Ekaterina Viktorovna Zaytseva

Dr. Ekaterina Viktorovna Zaytseva

orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
27 June 2025 in Advanced Engineering Research (Rostov-on-Don)
Verified
Journal Article
Open access
PDF file
VRV. K. Rezvanov
V. K. Rezvanov
OROksana Romakina
Oksana Romakina
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
Introduction. Trade development requires the implementation of artificial intelligence and machine learning technologies to improve the accuracy of delivery forecasts. The scientific research published to date in this area appears insufficient for two reasons. First, it focuses primarily on global supply chains, although the issue is relevant for local businesses as well. Second, forecasting typically requires large amounts of data for machine learning and significant computing resources that are not available to the majority of companies. The presented study aims to fill these gaps and demonstrate the efficiency of using open, accessible data and known algorithms. The research objective is to describe a pattern of appropriate selection of the least resource-intensive delivery forecasting model based on the analysis of machine learning algorithms.Materials and Methods. The open data set DataCo Smart supply chain for big data analysis on deliveries in online trade was used. To process and analyze the information, methods of data cleaning, eliminating multicollinearity, normalization and coding of categorical features were applied. The following algorithms were used with the cleaned data: Decision tree, Random Forest, k-nearest neighbors, Naïve Bayes, Linear discriminant analysis, XGBoost, CatBoost, LightGBM, AdaBoost, and Perceptron.Results. The basic algorithm for the delivery forecasting model was the Decision Tree algorithm. This choice was due to its high accuracy, ease of use, and low risk of overfitting. The model evaluation showed a high determination coefficient close to one (0.986). Low values of the mean square error (0.0367) and mean absolute error (0.0324) were recorded. The model showed satisfactory results in terms of time spent on training (3.3087 s) and forecasting (0.0051 s). Actual and predicted values almost perfectly matched. Deviations from actual values were minimal.Discussion and Conclusion. The proposed model is efficient and has a high predictive ability. High-quality forecasting of delivery time is possible without the use of extensive databases and powerful computing resources. The study opens up the prospect of high-quality organization of logistics operations for small and medium enterprises. In further research, it is advisable to integrate weather data, traffic conditions and other indicators into the model. Using such information in real time will increase the adaptability and accuracy of forecasting.

15 March 2018 in Transportation systems and technology
Verified
Journal Article
Open access
PDF file
VKViacheslav V. Kapustin
Viacheslav V. Kapustin
AMAndrey K. Movchan
Andrey K. Movchan
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
MKMikhail I. Kuryachy
Mikhail I. Kuryachy
КИКурячий Михаил Иванович
Курячий Михаил Иванович
This paper presents research results of the Active Vision Area, formed by the Active Pulse Television Measuring System in conditions of decreased transparency of propagation medium. Aim: To increase backscatter interference suppression efficiency by the Active Pulse Television Measuring System for ensuring navigation of transport means in heavy weather conditions. Methods: Simulation of Active Vision Area considering light energy attenuation is proportionate to the square of distance and attenuation caused by propagation atmosphere. Performance of experimental researches with the Prototype of Active Pulse Television Measuring System using Big Aerosol Chamber, simulating dense fog and smoke conditions. Results: The designed model of Active Vision Area allowed estimating the changes of light energy distribution in the observed space layer depending on range of observation and transparency of radiation propagation medium. With equal duration values of the illumination and strobing pulses of the photodetector in conditions of dense fog, significantly big residual backscatter interference was revealed, maximum intensity area of the radiation reflected from objects was displaced from a distance of strobing delay. Illumination pulse duration reduction led to increase of backscatter interference suppression efficiency, improvement of image contrast and increase of accuracy of determination of distance to the observed objects. Conclusion: The increase of backscatter interference suppression efficiency by the Active Pulse Television Measuring System for ensuring navigation of transport means in heavy weather conditions is a relevant task

1 November 2016
Verified
Conference Paper
Closed access
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
The techniques integral and spectral sensitivity assessment in the active-pulsed television system, taking into account the loss in agreeing an optoelectronic transducer and a television transmitter, are consider.

3 October 2023 in МОДЕЛИРОВАНИЕ, ОПТИМИЗАЦИЯ И ИНФОРМАЦИОННЫЕ ТЕХНОЛОГИИ
Verified
Journal Article
Closed access
AKA.A. Kochneva
A.A. Kochneva
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
EKE.V. Katuntsov
E.V. Katuntsov
The main subtle aspects of airborne laser scanning (ALS) involve a large level of density of laser reflection points (LRP) within a certain unit area. This results in the need to process a large amount of information while building digital terrain models (DTMs). Such processing is computationally intensive. For this reason, the main task which is solved during DTM building is to create an accurate description of terrain features required for geodetic works. At the same time, it is necessary to observe the minimum number of LRPs related to the characteristic landforms in the considered location to minimize the use of computing power. Currently available algorithms of information distribution for DTMs built on standard coordinate grids do not allow to successfully resolve data arrays while preserving the proper detalisation level of certain locations. New software, which is used in geodesy and makes it possible to create sparse data arrays during DTM building, is based on a closed code. The paper proposes an algorithm for finding unknown intermediate data obtained with laser scanning of terrain relief, which allows effective thinning of laser reflection points that are insignificant when describing the terrain relief. An automatic technique of DTM building is developed. An algorithm for searching unknown intermediate LRP arrays is formed. Displot is available for sloped areas as well. At the same time detailisation in the quality of structure lines and special points is preserved.

1 September 2016
Verified
Conference Paper
Closed access
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
For assessment sensitivity TV camera must know sensitivity a photoelectric cell. The purpose of the research: development of techniques assessment sensitivity of CCDs television sensors. Formulas for assessment of integral, spectral and threshold sensitivity of CCDs television sensors are received. The formula for determination of the optical transmission coefficient on brightness considering losses in case of coordination of the electron-optical transformer (EOT) and television sensor is specified. These dependences are applicable when using as object of observation of the EOT's screen.

1 April 2018
Verified
Conference Paper
Closed access
Ekaterina Viktorovna ZaytsevaEkaterina Viktorovna Zaytseva
Ekaterina Viktorovna Zaytseva
In this article assessment techniques of qualitative characteristics of television systems depending on type of the television sensor “light signal” are offered. Types of the television sensors used in different television systems are considered. Scopes of the appropriate television systems are given. The analysis of the existing assessment models of the qualitative characteristics using as the television sensor CCD and the CMOS array is carried out. Analytical models of assessment of sensitivity and illuminance of television systems on CMOS and CCD for valuation methods enhancement of the quantitative characteristics of television sensors on CMOS and CCD are provided. In analytical models influence of parameters of a lens on qualitative characteristics of television systems is considered. The fields of application of models for quality assessment of the television systems applied in application-oriented and measuring television in processes of digital society communication are offered.