Trafik Yoğunluğunun Takibi için Zaman Serileri Analizi Tabanlı Karar Destek Sisteminin Uygulanması

Öz

İnternet veri aktarım ağ bant genişliği teknolojilerindeki gelişmelerle doğru orantılı olarak, internetin günlük hayatta kullanımı daha yaygın hale gelmektedir. Nesnelerin interneti (IoT) kavramı, bu teknolojilere eklemlenebilecek sayısız nesnenin oluşturduğu yeni teknolojik ekosistemi ifade etmektedir. IoT kavramının en önemli vizyonlarının başında akıllı şehir konsepti gelmektedir. Şehirlerde, iletişimden ulaşıma kadar her bir bileşenin internete bağlı şekilde, yapay zekaya dayalı bilgisayar algoritmalarıyla kontrol ve takip edilmesi anlamına gelen bu konsept, gittikçe daha kalabalık hale gelen şehirlerin, bir kaosa girmeden düzen içinde işlemesini sağlamayı vaat etmektedir. Bu çalışmada, şehir trafik akış yoğunluğunu takip eden ve geleceğe yönelik öngörüler sağlayan, zaman serisi analizine dayalı bir karar destek yöntemi önerilmektedir. Önerilen yaklaşım, yapay sinir ağı tabanlı bir zaman serisi karar destek yöntemidir. Çalışmada şehir trafiğinde belirlenen rastgele kavşaklardan, saatlik geçen araç sayıları veri olarak kullanılmıştır. Kavşakların sahip olduğu araç yoğunluğunun bağıl etkileri hesaplanmış ve trafik akışıyla ilgili modeller tasarlanmıştır. Oluşturulan modellerin sağladığı tahminsel verilerin doğruluk oranına göre en uygun trafik akış modeli belirlenmektedir. Veriler sabit kabul edildiğinde, yapay sinir ağı tabanlı zaman serisi modelleri J1 ve J2 için %93 ve J3 için %66 doğrulukla tahminler yapılabilmektedir. Dinamik veri modeli için, bağıl etkileşime sahip trafik akışı tasarımına göre, kavşaklar arasında seri bağlı trafik modelinin 0.86 ile en yüksek doğruluğa sahip olduğu bulunmuştur.

Anahtar Kelimeler

• Veri Madenciliği
• Karar Verme
• Zaman Serileri Analizi
• Karar Destek Sistemleri
• Yapay Sinir Ağları

Implementing of Time Series Analysis Based Decision Support System for Traffic Density Monitoring

Abstract

In direct proportion to developments in bandwidth technologies for Internet data transmission networks, the use of the internet in daily life is becoming more common. The concept of the Internet of Things (IoT) refers to the new technological ecosystem consisting of numerous objects that can be added to these technologies. One of the most important visions of the IoT is the concept of a smart city. This concept, which means that every component in cities, from communications to transportation, is connected to the internet and controlled and monitored by artificial intelligence-based computer algorithms, promises to ensure that increasingly crowded cities function in an orderly manner without descending into chaos. This study proposes a decision support system based on time series analysis that monitors traffic density in cities and makes future predictions. The proposed procedure is an Artificial Neural Network (ANN) based Time Series (TS) decision support technique. The study used the number of vehicles passing by three randomly selected junctions every hour as data. The relative effects of vehicle density at the junctions were calculated and traffic flow models were designed. The most appropriate traffic flow model is determined based on the accuracy of the forecast data provided by the models created. When the data are considered stable, predictions can be made with 93% accuracy for the ANN-based TS models J1 and J2 and 66% for J3. For the dynamic model, according to the design of the traffic flow, it was found that the model of serially connected traffic between the junctions has the highest accuracy with a joint mean value of 0.86.

