Dissertations / Theses on the topic 'Multi-layer perceptron networks (MLPNs)'

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.

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.

Background:- Artificial Neural networks are motivated from biological nervous system and can be used for classification and forecasting the data. Each neural node contains activation function could be used for solving non-linear problems and optimization function to minimize the loss and give more accurate results. Neural networks are bustling in the field of machine learning, which inspired this study to analyse the performance variation based on the use of different combinations of the activation functions and optimization algorithms in terms of accuracy results and metrics recall and impact of data-set features on the performance of the neural networks. Objectives:- This study deals with an experiment to analyse the performance of the combinations are performing well and giving more results and to see impact of the feature segregation from data-set on the neural networks model performance. Methods:- The process involve the gathering of the data-sets, activation functions and optimization algorithm. Execute the network model using 7X5 different combinations of activation functions and optimization algorithm and analyse the performance of the neural networks. These models are tested upon the same data-set with some of the discarded features to know the effect on the performance of the neural networks. Results:- All the metrics for evaluating the neural networks presented in separate table and graphs are used to show growth and fall down of the activation function when associating with different optimization function. Impact of the individual feature on the performance of the neural network is also represented. Conclusions:- Out of 35 combinations, combinations made from optimizations algorithms Adam,RMSprop and Adagrad and activation functions ReLU,Softplus,Tanh Sigmoid and Hard_Sigmoid are selected based on the performance evaluation and data has impact on the performance of the combinations of the algorithms and activation functions which is also evaluated based on the experimentation. Individual features have their corresponding effect on the neural network.

Graças aos avanços tecnológicos nas áreas da computação, eletrônica embarcada e mecatrônica a robótica está cada vez mais presente no cotidiano da pessoas. Nessas últimas décadas, uma infinidade de ferramentas e métodos foram desenvolvidos no campo da Robótica Móvel. Um exemplo disso são os sistemas inteligentes embarcados nos veículos de passeio. Tais sistemas auxiliam na condução através de sensores que recebem informações do ambiente e algoritmos que analisam os dados e tomam decisões para realizar uma determinada tarefa, como por exemplo estacionar um carro. Este trabalho tem por objetivo apresentar estudos realizados no desenvolvimento de um controlador inteligente capaz de estacionar um veículo simulado em vagas paralelas, na qual seja possível entrar com uma única manobra. Para isso, foi necessário realizar estudos envolvendo a modelagem de ambientes, cinemática veicular e sensores, os quais foram implementados em um ambiente de simulação desenvolvido em C# com o Visual Studio 2008. Em seguida é realizado um estudo sobre as três etapas do estacionamento, que consistem em procurar uma vaga, posicionar o veículo e manobrá-lo. Para realizar a manobra foi adotada a trajetória em S desenvolvida e muito utilizada em outros trabalhos encontrados na literatura da área. A manobra consiste em posicionar corretamente duas circunferências com um raio de esterçamento do veículo. Sendo assim, foi utilizado um controlador robusto baseado em aprendizado supervisionado utilizando Redes Neurais Artificiais (RNA), pois esta abordagem apresenta grande robustez com relação à presença de ruídos no sistema. Este controlador recebe dados de dois sensores laser (um fixado na frente do veículo e o outro na parte traseira), da odometria e de orientação de um sensor inercial. Os dados adquiridos desses sensores e a etapa da manobra em que o veículo está, servem de entrada para o controlador. Este é capaz de interpretar tais dados e responder a esses estímulos de forma correta em aproximadamente 99% dos casos. Os resultados de treinamento e de simulação se mostraram muito satisfatórios, permitindo que o carro controlador pela RNA pudesse estacionar corretamente em uma vaga paralela.
Thanks to technological advances in the fields of computer science, embedded electronics and mechatronics, robotics is increasingly more present in people\'s lives. On the past few decades a great variety of tools and methods were developed in the Mobile Robotics field, e.g. the passenger vehicles with smart embedded systems. Such systems help drivers through sensors that acquire information from the surrounding environment and algorithms which process this data and make decisions to perform a task, like parking a car. This work aims to present the studies performed on the development of a smart controller able to park a simulated vehicle in parallel parking spaces, where a single maneuver is enough to enter. To accomplish this, studies involving the modeling of environments, vehicle kinematics and sensors were conducted, which were implemented in a simulated environment developed in C# with Visual Studio 2008. Next, a study about the three stages of parking was carried out, which consists in looking for a slot, positioning the vehicle and maneuvering it. The \"S\" trajectory was adopted and developed to maneuver the vehicle, since it is well known and highly used in related works found in the literature of this field. The maneuver consists in the correct positioning of two circumferences with the possible steering radius of the vehicle. For this task, a robust controller based on supervised learning using Artificial Neural Networks (ANN) was employed, since this approach has great robustness regarding the presence of noise in the system. This controller receives data from two laser sensors (one attached on the front of the vehicle and the other on the rear), from the odometry and from the inertial orientation sensor. The data acquired from these sensors and the current maneuver stage of the vehicle are the inputs of the controller, which interprets these data and responds to these stimuli in a correct way in approximately 99% of the cases. The results of the training and simulation were satisfactory, allowing the car controlled by the ANN to correctly park in a parallel slot.

