No description available.

Classification tasks are an integral part of science, industry, medicine, and business; being such a pervasive technique, its smallest improvement is valuable. Artificial Neural Network (ANN) is one of the strongest techniques used in many disciplines for classification. The ANN technique suffers from drawbacks such as intransparency in spite of its high prediction power. In this dissertation, motivated by learning styles in human brains, ANN’s shortcomings are assuaged and its learning power is improved. Self-Organizing Map (SOM), an ANN variation which has strong unsupervised power, and Feedforward ANN, traditionally used for classification tasks, are hybridized to solidify their benefits and help remove their limitations. These benefits are in two directions: enhancing ANN’s learning power, and improving decision-making. First, the proposed method, named Self-Organizing Error-Driven (SOED) Artificial Neural Network (ANN), shows significant improvements in comparison with usual ANNs. We show SOED is a more accurate, more reliable, and more transparent technique through experimentation with five famous benchmark datasets. Second, the hybridization creates space for inclusion of decision-making goals at the level of ANN’s learning. This gives the classifier the opportunity to handle the inconclusiveness of the data smarter and in the direction of decision-making goals. Through three case studies, naming 1) churn decision analytics, 2) breast cancer diagnosis, and 3) quality control decision making through thermal monitoring of additive manufacturing processes, this novel and cost-sensitive aspect of SOED has been explored and lead to much quantified improvement in decision-making.

The Fennoscandian Shield as a part of a large Precambrian basement area is located in northern Europe and hosts economically important mineral deposits including base metals and precious metals. Regional geophysical data such as potential field and magnetotelluric data in combination with other geoscientific data contain information of importance for an understanding of the crustal and upper mantle structure. Knowledge about regional-scale structures is important for an optimized search for mineralisation. In order to investigate in more detail the spatial distribution of regional electrically conductive structures and near-surface mineral deposits, complementary magnetotelluric measurements have been done within the Precambrian Shield in the north-eastern part of the Norrbotten ore province. The potential field data provided by the Geological Survey of Sweden have been included in the current study. Processing of magnetotelluric data was performed using a robust multi-remote reference technique. The dimensionality analysis of the phase tensors indicates complex 3D structures in the area. A 3D crustal model of the electrical conductivity structure was derived based on 3D inversion of the data using the ModEM code. The final inversion 3D resistivity model revealed the presence of strong crustal conductors with the conductance of more than 3000 S at depth of tens of kilometres within a generally resistive crust. A significant part of the middle crust conductors is elongated in directions that coincide with major ductile deformation zones that have been mapped from airborne magnetic data and geological fieldwork. Some of these conductors have near-surface expression where they spatially correlate with the locations of known mineralisation. Processing and 3D inversion of the regional magnetic and gravity field data were performed, and the structural information derived from these data by using an open-source object-oriented package code written in Python called SimPEG. In this study, a new approach is proposed to extract and analyse the correlation between the modelled physical properties and for domain classification. For this, a neural net Self-Organizing Map procedure (SOM) was used for data reduction and simplification. The input data to the SOM analysis contain resistivity, magnetic susceptibility, and density model values for some selected depth levels. The domain classification is discussed with respect to geological boundaries and composition. The classification is furthermore applied for prediction of favourable areas for mineralisation. Based on visual inspection of processed regional gravity and magnetic field data and a SOM analysis performed on higher-order derivatives of the magnetic data, an interpretation of a sinistral fault with 52 km offset is proposed. The fault is oriented N10E and can be traced 250 km from Karesuando at the Swedish-Finish border southwards to the Archaean-Proterozoic boundary marked by the Luleå-Jokkmokk Zone.

