is built between the diagnostic purposes in these fields and suitable nonlinear methods. Along the lines of the neural networks theory, the basic models Perceptron, Multilayer-Perceptron, and Self-Organizing Feature Maps are subsequently elucidated.</p> <p>In the empirical part of the thesis, three studies conducted with top level adolescent swimmers are presented that focus on the nonlinear analysis of personal athletic ability structures, different states of athletic shape, and the prognosis of athletic talent. The nonlinear methods are thus examined as to how worthwhile they are for analytical purposes in training science on the one hand, and they are compared to each other as well as to linear methods on the other hand.</p>

Promoter classification is the task of separating promoter from non promoter sequences. Determining promoter regions where the transcription initiation takes place is important for several reasons such as improving genome annotation and defining transcription start sites. In this study, various promoter prediction methods called ProK-means, ProSVM, and 3S1C are proposed. In ProSVM and ProK-means algorithms, structural features of DNA sequences are used to distinguish promoters from non promoters. Obtained results are compared with ProSOM which is an existing promoter prediction method. It is shown that ProSVM is able to achieve greater recall rate compared to ProSOM results. Another promoter prediction methods proposed in this study is 3S1C. The difference of the proposed technique from existing methods is using signal, similarity, structure, and context features of DNA sequences in an integrated way and a hierarchical manner. In addition to current methods related to promoter classification, the similarity feature, which compares the promoter regions between human and other species, is added to the proposed system. We show that the similarity feature improves the accuracy. To classify core promoter regions, firstly, signal, similarity, structure, and context features are extracted and then, these features are classified separately by using Support Vector Machines. Finally, output predictions are combined using multilayer perceptron. The result of 3S1C algorithm is very promising.

This thesis develops a strategy for polymerized volume data set construction. Given a volume data set defined over a regular three-dimensional grid, a polymerized volume data set (PVDS) can be defined as follows: edges between adjacent vertices of the grid are labeled 1 (active) or 0 (inactive) to indicate the likelihood that an edge is contained in (or spans the boundary of) a common underlying object, adding information not in the original volume data set. This edge labeling “polymerizes” adjacent voxels (those sharing a common active edge) into connected components, facilitating segmentation of embedded objects in the volume data set. Polymerization of the volume data set also aids real-time data compression, geometric modeling of the embedded objects, and their visualization. To construct a polymerized volume data set, an adjacency class within the grid system is selected. Edges belonging to this adjacency class are labeled as interior, exterior, or boundary edges using discriminant functions whose functional forms are derived for three local adjacency classes. The discriminant function parameter values are determined by supervised learning. Training sets are derived from an initial segmentation on a homogeneous sample of the volume data set, using an existing segmentation method. The strategy of constructing polymerized volume data sets is initially tested on synthetic data sets which resemble neuronal volume data obtained by three-dimensional microscopy. The strategy is then illustrated on volume data sets of mouse brain microstructure at a neuronal level of detail. Visualization and validation of the resulting PVDS is shown in both cases. Finally the procedures of polymerized volume data set construction are generalized to apply to any Bravais lattice over the regular 3D orthogonal grid. Further development of this latter topic is left to future work.

