Often there is a need to establish and understand the structure of multidimensional data: their clusters, outliers, similarity and dissimilarity. One of solution ways is a dimensionality reduction and visualization of the data. If a huge datasets is analyzed, it is purposeful to reduce the number of the data items before visualization. The area of research is reduction of the number of the data analyzed and mapping the data in a plane. In the dissertation, vector quantization methods, based on artificial neural networks, and visualization methods, based on a dimensionality reduction, have been investigated. The consecutive and integrated combinations of neural gas and multidimensional scaling have been proposed here as an alternative to combinations of self-organizing maps and multidimensional scaling. The visualization quality is estimated by König’s topology preservation measure, Spearman’s rho and MDS error. The measures allow us to evaluate the similarity preservation quantitatively after a transformation of multidimensional data into a lower dimension space. The ways of selecting the initial values of two-dimensional vectors in the consecutive combination and the first training block of the integrated combination have been proposed and the ways of assigning the initial values of two-dimensional vectors in all the training blocks, except the first one, of the integrated combination have been developed. The dependence of the quantization error on the values of training... [to full text] / Dažnai iškyla būtinybė nustatyti ir giliau pažinti daugiamačių duomenų struktūrą: susidariusius klasterius, itin išsiskiriančius objektus, objektų tarpusavio panašumą ir skirtingumą. Vienas iš sprendimų būdų – duomenų dimensijos mažinimas ir jų vizualizavimas. Kai analizuojamos didelės duomenų aibės, tikslinga prieš vizualizavimą sumažinti ne tik dimensiją, bet ir duomenų skaičių. Šio darbo tyrimų sritis yra daugiamačių duomenų skaičiaus mažinimas ir duomenų atvaizdavimas plokštumoje. Disertacijoje nagrinėjami dirbtiniais neuroniniais tinklais grindžiami vektorių kvantavimo ir dimensijos mažinimu pagrįsti vizualizavimo metodai. Kaip alternatyva saviorganizuojančių neuroninių tinklų ir daugiamačių skalių junginiams, darbe pasiūlyti nuoseklus neuroninių dujų ir daugiamačių skalių junginys bei integruotas, atsižvelgiantis į neuroninių dujų metodo mokymosi eigą ir leidžiantis gauti tikslesnę daugiamačių vektorių projekciją plokštumoje. Junginiais gautų vaizdų kokybės vertinimui pasirinkti Konigo matas, Spirmano koeficientas bei MDS paklaida. Šie matai leidžia kiekybiškai įvertinti panašumų išlaikymą po daugiamačių duomenų transformavimo į mažesnės dimensijos erdvę. Taip pat pasiūlyti dvimačių vektorių pradinių koordinačių parinkimo būdai nuosekliame junginyje ir integruoto junginio pirmame mokymo bloke bei koordinačių reikšmių priskyrimo būdai integruoto junginio kituose mokymo blokuose. Eksperimentiškai nustatyta kvantavimo paklaidos priklausomybė nuo neuroninių dujų tinklo... [toliau žr. visą tekstą]

Dažnai iškyla būtinybė nustatyti ir giliau pažinti daugiamačių duomenų struktūrą: susidariusius klasterius, itin išsiskiriančius objektus, objektų tarpusavio panašumą ir skirtingumą. Vienas iš sprendimų būdų – duomenų dimensijos mažinimas ir jų vizualizavimas. Kai analizuojamos didelės duomenų aibės, tikslinga prieš vizualizavimą sumažinti ne tik dimensiją, bet ir duomenų skaičių. Šio darbo tyrimų sritis yra daugiamačių duomenų skaičiaus mažinimas ir duomenų atvaizdavimas plokštumoje. Disertacijoje nagrinėjami dirbtiniais neuroniniais tinklais grindžiami vektorių kvantavimo ir dimensijos mažinimu pagrįsti vizualizavimo metodai. Kaip alternatyva saviorganizuojančių neuroninių tinklų ir daugiamačių skalių junginiams, darbe pasiūlyti nuoseklus neuroninių dujų ir daugiamačių skalių junginys bei integruotas, atsižvelgiantis į neuroninių dujų metodo mokymosi eigą ir leidžiantis gauti tikslesnę daugiamačių vektorių projekciją plokštumoje. Junginiais gautų vaizdų kokybės vertinimui pasirinkti Konigo matas, Spirmano koeficientas bei MDS paklaida. Šie matai leidžia kiekybiškai įvertinti panašumų išlaikymą po daugiamačių duomenų transformavimo į mažesnės dimensijos erdvę. Taip pat pasiūlyti dvimačių vektorių pradinių koordinačių parinkimo būdai nuosekliame junginyje ir integruoto junginio pirmame mokymo bloke bei koordinačių reikšmių priskyrimo būdai integruoto junginio kituose mokymo blokuose. Eksperimentiškai nustatyta kvantavimo paklaidos priklausomybė nuo neuroninių dujų tinklo... [toliau žr. visą tekstą] / Often there is a need to establish and understand the structure of multidimensional data: their clusters, outliers, similarity and dissimilarity. One of solution ways is a dimensionality reduction and visualization of the data. If a huge datasets is analyzed, it is purposeful to