Increasing the share of correct clustering of characteristic signal with random losses in self-organizing maps
Journal Title: Восточно-Европейский журнал передовых технологий - Year 2019, Vol 2, Issue 4
Abstract
<p class="Standard"><span lang="EN-US">Analysis of methods for optimizing algorithms of functioning of the Kohonen neural networks, self-organizing maps (SOM), in terms of training speed and percentage of correct clustering was made. Effective optimization of self-organizing maps was determined by the second criterion, the enhanced self-organizing incremental neural network (ESOINN). It was established that in the case of incomplete input signal, that is the signal with losses at unknown time points, the share of correct clustering is unacceptably low with any SOM algorithms, both basic and optimized.</span></p><p class="Standard"><span lang="EN-US">The incomplete signal was represented as the input vector of the neural network, the values of which are represented by a single array, that is without taking into consideration conformity of the moments of losses to the current values and without the possibility of determining these moments. A method for determining conformance of the incomplete input vector to the input layer of neurons to increase percentage of correct recognition was programmed and proposed. The method is based on finding the minimum distance between the current input vector and the vector of weights of each neuron. To reduce operating time of the algorithm, it was proposed to operate not with individual values of the input signal but their indivisible parts and the corresponding groups of input neurons. The proposed method was implemented for the SOM and ESOINN. To prove effectiveness of implementation of the basic algorithm of the SOM, its comparison with existing counterparts of other developers was made.</span></p><p class="Standard"><span lang="EN-US">A mathematical model was developed for formation of examples of complete signals of a training sample on the basis of reference curves of the second order and a training sample was generated. In accordance with the training sample, training of all neural networks implemented with and without the proposed method was made. A diagram of simulation of losses was developed and test samples were generated for computational experiments with incomplete signals.</span></p><span lang="EN-US">On the basis of experiments, efficiency of the proposed method for classification in terms of incomplete input signal on the basis of self-organizing maps was proved both for implementations of the basic algorithm of SOM and ESOINN</span>
Authors and Affiliations
Svitlana Shapovalova, Yurii Moskalenko
Keywords
Related Articles
- EP ID EP666296
- DOI 10.15587/1729-4061.2019.160670
- Views 79
- Downloads 0
Researching the interaction of different printed materials types with liquids
<p>The interaction of papers and films with the testing liquid was researched. Measurements of the contact angle were taken depending on the substrate and its morphology. Linear dimensions of the paper were determined wh...
Development of the method for modeling the propagation of delays in noncyclic train scheduling on the railroads with mixed traffic
<p>The main goal of present study is to develop a method for modeling delay propagation in non-cyclic train scheduling on a railroad network with mixed traffic. This will make it possible to explore the dynamics of delay...
Study into the resonator structures with microprobe sensing elements
<p>By using methods of mathematical modeling and in the course of an experimental study we have investigated various types of microwave resonator measuring transducers with microprobe sensing elements of coaxial type. Su...
Influence of the carbonate ion on characteristics of electrochemically synthesized layered (α+β) nickel hydroxide
Nickel hydroxide is widely used as the active material of supercapacitors. The most active are samples of Ni(OH)<sub>2</sub> with (α+β) layered structure, synthesized in the slit diaphragm electrolyzer. Influence of carb...
Construction of an analytical method for limiting the complexity of neural-fuzzy models with guaranteed accuracy
<p>We have proposed an analytical method for limiting the complexity of neural-fuzzy models that provide for the guaranteed accuracy of their implementation when approximating functions with two or more derivatives. The...