Census operations are very important events in the history of a nation. These operations cover every bit of land and property of the country and its citizens. Census data is also known as demographic data providing valuable information to various users, particularly planners to know the trends in the key areas. Since 2006, Turkey aims to produce this census data not as &ldquo / de-facto&rdquo / (static) but as &ldquo / de-jure&rdquo / (real-time) by the new Address Based Register Information System (ABPRS). Besides, by this new register based census, personal information is matched with their address information and censuses gained a spatial dimension. Data obtained from this kind of a system can be a great input for the creation of &ldquo / small statistical areas (SSAs)&rdquo / which can compose of street blocks or any other small geographical unit to which social data can be referenced and to establish a complete census geography for Turkey. Because, statistics on large administrative units are only necessary for policy design only at an extremely abstracted level of analysis which is far from &quot / real&quot / problems as experienced by individuals. In this thesis, it is aimed to employ some spatial clustering and districting methodologies to automatically produce SSAs which are basically built upon the ABPRS data that is geo-referenced with the aid of geographical information systems (GIS) and thus help improving the census geography concept which is limited with only higher level administrative boundaries in Turkey. In order to have a clear idea of what strategy to choose for its realization, small area identification criteria and methodologies are searched by looking into the United Nations&rsquo / recommendations and by taking some national and international applications into consideration. In addition, spatial clustering methods are examined for obtaining SSAs which fulfills these criteria in an automated fashion. Simulated annealing on k-means clustering, only k-means clustering and simulated annealing on k-means clustering of Self-Organizing Map (SOM) unified distances are deemed as suitable methods. Then these methods are implemented on parcel and block datasets having either raw data or socio-economic status (SES) indices in nine neighborhoods of Ke&ccedil / i&ouml / ren whose graphical and non-graphical raw data are manipulated, geo-referenced and combined in common basemaps. Consequently, simulated annealing refinement on k-means clustering of SOM u-distances is selected as the optimum method for constructing SSAs for all datasets after making a comparative quality assessment study which allows us to see how much each method obeyed the basic criteria of small area identification while creating SSA layers.

In today's society, companies are trying to find ways to utilize all the data they have, which considers valuable information and insights to make better decisions. This includes data used to keeping track of timber that flows between forest and industry. The growth of Artificial Intelligence (AI) and Machine Learning (ML) has enabled the development of ML modes to automate the measurements of timber on timber trucks, based on images. However, to improve the results there is a need to be able to get information from unlabeled images in order to decide weather and lighting conditions. The objective of this study is to perform an extensive for classifying unlabeled images in the categories, daylight, darkness, and snow on the load. A comparative study between partitional clustering and competitive learning is conducted to investigate which method gives the best results in terms of different clustering performance metrics. It also examines how dimensionality reduction affects the outcome. The algorithms K-means and Kohonen Self-Organizing Map (SOM) are selected for the clustering. Each model is investigated according to the number of clusters, size of dataset, clustering time, clustering performance, and manual samples from each cluster. The results indicate a noticeable clustering performance discrepancy between the algorithms concerning the number of clusters, dataset size, and manual samples. The use of dimensionality reduction led to shorter clustering time but slightly worse clustering performance. The evaluation results further show that the clustering time of Kohonen SOM is significantly higher than that of K-means.

This research created a new theoretical Soft Computing (SC) hybridized network intrusion detection diagnostic system including complex hybridization of a 3D full color Self-Organizing Map (SOM), Artificial Immune System Danger Theory (AISDT), and a Fuzzy Inference System (FIS). This SOM+ diagnostic archetype includes newly defined intrusion types to facilitate diagnostic analysis, a descriptive computational model, and an Invisible Mobile Network Bridge (IMNB) to collect data, while maintaining compatibility with traditional packet analysis. This system is modular, multitaskable, scalable, intuitive, adaptable to quickly changing scenarios, and uses relatively few resources.

Made available in DSpace on 2016-06-02T20:06:03Z (GMT). No. of bitstreams: 1 2596.pdf: 1631367 bytes, checksum: 90f2d842a935f1dd50bf587a33f6a2cb (MD5) Previous issue date: 2009-02-16 / The clustering techniques have frequently been used in literature to the analyse data in several fields of application. The main objective of this work is to study such techniques. There is a large number of clustering techniques in literature. In this work we concentrate on Self Organizing Map (SOM), k-means, k-medoids and Expectation- Maximization (EM) algorithms. These algorithms are applied to gene expression data. The analisys of gene expression, among other possibilities, identifies which genes are differently expressed in synthesis of proteins associated to normal and sick tissues. The purpose is to do a comparing of these metods, sticking out advantages and disadvantages of such. The metods were tested for simulation and after we apply them to a real data set. / As técnicas de agrupamento (clustering) vêm sendo utilizadas com freqüência na literatura para a solução de vários problemas de aplicações práticas em diversas áreas do conhecimento. O principal objetivo deste trabalho é estudar tais técnicas. Mais especificamente, estudamos os algoritmos Self Organizing Map (SOM), k-means, k-medoids, Expectation-Maximization (EM). Estes algoritmos foram aplicados a dados de expressão gênica. A análise de expressão gênica visa, entre outras possibilidades, a identificação de quais genes estão diferentemente expressos na sintetização de proteínas associados a tecidos normais e doentes. O objetivo deste trabalho é comparar estes métodos no que se refere à eficiência dos mesmos na identificação de grupos de elementos similares, ressaltando vantagens e desvantagens de cada um. Os métodos foram testados por simulação e depois aplicamos as metodologias a um conjunto de dados reais.