CC BY
0METHODS OF DETERMINING AND ANALYZING THE TRAFFIC INDEX ON CITY ROADS
A. R. Akhatov, B.Sh. Eshtemirov, F.M. Nazarov
Samarkand State University named after Sharof Rashidov Samarkand, Uzbekistan
DOI: 10.24412/2073-0667-2025-1-18-28 EDX: XXXLMB
Traffic congestion has become a major issue impacting the economy, the ecology, and the general well-being of urban dwellers in the rapidly urbanizing 21st-century landscape. In order to effectively address and reduce the consequences of congestion, it is becoming more and more vital to develop and employ Road Congestion Index (RCI) calculations. The significance of RCI and its influence on the future of the city were examined in this article. For the purpose of analyzing traffic flow, the index of road congestion is crucial. Road congestion assessment, traffic planning and organization for road management, and the ability of drivers and passengers to make educated judgments on traffic are all dependent on the calculation and analysis of the congestion index. A number of assessment index approaches were examined. Traffic congestion affects the economy, the environment, public health, and general quality of life, hence it is imperative to address it for a number of reasons. Additionally, it decreases overall efficiency and wastes fuel and time. Because they make it easier for people and cars to move around, efficient triband systems are essential for economic expansion. Significant financial costs are also associated with traffic, such as higher fuel consumption, higher auto maintenance expenses, and longer freight delays, all of which can raise the price of goods and services.
Key words: Urban traffic, index of traffic jam, saturation degree, average velocity, speed interval, map show color.
References
1. Xing Y., Ban X., Liu X., Shen Q. Large-Scale Traffic Congestion Prediction Based onthe Symmetric Extreme Learning Machine ClusterFast Learning Method /7 2019. Symmetry in Cooperative Applications III, 11, 730, DOI: https://doi.org/10.3390/symll060730.
2. Liu L., Lian M., Lu C., Zhang S., Liu R., Xiong X.X. TCSA: A Traffic Congestion Situation Assessment Scheme Based on Multi-Index Fuzzy Comprehensive Evaluation in 5G-IoV /7 2022. Electronics 11, 1032, DOI: https://doi.org/10.1177/1687814018781482.
3. Rashidov A., Akhatov A.R., Xazarov F.M. Real-Time Big Data Processing Based on a Distributed Computing Mechanism in a Single Server /7 In Stochastic Processes and Their Applications in Artificial Intelligence (P. 121 138). IGI Global. DOI: https://doi.org/10.4018/978-l-6684-7679-6.ch009.
4. Xazarov F.M., Y. S. S. o'g'li, E. B. S. o'g'li. Algorithms To Increase Data Reliability In Video Transcription /7 2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT), Washington DC, DC, USA, 2022, P. 1 6, DOI: 10.1109/AICT55583.2022.10013558.
© A.R. Akhatov, B.Sh. Eshtemirov, F.M. Xazarov, 2025
5. Ghosh B., Basu B., O'Mahonv M. Bavesian Time-Series Model for Short-Term Traffic Flow Forecasting /7 .J. Transp. Eng. 2007. N 133. P. 180 189.
6. Chow A.H., Santacreu A., Tsapakis I., Tanasaranond G., Cheng T. Empirical assessment of urban traffic congestion /7 J. Adv. Transp. 2014. N 48. P. 1000 1016.
7. Guo .J., Huang W., Williams B.M. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification /7 Transp. Res. Part C 2014. N 43. P. 50 64.
8. Yang Q., Zhang B., Gao P. Based on improved dynamic recurrent neural network for short time prediction of traffic volume /7 .J. .Jilin Univ. Eng. Edit. 2012. N 4. P. 887 891.
9. Shankar H., Raju P. L.N., Rao K.R. M. Multi model criteria for the estimation of road traffic congestion from traffic flow information based on fuzzy logic /7 .J. Transp. Technol. 2012. N 2. P. 50.
10. Li S., Da Xu L., Zhao S. 5G Internet of Things: A survey. .J. Ind. Inf. /7 Integr. 2018. N 10. P. 1 9.
11. Duan W., Gu .J., Wen M., Zhang G., Ji Y., Mumtaz S. Emerging Technologies for 5G-IoV Networks: Applications, Trends and Opportunities /7 IEEE Netw. 2020. N 34. P. 283 289.
