MACHINE VISION FOR AUTOMATICVISUAL INSPECTION OF WOODENRAILWAY SLEEPERS USING UNSUPERVISED NEURAL NETWORKS

The motivation for this thesis work is the need for improving reliability of equipment and quality of service to railway passengers as well as a requirement for cost-effective and efficient condition maintenance management for rail transportation. This thesis work develops a fusion of various machine vision analysis methods to achieve high performance in automation of wooden rail track inspection.The condition monitoring in rail transport is done manually by a human operator where people rely on inference systems and assumptions to develop conclusions. The use of conditional monitoring allows maintenance to be scheduled, or other actions to be taken to avoid the consequences of failure, before the failure occurs. Manual or automated condition monitoring of materials in fields of public transportation like railway, aerial navigation, traffic safety, etc, where safety is of prior importance needs non-destructive testing (NDT).In general, wooden railway sleeper inspection is done manually by a human operator, by moving along the rail sleeper and gathering information by visual and sound analysis for examining the presence of cracks. Human inspectors working on lines visually inspect wooden rails to judge the quality of rail sleeper. In this project work the machine vision system is developed based on the manual visual analysis system, which uses digital cameras and image processing software to perform similar manual inspections. As the manual inspection requires much effort and is expected to be error prone sometimes and also appears difficult to discriminate even for a human operator by the frequent changes in inspected material. The machine vision system developed classifies the condition of material by examining individual pixels of images, processing them and attempting to develop conclusions with the assistance of knowledge bases and features.A pattern recognition approach is developed based on the methodological knowledge from manual procedure. The pattern recognition approach for this thesis work was developed and achieved by a non destructive testing method to identify the flaws in manually done condition monitoring of sleepers.In this method, a test vehicle is designed to capture sleeper images similar to visual inspection by human operator and the raw data for pattern recognition approach is provided from the captured images of the wooden sleepers. The data from the NDT method were further processed and appropriate features were extracted.The collection of data by the NDT method is to achieve high accuracy in reliable classification results. A key idea is to use the non supervised classifier based on the features extracted from the method to discriminate the condition of wooden sleepers in to either good or bad. Self organising map is used as classifier for the wooden sleeper classification.In order to achieve greater integration, the data collected by the machine vision system was made to interface with one another by a strategy called fusion. Data fusion was looked in at two different levels namely sensor-level fusion, feature- level fusion. As the goal was to reduce the accuracy of the human error on the rail sleeper classification as good or bad the results obtained by the feature-level fusion compared to that of the results of actual classification were satisfactory.

Simultaneous prediction of symptom severity and cause in data from a test battery for Parkinson patients, using machine learning methods

The main purpose of this thesis project is to prediction of symptom severity and cause in data from test battery of the Parkinson’s disease patient, which is based on data mining. The collection of the data is from test battery on a hand in computer. We use the Chi-Square method and check which variables are important and which are not important. Then we apply different data mining techniques on our normalize data and check which technique or method gives good results.The implementation of this thesis is in WEKA. We normalize our data and then apply different methods on this data. The methods which we used are Naïve Bayes, CART and KNN. We draw the Bland Altman and Spearman’s Correlation for checking the final results and prediction of data. The Bland Altman tells how the percentage of our confident level in this data is correct and Spearman’s Correlation tells us our relationship is strong. On the basis of results and analysis we see all three methods give nearly same results. But if we see our CART (J48 Decision Tree) it gives good result of under predicted and over predicted values that’s lies between -2 to +2. The correlation between the Actual and Predicted values is 0,794in CART. Cause gives the better percentage classification result then disability because it can use two classes.

Microstructural, Mechanical and Tribological Characterisation of CVD and PVD Coatings for Metal Cutting Applications

The present thesis focuses on characterisation of microstructure and the resulting mechanical and tribological properties of CVD and PVD coatings used in metal cutting applications. These thin and hard coatings are designed to improve the tribological performance of cutting tools which in metal cutting operations may result in improved cutting performance, lower energy consumption, lower production costs and lower impact on the environment.  In order to increase the understanding of the tribological behaviour of the coating systems a number of friction and wear tests have been performed and evaluated by post-test microscopy and surface analysis. Much of the work has focused on coating cohesive and adhesive strength, surface fatigue resistance, abrasive wear resistance and friction and wear behaviour under sliding contact and metal cutting conditions. The results show that the CVD deposition of accurate crystallographic phases, e.g. α-Al2O3 rather than κ-Al2O3, textures and multilayer structures can increase the wear resistance of Al2O3. However, the characteristics of the interfaces, e.g. topography as well as interfacial porosity, have a strong impact on coating adhesion and consequently on the resulting properties.  Through the deposition of well designed bonding and template layer structures the above problems may be eliminated. Also, the presence of macro-particles in PVD coatings may have a significant impact on the interfacial adhesive strength, increasing the tendency to coating spalling and lowering the surface fatigue resistance, as well as increasing the friction in sliding contacts. Finally, the CVD-Al2O3 coating topography influences the contact conditions in sliding as well as in metal cutting. In summary, the work illuminates the importance of understanding the relationships between deposition process parameters, composition and microstructure, resulting properties and tribological performance of CVD and PVD coatings and how this knowledge can be used to develop the coating materials of tomorrow.