Keywords

• Data Mining
• Decision-Making
• Time Series Analysis
• Decision Support Systems
• Artificial Neural Network

References

1. Ahmed, G., Hilmani, A., Maizate, A., & Hassouni, L. (2020). Automated Real-Time Intelligent Traffic Control System for Smart Cities Using Wireless Sensor Networks. Wireless Communications and Mobile Computing. doi:https://doi.org/10.1155/2020/8841893
2. Bearn, C., Mingus, C., & Watkins, K. (2018). An adaption of the level of traffic stress based on evidence from the literature and widely available data. Research in Transportation Business & Management, 29, 50-62. doi:https://doi.org/10.1016/j.rtbm.2018.12.002
3. Bijl, B. v., Gijsbertsen, B., Loon, S. v., Reurich, Y., Valk, T. d., Koch, T., & Dugundji, E. (2022). A Comparison of Approaches for the Time Series Forecasting of Motorway Traffic Flow Rate at Hourly and Daily Aggregation Levels. Procedia Computer Science, 201, 213-222. doi:https://doi.org/10.1016/j.procs.2022.03.030
4. Chen, Y.-T., Sun, E. W., Chang, M.-F., & Lin, Y.-B. (2021). Pragmatic real-time logistics management with traffic IoT infrastructure: Big data predictive analytics of freight travel time for Logistics 4.0. International Journal of Production Economics, 238. doi:https://doi.org/10.1016/j.ijpe.2021.108157
5. Chhajer, P., Shah, M., & Kshirsagar, A. (2022). The applications of artificial neural networks, support vector machines, and long–short term memory for stock market prediction. Decision Analytics Journal, 2. doi:https://doi.org/10.1016/j.dajour.2021.100015
6. Dey, A. (2016). Machine Learning Algorithms: A Review. International Journal of Computer Science and Information Technologies, 7(3), 1174-1179. http://www.ijcsit.com/ adresinden alındı
7. Espinosa, S. I., Ynoue, R., Giannotti, M., Ropkins, K., & De Freitas, E. D. (2019). Generating traffic flow and speed regional model data using internet GPS vehicle records. MethodsX, 6, 2065-2075. doi:https://doi.org/10.1016/j.mex.2019.08.018
8. Govindan, K., Mina, H., & Alavi, B. (2020). A decision support system for demand management in healthcare supply chains considering the epidemic outbreaks: A case study of coronavirus disease 2019 (COVID-19). Transportation Research Part E: Logistics and Transportation Review, 138. doi:https://doi.org/10.1016/j.tre.2020.101967

