PROGRAM SYSTEMS: THEORY AND APPLICATIONS

12+

 

Online Scientific Journal published by the Ailamazyan Program Systems Institute of the Russian Academy of Sciences

[menu.en1.html]

• Содержание выпуска •
• Supercomputing Software and Hardware •
• Artificial Intelligence, Intelligence Systems, Neural Networks •
• Information Systems in Culture and Education •
• Methods for Optimal Control and Control Theory •
• Mathematical Foundations of Programming •
• Software and Hardware for Distributed Systems and Supercomputers •

Artificial Intelligence, Intelligence Systems, Neural Networks

Responsible for the Section: doctor of technical Sciences Vyacheslav Khachumov., candidate of technical Sciences Eugene Kurshev.

On the left: assigned number of the paper, submission date, the number of A5 pages contained in the paper, and the reference to the full-text PDF .

 

Article # 27_2017

10 p.

PDF

submitted on 05th Oct 2017 displayed on website on 01th Nov 2017

Natalia Vlasova, Alexey Podobryaev
Automatic noun phrases extraction using preliminary segmentation and CRF with semantic features

We consider the task of finding the borders of noun phrases (NP) that are actants of predicates. First, we make a preliminary segmentation of sentences to fragments that contain NPs. Second, we use CRF to find the borders of NPs inside the fragments. Data from the knowledge base and information about named entities found in the text are used as features for machine learning. We present the results of our experiment and discuss future work. (in Russian).


Key words: shallow parsing, automatic information extraction, named entities, machine learning.

article citation

http://psta.psiras.ru/read/psta2017_4_21-30.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-21-30

Article # 30_2017

15 p.

PDF

submitted on 21th Oct 2017 displayed on website on 04th Dec 2017

Alexandr Smirnov, Egor Ivanov
Automatic noun phrases extraction using preliminary segmentation and CRF with semantic features

The paper describes the method of searching for objects on aerial photographs using neural networks, as well as an algorithm that allows postprocessing of data obtained as a result of the operation of neural networks. The problem of searching for aircraft in images is considered. (In Russian).


Key words: object detection, neutal networks, aerial photos.

article citation

http://psta.psiras.ru/read/psta2017_4_85-99.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-85-99

Article # 33_2017

15 p.

PDF

submitted on 01th Dec 2017 displayed on website on 25th Dec 2017

Andrey Mamontov, Stanislav Rjabinov
On one method of saving memory when classifying texts

The article investigates the method of memory saving in tasks of classification of texts by searching for matching parts of linear polynomials. The algorithm for finding matching parts in linear polynomials with integer coefficients is given at the beginning. This algorithm makes it possible to calculate systems of linear polynomials with integer coefficients more quickly and use less memory for their storage. The algorithm is then used to find the matching parts of the linear polynomials that arise when classifying texts using the Bayesian classifier. We provide computational experiments that show memory saving. (In Russian).


Key words: text classification, linear polynomials, integers, Bayes classifier.

article citation

http://psta.psiras.ru/read/psta2017_4_133-147.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-133-147

Article # 36_2017

11 p.

PDF

submitted on 04th Dec 2017 displayed on website on 25th Dec 2017

Nikolai Abramov, Vitaly Fralenko
Neural network data protection system for computer systems

The work is devoted to the neural network protection against network attacks for computer systems. The methods of information protection using the neural network approach, the algorithm of the analysis of network traffic are offered. The results of software testing are presented. (In Russian).


Key words: information, analysis, system, security, protection, artificial neural network.

article citation

http://psta.psiras.ru/read/psta2017_4_197-207.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-197-207

Article # 38_2017

12 p.

PDF

submitted on 01th Dec 2017 displayed on website on 25th Dec 2017

Duy Nguyen, Mikhail Khacumov
The method of comparing a 3D object model with a 2D image based on invariant moments

 The solution of the comparison problem comes down to that of optimizing the orientation of the 3D object model in order to achieve maximum matching of its projection to the presented image. The closeness measure is the Euclidean distance between invariant moments of the compared 2D images. In the presented formulation, the projection of the 3D model is a grayscale image and the brightness of the pixel is determined by the distance to the viewing plane. (In Russian).


Key words: 3D object model, range image, projection, comparison, orientation control, invariant moments.

article citation

http://psta.psiras.ru/read/psta2017_4_209-220.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-209-220

Article # 45_2017

18 p.

PDF

submitted on 04th Dec 2017 displayed on website on 28th Dec 2017

Aleksandr Buyko, Andrey Vinogradov
Action recognition on video using recurrent neural networks

In this paper, we consider the application of computer vision and recurrent neural networks to solve the problem of identifying and classifying actions on video. The article describes the approach taken by the authors to analyze video files. Recurrent
neural networks uses as a classifier. The classifier takes data in a “bags of words” format that describes low-level actions. The histograms contained in a “bags of words” are represented by sets of video file descriptors. Next algorithms are used to search for descriptors: SIFT, ORB, BRISK, AKAZE. (In Russian).


Key words: computer vision, descriptors, bags of words, deep learning, recurrent neural networks, long short-term memory networks, video analysis.

article citation

http://psta.psiras.ru/read/psta2017_4_327-345.pdf

DOI

https://doi.org/10.25209/2079-3316-2017-8-4-327-345
   

• Supercomputing Software and Hardware •
• Artificial Intelligence, Intelligence Systems, Neural Networks •
• Information Systems in Culture and Education •
• Methods for Optimal Control and Control Theory •
• Mathematical Foundations of Programming •
• Software and Hardware for Distributed Systems and Supercomputers •

 

Adress: Ailamazyan Program Systems Institute of the Russian Academy of Sciences, PSTA Online Journal, 4 a Peter the First Street,
Veskovo village, Pereslavl area, Yaroslavl region, 152021 Russia
Phone: +7-4852-695-228.       E-mail: info@psta.psiras.ru.      Website: http://psta.psiras.ru

© Electronic Scientific Journal "Program Systems: Theory and Applications" 2010-2017
© Ailamazyan Program System Institute of RAS 2010-2017