2687-0517 12 3 2019 1-83

RAR RUS 7-24 Solomenko Institute of Transport Problems of the Russian Academy of Sciences, University National Technology Initiative 2035 Seliverstov Yaroslav maxwell_8-8@mail.ru Peter the Great St.Petersburg Polytechnic University Nikitin Kirill execiter@mail.ru Solomenko Institute of Transport Problems of the RAS Shatalova Natalya shatillen@mail.ru

St. Petersburg, Russian Federation

Saint Petersburg Stieglitz State Academy of Art and Design Kiselev Arseny ars8ars@mail.ru

St. Petersburg, Russian Federation

Road pavement assessment of the North-West Federal District using sentiment analysis of the Internet user reviews As a result of the analysis, it was revealed that social networks, thematic communities, transport portals are a source of actual information about the traffic situation. The article deals with the task of analyzing the road pavement assessment of the North-West Federal District from reviews posted in the web. To solve this problem, a system for automatic classification of reviews based on the sentiment classifier has been developed. The crawler was developed using the Scrapy framework in Python3 and collected reviews from the site http://autostrada.info/ru. The methods of vectorization and lemmatization of texts and their implementation in the Scikit-Learn library are considered: Bag-of-Words, N-gram, CountVectorizer and TF-IDF Vectorizer. For the classification, a naive Bayes algorithm and a linear classifier model with optimization of stochastic gradient descent were used. As a training sample, a base of marked reviews from the Twitter resource was used. The classifier was trained, during which the cross-validation strategy and the ShuffleSplit method were used. According to the results of validation, the linear model with the N-gram scheme and the TF-IDF Vectorizer turned out to be the best. During the approbation of the developed system, the collection and analysis of feedback related to the quality of transport networks in the North-West Federal District was conducted. Based on the results, a color marking of the roads was produced, reflecting the visibility of the research results. Conclusions and prospects for the further development of this study are given. 10.18721/JCSTCS.12301 004.8, 004.62, 007.5 , 51-74, 510.67, 656 automatic text analysis crowlers texts classification intelligent transport systems machine learning TF-IDF N-gram naive Bayes algorithm linear classifier sentiment analysis https://infocom.spbstu.ru/article/2019.62.1/ 7-24.pdf

RAR RUS 25-36 Voronezh State University Bogatikov Evgenii evbogatikov@yandex.ru

Voronezh, Russian Federation

Voronezh State University Shebanov Alexandr anshebanov@hotmail.com

Voronezh, Russian Federation

Voronezh State University Angarita Lores Carlos Eduardo loresruizlozano@gmail.com

Voronezh, Russian Federation

Ultrasound detection and digital processing device The device has been developed that registers ultrasound with a frequency of up to 100 kHz, which converts it into sound in real time with a delay of less than 2 ms and reproduces the received sound. The signal frequency is changed using the fast Fourier transform and the selection of the dominant frequency in real time on a microcontroller with an ARM Cortex M3 core. The preservation of the pulse envelope with a time resolution of up to 1.2 ms and the good sensitivity of the used MEMS microphones in the ultrasound region make it possible to use the device for detecting and classifying animals' echolocation signals. The low cost of the used components and their accessibility make it possible to use the device in the domestic sphere to monitor the performance of devices that emit ultrasound, and to monitor the absence of ultrasonic noise, which can adversely affect a person's well-being during prolonged exposure. 10.18721/JCSTCS.12302 534.44 ultrasound microphone MEMS microcontroller FFT https://infocom.spbstu.ru/article/2019.62.2/ 25-36.pdf

RAR RUS 37-47 Peter the Great St.Petersburg Polytechnic University Tan Hoang Phuoc Nguyen Tan Hoang Phuoc Nguyen nguyentanhoangphuoc@gmail.com

St. Petersburg, Russian Federation

Gelgor Alexandr Improving spectral efficiency of DVB-S2 by using signals with controlled intersymbol interference and finite pulses This paper considers the formulation and solution of the optimization problems for pulse synthesis for multicomponent bandwidth-effective signals taking into account a given frequency mask. A solution is proposed for various types of optimization problems, including maximizing the free Euclidean distance and minimizing the partial correlation coefficients. The frequency mask and other parameters for error correcting LDPC and BCH encoders are taken from the DVB-S2 standard. A simulation model of the DVB-S2 system is proposed, in which RRC pulses are replaced by obtained finite optimal pulses to improve the bandwidth efficiency of the system. The simulation results show that the transition from RRC pulses to multicomponent optimal pulses leads to an increase of bandwidth efficiency by 10 %, but the system suffers the energy losses of about 0.1 and 0.25 dB for QPSK and 8PSK, respectively. 10.18721/JCSTCS.12303 621.391.8 bandwidth efficiency partial response signaling optimal finite pulses multi-component signals DVB-S2 https://infocom.spbstu.ru/article/2019.62.3/ 37-47.pdf