12. Wang Z., Li T., Xiong N., Pan Y. A novel dynamic network data replication scheme based on historical access record and proactive deletion /7 .J. Supercomput. 2012. N 62. P. 227 250.
13. Ahmad M., Chen Q., Khan, Z. Microscopic Congestion Detection Protocol in VANETs /7 .J. Adv. Transp. 2018, 2018, 6387063.
14. Makhmadiyarovich N.F., Sherzodjon Y. Methods of increasing data reliability based on distributed and parallel technologies based on bloekehain /7 Artificial Intelligence, Bloekehain, Computing and Security Volume 2. cBook ISBN: 9781032684994, P. 637 642, .January 2023.
15. Akhatov A., Rashidov A., Renavikar A. Optimization of the database structure based on Machine Learning algorithms in case of increased data flow /7 Artificial Intelligence. Bloekehain. Computing and Security Volume 2, CRC Press, 2023. P. 675 680.
16. Guo W., Xiong N., Vasilakos, A. V., Chen G., Cheng H. Multi-source temporal data aggregation in wireless sensor networks /7 Wirel. Pers. Commun. 2011. N 56. P. 359 370.
17. Shang Q., Lin C., Yang Z., et al. Short-term traffic flow prediction model using particle swarm optimization based combined kernel function-least squares support vector machine combined with chaos theory /7 .J. Advances in Mechanical Engineering, 2016. N 8. P. 1 12.
18. Rashidov A., Akhatov A., Aminov I., Mardonov D. Distribution of data flows in distributed systems using hierarchical clustering /7 International conference on Artificial Intelligence and Information Technologies (ICAIIT 2023), Uzbekistan, Samarkand, 2023.
19. Sabharwal M., Nazarov F.M., Eshtemirov B. Effectiveness Analysis Of Bloekehain Mechanisms Using Consensus Algorithms /7 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), ISBN: 978-1-6654-7436-8/22/, DOI: 10.1109/ICAC3N56670.2022.10074408, 16 17 December, 2022.
20. Nazarov F.M., Yarmatov S. Optimization of Prediction Results Based on Ensemble Methods of Machine Learning /7 2023 International Russian Smart Industry Conference (SmartlndustrvCon), Sochi, Russian Federation, 2023, P. 181 185, DOI: 10.1109/SmartIndustryCon57312.2023.10110726.
21. Akhatov A., Nazarov F. M., Eshtemirov B. Detection and analysis of traffic jams using computer vision technologies /7 International conference on Artificial Intelligence and Information Technologies (ICAIIT 2023). Uzbekistan, Samarkand, 2023. N 2. P. 761 766.
МЕТОДЫ ОПРЕДЕЛЕНИЯ И АНАЛИЗА ИНДЕКСА ДВИЖЕНИЯ НА ГОРОДСКИХ ДОРОГАХ
А. Р. Ахатов, Б. Ш. Эштемиров, Ф. М. Назаров
Самаркандский государственный университет, 140101, Самарканд, Узбекистан
УДК 65.012
DOI: 10.24412/2073-0667-2025-1-18-28 EDX: XXXLMB
Пробки на дорогах стали серьезной проблемой, влияющей на экономику, экологию и общее благополучие городских жителей в быстро урбанизирующемся ландшафте 21-х'о века. Для эффективного решения и уменьшения последствий пробок становится все более и более важным разрабатывать и использовать расчеты индекса загруженности дорог (RCI). Значимость RCI и сх'о влияние на будущее х'орода были рассмотрены в этой статье. Для анализа транспортного потока индекс загруженности дорог имеет решающее значение. Оценка загруженности дорог, планирование движения и организация управления дорогами, а также способность водителей хх пассажиров принимать обоснованные решения о дорожном движении зависят от расчета и анализа индекса загруженности. Был рассмотрен ряд подходов к индексу оценки. Пробки на дорогах влияют на экономику, окружающую среду, общественное здравоохранение хх общее качество жххзнхх, поэтому крайне важно решать эту проблему но ряду при чин. Кроме того, это снижает общую эффективность хх приводит к потере топлива хх времени. Поскольку они облегчают передвижение людей хх автомобилей, эффективные трехполосные системы имеют важное значение для экономического роста. С дорожным движением также связаны значительные финансовые затраты, такие как повышенный расход топлива, более высокие расходы на техническое обслуживание автомобилей хх более длительные задержки грузов, что может привести к повышению цен на товары хх услуги.