Machine Translation and the Disruption of Foreign Language Learning Activities

This study examines the question of how language teachers in a highly technologyfriendly university environment view machine translation and the implications that this has for the personal learning environments of students. It brings an activity-theory perspective to the question, examining the ways that the introduction of new tools can disrupt the relationship between different elements in an activity system. This perspective opens up for an investigation of the ways that new tools have the potential to fundamentally alter traditional learning activities. In questionnaires and group discussions, respondents showed general agreement that although use of machine translation by students could be considered cheating, students are bound to use it anyway, and suggested that teachers focus on the kinds of skills students would need when using machine translation and design assignments and exams to practice and assess these skills. The results of the empirical study are used to reflect upon questions of what the roles of teachers and students are in a context where many of the skills that a person needs to be able to interact in a foreign language increasingly can be outsourced to laptops and smartphones.

Wear of coated and uncoated PCBN cutting tool used in turning and milling

This licentiate thesis has the main focus on evaluation of the wear of coated and uncoated polycrystalline cubic boron nitride cutting tool used in cutting operations against hardened steel. And to exam the surface finish and integrity of the work material used. Harder work material, higher cutting speed and cost reductions result in the development of harder and more wear resistance cutting tools. Although PCBN cutting tools have been used in over 30 years, little work have been done on PVD coated PCBN cutting tools. Therefore hard turning and hard milling experiments with PVD coated and uncoated cutting tools have been performed and evaluated. The coatings used in the present study are TiSiN and TiAlN. The wear scar and surface integrity have been examined with help of several different characterization techniques, for example scanning electron microscopy and Auger electron spectroscopy.   The results showed that the PCBN cutting tools used displayed crater wear, flank wear and edge micro chipping. While the influence of the coating on the crater and flank wear was very small and the coating showed a high tendency to spalling. Scratch testing of coated PCBN showed that, the TiAlN coating resulted in major adhesive fractures. This displays the importance of understanding the effect of different types of lapping/grinding processes in the pre-treatment of hard and super hard substrate materials and the amount and type of damage that they can create. For the cutting tools used in turning, patches of a adhered layer, mainly consisting of FexOy were shown at both the crater and flank. And for the cutting tools used in milling a tribofilm consisting of SixOy covered the crater. A combination of tribochemical reactions, adhesive wear and mild abrasive wear is believed to control the flank and crater wear of the PCBN cutting tools. On a microscopic scale the difference phases of the PCBN cutting tool used in turning showed different wear characteristics. The machined surface of the work material showed a smooth surface with a Ra-value in the range of 100-200 nm for the turned surface and 100-150 nm for the milled surface. With increasing crater and flank wear in combination with edge chipping the machined surface becomes rougher and showed a higher Ra-value. For the cutting tools used in milling the tendency to micro edge chipping was significant higher when milling the tools steels showing a higher hard phase content and a lower heat conductivity resulting in higher mechanical and thermal stresses at the cutting edge.

Machine translation and the disruption of foreign language learning activities

This study examines the question of how language teachers in a highly technology-friendly university environment view machine translation and the implications that this has for the personal learning environments of students. It brings an activity-theory perspective to the question, examining the ways that the introduction of new tools can disrupt the relationship between different elements in an activity system. This perspective opens up for an investigation of the ways that new tools have the potential to fundamentally alter traditional learning activities. In questionnaires and group discussions, respondents showed general agreement that although use of machine translation by students could be considered cheating, students are bound to use it anyway, and suggested that teachers focus on the kinds of skills students would need when using machine translation and design assignments and exams to practice and assess these skills. The results of the empirical study are used to reflect upon questions of what the roles of teachers and students are in a context where many of the skills that a person needs to be able to interact in a foreign language increasingly can be outsourced to laptops and smartphones.

Machine Learning Algorithms in Heavy Process Manufacturing

In a global economy, manufacturers mainly compete with cost efficiency of production, as the price of raw materials are similar worldwide. Heavy industry has two big issues to deal with. On the one hand there is lots of data which needs to be analyzed in an effective manner, and on the other hand making big improvements via investments in cooperate structure or new machinery is neither economically nor physically viable. Machine learning offers a promising way for manufacturers to address both these problems as they are in an excellent position to employ learning techniques with their massive resource of historical production data. However, choosing modelling a strategy in this setting is far from trivial and this is the objective of this article. The article investigates characteristics of the most popular classifiers used in industry today. Support Vector Machines, Multilayer Perceptron, Decision Trees, Random Forests, and the meta-algorithms Bagging and Boosting are mainly investigated in this work. Lessons from real-world implementations of these learners are also provided together with future directions when different learners are expected to perform well. The importance of feature selection and relevant selection methods in an industrial setting are further investigated. Performance metrics have also been discussed for the sake of completion.