La prévision des séries temporelles est un problème qui est traité depuis de nombreuses années. On y trouve des applications dans différents domaines tels que : la finance, la médecine, le transport, etc. Dans cette thèse, on s’est intéressé aux méthodes issues de l’apprentissage artificiel : les réseaux de neurones et les SVM. On s’est également intéressé à l’intérêt des méta-méthodes pour améliorer les performances des prédicteurs, notamment l’approche locale. Dans une optique de diviser pour régner, les approches locales effectuent le clustering des données avant d’affecter les prédicteurs aux sous ensembles obtenus. Nous présentons une modification dans l’algorithme d’apprentissage des réseaux de neurones récurrents afin de les adapter à cette approche. Nous proposons également deux nouvelles techniques de clustering, la première basée sur les cartes de Kohonen et la seconde sur les arbres binaires
Time series forecasting is a widely discussed issue for many years. Researchers from various disciplines have addressed it in several application areas : finance, medical, transportation, etc. In this thesis, we focused on machine learning methods : neural networks and SVM. We have also been interested in the meta-methods to push up the predictor performances, and more specifically the local models. In a divide and conquer strategy, the local models perform a clustering over the data sets before different predictors are affected into each obtained subset. We present in this thesis a new algorithm for recurrent neural networks to use them as local predictors. We also propose two novel clustering techniques suitable for local models. The first is based on Kohonen maps, and the second is based on binary trees

