Robust Classification of Traffic Signs Using Relief Feature Reduction Technique

Year : 2025 | Volume : 12 | Issue : 03 | Page : 30 37
    By

    Manisha Vashisht,

  • Joy Vashisht,

  1. Professor, Department of Computer Science and Engineering, Echelon Institute of Technology, Faridabad, Haryana, India
  2. Student, Department of Computer Science and Engineering, Amity University, Noida, Haryana, India

Abstract

Ensuring driver safety amidst the rapid growth of global population and vehicular density continues to be a paramount challenge for transportation authorities and governments worldwide. With the rise of smart mobility solutions and autonomous driving technologies, the ability to detect, classify, and respond to traffic signs accurately has become critically important, especially under diverse and adverse environmental conditions such as rain, fog, or poor lighting. Reliable traffic sign recognition not only ensures the safety of autonomous vehicle passengers but also contributes significantly to real-time decision-making on the road. Previous studies have explored a wide range of Artificial Intelligence (AI) and machine learning techniques for traffic sign detection and classification. However, many approaches face challenges related to feature redundancy and model generalization across complex datasets. This study addresses these limitations by leveraging the publicly available Mapillary traffic sign image dataset and applying the RRelieff feature selection algorithm, known for its robustness in high-dimensional data environments. Relieff works by estimating the relevance of individual features based on their ability to distinguish between similar and dissimilar instances, thereby enabling more efficient learning. By integrating RReliefF into the traffic sign classification pipeline, this research aims to enhance performance in terms of both accuracy and computational efficiency. Experimental evaluations demonstrate that the proposed method outperforms conventional models, showcasing improved robustness and adaptability in real-world traffic scenarios, making a meaningful contribution to the advancement of autonomous driving systems.

Keywords: Rrelieff test, artificial neural network, feature selection, traffic sign image

[This article belongs to Journal of Artificial Intelligence Research & Advances ]

How to cite this article:
Manisha Vashisht, Joy Vashisht. Robust Classification of Traffic Signs Using Relief Feature Reduction Technique. Journal of Artificial Intelligence Research & Advances. 2025; 12(03):30-37.
How to cite this URL:
Manisha Vashisht, Joy Vashisht. Robust Classification of Traffic Signs Using Relief Feature Reduction Technique. Journal of Artificial Intelligence Research & Advances. 2025; 12(03):30-37. Available from: https://journals.stmjournals.com/joaira/article=2025/view=225023