Safety and reliability are prime concerns in aircraft performance due to the involved costs and risk to lives. Despite the best efforts in design methodology, quality evaluation in production and structural integrity assessment in-service, attainment of one hundred percent safety through development and use of a suitable in-flight health monitoring system is still a farfetched goal. And, evolution of such a system requires, first, identification of an appropriate Technique and next its adoption to meet the challenges posed by newer materials (advanced composites), complex structures and the flight environment. In fact, a quick survey of the available Non-Destructive Evaluation (NDE) techniques suggests Acoustic Emission (AE) as the only available method. High merit in itself could be a weakness - Noise is the worst enemy of AE. So, while difficulties are posed due to the insufficient understanding of the basic behavior of composites, growth and interaction of defects and damage under a specified load condition, high in-flight noise further complicates the issue making the developmental task apparently formidable and challenging. Development of an in-flight monitoring system based on AE to function as an early warning system needs addressing three aspects, viz., the first, discrimination of AE signals from noise data, the second, extraction of required information from AE signals for identification of sources (source characterization) and quantification of its growth, and the third, automation of the entire process. And, a quick assessment of the aspects involved suggests that Artificial Neural Networks (ANN) are ideally suited for solving such a complex problem. A review of the available open literature while indicates a number of investigations carried out using noise elimination and source characterization methods such as frequency filtering and statistical pattern recognition but shows only sporadic attempts using ANN. This may probably be due to the complex nature of the problem involving investigation of a large number of influencing parameters, amount of effort and time to be invested, and facilities required and multi-disciplinary nature of the problem. Hence as stated in the foregoing, the need for such a study cannot be over emphasized. Thus, this thesis is an attempt addressing the issue of analysis and automation of complex sets of AE data such as AE signals mixed with in-flight noise thus forming the first step towards in-flight monitoring using AE. An ANN can in fact replace the traditional algorithmic approaches used in the past. ANN in general are model free estimators and derive their computational efficiency due to large connectivity, massive parallelism, non-linear analog response and learning capabilities. They are better suited than the conventional methods (statistical pattern recognition methods) due to their characteristics such as classification, pattern matching, learning, generalization, fault tolerance and distributed memory and their ability to process unstructured data sets which may be carrying incomplete information at times and hence chosen as the tool. Further, in the current context, the set of investigations undertaken were in the absence of sufficient a priori information and hence clustering of signals generated by AE sources through self-organizing maps is more appropriate. Thus, in the investigations carried out under the scope of this thesis, at first a hybrid network named "NAEDA" (Neural network for Acoustic Emission Data Analysis) using Kohonen self-organizing feature map (KSOM) and multi-layer perceptron (MLP) that learns on back propagation learning rule was specifically developed with innovative data processing techniques built into the network. However, for accurate pattern recognition, multi-layer back propagation NN needed to be trained with source and noise clusters as input data. Thus, in addition to optimizing the network architecture and training parameters, preprocessing of input data to the network and multi-class clustering and classification proved to be the corner stones in obtaining excellent identification accuracy. Next, in-flight noise environment of an aircraft was generated off line through carefully designed simulation experiments carried out in the laboratory (Ex: EMI, friction, fretting and other mechanical and hydraulic phenomena) based on the in-flight noise survey carried out by earlier investigators. From these experiments data was acquired and classified into their respective classes through MLP. Further, these noises were mixed together and clustered through KSOM and then classified into their respective clusters through MLP resulting in an accuracy of 95%- 100% Subsequently, to evaluate the utility of NAEDA for source classification and characterization, carbon fiber reinforced plastic (CFRP) specimens were subjected to spectrum loading simulating typical in-flight load and AE signals were acquired continuously up to a maximum of three designed lives and in some cases up to failure. Further, AE signals with similar characteristics were grouped into individual clusters through self-organizing map and labeled as belonging to appropriate failure modes, there by generating the class configuration. Then MLP was trained with this class information, which resulted in automatic identification and classification of failure modes with an accuracy of 95% - 100%. In addition, extraneous noise generated during the experiments was acquired and classified so as to evaluate the presence or absence of such data in the AE data acquired from the CFRP specimens. In the next stage, noise and signals were mixed together at random and were reclassified into their respective classes through supervised training of multi-layer back propagation NN. Initially only noise was discriminated from the AE signals from CFRP failure modes and subsequently both noise discrimination and failure mode identification and classification was carried out resulting in an accuracy of 95% - 100% in most of the cases. Further, extraneous signals mentioned above were classified which indicated the presence of such signals in the AE signals obtained from the CFRP specimen. Thus, having established the basis for noise identification and AE source classification and characterization, two specific examples were considered to evaluate the utility and efficiency of NAEDA. In the first, with the postulation that different basic failure modes in composites have unique AE signatures, the difference in damage generation and progression can be clearly characterized under different loading conditions. To examine this, static compression tests were conducted on a different set of CFRP specimens till failure with continuous AE monitoring and the resulting AE signals were classified through already trained NAEDA. The results obtained shows that the total number of signals obtained were very less when compared to fatigue tests and the specimens failed with hardly any damage growth. Further, NAEDA was able to discriminate the"noise and failure modes in CFRP specimen with the same degree of accuracy with which it has classified such signals obtained from fatigue tests. In the second example, with the same postulate of unique AE signatures for different failure modes, the differences in the complexion of the damage growth and progression should become clearly evident when one considers specimens with different lay up sequences. To examine this, the data was reclassified on the basis of differences in lay up sequences from specimens subjected to fatigue. The results obtained clearly confirmed the postulation. As can be seen from the summary of the work presented in the foregoing paragraphs, the investigations undertaken within the scope of this thesis involve elaborate experimentation, development of tools, acquisition of extensive data and analysis. Never the less, the results obtained were commensurate with the efforts and have been fruitful. Of the useful results that have been obtained, to state in specific, the first is, discrimination of simulated noise sources achieved with significant success but for some overlapping which is not of major concern as far as noises are concerned. Therefore they are grouped into required number of clusters so as to achieve better classification through supervised NN. This proved to be an innovative measure in supervised classification through back propagation NN. The second is the damage characterization in CFRP specimens, which involved imaginative data processing techniques that proved their worth in terms of optimization of various training parameters and resulted in accurate identification through clustering. Labeling of clusters is made possible by marking each signal starting from clustering to final classification through supervised neural network and is achieved through phenomenological correlation combined with ultrasonic imaging. Most rewarding of all is the identification of failure modes (AE signals) mixed in noise into their respective classes. This is a direct consequence of innovative data processing, multi-class clustering and flexibility of grouping various noise signals into suitable number of clusters. Thus, the results obtained and presented in this thesis on NN approach to AE signal analysis clearly establishes the fact that methods and procedures developed can automate detection and identification of failure modes in CFRP composites under hostile environment, which could lead to the development of an in-flight monitoring system.