Este trabalho fundamenta-se no conceito de máquina de comitê de redes neurais artificiais e tem por objetivo resolver o problema inverso de transferência radiativa em um meio unidimensional, homogêneo, absorvedor e espalhador isotrópico. A máquina de comitê de redes neurais artificiais agrega e combina o conhecimento adquirido por um certo número de especialistas aqui representados, individualmente, por cada uma das redes neurais artificiais (RNA) que compõem a máquina de comitê de redes neurais artificiais. O objetivo é atingir um resultado final melhor do que o obtido por qualquer rede neural artificial separadamente, selecionando-se apenas àquelas redes neurais artificiais que apresentam os melhores resultados na fase de generalização descartando-se as demais, o que foi feito neste trabalho. Aqui são utilizados dois modelos estáticos de máquinas de comitê, usando a média aritmética de conjunto, que se diferenciam entre si apenas na composição do combinador de saída de cada máquina de comitê. São obtidas, usando-se máquinas de comitê de redes neurais artificiais, estimativas para os parâmetros de transferência radiativa, isto é, a espessura óptica do meio, o albedo de espalhamento simples e as refletividades difusas. Finalmente, os resultados obtidos com ambos os modelos de máquina de comitê são comparados entre si e com aqueles encontrados usando-se apenas redes neurais artificiais do tipo perceptrons de múltiplas camadas (MLP), isoladamente. Aqui essas redes neurais artificiais são denominadas redes neurais especialistas, mostrando que a técnica empregada traz melhorias de desempenho e resultados a um custo computacional relativamente baixo.
This work is based on the concept of neural networks committee machine and has the objective to solve the inverse radiative transfer problem in one-dimensional, homogeneous, absorbing and isotropic scattering media. The artificial neural networks committee machine adds and combines the knowledge acquired by an exact number of specialists which are represented, individually, by each one of the artificial neural networks (ANN) that composes the artificial neural network committee machine. The aim is to reach a final result better than the one obtained by any of the artificial neural network separately, selecting only those artificial neural networks that presents the best results during the generalization phase and discarding the others, what was done in this present work. Here are used two static models of committee machines, using the ensemble arithmetic average, that differ between themselves only by the composition of the output combinator by each one of the committee machine. Are obtained, using artificial neural networks committee machines, estimates for the radiative transfer parameters, that is, medium optical thickness, single scattering albedo and diffuse reflectivities. Finally, the results obtained with both models of committee machine are compared between themselves and with those found using artificial neural networks type multi-layer perceptrons (MLP), isolated. Here that artificial neural networks are named as specialists neural networks, showing that the technique employed brings performance and results improvements with relatively low computational cost.

The desire to model the true gain from targeting an individual in marketing purposes has lead to the common use of uplift modeling. Uplift modeling requires the existence of a treatment group as well as a control group and the objective hence becomes estimating the difference between the success probabilities in the two groups. Efficient methods for estimating the probabilities in uplift models are statistical machine learning methods. In this project the different uplift modeling approaches Subtraction of Two Models, Modeling Uplift Directly and the Class Variable Transformation are investigated. The statistical machine learning methods applied are Random Forests and Neural Networks along with the standard method Logistic Regression. The data is collected from a well established retail company and the purpose of the project is thus to investigate which uplift modeling approach and statistical machine learning method that yields in the best performance given the data used in this project. The variable selection step was shown to be a crucial component in the modeling processes as so was the amount of control data in each data set. For the uplift to be successful, the method of choice should be either the Modeling Uplift Directly using Random Forests, or the Class Variable Transformation using Logistic Regression. Neural network - based approaches are sensitive to uneven class distributions and is hence not able to obtain stable models given the data used in this project. Furthermore, the Subtraction of Two Models did not perform well due to the fact that each model tended to focus too much on modeling the class in both data sets separately instead of modeling the difference between the class probabilities. The conclusion is hence to use an approach that models the uplift directly, and also to use a great amount of control data in each data set.
Behovet av att kunna modellera den verkliga vinsten av riktad marknadsföring har lett till den idag vanligt förekommande metoden inkrementell responsanalys. För att kunna utföra denna typ av metod krävs förekomsten av en existerande testgrupp samt kontrollgrupp och målet är således att beräkna differensen mellan de positiva utfallen i de två grupperna. Sannolikheten för de positiva utfallen för de två grupperna kan effektivt estimeras med statistiska maskininlärningsmetoder. De inkrementella responsanalysmetoderna som undersöks i detta projekt är subtraktion av två modeller, att modellera den inkrementella responsen direkt samt en klassvariabeltransformation. De statistiska maskininlärningsmetoderna som tillämpas är random forests och neurala nätverk samt standardmetoden logistisk regression. Datan är samlad från ett väletablerat detaljhandelsföretag och målet är därmed att undersöka vilken inkrementell responsanalysmetod och maskininlärningsmetod som presterar bäst givet datan i detta projekt. De mest avgörande aspekterna för att få ett bra resultat visade sig vara variabelselektionen och mängden kontrolldata i varje dataset. För att få ett lyckat resultat bör valet av maskininlärningsmetod vara random forests vilken används för att modellera den inkrementella responsen direkt, eller logistisk regression tillsammans med en klassvariabeltransformation. Neurala nätverksmetoder är känsliga för ojämna klassfördelningar och klarar därmed inte av att erhålla stabila modeller med den givna datan. Vidare presterade subtraktion av två modeller dåligt på grund av att var modell tenderade att fokusera för mycket på att modellera klassen i båda dataseten separat, istället för att modellera differensen mellan dem. Slutsatsen är således att en metod som modellerar den inkrementella responsen direkt samt en relativt stor kontrollgrupp är att föredra för att få ett stabilt resultat.

