Development of the modified methods to train a neural network to solve the task on recognition of road users

Abstract

<p>We have developed modifications of a simple genetic algorithm for pattern recognition. In the proposed modification Alpha-Beta, at the stage of selection of individuals to the new population the individuals are ranked in terms of fitness, then the number of pairs is randomly determined ‒ a certain number of the fittest individuals, and the same number of the least adapted. The fittest individuals form the subset B, those least adapted ‒ the subset W. Both subsets are included in a set of pairs V. The number of individuals that can be selected to pairs is in the range of 20‒60 % of the total number of individuals. In the modification Alpha Beta fixed compared to the original version of a simple genetic algorithm we added a possibility of the emergence of two mutations, added a fixed point of intersection, as well as changed the selection of individuals for crossbreeding. This makes it possible to increase the indicator of accuracy in comparison with the basic version of a simple genetic algorithm. In the modification Fixed a fixed point of intersection was established. The cross-breeding involves half the genes ‒ those genes that are responsible for the number of neurons in layers, values for other genes are always passed to the descendants from one of the individuals. In addition, at the stage of mutation there are randomly occurring mutations using a Monte-Carlo method.</p>The developed methods were implemented in software to solve the task on recognizing motorists (cars, bicycles, pedestrians, motorcycles, trucks). We also compared indicators for using modifications of a simple genetic algorithm and determined the best approach to solving the task on recognizing road traffic participants. It was found that the developed modification Alpha-Beta showed better results compared to other modifications when solving the task on recognizing road traffic participants. When applying the developed modifications, the following indicators for the accuracy of Alpha-Beta were obtained ‒ 96.90 %, Alpha‒Beta fixed ‒ 95.89 %, fixed ‒ 85.48 %. In addition, applying the developed modifications reduces the time for the neuromodel’s parameters selection, specifically using the Alpha-Beta modification employs only 73.9 % of the time required by the basic method, applying the Fixed modification ‒ 91.1 % of the time required by the basic genetic method

Authors and Affiliations

Ievgen Fedorchenko, Andrii Oliinyk, Alexander Stepanenko, Tetiana Zaiko, Serhii Shylo, Anton Svyrydenko

Keywords

Related Articles

Modeling of the process of the shot based on the numerical solution of the equations of internal ballistics

<p>The study of the process of firing a firearm, taking into account the degree of wear of the barrel, requires an assessment of the losses of powder gases due to their breakthrough between the barrel walls and the proje...

Testing of measurement instrument software with the purpose of conformity assessment

<p>The analysis of the regulatory framework for testing measuring instruments (MI) software at the national level to determine its suitability for carrying out conformity assessment was conducted. Comparison of the gener...

Detection of regularities in the parameters of the ateb­gabor method for biometric image filtration

<p>The study has developed a new image filtering method based on Ateb-Gabor. The method involves the well-known Gabor filter that helps convert images with clear contours. Therefore, this method is applicable to biometri...

Detection of human respiration patterns using deep convolution neural networks

<p class="a"><span lang="EN-US">The method for real­time recognition of respiration types (patterns) of a patient to monitor his conditions and threats to his health, which is a special case of the problem of human activ...

Influence of elastic characteristics of raw cotton on the mechanics of feed rollers in the cleaners from small impurities

<p>The effect of the elastic characteristics of raw cotton on the mechanics of the feed rollers in fine impurity cleaners depends on maturity. In cleaners from small impurities, mechanisms are used with spike rollers hav...

Download PDF file
  • EP ID EP666325
  • DOI 10.15587/1729-4061.2019.164789
  • Views 97
  • Downloads 0

How To Cite

Ievgen Fedorchenko, Andrii Oliinyk, Alexander Stepanenko, Tetiana Zaiko, Serhii Shylo, Anton Svyrydenko (2019). Development of the modified methods to train a neural network to solve the task on recognition of road users. Восточно-Европейский журнал передовых технологий, 2(9), 46-55. https://europub.co.uk/articles/-A-666325