9. Grosan, C., & Abraham, A. (2011). Artificial Neural Networks: Intelligent Systems: A Modern Approach. 281-323. doi:https://doi.org/10.1007/978-3-642-21004-4_12
10. He, J., Yang, H., He, L., & Zhao, L. (2021). Neural networks based on vectorized neurons. Neurocomputing, 465, 63-70. doi:https://doi.org/10.1016/j.neucom.2021.09.006
11. Huang, H., Chen, J., Sun, R., & Wang, S. (2022). Short-term traffic prediction based on time series decomposition. Physica A: Statistical Mechanics and its Applications, 585. doi:https://doi.org/10.1016/j.physa.2021.126441
12. Jastrzebska, A. (2022). Time series classification through visual pattern recognition. Journal of King Saud University - Computer and Information Sciences, 34(2), 134-142. doi:https://doi.org/10.1016/j.jksuci.2019.12.012
13. Karimi, H., Ghadirifaraz, B., Boushehri, S., Hosseininasab, S. M., & Rafiei, N. (2022). Reducing traffic congestion and increasing sustainability in special urban areas through one-way traffic reconfiguration. Transportation, 49. doi:10.1007/s11116-020-10162-4
14. Kuddus, M. A., Tynan, E., & McBryde, E. (2020). Urbanization: a problem for the rich and the poor? Public Health Reviews, 41(1). doi:https://doi.org/10.1186/s40985-019-0116-0
15. Li, W., Zuo, M., Zhao, H., Xu, Q., & Chen, D. (2022). Prediction of coronary heart disease based on combined reinforcement multitask progressive time-series networks,. Methods, 198, 96-106. doi:https://doi.org/10.1016/j.ymeth.2021.12.009
16. Liang, X., Chen, R. C., He, Y., & Chen, Y. (2013). Associating stock prices with web financial information time series based on support vector regression. Neurocomputing, 115, 142-149. doi:https://doi.org/10.1016/j.neucom.2013.01.011.
17. Lim, S. (2021). Hebbian learning revisited and its inference underlying cognitive function. Current Opinion in Behavioral Sciences, 38, 96-102. doi:https://doi.org/10.1016/j.cobeha.2021.02.006
18. Lim, S., Kim, S. J., Park, Y., & Kwon, N. (2021). A deep learning-based time series model with missing value handling techniques to predict various types of liquid cargo traffic. Expert Systems with Applications, 184. doi:https://doi.org/10.1016/j.eswa.2021.115532
19. Masuduzzaman, M., Islam, A., Sadia, K., & Shin, S. Y. (2022). UAV-based MEC-assisted automated traffic management scheme using blockchain. Future Generation Computer Systems. doi:https://doi.org/10.1016/j.future.2022.04.018
20. McCulloch, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4), 115-133. doi:https://doi.org/10.1007/BF02478259
21. Mumali, F. (2022). Artificial neural network-based decision support systems in manufacturing processes: A systematic literature review. Computers & Industrial Engineering, 165. doi:https://doi.org/10.1016/j.cie.2022.107964
22. Nugmanova, A., Arndt, W. H., Hossain, M., & Kim, J. R. (2019). Effectiveness of Ring Roads in Reducing Traffic Congestion in Cities for Long Run: Big Almaty Ring Road Case Study. Sustainability, 11(18). doi:10.3390/su11184973
23. Ponnusamy, M., & Alagarsamy, A. (2021). Traffic monitoring in smart cities using internet of things assisted robotics. Materials Today: Proceedings. doi:https://doi.org/10.1016/j.matpr.2021.03.192
24. Shahid, N., Shah, M. A., Khan, A., Maple, C., & Jeon, G. (2021). Towards greener smart cities and road traffic forecasting using air pollution data. Sustainable Cities and Society, 72. doi:https://doi.org/10.1016/j.scs.2021.103062
25. Singh, V. P., Pandey, M. K., Singh, P. S., & Karthikeyan, S. (2020). Neural Net Time Series Forecasting Framework for Time-Aware Web Services Recommendation. Procedia Computer Science, 171, 1313-1322. doi:https://doi.org/10.1016/j.procs.2020.04.140
26. Soni, G., Kumar, S., Mahto, R. V., Mangla, S. K., Mittal, M. L., & Lim, W. M. (2022). A decision-making framework for Industry 4.0 technology implementation: The case of FinTech and sustainable supply chain finance for SMEs,. Technological Forecasting and Social Change,, 180. doi:https://doi.org/10.1016/j.techfore.2022.121686
27. Wang, P., Zheng, X., Ai, G., Liu, D., & Zhu, B. (2020). Time series prediction for the epidemic trends of COVID-19 using the improved LSTM deep learning method: Case studies in Russia, Peru and Iran. Chaos, Solitons & Fractals, 140. doi:https://doi.org/10.1016/j.chaos.2020.110214
28. Withington, L., De Vera, D. D., Guest, C., Mancini, C., & Piwek, P. (2021). Artificial neural networks for classifying the time series sensor data generated by medical detection dogs. Expert Systems with Applications, 184. doi:https://doi.org/10.1016/j.eswa.2021.115564
29. Wu, J., Xu, K., Chen, X., Li, S., & Zhao, J. (2022). Utilizing the structural information of financial time series for stock prediction. Information Sciences, 588, 405-424. doi:https://doi.org/10.1016/j.ins.2021.12.089
30. Wu, K., Fu, Y., & Kong, D. (2022). Does the digital transformation of enterprises affect stock price crash risk? Finance Research Letters, 48. doi:https://doi.org/10.1016/j.frl.2022.102888
31. Xing, J., Wu, W., Cheng, Q., & Liu, R. (2022). Traffic state estimation of urban road networks by multi-source data fusion: Review and new insights. Physica A: Statistical Mechanics and its Applications, 595. doi:https://doi.org/10.1016/j.physa.2022.127079