reduce the number of the data items before visualization. The area of research is reduction of the number of the data analyzed and mapping the data in a plane. In the dissertation, vector quantization methods, based on artificial neural networks, and visualization methods, based on a dimensionality reduction, have been investigated. The consecutive and integrated combinations of neural gas and multidimensional scaling have been proposed here as an alternative to combinations of self-organizing maps and multidimensional scaling. The visualization quality is estimated by König’s topology preservation measure, Spearman’s rho and MDS error. The measures allow us to evaluate the similarity preservation quantitatively after a transformation of multidimensional data into a lower dimension space. The ways of selecting the initial values of two-dimensional vectors in the consecutive combination and the first training block of the integrated combination have been proposed and the ways of assigning the initial values of two-dimensional vectors in all the training blocks, except the first one, of the integrated combination have been developed. The dependence of the quantization error on the values of training... [to full text]

Machine learning (ML) methods have been applied to the analysis of a range of biological systems. This thesis evaluates the application of these methods to the problem domain of skin permeability. ML methods offer great potential in both predictive ability and their ability to provide mechanistic insight to, in this case, the phenomena of skin permeation. Historically, refining mathematical models used to predict percutaneous drug absorption has been thought of as a key factor in this field. Quantitative Structure-Activity Relationships (QSARs) models are used extensively for this purpose. However, advanced ML methods successfully outperform the traditional linear QSAR models. In this thesis, the application of ML methods to percutaneous absorption are investigated and evaluated. The major approach used in this thesis is Gaussian process (GP) regression method. This research seeks to enhance the prediction performance by using local non-linear models obtained from applying clustering algorithms. In addition, to increase the model's quality, a kernel is generated based on both numerical chemical variables and categorical experimental descriptors. Monte Carlo algorithm is also employed to generate reliable models from variable data which is inevitable in biological experiments. The datasets used for this study are small and it may raise the over-fitting/under-fitting problem. In this research I attempt to find optimal values of skin permeability using GP optimisation algorithms within small datasets. Although these methods are applied here to the field of percutaneous absorption, it may be applied more broadly to any biological system.

The thesis deals with the analysis of the clustering and mapping techniques derived from the principles of the neural and statistical learning and growth theory. The selected branch of the unsupervised bio-inspired prototype-based models is described in terms of the proposed logical framework, which highlights the continuity of these methods with the classical "pure" statistical methods. Moreover, as those methods are broadly understood as the "black boxes" with the unpredictable, unclear and especially hidden behavior, the examples of the spatial computational and organizational patterns in two-dimensional space are provided. Additionally, this thesis presents the novel concept based on the non-linear, non-Gaussian Gompertzian function, which has been widely used as the universal law in dynamic growth models, but has not yet been applied in the field of computational intelligence. The essence of Gompertzian dynamics is mathematically analyzed and a novel simple version of the Gompertzian normalized function is introduced. Furthermore, the function was modified for use in the field of artificial intelligence and neural implications were discussed. Additionally, the novel neural networks were proposed and derived from the topological principles of Kohonen's self-organizing maps and neural gas algorithm. The Gompertzian networks were evaluated using several indicators for various generated and real datasets. Gompertzian neural networks with fixed grid and integrated neighborhood ranking principle generally show lower mean squared errors than the original SOM algorithms. Likewise, the unconstrained Gompertzian networks have demonstrated overall low error rates comparable to neural gas algorithm, more stable and lower error solutions than the k- means sequential procedure. In conclusion, the Gompertzian function has been shown to be a viable concept and an effective computational tool for multidimensional data analysis.