References

  1. National Highway Traffic Safety Administration. National Center for Statistics and Analysis, Traffic Safety Facts 2009. Washington, DC: US Department of Transportation; 2012.
  2. Chand A, Jayesh S, Bhasi AB. Road traffic accidents: An overview of data sources, analysis techniques and contributing factors. Mater Today: Proc. 2021 Jan 1; 47: 5135–41.
  3. Moroz PJ, Spiegel DA. The World Health Organization’s action plan on the road traffic injury pandemic: is there any action for orthopaedic trauma surgeons? J Orthop Trauma. 2014 Jun 1; 28: S11–4.
  4. Ma D, Fan H, Li W, Ding X. The state of Mapillary: An exploratory analysis. ISPRS Int J Geo-Inf. 2019 Dec 20; 9(1): 10.
  5. Gopi R, Sathiyamoorthi V, Selvakumar S, Manikandan R, Chatterjee P, Jhanjhi NZ, Luhach AK. Enhanced method of ANN based model for detection of DDoS attacks on multimedia internet of things. Multimed Tools Appl. 2022 Aug; 81(19): 26739–57.
  6. Nandal M, Mor N, Sood H. An overview of use of artificial neural network in sustainable transport system. Computational Methods and Data Engineering: Proceedings of ICMDE 2020, Volume 1. 2020 Aug 20; 83–91.
  7. Gupta A, Hinchey M, Zalevsky Z, editors. Artificial Intelligence and Its Applications: First International Conference, ICAIA 2023, Pune, India, December 18–19, 2023, Proceedings, Part II. Switzerland: Springer Nature; 2025 Mar 12.
  8. Vashisht V, Lal M, Sureshchandar GS. Defect prediction framework using neural networks for software enhancement projects. British Journal of Mathematics & Computer Science. 2016 Jan 1; 16(5): 1–2.
  9. Vashisht V, Lal M, Suresh Chandar GS. A framework for software defect prediction using neural networks. J Softw Eng Appl. 2015; 8(08): 384–394.
  10. Vashisht V, Kamya S, Vashisht M. Defect prediction framework using neural networks for business intelligence technology based projects. In 2020 IEEE international conference on computer science, engineering and applications (ICCSEA). 2020 Mar 13; 1–5.
  11. Sabhapandit R, Vashisht V, Sharma A. An Investigation into the Various Statistical Process Control Tools. International Journal of Engineering and Technology (IJET). 2016; 6(2): 56–61.
  12. Nudurupati SS, Bititci US. Implementation and impact of IT-supported performance measurement systems. Prod Plan Control. 2005 Mar 1; 16(2): 152–62.
  13. Yildiz G, Dizdaroğlu B. Convolutional neural network for traffic sign recognition based on color space. In 2021 IEEE 2nd International Informatics and Software Engineering Conference (IISEC). 2021 Dec 16; 1–5.
  14. Saadna Y, Behloul A. An overview of traffic sign detection and classification methods. Int J Multimed Inf Retr. 2017 Sep; 6(3): 193–210.
  15. Zaffar M, Hashmani MA, Savita KS, Rizvi SS. A study of feature selection algorithms for predicting students academic performance. Int J Adv Comput Sci Appl. 2018; 9(5): 541–549.
  16. Kerim A, Efe MÖ. Recognition of traffic signs with artificial neural networks: A novel dataset and algorithm. In 2021 IEEE International Conference on Artificial Intelligence in Information and Communication (ICAIIC). 2021 Apr 13; 171–176.
  17. Ghazal TM, Said RA, Taleb N. RETRACTED ARTICLE: Internet of vehicles and autonomous systems with AI for medical things. Soft Comput. 2023 Jan; 27(2): 1211.
  18. Najafi Moghaddam Gilani V, Hosseinian SM, Ghasedi M, Nikookar M. Data‐driven urban traffic accident analysis and prediction using logit and machine learning‐based pattern recognition models. Math Probl Eng. 2021; 2021(1): 9974219.
  19. Lahmyed R, Ansari ME, Kerkaou Z. Automatic road sign detection and recognition based on neural network. Soft Comput. 2022 Feb; 26(4): 1743–64.
  20. Tchernykh A, Shepelev V. Computational intelligence for analysis of traffic data. In Smart Cities: Third Ibero-American Congress, ICSC-Cities 2020, San José, Costa Rica, November 9–11, 2020, Revised Selected Papers. Cham: Springer Nature; 2021 Feb 6; 1359: 167.
  21. Alam NA, Ahsan M, Based MA, Haider J. Intelligent system for vehicles number plate detection and recognition using convolutional neural networks. Technologies. 2021 Jan 20; 9(1): 9.
  22. Liang Y, Fu S, Wang K, Jiang Z, Wang X. Predicting Aircraft Taxi Time at Airport with RReliefF Feature Selection and Machine Learning Methods. In 2023 IEEE China Automation Congress (CAC). 2023 Nov 17; 4800–4805.
  23. Aggarwal N, Shukla U, Saxena GJ, Rawat M, Bafila AS, Singh S, Pundir A. Mean based relief: an improved feature selection method based on ReliefF. Appl Intell. 2023 Oct; 53(19): 23004–28.
Regular Issue Subscription Review Article
Volume 12
Issue 03
Received 20/06/2025
Accepted 24/07/2025
Published 07/08/2025
Publication Time 48 Days
142

Login


My IP

PlumX Metrics