Search

Search Results

• METHOD OF GENETIC PROGRAMMING FOR SOLVING THE PROBLEM OF OPERATIONAL SCHEDULE PLANNING OF DISCRETE PRODUCTION

  К. О. Obukhov, I.Y. Kvyatkovskaya, А. V. Morozov

  2025-01-20

  Abstract ▼

  One of the main conditions for the successful functioning of the enterprise is a well-organized production
  planning process. Production planning systems of the APS/MES class, the basis of which are algorithms
  for building production plans, allow automating this activity. The paper examines the problem of
  scheduling for enterprises of a discrete type of production, related to the field of multi-criteria optimization
  problems. A formal description of the planning task is given, taking into account the main production
  constraints (time constraints, equipment requirements and the order of operations). The main methods of
  solving problems of this class are briefly considered; their main advantages and disadvantages are noted.
  To solve this problem, an approach based on the generation of heuristic rules used in planning production
  operations for specified resources has been chosen. Based on this approach, a two-stage algorithm for
  building production schedules is proposed, which includes the generation of dispatching rules and their
  further application in building schedules. A genetic algorithm is responsible for generating dispatch rules.
  The implementation of its genetic operators is described in detail, as well as the composition of the chromosome and the tree representation of the dispatch rules included in the chromosome. The algorithm is
  implemented in C# 12 using a free platform.NET 8. The implemented algorithm has shown its effectiveness
  in comparison with the greedy algorithm on small generated datasets. Further research in this area is
  aimed at evaluating the effectiveness of the constructed algorithm with more complex genetic operators
  and the structure of the expression tree, as well as reducing the duration of the process of generating heuristic
  rules for large data sets.

• MODERN APPROACHES TO FACE RECOGNITION IN LOW-LIGHT CONDITIONS: A REVIEW AND THE CONCEPT OF A HYBRID END-TO-END ARCHITECTURE

  D. А. Morozov , V.V. Gilka , А. S. Kuznetsova

  113-133

  2026-07-07

  Abstract ▼

  The article addresses the problem of reliable face recognition in critical areas such as video surveillance and biometric authentication under low-light conditions. Existing approaches typically separate the tasks of image enhancement and face identification, which leads to error accumulation and loss of informative features. The aim of this work is to overcome this limitation by developing and theoretically substantiating a hybrid end-to-end architecture in which image enhancement and face recognition are solved jointly. The study provides a systematic review of modern methods, including classical algorithms (such as histogram equalization and noise suppression) and advanced deep neural networks (including EnlightenGAN, Zero-DCE, ArcFace, and RetinaFace). The main contribution is the integration of generative and identification modules into a single computational graph. The key result of the study is the demonstration that joint optimization of all processing stages within a unified model, unlike fragmented solutions, fundamentally changes the approach to the problem. Theoretical analysis and comparative evaluation of existing concepts show that the proposed architecture ensures a more efficient gradient flow during training, leading to the formation of higher-quality and noise-robust identity features. It is shown that this approach prevents error accumulation between stages and minimizes information loss. The novelty of the work lies in the holistic, end-to-end view of the face recognition problem under low-light conditions. The practical significance is confirmed by the applicability of the architecture in real systems, where its implementation can potentially improve reliability and processing speed by combining heterogeneous tasks into a single optimizable framework.

  The article addresses the problem of reliable face recognition in critical areas such as video surveillance and biometric authentication under low-light conditions. Existing approaches typically separate the tasks of image enhancement and face identification, which leads to error accumulation and loss of informative features. The aim of this work is to overcome this limitation by developing and theoretically substantiating a hybrid end-to-end architecture in which image enhancement and face recognition are solved jointly. The study provides a systematic review of modern methods, including classical algorithms (such as histogram equalization and noise suppression) and advanced deep neural networks (including EnlightenGAN, Zero-DCE, ArcFace, and RetinaFace). The main contribution is the integration of generative and identification modules into a single computational graph. The key result of the study is the demonstration that joint optimization of all processing stages within a unified model, unlike fragmented solutions, fundamentally changes the approach to the problem. Theoretical analysis and comparative evaluation of existing concepts show that the proposed architecture ensures a more efficient gradient flow during training, leading to the formation of higher-quality and noise-robust identity features. It is shown that this approach prevents error accumulation between stages and minimizes information loss. The novelty of the work lies in the holistic, end-to-end view of the face recognition problem under low-light conditions. The practical significance is confirmed by the applicability of the architecture in real systems, where its implementation can potentially improve reliability and processing speed by combining heterogeneous tasks into a single optimizable framework.

