Hava Durumu Değişkenleriyle Trafik Analizi ve Tahmini için Nesnelerin İnterneti ve Derin Öğrenmenin Entegre Edilmesi

Yıl 2025, Cilt: 6 Sayı: 1, 10 - 19

Berkay Önk , Zuhal Can

https://doi.org/10.53608/estudambilisim.1574504

Öz

Nüfus arttıkça, trafik tıkanıklığını azaltmak ve ulaşım verimliliğini artırmak için etkili trafik yönetimi giderek daha kritik hale geliyor. Bu çalışma, hava durumu verilerini önemli bir değişken olarak dahil ederek gerçek zamanlı trafik analizini ve tahminini geliştirmek için Nesnelerin İnterneti (IoT) cihazlarının ve derin öğrenme algoritmalarının entegrasyonunu araştırıyor. Önerilen sistem, daha sonra gelişmiş derin öğrenme teknikleri kullanılarak işlenen araç sayısı, tarih, saat ve hava durumu koşulları hakkında veri toplamak için IoT sensörlerinden yararlanıyor. On üç ay boyunca İstanbul'dan trafik ve hava durumu bilgilerini içeren bir veri setini kullanan çalışma, trafik modellerini tahmin etmek için bir Kapılı Yinelemeli Birim (GRU) evrişimli sinir ağı modeli kullanıyor. Bu model, 0,7729'luk ortalama bir Kök Ortalama Kare Hatası (RMSE) ile sonuçlandı. Bu araştırma, sensör dağıtımı ve veri entegrasyonunun zorlukları ve iyileştirilmiş trafik tahmin doğruluğunun faydaları da dahil olmak üzere, bu tür entegre sistemlerin kentsel ortamlarda konuşlandırılmasının pratik etkilerini tartışarak sonuçlanır.

Anahtar Kelimeler

Trafik, Nesnelerin İnterneti, Derin Öğrenme, Yönetim, Sıkışıklık

Integrating IoT and Deep Learning for Traffic Analysis and Prediction with Weather Variables

Öz

As the population grows, effective traffic management becomes increasingly critical for reducing traffic congestion and improving transportation efficiency. This study explores the integration of Internet of Things (IoT) devices and deep learning algorithms to enhance real-time traffic analysis and prediction, incorporating weather data as a significant variable. The proposed system leverages IoT sensors to collect data on the number of vehicles, date, time, and weather conditions, which are then processed using advanced deep learning techniques. Utilizing a dataset comprising traffic and weather information from Istanbul over thirteen months, the study employs a Gated Recurrent Unit (GRU) convolutional neural network model to predict traffic patterns. This model resulted in an average Root Mean Square Error (RMSE) of 0.7729. This research concludes by discussing the practical implications of deploying such integrated systems in urban settings, including the challenges of sensor deployment and data integration and the benefits of improved traffic prediction accuracy.

