Vladislav Skorpil

Comparison of learning algorithms

There are several learning methods which are suitable for neural networks. In this paper two of them are described - Back-propagation (BP) and Genetic (GA) algorithms. These learning methods are compared here and they are used for the control of modern telecommunication network nodes.

Analysis of Algorithms for Radial Basis Function Neural Network

This paper describes the analysis of algorithms for the hidden layer construction of network and for learning of the Radial Basis Function neural Network (RBFN). We compared results obtained by using of learning algorithms LMS (Least Mean Square) and Gradient Algorithms (GA) and results are obtained by using of algorithms APC-III and K-means for hidden layer contruction of neural network. The principles and algorithms given below have been used in an application for object classification that was developed at Brno University of Technology. This solution is suitable for the research of personal wireless communications and similar systems.

Estimation of free space optics systems availability based on meteorological visibility

A number of phenomena in the atmosphere such as scattering, absorption and turbulence can cause large variation in laser beam attenuation. The influence of absorption and turbulence can in some cases be significantly reduced by an appropriate design of free space optics (FSO) systems. Thus, in a typical continental area, where rain, snow or fog occur, scattering is the most important phenomenon causing power losses. Attenuation due to scattering can be expressed as a function of the link distance, wavelength and meteorological visibility. The paper deals with the estimation of FSO availability based on statistical evaluation of visibility data collected at several airports in Europe. The availability is evaluated in dependence on link distance, wavelength and power link margin.

Back propagation and Genetic Algorithms for control of the network element

The authors have for long been interested in the design of the network element for multimedia networks. The designed network element is not controlled sequentially, as is still usual in neural networks. In this contribution the Back Propagation and the Genetic Algorithms are compared with respect to the control of neural networks.

Wavelet transform for image analysis

The wavelet transform is a comparatively new and fast developing method for analysing signals. The main advantage of applying the wavelet transform to the detection of edges in an image is the possibility of choosing the size of the details that are detected. The size of detected edges is set by the wavelet scale. In the case of the discrete wavelet transform the choice of the scale is performed by multiple signal passage through the wavelet filter. When processing a 2-D image, the wavelet analysis is performed separately for the horizontal and the vertical function. The vertical and the horizontal edges are thus detected separately. The wavelet transform splits the input signal into two components. One contains the low-frequency (LP) part of input signal, which corresponds to major changes in the function (individual objects in the image, etc.). The other part contains the high-frequency (HP) part of input signal, which corresponds to details in the function (noise, edges, etc.). This signal component is not processed on the next level of transformation.

New Architecture of Network Elements

This paper describes design and computer simulation of a new architecture of a node active network element, based on artificial neural network technology with the support of priority processing for different connection types. As an example of a network element was selected switching area. This network element with optimized switching area is able to transfer large data quantity with minimum delay. Architecture of network element, that contains artificial neural network for optimized priority switching is described in this paper. It describes implementation of neural network in control process for data units switching. The programming language MATLAB 7.0 was used for software simulation. Network elements with new architecture, which uses a neural network, as well as intimated simulation, are suitable for working for example in personal wireless network communication systems.

Ensuring invariances for structural methods of object recognition

The paper discusses ensuring invariances for the structural methods of recognition of randomly deformed object. Initially, the types of invariances are described. Further, the ways of effective ensuring all types of invariances are described, mainly using automatic selection of point of description origin, differential primitives and object rotation. Finally, the results of this method are evaluated.

Visualization of uncertainty in LANDSAT classification process

Many uncertainties can be found in the classification of remotely sensed data. Namely they can arise in defining classification classes. We use two ways, incorporating acquired Corine Land Cover labels and our manually annotated labels. We are describing several visualization possibilities to demonstrate uncertainties in labels and their connections with classification results. We use parallel coordinates to visualize data, presenting problems in classes definitions. These failures can be consequently seen in the results of classification in confusion matrix. We inspect also posterior probabilities of k-Nearest Neighbor (k-NN) classifier visualizing maximum likelihood class probabilities as alpha channel of resulting classification map.

Audio data classification by means of new algorithms

This paper describes classification of sound recordings based on their audio features. This is useful for querying large datasets, searching for recordings with some desired content. We use musical recordings as well as birdsongs recordings, which usually have rich structure and contain a lot of patterns suitable for classification. We present two different classification methods, one for musical recordings and one for birdsongs. These methods are compared and their differences are discussed. We use feature vectors that capture the audio content of recording as a whole piece and then classify these feature vectors using combination of the Self-organizing map and the Learning Vector Quantization, which represent a powerful algorithm using unlabeled as well as labeled data. In case of birdsongs we use feature vectors representing time frames of a recording.

Object recognition by means of early parser effective implementation

The paper discusses effective implementation of Earley parser for structural methods of recognition of randomly deformed object. Initially, basics of Earley parser are described. Further, ways of effective implementation and improvements of this method are described, mainly using prediction look-ahead and grammar optimization for improvement of the analysis. Finally, results of this method are evaluated.