Sowohl im Zusammenhang mit der durch den Menschen verursachten Erzeugung von Daten, als auch durch maschinell herbeigeführte Kommunikationsaufwände besteht der Wunsch, aus diesen Daten unter verschiedenen Gesichtspunkten Informationen zu gewinnen. Außerdem wächst die Menge der auszuwertenden Daten stetig. Als technische Grundlage zur Erfassung und Verarbeitung dieser Datenaufkommen werden skalierbare Systemkonzepte genutzt, die Datenwachstum durch inhärente Skalierbarkeit begegnen. Unter analytischen Gesichtspunkten handelt es sich um BigData-Systemkonzepte, deren technische Basis häufig durch nichtrelationale NoSQL-Systeme gebildet wird. In dieser Arbeit werden auf Basis der Growing Neural Gas, einem künstlichen Neuronalen Netz, zwei verteilte Algorithmen zum Erlernen inhaltlicher Merkmale für die Datenorganisation mit einem inhaltsorientierten Index betrachtet. Des Weiteren wird der inhaltsorientierte Index ICIx für Column Family Stores adaptiert, um die Informationsgewinnung in verteilten, dezentralen Systemen auch nach Merkmalen inhaltlicher Ähnlichkeit zu ermöglichen. Die durchgeführten Versuche zeigen, dass die verteilten Varianten des Growing Neural Gas Daten ohne Qualitätsverlust repräsentieren können. Außerdem ergibt die Anwendung der durch dieses künstliche Neuronale Netz organisierten Daten, dass die betrachtete Indexstruktur auch in verteilten, dezentralen Systemen den Datenzugriff gegenüber vergleichbaren Indizes beschleunigt. / Both in the context of man-made data generation and machine-generated communication efforts, there is a desire to extract information from these data from a variety of perspectives. In addition, the amount of data to be evaluated steadily increases. As a technical basis for the collection and processing of this data volume, scalable system concepts are used that counteract data growth through inherent scalability. From an analytical point of view, these are BigData system concepts whose technical basis is often formed by non-relational NoSQL systems. In this work, based on the Growing Neural Gas, an artificial neural network, two distributed algorithms for the acquisition of content characteristics for data organization with a content-oriented index are considered. Furthermore, the content-oriented index ICIx for Column Family Stores will be adapted to enable information gathering in distributed, decentralized systems, even in terms of similarity in content. The experiments show that the distributed variants of Growing Neural Gas can represent data without loss of quality. In addition, the application of the data organized by this artificial neural network results in the fact that the index structure in question also accelerates the data access in comparison to comparable indices in distributed, decentralized systems.

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.