RAR RUS 48-57 Peter the Great St.Petersburg Polytechnic University Ovsyannikova Anna anny-ov97@mail.ru

St. Petersburg, Russian Federation

Zavialov Sergey 0000-0001-7726-8492 Volvenko Sergey The efficiency estimation of the joint application of optimal FTN signals and polar coding To develop future generations of networks it is necessary to improve both spectral and energy efficiency. The first one may be improved due to the application of optimal faster than Nyquist (FTN) signals which occupy less bandwidth comparing to «classic» signals and may be transmitted with increased symbol rate. Improvement of energy efficiency is associated with the application of error-correcting coding, in particular, polar coding and turbo coding. The using of the techniques mentioned above in total allows becoming closer to the Shannon limit. In this paper, the efficiency of the joint application of optimal signals and polar coding was estimated and polar codes and turbo codes were compared in terms of the distance to the Shannon limit. 10.18721/JCSTCS.12304 621.39 faster than Nyquist polar coding turbo coding spectral efficiency energy efficiency Shannon limit https://infocom.spbstu.ru/article/2019.62.4/ 48-57.pdf

RAR RUS 58-66 The Bonch-Bruevich Saint-Petersburg State University of Telecommunications (SUT) Ometov Aleksander alexander.ometov@gmail.com

Prospekt Bolshevikov, 22 - 1, Saint-Petersburg,193232, Russia

St. Petersburg State University of Aerospace Instrumentation Zhidanov Konstantin konstantin.zhidanov@gmail.com

St. Petersburg, Russian Federation

Saint Petersburg National Research University of Information Technologies, Mechanics and Optics Bezzateev Sergey bsv@aanet.ru

49 Kronverksky Pr. St. Petersburg, 197101 Russia

D-5155-2014 6507253900 0000-0003-3976-2971 Higher School of Economics Yevgeni A. ykoucheryavy@hse.ru

Korkeakoulunkatu 10, FI-33720 Tampere Finland

On the utilization of D2D technology in cellular networks Today, wireless research offers an enormous range of technologies for potential prototyping and real-life integration. One of the promising directions in this area is the utilization of proximity-based direct connections between mobile nodes (D2D). This paper studies proximity-based D2D communication scenarios related to beyond 5G cellular networks. A method of clustering mobile nodes in physical and social proximity is proposed. Numerical evaluation of delays, aggregated traffic, and the session interruption probability is provided aiming to identify the effects associated with the use of direct connections in 5G networks. The advantages of using classic infrastructure solutions in cases of incomplete cellular coverage are also provided. 10.18721/JCSTCS.12305 621.391 D2D 5G clustering simulation campaign wireless communications https://infocom.spbstu.ru/article/2019.62.5/ 58-66.pdf

RAR RUS 67-80 Peter the Great St.Petersburg Polytechnic University Kovalevsky Vladislav vladkov@spbstu.ru

St. Petersburg, Russian Federation

Peter the Great St.Petersburg Polytechnic University Onufriev Vadim ovavadim@gmail.com

Polytechnicheskaya, 29, St.Petersburg, 195251, Russia

Multi-agent algorithms for enterprise's key performance indicators reconciliation In this work the task of production key performance indicators' values reconciliation is set, that takes into account their hierarchical structure and interrelationships. The structural scheme of a hierarchical multiagent system for production control was developed where horizontal (sibling) and vertical (multilevel) connections between agents are shown. Then possible situations of sibling and multilevel interactions are described, such as changing of a task by the controlling agent, sending notifications about the impossibility of a maintaining current operation mode, and others. The agents’ data exchange algorithms, which are used in order to optimise key performance indicators are shown. The implementation of developed algorithms using client-server architecture is shown, which also includes at the bottom level data exchange between the agents and programmable logic controllers. The single bytes command system for agents interactions is described. 10.18721/JCSTCS.12306 004.896 cyber-physical systems intelligent control systems multiagent systems digital twin Industry 4.0. https://infocom.spbstu.ru/article/2019.62.6/ 67-80.pdf