Machine learning and small robot navigation

Developing successful navigation and mapping strategies is an essential part of autonomous robot research. However, hardware limitations often make for inaccurate systems. This project serves to investigate efficient alternatives to mapping an environment, by first creating a mobile robot, and then applying machine learning to the robot and controlling systems to increase the robustness of the robot system. My mapping system consists of a semi-autonomous robot drone in communication with a stationary Linux computer system. There are learning systems running on both the robot and the more powerful Linux system. The first stage of this project was devoted to designing and building an inexpensive robot. Utilizing my prior experience from independent studies in robotics, I designed a small mobile robot that was well suited for simple navigation and mapping research. When the major components of the robot base were designed, I began to implement my design. This involved physically constructing the base of the robot, as well as researching and acquiring components such as sensors. Implementing the more complex sensors became a time-consuming task, involving much research and assistance from a variety of sources. A concurrent stage of the project involved researching and experimenting with different types of machine learning systems. I finally settled on using neural networks as the machine learning system to incorporate into my project. Neural nets can be thought of as a structure of interconnected nodes, through which information filters. The type of neural net that I chose to use is a type that requires a known set of data that serves to train the net to produce the desired output. Neural nets are particularly well suited for use with robotic systems as they can handle cases that lie at the extreme edges of the training set, such as may be produced by "noisy" sensor data. Through experimenting with available neural net code, I became familiar with the code and its function, and modified it to be more generic and reusable for multiple applications of neural nets.

Prediction Of Hydrological Models’ Uncertainty By A Committee Of Machine Learning-Models

This study presents an approach to combine uncertainties of the hydrological model outputs predicted from a number of machine learning models. The machine learning based uncertainty prediction approach is very useful for estimation of hydrological models' uncertainty in particular hydro-metrological situation in real-time application [1]. In this approach the hydrological model realizations from Monte Carlo simulations are used to build different machine learning uncertainty models to predict uncertainty (quantiles of pdf) of the a deterministic output from hydrological model . Uncertainty models are trained using antecedent precipitation and streamflows as inputs. The trained models are then employed to predict the model output uncertainty which is specific for the new input data. We used three machine learning models namely artificial neural networks, model tree, locally weighted regression to predict output uncertainties. These three models produce similar verification results, which can be improved by merging their outputs dynamically. We propose an approach to form a committee of the three models to combine their outputs. The approach is applied to estimate uncertainty of streamflows simulation from a conceptual hydrological model in the Brue catchment in UK and the Bagmati catchment in Nepal. The verification results show that merged output is better than an individual model output. [1] D. L. Shrestha, N. Kayastha, and D. P. Solomatine, and R. Price. Encapsulation of parameteric uncertainty statistics by various predictive machine learning models: MLUE method, Journal of Hydroinformatic, in press, 2013.

Sexual blinging of women : Alice Walker's african character tashi and issue of female genital cutting

This thesis provides a reading of the different forms of representation that can be attributed to the character Tashi, the protagonist of the novel Possessing the Secret of Joy (1992), written by the African American writer Alice Walker. Before this work Tashi had already appeared in two previous novels by Walker, first, in The Color Purple (1982) and then, as a mention, in The Temple of My Familiar (1989). With Tashi, the author introduces the issue of female circumcision, a ritual Tashi submits herself to at the beginning of her adult life. The focus of observation lies in the ways in which the author’s anger is transformed into a means of creative representation. Walker uses her novel Possessing the Secret of Joy openly as a political instrument so that the expression “female mutilation” (term used by the author) receives ample attention from the media and critics in general. The aim of this investigation is to evaluate to what extent Walker’s social engagement contributes to the development of her work and to what extent it undermines it. For the analysis of the different issues related to “female genital cutting”, the term I use in this thesis, the works of feminist critics and writers such as Ellen Gruenbaum, Lightfoot-Klein, Nancy Hartsock, Linda Nicholson, Efrat Tseëlon and the Egyptian writer and doctor Nawal El Saadawi will be consulted. I hope that this thesis can contribute as an observation about Alice Walker’s use of her social engagement in the creation of her fictional world.

Cryptococcus haglerorum, sp nov., an anamorphic basidiomycetous yeast isolated from nests of the leaf-cutting ant Atta sexdens

A yeast strain (CBS 8902) was isolated from the nest of a leaf-cutting ant and was shown to be related to Cryptococcus humicola. Sequencing of the D1/D2 region of the 26S ribosomal DNA and physiological characterization revealed a separate taxonomic position. A novel species named Cryptococcus haglerorum is proposed to accommodate strain CBS 8902 that assimilates n-hexadecane and several benzene compounds. Physiological characteristics distinguishing the novel species from some other members of the C. humicola complex are presented. The phylogenetic relationship of these strains to species of the genus Trichosporon Behrend is discussed.