Ключевые слова: городские пробки, индекс пробок, степень насыщенности, средняя скорость, интервал скорости, цвет отображения карты.
Introduction. Millions of people see traffic congestion every day; they are now an unavoidable aspect of living in a contemporary metropolis. Traffic congestion will continue to have negative effects as cities expand and become more crowded. The ramifications of traffic congestion are felt in many facets of our life, from environmental concerns to economic ones. Although it may just appear to be a small annoyance, traffic congestion has far-reaching and complex effects. The knock-on effects of traffic include everything from health issues to environmental deterioration and economic downturns |2|, Urban planning, funding for public transportation, and the implementation of economical and environmentally friendly transportation options are all necessary components of a comprehensive strategy to address these issues. Traffic congestion affects the economy, the environment, public health, and general quality of life, hence it is imperative to address it for a number of reasons. Additionally, it decreases overall efficiency and wastes fuel and time. Because they make it easier for people and
(с) A. P. Ахатов, Б. Ш. Эштемиров, Ф.М. Назаров, 2025
Table 1
Traffic congestion level 5
UB BU MiC MoC SC
SI H, E MR SR, B (65,300) (40,300) (35,300) (50,65] (30,40] (25,35] (35,50] (20,30] (15,25] (20,35] (15,20] (10,15] [0,20] [0,15] [0,10]
CV (0,20) (0,20) [20,40) [40,60) [60,80)
MShC LG G Y R DR
UB Unblocked. BU Basic Unblocked. MiC Mild Congestion. MoC Moderate Congestion. SC Serions Congestion. SI Speed Interval (km/h), H Highways. E Expressways. MR Main Road SR. Secondary Roads. B Branches. CV Congestion Value, MShC Map Show Color, LG Light green, G Green, Y Yellow, R Red, DR Deep red
cars to move around, efficient triband systems are essential for economic expansion. Significant financial costs are also associated with traffic, such as higher fuel consumption, higher auto maintenance expenses, and longer freight delays, all of which can raise the price of goods and services. An indicator used to assess the degree of traffic congestion in a given location -typically an urban area or a particular road — is the Traffic Congestion Index (TCI) |1|, This is a figure that represents the efficiency of the traffic flow and is typically given as a percentage or score. The index considers a number of variables that contribute to traffic jam, such is the amount of vehicles on the route., the infrastructure's capacity, and the effectiveness of the transportation system. Prolonged traffic jams can lengthen travel times, increase fuel consumption, and decrease the effectiveness of transportation as a whole. Travel time data, traffic volume data, and road infrastructure data are typical components of the congestion index calculation procedures used by many authorities and organizations. Urban planners, transportation authorities, and policy makers frequently utilize this index to pinpoint high-traffic regions and devise solutions, including enhancing public transportation, increasing road capacity, or adjusting traffic signal timing, to mitigate traffic issues.
1. Traffic congestion index. There is no clear standard definition of traffic congestion. Through significant investigation and understanding of road characteristics, a congestion evaluation index in the range of |0,100| is developed. According to him, if the speed is 0, it means that the highway is very triband, that is, the value of road traffic is equal to 100 |2-4|. If the speed has an infinitely large value, then the value of traffic congestion will be equal to 0. Accordingly, traffic congestion can be divided into 5 levels (Table 1).
In this case, the relationship between the traffic index D (z) and the vehicle speed z (z > 0) can be expressed as follows:
D(z) = 100-1-—1--J)*200 (1)
v ' \l + e~az 2J K '
The a parameter in this formula varies with different road levels. Traffic at the same pace will vary on main routes, thoroughfares, main routes, secondary routes, branches, and other road levels. However, if the speed is the same, a road with a higher grade will also have a higher congestion index. So, the a parameter is used to reflect the impact of route levels on the traffic indication. Use the trained model to predict green building prices for new data.