• ANALYSIS OF THE CAUSES OF ERRORS IN THE AMPLITUDE-PHASE DISTRIBUTION OF LINEAR PHASED ANTENNA ARRAYS AND METHODS FOR THEIR REDUCTION

  S.S. Bybin , N.P. Dunaev , S.V. Kuzmin , А.N. Morozov

  2026-02-27

  Abstract ▼

  To use a phased array antenna in the beamforming mode, it is necessary to establish a certain amplitude-phase distribution at the inputs of the emitting elements. Amplitude and phase errors distort the radiation pattern. The paper analyzes the sources of errors in the amplitude-phase distribution of phased antenna arrays, including parasitic phase shifts, nonlinear amplification paths, temperature instability and mutual electromagnetic coupling between the elements. Three methods of calibration and adjustment of phased antenna arrays are described, based on direct measurements of the transmission coefficients in the near zone and the subsequent calculation of the impact vector using inverse and pseudo-inverse matrices of mutual connections, which provides a systematic approach to error elimination. To obtain the initial values, each channel was pre-calibrated along a closed path using a vector network analyzer. Technique 1 implements correction for a set of points in space and one set of states of each channel. To increase the stability of the solution, method 2 uses the regularization of the elements of the matrix of interconnections based on an additional set of measured states of each channel. Method 3 makes it possible to construct a mathematical model of a specific implementation of a phased array antenna based on measurements with a fixed channel state, which ensures the formation of an arbitrary amplitude-phase state without repeated measurements. An experimental setup of an eight-element equidistant linear phased array antenna was carried out. The lattice attenuator/phase shifter modules are based on the PE44820 phase shifter and PE4302 attenuator debugging boards and are controlled by a microcontroller to automatically change phases and amplitudes. The measurements were carried out automatically on a near-field stand in an anechoic shielded chamber using a vector network analyzer. Calibration results are presented, matrices of mutual relationships are constructed and radiation patterns are formed, confirming the operability of the proposed approaches. Since the experimental array is low-element, the results of applying the considered techniques are compared with the results of tuning in the far zone performed using an evolutionary algorithm.

• MODERN APPROACHES TO NATURAL FIRE MONITORING AND FORECASTING: REVIEW AND CONCEPT OF AUTONOMOUS UAV-BASED SYSTEM

  N.D. Boldyrev , V. V. Gilka , А.S. Kuznetsova , D.А. Morozov

  58-80

  2025-12-30

  Abstract ▼

  Natural fires cause serious damage to ecosystems, the economy, and public safety every year, and timely detection of fires and prediction of their development increases the speed of response to threats and allows for optimal allocation of resources during emergency response. Existing monitoring methods are limited by the speed of detecting fire outbreaks and the speed of their further spread, which reduces the effectiveness of rescue services. To solve this problem, heterogeneous data sources can be used, including unmanned aerial vehicles (UAVs), distributed sensor networks, mobile field observation systems, ground-based thermal imaging stations, etc., which can contribute to a more accurate analysis of the current situation and improve the reliability of predictive models of fire spread. The aim of the study was to develop a concept for an automated approach to monitoring and predicting wildfires based on unmanned aerial vehicles. We believe that this approach will improve the speed of detecting fire outbreaks and the accuracy of predicting their spread. The tasks include analyzing existing monitoring methods, developing a concept for a system that integrates multispectral imaging, optimized data transmission, automatic segmentation, and forecasting based on machine learning, as well as ensuring interaction between the operator and alert specialists. The work used methods of collecting, analyzing, and transmitting data from UAVs, processing multispectral images, machine learning and neural networks for fire detection, image segmentation algorithms and simulation modeling for fire spread prediction, data visualization to support decision-making by operators and administrators, logging and analysis of results for model training, software engineering, and human-computer interaction technologies. The system will reduce the time required to detect and predict fires, enable operators to launch multiple drones simultaneously, and automate the processing of data received from them. Process automation will reduce emergency response times and staffing levels, improve resource allocation, increase forecast accuracy, and improve the timeliness of emergency service notifications. This will help reduce damage from wildfires and improve the safety of people and ecosystems. Despite the progress made in addressing this challenge, the comprehensive system described in this article does not yet exist in its entirety in Russia, the CIS countries, or in Western and Asian countries. Although individual components, such as UAVs for monitoring and artificial intelligence (AI) for data analysis, are already in active use, there is currently no integrated solution that combines all elements (drone control, near real-time fire spread prediction, data transmission, and interaction with emergency services). does not currently exist. This concept represents a new approach that could become a breakthrough technology for combating natural disasters.