The hybridization of soft computing methods of Radial Basis Function (RBF) neural networks, Multi Layer Perceptron (MLP) neural networks with back-propagation learning, fuzzy sets and rough sets are studied in the scope of this thesis. Conventional MLP, conventional RBF, fuzzy MLP, fuzzy RBF, rough fuzzy MLP, and rough fuzzy RBF networks are compared. In the fuzzy neural networks implemented in this thesis, the input data and the desired outputs are given fuzzy membership values as the fuzzy properties &ldquo / low&rdquo / , &ldquo / medium&rdquo / and &ldquo / high&rdquo / . In the rough fuzzy MLP, initial weights and near optimal number of hidden nodes are estimated using rough dependency rules. A rough fuzzy RBF structure similar to the rough fuzzy MLP is proposed. The rough fuzzy RBF was inspected whether dependencies like the ones in rough fuzzy MLP can be concluded.

The thesis reports a contribution to the development of neural-like network- based element-free methods for the numerical simulation of some non-Newtonian fluid flow problems. The numerical approximation of functions and solution of the governing partial differential equations are mainly based on radial basis function networks. The resultant micro-macroscopic approaches do not require any element-based discretisation and only rely on a set of unstructured collocation points and hence are truly meshless or element-free. The development of the present methods begins with the use of the multi-layer perceptron networks (MLPNs) and radial basis function networks (RBFNs) to effectively eliminate the volume integrals in the integral formulation of fluid flow problems. An adaptive velocity gradient domain decomposition (AVGDD) scheme is incorporated into the computational algorithm. As a result, an improved feed forward neural network boundary-element-only method (FFNN- BEM) is created and verified. The present FFNN-BEM successfully simulates the flow of several Generalised Newtonian Fluids (GNFs), including the Carreau, Power-law and Cross models. To the best of the author's knowledge, the present FFNN-BEM is the first to achieve convergence for difficult flow situations when the power-law indices are very small (as small as 0.2). Although some elements are still used to discretise the governing equations, but only on the boundary of the analysis domain, the experience gained in the development of element-free approximation in the domain provides valuable skills for the progress towards an element-free approach. A least squares collocation RBFN-based mesh-free method is then developed for solving the governing PDEs. This method is coupled with the stochastic simulation technique (SST), forming the mesoscopic approach for analyzing viscoelastic flid flows. The velocity field is computed from the RBFN-based mesh-free method (macroscopic component) and the stress is determined by the SST (microscopic component). Thus the SST removes a limitation in traditional macroscopic approaches since closed form constitutive equations are not necessary in the SST. In this mesh-free method, each of the unknowns in the conservation equations is represented by a linear combination of weighted radial basis functions and hence the unknowns are converted from physical variables (e.g. velocity, stresses, etc) into network weights through the application of the general linear least squares principle and point collocation procedure. Depending on the type of RBFs used, a number of parameters will influence the performance of the method. These parameters include the centres in the case of thin plate spline RBFNs (TPS-RBFNs), and the centres and the widths in the case of multi-quadric RBFNs (MQ-RBFNs). A further improvement of the approach is achieved when the Eulerian SST is formulated via Brownian configuration fields (BCF) in place of the Lagrangian SST. The SST is made more efficient with the inclusion of the control variate variance reduction scheme, which allows for a reduction of the number of dumbbells used to model the fluid. A highly parallelised algorithm, at both macro and micro levels, incorporating a domain decomposition technique, is implemented to handle larger problems. The approach is verified and used to simulate the flow of several model dilute polymeric fluids (the Hookean, FENE and FENE-P models) in simple as well as non-trivial geometries, including shear flows (transient Couette, Poiseuille flows)), elongational flows (4:1 and 10:1 abrupt contraction flows) and lid-driven cavity flows.