Anahtar Kelimeler

Traffic, Internet of Things, Deep Learning, Management, Congestion

Kaynakça

• Phapale, A., Shravagi, S. 2024. Traffic Flow Prediction on Road using Machine Learning. International Journal of Applied Advanced Multidisciplinary Research, 2, 31–38. DOI: 10.59890/ijaamr.v2i1.690.
• Deekshetha, H. R., Shreyas Madhav, A. V., Tyagi, A. K. 2022. Traffic Prediction Using Machine Learning. Evolutionary Computing and Mobile Sustainable Networks: Proceedings of ICECMSN 2021, Springer, 969–983.
• Zantalis, F., Koulouras, G., Karabetsos, S., Kandris, D. 2019. A Review of Machine Learning and IoT in Smart Transportation. Future Internet, 11(4). DOI: 10.3390/fi11040094.
• Cini, N., Aydin, Z. 2024. A Deep Ensemble Approach for Long-Term Traffic Flow Prediction. Arabian Journal of Science and Engineering, 1–16. DOI: 10.1007/s13369-023-08672-1.
• Zheng, J., Huang, M. 2020. Traffic Flow Forecast Through Time Series Analysis Based on Deep Learning. IEEE Access, 8, 82562–82570. DOI: 10.1109/ACCESS.2020.2990738.
• Zhang, S., Li, S., Li, X., Yao, Y. 2020. Representation of Traffic Congestion Data for Urban Road Traffic Networks Based on Pooling Operations. Algorithms, 13(4). DOI: 10.3390/a13040084.
• Ding, H., Li, Z., Su, N. 2023. Traffic Prediction Based on the GRU Neural Network. Applied Computational Engineering, 8, 305–309. DOI: 10.54254/2755-2721/8/20230168.
• Alghamdi, T., Elgazzar, K., Bayoumi, M., Sharaf, T., Shah, S. 2019. Forecasting Traffic Congestion Using ARIMA Modeling. 15th International Wireless Communications & Mobile Computing Conference (IWCMC), 1227–1232.
• Ghosh, B., Basu, B., O’Mahony, M. 2009. Multivariate Short-Term Traffic Flow Forecasting Using Time-Series Analysis. IEEE Transactions on Intelligent Transportation Systems, 10(2), 246–254. DOI: 10.1109/TITS.2009.2021448.
• Khedkar, S. P., Canessane, R. A., Najafi, M. L. 2021. Prediction of Traffic Generated by IoT Devices Using Statistical Learning Time Series Algorithms. Wireless Communications and Mobile Computing, 2021. DOI: 10.1155/2021/5366222.
• Neelakandan, S., Berlin, M. A., Tripathi, S., Devi, V. B., Bhardwaj, I., Arulkumar, N. 2021. IoT-Based Traffic Prediction and Traffic Signal Control System for Smart City. Soft Computing, 25(18), 12241–12248. DOI: 10.1007/s00500-021-05896-x.
• Zhang, T., Xu, J., Cong, S., Qu, C., Zhao, W. 2023. A Hybrid Method of Traffic Congestion Prediction and Control. IEEE Access, 11, 36471–36491. DOI: 10.1109/ACCESS.2023.3266291.
• Chahal, A., Gulia, P., Gill, N. S., Priyadarshini, I. 2023. A Hybrid Univariate Traffic Congestion Prediction Model for IoT-Enabled Smart City. Information, 14(5). DOI: 10.3390/info14050268.
• Kumar, S., Singh, J. 2020. Internet of Vehicles (IoV) over VANETs: Smart and Secure Communication Using IoT. Scalable Computing: Practice and Experience, 21(3), 425–440. DOI: 10.12694/scpe.v21i3.1741.
• Akhtar, M., Moridpour, S. 2021. A Review of Traffic Congestion Prediction Using Artificial Intelligence. Journal of Advanced Transportation, 2021, 1–18. DOI: 10.1155/2021/8878011.
• Lakshmanna, K., et al. 2022. A Review on Deep Learning Techniques for IoT Data. Electronics, 11(10), 1604. DOI: 10.3390/electronics11101604.
• Aslan, E., Özüpak, Y. 2025. Detection of Road Extraction from Satellite Images with Deep Learning Method. Cluster Computing, 28(1), 1–10. DOI: 10.1007/s10586-024-04880-y.
• Martin-Baos, J. A., Rodriguez-Benitez, L., Garcia-Rodenas, R., Liu, J. 2022. IoT-Based Monitoring of Air Quality and Traffic Using Regression Analysis. Applied Soft Computing, 115. DOI: 10.1016/j.asoc.2021.108282.
• Bilotta, S., Nesi, P. 2022. Estimating CO2 Emissions from IoT Traffic Flow Sensors and Reconstruction. Sensors, 22(9). DOI: 10.3390/s22093382.
• Alvi, U., Khattak, M. A. K., Shabir, B., Malik, A. W., Muhammad, S. R. 2020. A Comprehensive Study on IoT-Based Accident Detection Systems for Smart Vehicles. IEEE Access, 8, 122480–122497. DOI: 10.1109/ACCESS.2020.3006887.
• Mohanta, B. K., Jena, D., Mohapatra, N., Ramasubbareddy, S., Rawal, B. S. 2022. Machine Learning Based Accident Prediction in Secure IoT-Enabled Transportation System. Journal of Intelligent & Fuzzy Systems, 42(2), 713–725. DOI: 10.3233/JIFS-189743.
• Balasubramanian, S. B., et al. 2023. Machine Learning-Based IoT System for Secure Traffic Management and Accident Detection in Smart Cities. PeerJ Computer Science, 9. DOI: 10.7717/peerj-cs.1259.
• Liu, Y., Cai, Z., Dou, H. 2023. Highway Traffic Congestion Detection and Evaluation Based on Deep Learning Techniques. Soft Computing, 27(17), 12249–12265. DOI: 10.1007/s00500-023-08821-6.
• Ata, A., Khan, M. A., Abbas, S., Khan, M. S., Ahmad, G. 2021. Adaptive IoT Empowered Smart Road Traffic Congestion Control System Using Supervised Machine Learning Algorithm. Computer Journal, 64(11), 1672–1679. DOI: 10.1093/comjnl/bxz129.
• Bawaneh, M., Simon, V. 2023. Novel Traffic Congestion Detection Algorithms for Smart City Applications. Concurrency and Computation: Practice and Experience, 35(5). DOI: 10.1002/cpe.7563.
• Kaggle. 2024. Hourly Traffic Density Data Set. https://data.ibb.gov.tr/en/dataset/hourly-traffic-density-data-set (Access Date: 22.05.2024).
• Open-meteo.com. 2024. Open-meteo. https://open-meteo.com/en/docs/historical-weather-api?trk=article-ssr-frontend-pulse_little-text-block#start_date=2020-01-01&end_date=2024-11-30 (Access Date: 13.12.2024).
• National Centers for Environmental Information. 2024. https://www.nodc.noaa.gov/archive/arc0021/0002199/1.1/data/0-data/HTML/WMO-CODE/WMO4677.HTM (Access Date: 19.12.2024).
• GeeksforGeeks. Gated recurrent unit networks. https://www.geeksforgeeks.org/gated-recurrent-unit-networks (Access Date: 11.01.2024).