Abstract:

This paper presents a neuro-fuzzy algorithm for high-speed grayscale image segmentation based on a modified defuzzification method using triangular membership functions. The aim of the study is to analyze the effect of simplifying the defuzzification formula on the accuracy and contrast of object selection. The proposed approach includes adaptive learning of the weight coefficient, which allows dynamically adjusting the defuzzification process depending on the target values. The paper compares the basic method of averaging membership values and a modified version taking into account nonlinear weights. Experiments conducted on 1024x720 images demonstrate that the developed algorithm provides high segmentation accuracy and improved object contrast with minimal computational costs. The results confirm the superiority of the proposed method over traditional approaches, emphasizing the prospects for applying artificial intelligence in computer vision problems.

Abstract:

This article discusses the application of vector models for the preliminary analysis of students' free-form answers. Vector representations of words and documents were obtained using word2vec, doc2vec, and BERT models. The similarity between the answer given by the student and the correct answer was determined using the cosine measure. It was found that vector models allow identifying obviously incorrect answers with sufficient accuracy. For answers that are close in wording, an additional verification step is proposed. Using word2vec, binary classification of answers to certain questions was performed, and accuracy, precision, recall and F1-measure estimates were given.

Abstract:

In the modern world, the problems arising in the field of traffic are of great importance. In order to solve existing problems, various intelligent systems are being developed, one of which is the Smart City system. This work is devoted to the development of an information and analytical system (IAS) for controlling an intelligent traffic light. The presented system consists of two levels, each of which contains a set of specific operations. The first level is responsible for detecting objects, in particular pedestrians and cars at the intersection, and the second level calculates the operating time of traffic light signals for the control signal that is transmitted to the device. For comparative analysis, the combined method (HOG+SVM) Histogram of oriented gradients was chosen, based on counting the number of gradient directions on individual image areas and Support Vector Machines, which are used to construct hyperplanes in n-dimensional space in order to separate objects belonging to different classes. The results of an experimental study, during which the recognition of objects in images was carried out, showed the superiority of the developed information and analytical system over existing methods. The average accuracy of detecting pedestrians and cars through the IAS was 69.4%. In addition, according to the experiment, it was concluded that the accuracy of detecting objects in images is directly proportional to the distance from the video camera to the object.

Abstract:

The article is devoted to the results of the analysis of modern trends in functional programming, considered as a metaparadigm for solving the problems of organizing parallel computations and multithreaded programs for multiprocessor complexes and distributed systems. Taking into account the multi-paradigm nature of parallel programming, the paradigm analysis of languages and functional programming systems is used. This makes it possible to reduce the complexity of the problems being solved by methods of decomposition of programs into autonomously developed components, to evaluate their similarities and differences. Consideration of such features is necessary when predicting the course of application processes, as well as when planning the study and organizing the development of programs. There is reason to believe that functional programming has the ability to improve programs performance. A variety of paradigmatic characteristics inherent in the preparation and debugging of long-lived parallel computing programs are shown.

Abstract:

This article presents a new algorithm for 3D reconstruction using a combination of two existing methods – Structure from Motion (SfM) and Oriented FAST and Rotated BRIEF (ORB). The authors propose an approach that merges the advantages of both methods to enhance the accuracy and efficiency of reconstructing the 3D structure of scenes from images. To improve reconstruction quality, filtering and outlier removal are applied, along with other optimizations. Comparative results between the new algorithm and existing methods demonstrate its superiority in accuracy and noise robustness. The proposed approach is highly scalable and can be successfully applied in various fields that require precise 3D reconstruction of image scenes.

Abstract:

In this paper we research two modifications of recurrent neural networks – Long Short-Term Memory networks and networks with Gated Recurrent Unit with the addition of an attention mechanism to both networks, as well as the Transformer model in the task of generating queries to search engines. GPT-2 by OpenAI was used as the Transformer, which was trained on user queries. Latent-semantic analysis was carried out to identify semantic similarities between the corpus of user queries and queries generated by neural networks. The corpus was convert-ed into a bag of words format, the TFIDF model was applied to it, and a singular value decomposition was performed. Semantic similarity was calculated based on the cosine measure. Also, for a more complete evaluation of the applicability of the models to the task, an expert analysis was carried out to assess the coherence of words in artificially created queries.

Abstract:

A study of two graphs of scientific cooperation based on co-authorship and citation according to the all-Russian mathematical portal was conducted Math-Net.Ru. A citation-based scientific collaboration graph is a directed graph without loops and multiple edges, whose vertices are the authors of publications, and arcs connect them when there is at least one publication of the first author that cites the publication of the second author. A co-authorship graph is an undirected graph in which the vertices are the authors, and the edges record the co-authorship of two authors in at least one article. The customary study of the main characteristics of both graphs is carried out: diameter and average distance, connectivity components and clustering. In both graphs, we observe a similar connectivity structure – the presence of a giant component and a large number of small components. The similarity and difference of scientific cooperation through co-authorship and citation is noted.

Abstract: The rapid development of complex virtual worlds (most notably, in 3D computer and video games) introduces new challenges for the creation of virtual agents, controlled by artificial intelligence (AI) systems. Two important subproblems in this topic area which need to be addressed are (a) believability and (b) effectiveness of agents' behavior, i.e. human-likeness of the characters and high ability to achieving their own goals. In this paper, we study current approaches to believability and effectiveness of AI behavior in virtual worlds. We examine the concepts of believability and effectiveness and analyze several successful attempts to address these challenges. In conclusion, we suggest that believable and effective behavior can be achieved through learning behavioral patterns from observation with subsequent automatic selection of winning acting strategies.

Abstract:

The article investigates the problem of aspect-based sentiment analysis. Such version of analysis is more challenging compared to general task of sentiment detection problem. It implies the solutions to the number of related subtasks such as aspect term extraction, aspect term polarity detection and aspect category polarity detection. The solution of aspect-based sentiment analysis problem significantly extends the capabilities of natural language processing systems.

The article gives the overview of previous works in the field and describes the train and test data from the Russian evaluation workshop SentiRuEval. For the task of aspect term extraction the vector space of distributed representations of words was used. Aspect term detection is based on mutual information method and semantic similarity. The paper contains the number of experimental results. At the end the final conclusions are drawn.