22
Teopemii,uecmx u cucmeMit,a„n, imtfiopMamima
Table 2
a values at different path levels
H, E MR2 SR, B
0.052 0.052 0.065
sawssssssecftiesssBSagsesgDjss
Scwed(km/h]
Fig. 1. The relationship between road equivalent and trafic congestion index
The following table shows the value of a on roads of different levels (Table 2) |5-7|:
Where H — Highways, E - Expressways, MR — Main Roads, SR — Secondary Roads, B -Branches. As shown in Fig. 1, the higher the road equivalent, the higher the congestion figure at the same speed.
2. Calculation of traffic congestion index in relation to travel time. When calculating the congestion index, it is calculated based on the average speed of the flow of vehicles on the road, which can be used to estimate road congestion |7-8|. This is calculated as follows:
1. In this, M is divided into days, each day is divided into N time intervals, and there are SR paths.
2. Two movement parameters are defined,Vkij is the acceptable movement speed and Vkij is the minimum movementspeed. In this case, it is possible to refer to Table 3 that k is selected on the road section, i is a day and j is a time interval.
3. The speed of each road section can be determined based on statistical data |9|, Let's compare V^ with Vkij. If it m Vuj > Vkij■ there is no traffic congestion and the traffic index is hij = 0; if V* < V^j, the path is triband and Ikij = 10. In addition, the function of the traffic index is as follows:
hij = x 10 (2)
Vkij Vkij
4. The traffic index of for i days on road section fcis calculated as follows:
N 3=1
where bd- is the ratio of traffic volume during the whole day to j.
Table 3
Rate of traffic flow estimation using average speed
RT SL
1 2 3 4 5
E >85 (70,851 (55,701 (40,551 < 40
AR >65 (55,651 (45,551 (35,451 < 35
SR >55 (45,551 (35,451 (30,351 < 30
BR >55 (45,551 (35,451 (30,351 < 30
Where, RT — Road Type, SL — Speed Level, E — Expressway, AR — Arterial road, SR -Secondary Roads, B — Branches Road,
Table 4
Traffic congestion index based on traffic flow rate
Time 7am- 8am- 9 am- 10 am- 11am- 12 am-
interval 8am 9 am 10am 11am 12am 1pm
Average speed (km/h) 13.70 19.10 22.40 50.30 61.10 52.10
Congestion index 8.60 7.90 7.10 2.10 0.10 1.30
Time 1pm- 2pm- 3pm- 4pm- 5pm- 6pm-
interval 2pm 3pm 4pm 5pm 6pm 7pm
Average speed (km/h) 58.30 60.10 61.03 53.20 49.40 52.90
Congestion index 0.10 0.21 0.32 0.02 0.00 0.01
5, The traffic index If on the zth day in a certain area is expressed as follows:
SR
(4)
k=1
where af is proportional to the flow rate in the knd part of the entire path. Similarly, the congestion index of l\rea is defined as 110-111:
M
(5)
¿=1
where is proportional to the flow rate of the znd day of the entire research period. Since the same j'-road section is explored on the same ¿-day, the membership function of the traffic index Clk in the time interval k — can be constructed as follows in the time interval k.
Clfe — hij — <
( 0, Vkij > 50
10 < Vkij < 50
40
(6)
10, Vkij < 10
Table 4 shows the traffic index at different time intervals.
Traffic congestion index based on road saturation level. There is a concept of the average level of saturation of city roads. If the speed of traffic on the road is 60 km/h, the power
24
Teopemii,uecmx u cu,cmeMH,ax imtfiopMamima
Table 5
Calculation values of the traffic index based on the saturation level of the road are presented
Time 7am- 8 am- 9 am- 10 am- 11am- 12 am-
interval 8 am 9 am 10am 11am 12am 1pm
Flow rate (veh/h) 3354 3078 3246 2676 2070 2688
Saturation degree, x2 1.20 1.10 1.16 0.96 0.74 0.96
Congestion index, C2 9.90 9.70 9.83 9.19 5.10 8.90
Time 1pm- 2pm- 3pm- 4pm- 5pm- 6pm-
interval 2pm 3pm 4pm 5pm 6pm 7pm
Flow rate (veh/h) 2417 2312 2203 2514 2385 2311
Saturation degree, x2 0.83 0.82 0.75 0.89 0.86 0.82
Congestion index, C2 6.90 7.30 5.80 8.10 7.80 7.50
of the road will be 1400 veh/h |12-14|. The level of saturation is directly proportional to the level of traffic, and as the level of road saturation increases, so does the level of congestion and vice versa. The degree of saturation can be divided into 6 parts and calculated in the range |0,10|, Using the saturation level x2. the traffic congestion index C2 membership function can be calculated. In this case, the evaluation function can be expressed as follows:
C2 =
fi * 2, s2 < 0.4
* 2 + 2, 0.4 < x2 < 0.6 ^^ * 2 + 4, 0.6 < x2 < 0.75 * 2 + 6, 0.75 < < 0.9 ™ * 2 + 8, 0.9 < z2 < 1 10," x2 > 1
X2
(?)