• ANALYSIS OF THE CONTROLLABILITY OF SOME DIGITAL FILTERS WITH A FINITE IMPULSE RESPONSE

  D. A. Guzhva , К.О. Sever, А. А. Morozov

  2021-08-11

  Abstract ▼

  This overview article covers finite impulse response filters and filter banks. The use of these filters
  for hearing aids is considered. Ways to compensate for hearing loss and ways to increase loudness
  using broadband amplification are considered. A schematic diagram of a method for digital
  signal processing using a bank of filters, as well as a technique for synthesizing interpolation filters
  with low computational complexity, is presented. Also, the application of the MATLAB system for the
  synthesis of narrow-band non-recursive FIR filters, their design procedure, methodology and examples
  are considered. Finite Impulse Response (FIR) filters and filter banks have specific properties
  that guarantee stability. Therefore, they are popular in many applications such as communication
  systems, audio signal processing, biomedical instruments, and so on. Unfortunately, due to the longer
  wavelength, the cost of implementing an FIR filter is usually not higher than an infinite impulse response
  (IIR) filter that meets the same requirements. It is well known that the length of an FIR filter is
  inversely proportional to its transition bandwidth. Therefore, the disadvantage becomes acute when a
  given filter has a narrow transition band. The main goal is to consider computationally efficient
  methods for designing FIR filters and filter banks. The masking method (FRM) results in significant
  savings in the number of multipliers. Next, a 16-band, low group delay, non-equal-spacing digital
  FIR filter bank is considered. Overall latency is significantly reduced as a result of a new filter structure
  that reduces the interpolation factor for prototype filters. Masking filter may be an interpolated
  finite impulse response (IFIR) filter that helps reduce complexity.

• ANALYSIS OF CERTAIN WEIGHT FUNCTIONS (WINDOWS) AND THEIR APPROXIMATIONS FOR IMPLEMENTATION OF CONTROLLED RECURSIVE LOW-PASS FILTERS WITH A FINITE IMPULSE RESPONSE ON THEIR BASIS

  T.V. Shushkevich , А.А. Morozov, I. I. Turulin

  2021-11-14

  Abstract ▼

  There are various types of weighting functions, the so-called windows in digital signal processing,
  such as rectangular (Dirichlet window), triangular (Bartlett window), Vallee-Poussin window,
  Kaiser-Bessel window, Barsilon-Temesh window, Hann, Bohman, Blackman, Gauss (Weierstrass),
  Dolph - Chebyshev, Hamming windows and many others and ideal characteristics of standard filters
  such as low-pass, high-pass, bandpass filters. The purpose of this review article is to determine the most
  suitable weighting function for implementation on its basis of a controlled recursive low-pass filter with
  a finite impulse response. This article presents an analysis of only some of the above windows and their
  approximations, namely the Dolph - Chebyshev window, the Gauss (Weierstrass) window and the
  Hamming window. In addition to the analysis, the synthesis of recursive filters with a finite impulse
  response for weighting data based on the selected windows and their approximations was considered.
  The method of synthesis of Dolph-Chebyshev windows is considered. The implementation of the Gauss
  (Weierstrass) window is considered. Methods for approximating the Hamming window and methods
  and several algorithms for developing filters with FIR in the form of this window are considered. The
  estimation of parameters dependencies some quick window of the maximum level of the side lobes.
  Based on the data obtained, conclusions were drawn about the selection of the most suitable and
  demonstrating maximum performance windows, suitable for implementation on its basis of a controlled
  recursive low-pass filter with a finite impulse response.