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.

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.

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.

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.

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.

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.

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.

Cette thèse s’intéresse à la problématique de la prédiction dans le cadre du design de systèmes énergétiques et des problèmes d’opération, et en particulier, à l’évaluation de l’adéquation de systèmes de production d’énergie renouvelables. L’objectif général est de développer une approche empirique pour générer des prédictions avec les incertitudes associées. En ce qui concerne cette direction de la recherche, une approche non paramétrique et empirique pour estimer les intervalles de prédiction (PIs) basés sur les réseaux de neurones (NNs) a été développée, quantifiant l’incertitude dans les prédictions due à la variabilité des données d’entrée et du comportement du système (i.e. due au comportement stochastique des sources renouvelables et de la demande d'énergie électrique), et des erreurs liées aux approximations faites pour établir le modèle de prédiction. Une nouvelle méthode basée sur l'optimisation multi-objectif pour estimer les PIs basée sur les réseaux de neurones et optimale à la fois en termes de précision (probabilité de couverture) et d’information (largeur d’intervalle) est proposée. L’ensemble de NN individuels par deux nouvelles approches est enfin présenté comme un moyen d’augmenter la performance des modèles. Des applications sur des études de cas réels démontrent la puissance de la méthode développée
This Ph.D. work addresses the problem of prediction within energy systems design and operation problems, and particularly the adequacy assessment of renewable power generation systems. The general aim is to develop an empirical modeling framework for providing predictions with the associated uncertainties. Along this research direction, a non-parametric, empirical approach to estimate neural network (NN)-based prediction intervals (PIs) has been developed, accounting for the uncertainty in the predictions due to the variability in the input data and the system behavior (e.g. due to the stochastic behavior of the renewable sources and of the energy demand by the loads), and to model approximation errors. A novel multi-objective framework for estimating NN-based PIs, optimal in terms of both accuracy (coverage probability) and informativeness (interval width) is proposed. Ensembling of individual NNs via two novel approaches is proposed as a way to increase the performance of the models. Applications on real case studies demonstrate the power of the proposed framework

With increasing demands on network reliability and speed, network suppliers need to effectivize their communications algorithms. Frequency measurements are a core part of mobile network communications, increasing their effectiveness would increase the effectiveness of many network processes such as handovers, load balancing, and carrier aggregation. This study examines the possibility of using supervised learning to predict the signal of inter-frequency measurements by investigating various learning algorithms and pre-processing techniques. We found that random forests have the highest predictive performance on this data set, at 90.7\% accuracy. In addition, we have shown that undersampling and varying the discriminator are effective techniques for increasing the performance on the positive class on frequencies where the negative class is prevalent. Finally, we present hybrid algorithms in which the learning algorithm for each model depends on attributes of the training data set. These algorithms perform at a much higher efficiency in terms of memory and run-time without heavily sacrificing predictive performance.

Self-adaptive systems have limited time to adjust their configurations whenever their adaptation goals, i.e., quality requirements, are violated due to some runtime uncertainties. Within the available time, they need to analyze their adaptation space, i.e., a set of configurations, to find the best adaptation option, i.e., configuration, that can achieve their adaptation goals. Existing formal analysis approaches find the best adaptation option by analyzing the entire adaptation space. However, exhaustive analysis requires time and resources and is therefore only efficient when the adaptation space is small. The size of the adaptation space is often in hundreds or thousands, which makes formal analysis approaches inefficient in large-scale self-adaptive systems. In this thesis, we tackle this problem by presenting an online learning approach that enables formal analysis approaches to analyze large adaptation spaces efficiently. The approach integrates with the standard feedback loop and reduces the adaptation space to a subset of adaptation options that are relevant to the current runtime uncertainties. The subset is then analyzed by the formal analysis approaches, which allows them to complete the analysis faster and efficiently within the available time. We evaluate our approach on two different instances of an Internet of Things application. The evaluation shows that our approach dramatically reduces the adaptation space and analysis time without compromising the adaptation goals.