Table 5 shows the traffic index according to the degree of saturation of the road in the period of 12 hours (7-19),
Calculation of congestion index based on comprehensive parameters,
In this case, the traffic index can be determined by several parameters. All of them can be obtained through video footage |15|,
Create membership functions. The lower speed ratio can be divided into 3 levels:
a) lower;
b) medium;
c) high,
A low level of congestion means that it will last for a short time and the traffic flow on the road is ideal, and conversely, if the traffic flow is high, it means that the congestion situation will last for a long time. Fig, 2 shows the graph of the dependence of the membership function on the lower speed ratio.
The corresponding membership function of the lower speed ratio can be expressed as:
1, K < 0.1
Vi =
0.2—K 0.1 '
0.1 < K < 0.2
(8)
0, K > 0.2
Fig. 2. Membership function graph of travel productivity
Fig. 3. The degree of membership of the saturation level
Low Medium High
1.0
r
o.s AA
0 In
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0
Fig. 4. Lower speed ratio membership level
uM = <
Vh =
0, K< 0.1
0.1 < if <0.2
1, 0.2 < K < 0.4
0.4 < K < 0.5 0, 0.5 < K < 1
0, K < 0.4
0.4 < K < 0.5
1, ' K > 0.5
(9)
(10)
where K is the lower speed ratio, ¡j,i is the corresponding membership for the lower level, uM is the corresponding membership for the middle level, and /X/j is the corresponding membership for the higher level.
In the same way, the membership function can be constructed when the degree of saturation is divided into three levels as in Fig. 3 118-211.
For example, if the low-speed travel speed is 0.14, the corresponding low, medium, and high travel efficiency vectors are (0.6, 0.4, 0) |16-17|.
Travel productivity can be conveniently divided into 6 levels: A, B, C, D, E and F. In this case, the interval |0,1| can be adjusted as follows (A,0) and (F.l) Fig. 4.
26
Теоретическая и системная, информатика
Table 6
Membership level of each index
Traffic Average Satura- Travel Membership Membership
Time flow speed tion effici- of saturation of travel
(veh/h) (km/h) degree ency degree efficiency
7am 8am 3451 15.06 1.18 0.76 1.01 1.01
8am 9am 3473 13.34 1.13 0.70 1.10 1.02
9 am 10 am 3241 19.87 1.09 0.68 1.02 0.32
10 am 11am 2076 46.13 0.96 0.31 1.20 0.38
11am 12 am 2671 57.95 0.75 0.20 0.67 1.12
12 am 1pm 3583 45.58 0.94 0.28 1.06 0.33
1pm 2pm 2124 57.16 0.77 0.13 0.45 1.07
2pm 3pm 2382 60.36 0.79 0.04 0.47 1.04
3pm 4pm 2124 58.12 0.78 0.01 0.59 1.13
4pm 5pm 2665 58.76 0.85 0.19 0.27 0.21
5pm 6pm 2316 51.40 0.83 0.23 0.35 0.32
6pm 7pm 2494 49.32 0.78 0.17 0.38 0.19
The measured traffic data and index membership levels are presented in Table 6,
Conclusion, In the context of rapid urbanization and the complexity of modern transportation, the Road Traffic Index has emerged as an important tool for urban planners and citizens. Its importance is not only in diagnosing the problems caused by traffic, but also in taking strategic measures, supporting sustainable mobility solutions and shaping the future of urban transport. As technologies continue to evolve, the role of RCI calculations will become more important, contributing to the development of sustainable, efficient and human-centered urban environments. Embracing and improving the use of RCI will be integral to creating cities that are not only well-connected, but also sustainable and livable for generations to come.
