This paper deals with two subjects. First, we will show how support vector machine (SVM) regression problem can be solved as the maximum a posteriori (MAP) prediction in the Bayesian framework. The second part describes an approximation technique that is useful in performing calculations for SVMs based on the mean field algorithm which was originally proposed in Statistical Physics of disordere...

Support vector machines can be regarded as algorithms for compressing information about class membership into a few support vectors with clear geometric interpretation. It is tempting to use this compressed information to select the most relevant input features. In this paper we present a method for doing so and provide evidence that it selects high-quality feature sets at a fraction of the cos...

Thanks I want to thank all people who supported me during my work on this thesis, and Eva in particular. Especially I want to thank my supervisors Christian Igel for his continuous support and advice, and Hans Ulrich Simon for actually making this thesis possible.

ii Dedication iii Acknowledgments iv List of Tables vii List of Figures viii Chapter

In this paper we propose a methodology for intelligent analysis of genomic measurements. It is based on a sequential scheme of Support Vector Machines and it can be used for class prediction of multiclass genomic samples. The proposed methodology was evaluated using two lung cancer datasets. The results are comparable and in many cases higher to the accuracy of relevant methodologies that have ...

Article history: PVT properties are very imp Received 2 January 2007 Accepted 1 December 2008

Demand prediction is an important aspect in the development of any model for electricity planning. The analysis of customer load profile and load estimation is an important and useful area of electricity distribution technology and management. In our system we are trying to analyze particular household data so as to define its load profile based upon various factors and try to predict its futur...

In this contribution we present a classification method based on the evidence theory. The classification method is compared to the state of the art support vector machine classifier on an industrial radioscopic data and 3D CT data of aluminium castings as well as 3D ultrasonic data of composite materials. The reported experimental results reveal the robustness of the proposed method and its adv...

In this paper we introduce the use of semi-supervised support vector machines for rainfall estimation using images obtained from visible and infrared NOAA satellite channels. Two experiments were performed, one involving traditional SVM and other using semi-supervised SVM (SVM). The SVM approach outperforms SVM in our experiments, with can be seen as a good methodology for rainfall satellite es...

Support Vector Machines (SVM) classifiers are applied to problem in Molecular Biology recognizing mitochondrial sеquences in the human genome. We present the results obtained by SVM hard classification, using the Plat’s model and Modified SVM outputs (MSVMO) method, an alternative way of interpreting and modifying the outputs of the SVM classifiers.