|
|
Detection of Elliptical Particles in Atomic Force Microscopy Images
Sedlář, Jiří ; Zitová, Barbara ; Kopeček, Jaromír ; Todorciuc, T. ; Kratochvílová, Irena
In this paper we describe a method for detection and measurement of elliptical particles in atomic force microscopy (AFM) images. AFM imaging is used in physics to scan surfaces; the measured heights are represented by pixel values. Each sample in our project consisted of elliptical particles of principally the same size; the size could be characterized by the average length and width of a number of salient particles. The method we proposed is based on segmentation of undamaged particles and their approximation by ellipses; the major and minor axes provide robust estimates of the lengths and widths of the particles, respectively. The method is robust to distortions typical of AFM images. Its performance was demonstrated on images of pyrroles and compared with manual detection. Results show that the automatic method could be used in place of the time-consuming manual detection.
|
|
|
State estimation with missing data and bounded uncertainty
Pavelková, Lenka
The paper deals with two problems in the state estimation: (i) bounded uncertainty and (ii) missing measurement data. An algorithm for the state estimation of the discrete-time state space model whose uncertainties are bounded is proposed here. The algorithm also copes with situations when some data for identification are missing. The Bayesian approach is used and maximum a posteriori probability estimates are evaluated in the discrete time instants. The proposed estimation algorithm is applied to the estimation of vehicle position when incomplete data from global positioning system together with complete data from the inertial measurement unit are at disposal.
|
|
| |
|
|
Fast Dependency-Aware Feature Selection in Very-High-Dimensional Pattern Recognition Problems
Somol, Petr ; Grim, Jiří
The paper addresses the problem of making dependency-aware feature selection feasible in pattern recognition problems of very high dimensionality. The idea of individually best ranking is generalized to evaluate the contextual quality of each feature in a series of randomly generated feature subsets. Each random subset is evaluated by a criterion function of arbitrary choice (permitting functions of high complexity). Eventually, the novel dependency-aware feature rank is computed, expressing the average benefit of including a feature into feature subsets. The method is efficient and generalizes well especially in very-high-dimensional problems, where traditional context-aware feature selection methods fail due to prohibitive computational complexity or to over-fitting. The method is shown well capable of over-performing the commonly applied individual ranking which ignores important contextual information contained in data.
|
|
|
Introduction to Feature Selection Toolbox 3 – The C++ Library for Subset Search, Data Modeling and Classification
Somol, Petr ; Vácha, Pavel ; Mikeš, Stanislav ; Hora, Jan ; Pudil, Pavel ; Žid, Pavel
We introduce a new standalone widely applicable software library for feature selection (also known as attribute or variable selection), capable of reducing problem dimensionality to maximize the accuracy of data models, performance of automatic decision rules as well as to reduce data acquisition cost. The library can be exploited by users in research as well as in industry. Less experienced users can experiment with different provided methods and their application to real-life problems, experts can implement their own criteria or search schemes taking advantage of the toolbox framework. In this paper we first provide a concise survey of a variety of existing feature selection approaches. Then we focus on a selected group of methods of good general performance as well as on tools surpassing the limits of existing libraries. We build a feature selection framework around them and design an object-based generic software library. We describe the key design points and properties of the library.
|
|
|
Sequential Retreating Search Methods in Feature Selection
Somol, Petr ; Pudil, Pavel
Inspired by Floating Search, our new pair of methods, the Sequential Forward Retreating Search (SFRS) and Sequential Backward Retreating Search (SBRS) is exceptionally suitable for Wrapper based feature selection. (Conversely, it cannot be used with monotonic criteria.) Unlike most of other known sub-optimal search methods, both the SFRS and SBRS are parameter-free deterministic sequential procedures that incorporate in the optimization process both the search for the best subset and the determination of the best subset size. The subset yielded by either of the two new methods is to be expected closer to optimum than the best of all subsets yielded in one run of the Floating Search. Retreating Search time complexity is to be expected slightly worse but in the same order of magnitude as that of the Floating Search. In addition to introducing the new methods we provide a testing framework to evaluate them with respect to other existing tools.
|
|
|
Automatic Removal of Sparse Artifacts in Electroencephalogram
Zima, Miroslav ; Tichavský, Petr ; Krajča, V.
This report presents an algorithm for removing artifacts from EEG signal, which is based on the method of independent component analysis utilizing the signal nonstationarity or sparsity of the artifacts. The algorithm is computationally very fast, enables online processing of long data records with excellent separation accuracy. The algorithm also incorporates using wavelet denoising of the artifact components, recently proposed by Castellanos and Makarov, which reduces distortion of the cleaned data.
|
|
|
Example creation system
Suzdaleva, Evgenia ; Nagy, Ivan ; Dungl, Martin
The technical report describes a system for creation of examples for fully probabilistic dynamic decision making. It represents a documentation for author who wishes to create examples for PhD students or to add their new developed algorithms to the system.
|
|
|
Comparison of trading algorithms
Zeman, Jan
The paper continues the previous research of designing the trading automatic system. The paper deals with rating the quality of designed approaches. It reviews methods of rating from general to trading ones, and designs the rating algorithm, which is tested.
|
|
|
Supra-Bayesian Approach to Merging of Incomplete and Incompatible Data
Sečkárová, Vladimíra
In practice we often need to take every available information into account. Unfortunately the pieces of information given by different sources are often incomplete (with respect to what we are interested in) and have different forms. In this work we try to solve the problem of treating such data in order to get an optimal merger of them. We present a systematic and unified way how to combine the pieces of information by using a Supra-Bayesian approach and other mathematical tools, e.g. Kerridge inaccuracy, maximum entropy principle. To show how the proposed method works a simple example is given at the end of the work.
|
guest ::