In conclusion, solving traffic congestion is important for promoting economic development, protecting the environment, ensuring public health and safety, and improving the overall quality of life for people. Addressing congestion has often shown to require a multi-pronged approach, including investment in public transport, infrastructure improvements, smart urban planning and the adoption of sustainable transport alternatives.
Список литературы
1. Xing Y., Ban X., Liu X., Shcn Q. Large-Seale Traffic Congestion Prediction Based onthc Symmetric Extreme Learning Machine ClusterFast Learning Method /7 2019. Symmetry in Cooperative Applications III, 11, 730, DOI: https://doi.org/10.3390/symll060730.
2. Liu L., Lian M., Lu C., Zhang S., Liu R., Xiong N.N. TCSA: A Traffic Congestion Situation Assessment Scheme Based on Multi-Index Fuzzy Comprehensive Evaluation in 5G-IoV /7 2022. Electronics 11, 1032, DOI: https://doi.org/10.1177/1687814018781482.
3. Rashidov A., Akhatov A.R., Nazarov F.M. Real-Time Big Data Processing Based on a Distributed Computing Mechanism in a Single Server /7 In Stochastic Processes and Their Applications in Artificial Intelligence (P. 121 138). IGI Global. DOI: https://doi.org/10.4018/978-l-6684-7679-6.ch009.
4. Nazarov F.M., Y. S. S. o'g'li, E. B. S. o'g'li. Algorithms To Increase Data Reliability In Video Transcription /7 2022 IEEE 16th International Conference on Application of Information and Communication Technologies (AICT), Washington DC, DC, USA, 2022, P. 1 6, DOI: 10.1109/AICT55583.2022.10013558.
5. Ghosh B., Basu B., O'Mahonv M. Bavesian Time-Series Model for Short-Term Traffic Flow Forecasting /7 J. Transp. Eng. 2007. N 133. P. 180 189.
6. Chow A.H., Santacreu A., Tsapakis I., Tanasaranond G., Cheng T. Empirical assessment of urban traffic congestion /7 J. Adv. Transp. 2014. N 48. P. 1000 1016.
7. Guo J., Huang W., Williams B.M. Adaptive Kalman filter approach for stochastic short-term traffic flow rate prediction and uncertainty quantification /7 Transp. Res. Part C 2014. N 43. P. 50 64.
8. Yang Q., Zhang B., Gao P. Based on improved dynamic recurrent neural network for short time prediction of traffic volume /7 J. Jilin Univ. Eng. Edit. 2012. N 4. P. 887 891.
9. Shankar H., Raju P. L.N., Rao K.R. M. Multi model criteria for the estimation of road traffic congestion from traffic flow information based on fuzzy logic /7 J. Transp. Teehnol. 2012. N 2. P. 50.
10. Li S., Da Xu L., Zhao S. 5G Internet of Things: A survey. J. Ind. Inf. /7 Integr. 2018. N 10. P. 1 9.
11. Duan W., Gu J., Wen M., Zhang G., Ji Y., Mumtaz S. Emerging Technologies for 5G-IoV Networks: Applications, Trends and Opportunities /7 IEEE Netw. 2020. N 34. P. 283 289.
12. Wang Z., Li T., Xiong N., Pan Y. A novel dynamic network data replication scheme based on historical access record and proactive deletion /7 J. Supercomput. 2012. N 62. P. 227 250.
13. Ahmad M., Chen Q., Khan, Z. Microscopic Congestion Detection Protocol in VANETs /7 J. Adv. Transp. 2018, 2018, 6387063.
14. Makhmadivarovich N.F., Sherzodjon Y. Methods of increasing data reliability based on distributed and parallel technologies based on bloekehain /7 Artificial Intelligence, Bloekehain, Computing and Security Volume 2. cBook ISBN: 9781032684994, P. 637 642, January 2023.
15. Akhatov A., Rashidov A., Renavikar A. Optimization of the database structure based on Machine Learning algorithms in case of increased data flow /7 Artificial Intelligence. Bloekehain. Computing and Security Volume 2, CRC Press, 2023. P. 675 680.
16. Guo W., Xiong N., Vasilakos, A. V., Chen G., Cheng H. Multi-source temporal data aggregation in wireless sensor networks /7 Wirel. Pers. Commun. 2011. N 56. P. 359 370.