Made available in DSpace on 2014-12-17T14:25:22Z (GMT). No. of bitstreams: 1 MarcoVMN_TESE.pdf: 3982733 bytes, checksum: 381ae79721c75a30e3373fe4487512c7 (MD5) Previous issue date: 2014-02-05 / In this paper artificial neural network (ANN) based on supervised and unsupervised algorithms were investigated for use in the study of rheological parameters of solid pharmaceutical excipients, in order to develop computational tools for manufacturing solid dosage forms. Among four supervised neural networks investigated, the best learning performance was achieved by a feedfoward multilayer perceptron whose architectures was composed by eight neurons in the input layer, sixteen neurons in the hidden layer and one neuron in the output layer. Learning and predictive performance relative to repose angle was poor while to Carr index and Hausner ratio (CI and HR, respectively) showed very good fitting capacity and learning, therefore HR and CI were considered suitable descriptors for the next stage of development of supervised ANNs. Clustering capacity was evaluated for five unsupervised strategies. Network based on purely unsupervised competitive strategies, classic "Winner-Take-All", "Frequency-Sensitive Competitive Learning" and "Rival-Penalize Competitive Learning" (WTA, FSCL and RPCL, respectively) were able to perform clustering from database, however this classification was very poor, showing severe classification errors by grouping data with conflicting properties into the same cluster or even the same neuron. On the other hand it could not be established what was the criteria adopted by the neural network for those clustering. Self-Organizing Maps (SOM) and Neural Gas (NG) networks showed better clustering capacity. Both have recognized the two major groupings of data corresponding to lactose (LAC) and cellulose (CEL). However, SOM showed some errors in classify data from minority excipients, magnesium stearate (EMG) , talc (TLC) and attapulgite (ATP). NG network in turn performed a very consistent classification of data and solve the misclassification of SOM, being the most appropriate network for classifying data of the study. The use of NG network in pharmaceutical technology was still unpublished. NG therefore has great potential for use in the development of software for use in automated classification systems of pharmaceutical powders and as a new tool for mining and clustering data in drug development / Neste trabalho foram estudadas redes neurais artificiais (RNAs) baseadas em algoritmos supervisionados e n?o supervisionados para emprego no estudo de par?metros reol?gicos de excipientes farmac?uticos s?lidos, visando desenvolver ferramentas computacionais para o desenvolvimento de formas farmac?uticas s?lidas. Foram estudadas quatro redes neurais artificiais supervisionadas e cinco n?o supervisionadas. Todas as RNAs supervisionadas foram baseadas em arquitetura de rede perceptron multicamada alimentada ? frente (feedfoward MLP). Das cinco RNAs n?o supervisionadas, tr?s foram baseadas em estrat?gias puramente competitivas, "Winner-Take- All" cl?ssica, "Frequency-Sensitive Competitive Learning" e "Rival-Penalize Competitive Learning" (WTA, FSCL e RPCL, respectivamente). As outras duas redes n?o supervisionadas, Self- Organizing Map e Neural Gas (SOM e NG) foram baseadas estrat?gias competitivo-cooperativas. O emprego da rede NG em tecnologia farmac?utica ? ainda in?dito e pretende-se avaliar seu potencial de emprego como nova ferramenta de minera??o e classifica??o de dados no desenvolvimento de medicamentos. Entre os prot?tipos de RNAs supervisionadas o melhor desempenho foi conseguido com uma rede de arquitetura composta por 8 neur?nios de entrada, 16 neur?nios escondidos e 1 neur?nio de sa?da. O aprendizado de rede e a capacidade preditiva em rela??o ao ?ngulo de repouso (α) foi deficiente, e muito boa para o ?ndice de Carr e fator de Hausner (IC, FH). Por esse motivo IC e FH foram considerados bons descritores para uma pr?xima etapa de desenvolvimento das RNAs supervisionadas. As redes, WTA, RPCL e FSCL, foram capazes de estabelecer agrupamentos dentro da massa de dados, por?m apresentaram erros grosseiros de classifica??o caracterizados pelo agrupamento de dados com propriedades conflitantes, e tamb?m n?o foi poss?vel estabelecer qual o crit?rio de classifica??o adotado. Tais resultados demonstraram a inviabilidade pr?tica dessas redes para os sistemas estudados sob nossas condi??es experimentais. As redes SOM e NG mostraram uma capacidade de classifica??o muito superior ?s RNAs puramente competitivas. Ambas as redes reconheceram os dois agrupamentos principais de dados correspondentes ? lactose (LAC) e celulose (CEL). Entretanto a rede som demonstrou defici?ncia na classifica??o de dados relativos aos excipientes minorit?rios, estearato de magn?sio (EMG), talco (TLC) e atapulgita (ATP). A rede NG, por sua vez, estabeleceu uma classifica??o muito consistente dos dados e resolveu o erro de classifica??o apresentados pela rede SOM, mostrando-se a rede mais adequada para a classifica??o dos dado do presente estudo. A rede Neural Gas, portanto, mostrou- se promissora para o desenvolvimento de softwares para uso na classifica??o automatizada de sistemas pulverulentos farmac?uticos