卷 15, 编号 4 (2024)
Synchronous interaction of distributed disordered digital objects
摘要
Methods of fast synchronization of interaction of unordered active distributed digital objects grouped into clusters are proposed. Unordered objects (which do not use addresses or other individual attributes) replace addressing individual objects by addresses with addressing clusters of objects specifying sets of attributes common to such objects. This allows any number of objects to simultaneously exchange signals and messages with any number of objects. Transfer of objects into synchronous state is performed in a single-cycle manner, by sending a single synchronization signal by the objects, and then maintained for a specified time. The main type of communication between objects is wireless channels, with the transmission of optical or radio signals. Violation of synchronization is restored by the objects by their own actions. Objects can be stationary and mobile. The main features of the structure of object connections are simultaneous visibility of the state of all objects by any object of the group and simultaneous delivery of messages from a group of objects to the input of any object with bit synchronization.
Program Systems: Theory and Applications. 2024;15(4):3-26
3-26
One method of optimal control searching in a heterogeneous discrete systems with a delay in the state of processes
摘要
It is considered a class of non-homogeneous discrete systems (DNS) with intermediate criteria containing two levels. Lower-level systems include delayed state variables. Such DNS are presented in practice and are obtained in the process of discretization of continuous systems when solving optimization problems using iterative methods. For this class, an analogue of Krotov’s sufficient optimality conditions is proposed, on the basis of which a method for improving control is constructed. The proposed method is illustrated with an example.
Program Systems: Theory and Applications. 2024;15(4):27-41
27-41
A heuristic algorithm for one nonlinear optimal control problem
摘要
The optimal control problem for one of the variants of a quasilinear system is considered. To solve it, the idea of Professor V. I. Gurman is used, who proposed to combine two variants of the expansion principle. One of them is the traditional Krotov approach, and the second is the penalty function method. The selected class of systems allows for an analytical study of the Krotov Lagrangian, which in turn leads to the formulation of the algorithm. The resulting algorithm is tested on two illustrative examples, for which minimizing sequences are constructed. The complexity of the calculations is comparable with methods based on the traditional expansion principle. The calculation results are illustrated by tables and graphs.
Program Systems: Theory and Applications. 2024;15(4):43-54
43-54
Mathematical modeling with constraints and research of the optimal configuration of an optical stereo system consisting of two flat mirrors and videocamera
摘要
The paper continues a series of studies devoted to mathematical modeling and optimization of optical stereo system configuration, consists of video camera and two flat mirrors. In previous work, we developed a model that takes into account various constraints on the configuration of such a system: the size of the stereo base, the size of the mirrors, overall dimensions of the optical system, the absence of double reflection of light rays, preventing the situation when the video camera is reflected in the mirrors. A conditional optimization problem is formulated, the perimeter of the rectangle that bounds the optical system is chosen as the objective function.In this work we added a set of constraints to the model that define the configuration of the working area, which is formed by the intersection of the fields of view of two virtual cameras. The corresponding changes were made to the program for the numerical solution of the constrained optimization problem using the SciPy package. The results obtained expand the theory of computer vision and can be used in the creation and research of computer vision systems for robotic systems and non-destructive testing systems.
Program Systems: Theory and Applications. 2024;15(4):55-77
55-77
Neural network classification of videos based on a small number of frames
摘要
The article proposes a method for neural network classification of short videos. The classification problem is considered from the point of view of reducing the number of operations required to categorize videos. The proposed solution consists of using a small number of frames (no more than 10) to perform classification using the lightest neural network architecture of the ResNet family of models. As part of the work, a proprietary training dataset was created, consisting of three classes: “animals”, “cars” and “people”. As a result, a classification accuracy of 79% was obtained, a database of classified videos was formed, and an application with GUI elements was developed for interacting with the classifier and viewing the results.
Program Systems: Theory and Applications. 2024;15(4):79-96
79-96
Building robust malware detection through conditional Generative Adversarial Network-based data augmentation
摘要
Malware detection is essential in cybersecurity, yet its accuracy is often compromised by class imbalance and limited labeled data. This study leverages conditional Generative Adversarial Networks (cGANs) to generate synthetic malware samples, addressing these challenges by augmenting the minority class.The cGAN model generates realistic malware samples conditioned on class labels, balancing the dataset without altering the benign class. Applied to the CICMalDroid2020 dataset, the augmented data is used to train a LightGBM model, leading to improved detection accuracy, particularly for underrepresented malware classes.The results demonstrate the efficacy of cGANs as a robust data augmentation tool, enhancing the performance and reliability of machine learning-based malware detection systems.
Program Systems: Theory and Applications. 2024;15(4):97-110
97-110
An analytical review\ of architectures, models, methods and algorithms\ for localization and tracking of non-rigid objects
摘要
Computer vision requires video stream analysis, including extracting information from frames, detecting specific objects, and collecting data about them. After detection, tracking or following objects in the video stream is often required. Non-rigidity or shape variability hinders object analysis, complicates their detection and tracking, and worsens localization.The review considers architectures, models, methods, and algorithms used in practice for detection and tracking of non-rigid objects, and highlights promising solutions.
Program Systems: Theory and Applications. 2024;15(4):111-151
111-151
Symptoms extraction and automatic diagnosis prediction from medical clinical records
摘要
The paper introduces a system for symptoms extraction from medical clinical records (texts in natural Russian language) and automatic prediction of a diagnosis in the form of the disease title and its ICD-10 code. The system is designed for a restricted domain of 6 pulmonary diseases (chronic obstructive pulmonary disease, pneumonia, bronchial asthma etc) and COVID-19.Different neural networks are employed for the symptoms extraction by recognizing certain medical entities and relations between them. A classifier based on a neural network is responsible for the automatic diagnosis. An annotated corpus of sentences is created for the training of the neural networks. The principles and rules of the annotation are described. A corpus of texts is used for the training of the classifier.Both subsystems were tested, the resulting accuracy estimates are provided. The accuracy of diagnosis in the given domain is 88.5%. We also compare our system with similar works on symptom extraction from texts in various languages, as well as on automatic diagnosis, including systems such as ChatGPT.
Program Systems: Theory and Applications. 2024;15(4):153-181
153-181