17. Shang Q., Lin C., Yang Z., et al. Short-term traffic flow prediction model using particle swarm optimization based combined kernel function-least squares support vector machine combined with chaos theory /7 -J. Advances in Mechanical Engineering, 2016. N 8. P. 1 12.
18. Rashidov A., Akhatov A., Aminov I., Mardonov D. Distribution of data flows in distributed systems using hierarchical clustering /7 International conference on Artificial Intelligence and Information Technologies (ICAIIT 2023), Uzbekistan, Samarkand, 2023.
19. Sabharwal M., Nazarov F.M., Eshtemirov B. Effectiveness Analysis Of Bloekehain Mechanisms Using Consensus Algorithms /7 2022 4th International Conference on Advances in Computing, Communication Control and Networking (ICAC3N), ISBN: 978-1-6654-7436-8/22/, DOI: 10.1109/ICAC3N56670.2022.10074408, 16 17 December, 2022.
20. Nazarov F.M., Yarmatov S. Optimization of Prediction Results Based on Ensemble Methods of Machine Learning /7 2023 International Russian Smart Industry Conference (SmartlndustrvCon), Sochi, Russian Federation, 2023, P. 181 185, DOI: 10.1109/SmartIndustryCon57312.2023.10110726.
21. Akhatov A., Nazarov F. M., Eshtemirov B. Detection and analysis of traffic jams using computer vision technologies /7 International conference on Artificial Intelligence and Information Technologies (ICAIIT 2023). Uzbekistan, Samarkand, 2023. N 2. P. 761 766.
28
Теоретическая и аист,е,м,пая информатика
Ша
та имени
05.01.02
Ахатов Акмаль Руста-мович — e-mail: akmalar® rambler.ru, тел: -998902716418. Д-р техн. наук, профессор, проректор по международному сотрудничеству Самаркандского государственного университе-арофа Рашидова по специальности «Системный анализ, управление и обработка информации». Количество опубликованных научных работ — более 100. Область научных интересов: обработка данных, повышение и обеспечение достоверности этого процесса, автоматизация процессов принятия решений и управления при обработке информации, системы искусственного интеллекта и большие данные.
Akmal Rustamovich Akhatov e-mail: [email protected], phone: -998902716418. Doctor of technical sciences, professor, vice-rector for international cooperation of Samarkand State University named after Sharof Rashidov, specialty 05.01.02 — "Systematic analysis, management and information processing". The number of published scientific works is more than 100. Field of scientific interests: data processing, increasing and ensuring the reliability of this process, automation of decision-making and management processes in information processing, artificial intelligence systems and Big Data.
Эштемиров Бунед
Шерали угли e-mail:
[email protected], тел.: -998979120814. Аспирант Самаркандского государственного университета имени Ша-рофа Рашидова. Количество опубликованных научных работ — более 10. Область научных интересов: большие данные, технологии распределенных вычислений, оптимизация систем управления данными, искус-
ственный интеллект, технологии программирования, веб-технологии.
Eshtemirov Bunyod Sherali o'g'li e-mail: [email protected], phone: -998979120814. A doctoral student of Samarkand State University named after Sharof Rashidov. The number of published scientific works is more than 10. Field of scientific interests: Big Data, distributed computing technologies, optimization of data management systems, artificial intelligence, programming technologies, web technologies.
Назаров Файзулло
Махмадиярович e-mail: [email protected], тел: -9989944798640. Канд. техн. наук, доцент, декан факультета интеллектуальных систем и компьютерных технологий Самаркандского государственного университета имени Шарофа Рашидова по специальности 05.01.02 — «Системный анализ, управление и обработка информации». Количество опубликованных научных работ: более 50. Область научных интересов: искусственный интеллект, информационная безопасность, технология Blockchain, технологии программирования, технология больших данных, технологии р аспр еделенных вычислений.
Nazarov Fayzullo Makhmadiyarovich e-mail: [email protected], phone: -9989944798640. PhD, associate professor, dean of the faculty of Faculty of Intelligent Systems and Computer Technologies of Samarkand State University named after Sharof Rashidov, specialty 05.01.02 — "Systematic analysis, management and information processing". The number of published scientific works is more than 50. Field of scientific interests: Artificial intelligence, information security, Blockchain technology, programming technologies, Big Data technologies, distributed computing technologies.
Дат,а поступления — 02.07.2024
