Against the backdrop of contemporary telecommunications, distinguishing, predicting, and alleviating deadlock have become crucial for optimizing transportation system control. With the advent of larger, higher-resolution datasets, deep learning is increasingly vital for these tasks. Recent scholarly assessments have highlighted the potential of deep learning in the transportation and communications sectors. However, the dynamic nature of transportation network models, especially during transitions between uncongested and congested phases, necessitates a clear understanding of congestion forecasting challenges. This audit examines the current landscape of deep learning applications aimed at identifying and predicting congestion to mitigate its impact. It addresses both irregular and non-repeating congestion. A significant challenge identified is the impedance and data interference that occurs during congestion. Biological constraints such as temperature, viscosity, humidity, and dust can provoke disturbances in recognized information, distorting results and increasing the likelihood of errors. As part of this proposal, we will perform a thorough survey to discover the fundamental issues and solutions related to previous research in an attempt to address signal impedance as well as data interference caused by congestion. In particular, we will present some of the key concepts and notions as well insights for future research works that are related to mitigating those issues. This study is intended to identify gaps and methods employed, in order to propose a new improved scheme for monitoring congestion and discrimination over communication systems. Results will be contrasted with similar studies of the past and present to ascertain durability in finding.

1. T. Litman, Evaluating transportation economic development impacts. Victoria Transport Policy Institute Victoria, BC, Canada, 2017.
2. C. Q. . W. R. Zhang, H., “Economic costs of traffic congestion: A comprehensive analysis.” Transportation Research Part A: Policy and Practice, vol. 144, pp. 99–114, 2021.
3. T. Reed, “Inrix global traffic scorecard,” 2019.
4. K. H. . Y. H. Kwon, J., “The effects of traffic congestion on aggressive driving and traffic accidents.” Transportation Research Part F: Traffic Psychology and Behaviour, vol. 58, pp. 38–50, 2018.
5. X. Z. . W. Y. Liu, Y., “Environmental impacts of traffic congestion: A review,” Environmental Science & Technology, vol. 53, no. 3, pp. 2722–2731, 2019.
6. Z. Y. . H. X. Ma, X., “Predicting traffic congestion with deep learning techniques.” in Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 2421–2428.
7. X. L. . W. Y. Zhao, J., “Early warning systems for traffic congestion using predictive analytics,” IEEE Access, vol. 6, pp. 46 824–46 832, 2018.
8. Z. X. . T. J. Wu, Y., “Leveraging deep learning for traffic prediction and management,” Journal of Transportation Technologies, vol. 11, no. 1, pp. 33–45, 2021.
9. L. S. Zhang, C., “Impact of environmental factors on sensor accuracy in traffic monitoring systems.” Sensors and Actuators B: Chemical, vol. 307, p. 127642, 2020.
10. C. W. . Z. Z. Wang, H., “Signal transmission challenges in traffic management systems during congestion.” IEEE Transactions on Intelligent Transportation Systems, vol. 20, no. 4, pp. 1115–1126, 2019.
11. L. X. . L. J. Chen, Y., “Data impedance and signal interference in congested traffic networks: A review.” Journal of Traffic and Transportation Engineering, vol. 12, no. 3, pp. 123–135, 2022.

A.M. N. Mustafa, M. M. B. Mohamad and F. B. Muchtar “Impedance and Data Interference During Congestion,” International Journal of Applied and Physical Sciences, vol. 10, pp. 38-44, 2024. Doi: https://dx.doi.org/10.20469/ijaps.10.50005