• ANALYSIS OF THE RELATIVE PLACEMENT OF THE SENSITIVE MASSES OF ACCELEROMETERS IN ALGORITHMS FOR STRAPDOWN INERTIAL NAVIGATION SYSTEMS

  А.Е. Morozov, N.D. Bogdanov

  2024-04-16

  Abstract ▼

  The present study introduces a method for algorithmic compensation of the displacement of
  the centers of sensitive elements of accelerometers within a high-precision inertial navigation
  system. Previous considerations omitted this compensation due to the potential for minimizing its
  impact through structural features—specifically, the close proximity of accelerometers to each
  other. With the upgrading of components in the inertial sensors, the influence of size-effect errors
  could become significant compared to gyroscopes and accelerometers errors. This study aims to
  analyze the impact of these errors on solving navigation tasks under the precision conditions of
  modern inertial sensors. The compensation scheme is elaborated in detail: compensation to an arbitrary center of the inertial measurement unit is separately discussed, considering the spreading
  effect of the accelerometer triad, and to the center of rotation of the vehicle, accounting for the
  installation location on the operational object. Additionally, designs of accelerometer placements
  on platforms of high-precision and compact inertial navigation system sensor blocks are analyzed.
  By conducting a series of rotations on an inclinable turntable, the spreading of accelerometers is
  calculated using the least squares method concerning the intersection point of the rotation axes of
  the stand used. An estimation of the discrepancy of the calculated spreading coefficients of sensitive
  elements from their nominal values is obtained. Through calibration rotations, the reduction
  of all parasitic phenomena in the accelerometer signal due to centripetal and tangential accelerations
  is achieved. The influence of parasitic accelerometer signals during the roll of the product on
  coordinate computation is analytically derived, revealing the dependency of the studied error on
  the product's operational time under constant rolling conditions. Real tests on the inclinable turntable
  were conducted for verification, and the obtained results of compensation effectiveness are
  presented. The compensation results from flight tests on a two-seat vertical takeoff and landing
  helicopter are provided. The flight test calculations were conducted through physical modeling
  based on recorded data with the synchronization of the employed sensors considered. Compensation
  in the mode of aligning the accelerometer triad to an arbitrary point and aligning accelerometers
  to the center of the vehicle's rotation is separately discussed

• DEVELOPMENT OF A HYBRID METHOD FOR PLANNING THE MOVEMENT OF A GROUP OF MARINE ROBOTIC COMPLEXES IN AN A PRIORI UNKNOWN ENVIRONMENT WITH OBSTACLES

  А.М. Maevsky, R.O. Morozov, А. Е. Gorely, V.A. Ryzhov

  2021-04-04

  Abstract ▼

  The article discusses the problem of organizing the group movement of marine robotics
  (MRS), in particular, unmanned autonomous underwater vehicles (AUV), in an a priori unknown
  environment with obstacles. A brief analysis of existing projects on the subject of MRS group control,
  and path-planning algorithms have been carried out. The presence of numerous studies in
  this area confirms the relevance of the indicated problem. The formal statement of the problem of
  the movement of four robots in formation is presented. The proposed method for a group path
  planning is based on a combined approach that organizes a multi-level solution to organizing the
  movement of MRS. At the upper level, a system for global path planning and mission control was
  developed based on the random tree method, which provides the general movement of the group
  based on a priori information about the state of the environment. The lower-level planning system
  adjusts the global path, allowing objects at the local level to carry out the group agents’ movement
  and interaction, including ensuring their collision-free movement in environment and exit from the
  areas of local minima. The article provides a detailed analytical description of the developed algorithm
  and a block diagram of its functioning. Numerical simulation of the movement of a group
  of 4 AUVs in a non-deterministic environment with fixed obstacles is carried out. The simulation
  was carried out taking into account obstacles of various shapes and complexity. The results of
  mathematical modeling demonstrated the solution to the problem of the exit of the AUV group
  from the area of the local minimum. Full-scale tests are presented on the example of a group of
  three unmanned boats: a group of mobile objects formed a formation and carried out a movement
  in a given formation to target positions and returned to the final zone. In addition, the local planning
  module developed within the framework of this article was integrated into the software of the
  "Shadow" underwater glider control system. In the conclusion, the results of the proposed method
  and its further development, in particular, its application in 3D environment, are considered.