Agriculture is becoming more dependent on computerized solutions to make thefarmer’s job easier. The big step that many companies are working towards is fullyautonomous vehicles that work the fields. To that end, the equipment fitted to saidvehicles must also adapt and become autonomous. Making this equipment autonomoustakes many incremental steps, one of which is developing an accurate and reliable tanklevel measurement system. In this thesis, a system for tank level measurement in a seedplanting machine is evaluated. Traditional systems use load cells to measure the weightof the tank however, these types of systems are expensive to build and cumbersome torepair. They also add a lot of weight to the equipment which increases the fuel consump-tion of the tractor. Thus, this thesis investigates the use of radar sensors together witha number of Machine Learning algorithms. Fourteen radar sensors are fitted to a tankat different positions, data is collected, and a preprocessing method is developed. Then,the data is used to test the following Machine Learning algorithms: Bagged RegressionTrees (BG), Random Forest Regression (RF), Boosted Regression Trees (BRT), LinearRegression (LR), Linear Support Vector Machine (L-SVM), Multi-Layer Perceptron Re-gressor (MLPR). The model with the best 5-fold crossvalidation scores was Random For-est, closely followed by Boosted Regression Trees. A robustness test, using 5 previouslyunseen scenarios, revealed that the Boosted Regression Trees model was the most robust.The radar position analysis showed that 6 sensors together with the MLPR model gavethe best RMSE scores.In conclusion, the models performed well on this type of system which shows thatthey might be a competitive alternative to load cell based systems.

Dans l'industrie de fabrication mécanique et notamment pour l'utilisation des centres d'usinage haute vitesse, la connaissance des propriétés dynamiques du système broche-outil-pièce en opération est d'une grande importance. L'accroissement des performances des machines-outils et des outils de coupe a œuvré au développement de ce procédé compétitif. D'innombrables travaux ont été menés pour accroître les performances et les remarquables avancées dans les matériaux, les revêtements des outils coupants et les lubrifiants ont permis d'accroître considérablement les vitesses de coupe tout en améliorant la qualité de la surface usinée. Cependant, l'utilisation rationnelle de cette technologie est encore fortement pénalisée par les lacunes dans la connaissance de la coupe, que ce soit au niveau microscopique des interactions fines entre l'outil et la matière coupée, aussi bien qu'au niveau macroscopique intégrant le comportement de la cellule élémentaire d'usinage, si bien que le comportement dynamique en coupe garde encore une grande part de questionnement et exige de l'utilisateur un bon niveau de savoir-faire et parfois d'empirisme pour exploiter au mieux les capacités des moyens de production. Le fonctionnement des machines d'usinage engendre des vibrations qui sont souvent la cause des dysfonctionnements et accélère l'usure des composantes mécaniques (roulements) et outils. Ces vibrations sont une image des efforts internes des systèmes, d'où l'intérêt d'analyser les grandeurs mécaniques vibratoires telle que la vitesse ou l'accélération vibratoire. Ces outils sont indispensables pour une maintenance moderne dont l'objectif est de réduire les coûts liés aux pannes

碩士
亞洲大學
資訊工程學系碩士在職專班
106
In this thesis, a multiple layer perceptron (MLP) and a recurrent neural network (RNN) are proposed for investigation and comparison in the sense of learning performances. The proposed RNN is a local feedback network and is composed by a state space realization. By using back propagation learning algorithm, the learning performances of the proposed RNN is better than that of the conven-tional MLP. Finally, numerical examples are performed to illustrate the effec-tiveness of the proposed approach.