International Journal of Computer Science & Network Security

국제컴퓨터통신보호논문지학회 (International Journal of Computer Science & Network Security)
권호 표지
DOI QR코드

DOI QR Code

Optimizing Clustering and Predictive Modelling for 3-D Road Network Analysis Using Explainable AI

  • 투고 : 2024.09.05
  • 발행 : 2024.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Building an accurate 3-D spatial road network model has become an active area of research now-a-days that profess to be a new paradigm in developing Smart roads and intelligent transportation system (ITS) which will help the public and private road impresario for better road mobility and eco-routing so that better road traffic, less carbon emission and road safety may be ensured. Dealing with such a large scale 3-D road network data poses challenges in getting accurate elevation information of a road network to better estimate the CO2 emission and accurate routing for the vehicles in Internet of Vehicle (IoV) scenario. Clustering and regression techniques are found suitable in discovering the missing elevation information in 3-D spatial road network dataset for some points in the road network which is envisaged of helping the public a better eco-routing experience. Further, recently Explainable Artificial Intelligence (xAI) draws attention of the researchers to better interprete, transparent and comprehensible, thus enabling to design efficient choice based models choices depending upon users requirements. The 3-D road network dataset, comprising of spatial attributes (longitude, latitude, altitude) of North Jutland, Denmark, collected from publicly available UCI repositories is preprocessed through feature engineering and scaling to ensure optimal accuracy for clustering and regression tasks. K-Means clustering and regression using Support Vector Machine (SVM) with radial basis function (RBF) kernel are employed for 3-D road network analysis. Silhouette scores and number of clusters are chosen for measuring cluster quality whereas error metric such as MAE ( Mean Absolute Error) and RMSE (Root Mean Square Error) are considered for evaluating the regression method. To have better interpretability of the Clustering and regression models, SHAP (Shapley Additive Explanations), a powerful xAI technique is employed in this research. From extensive experiments , it is observed that SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions SHAP analysis validated the importance of latitude and altitude in predicting longitude, particularly in the four-cluster setup, providing critical insights into model behavior and feature contributions with an accuracy of 97.22% and strong performance metrics across all classes having MAE of 0.0346, and MSE of 0.0018. On the other hand, the ten-cluster setup, while faster in SHAP analysis, presented challenges in interpretability due to increased clustering complexity. Hence, K-Means clustering with K=4 and SVM hybrid models demonstrated superior performance and interpretability, highlighting the importance of careful cluster selection to balance model complexity and predictive accuracy.

키워드

참고문헌

  1. Jain, A. K., Murty, M. N., & Flynn, P. J. (1999). Data clustering: a review. ACM computing surveys (CSUR), 31(3), 264-323. https://doi.org/10.1145/331499.331504
  2. Schubert, E. (2023). Stop using the elbow criterion for k-means and how to choose the number of clusters instead. ACM SIGKDD Explorations Newsletter, 25(1), 36-42. https://doi.org/10.1145/3606274.3606278
  3. Rousseeuw, P. J. (1987). Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. Journal of computational and applied mathematics, 20, 53-65. https://doi.org/10.1016/0377-0427(87)90125-7
  4. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  5. Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R news, 2(3), 18-22.
  6. Lundberg, S. M., & Lee, S. I. (2017). A unified approach to interpreting model predictions. Advances in neural information processing systems, 30.
  7. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016, August). "Why should i trust you?" Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135-1144).
  8. Hotelling, H. (1933). Analysis of a complex of statistical variables into principal components. Journal of educational psychology, 24(6), 417.
  9. McInnes, L., Healy, J., & Melville, J. (2018). Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426.
  10. Van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of machine learning research, 9(11).
  11. Kotsiantis, S., Kanellopoulos, D., & Pintelas, P. (2006). Handling imbalanced datasets: A review. GESTS international transactions on computer science and engineering, 30(1), 25-36.
  12. Wang, K., Chen, Z., Dang, X., Fan, X., Han, X., Chen, C. M., ... & Weng, J. (2023). Uncovering hidden vulnerabilities in convolutional neural networks through graph-based adversarial robustness evaluation. Pattern Recognition, 143, 109745.
  13. Jolliffe, I. T., & Cadima, J. (2016). Principal component analysis: a review and recent developments. Philosophical transactions of the royal society A: Mathematical, Physical and Engineering Sciences, 374(2065), 20150202.
  14. Breiman, L. (2001). Random forests. Machine learning, 45, 5-32. https://doi.org/10.1023/A:1010933404324
  15. Chen, J., Song, L., Wainwright, M., & Jordan, M. (2018, July). Learning to explain: An information-theoretic perspective on model interpretation. In International conference on machine learning (pp. 883-892). PMLR.
  16. Hennig, C. (2007). Cluster-wise assessment of cluster stability. Computational Statistics & Data Analysis, 52(1), 258-271. https://doi.org/10.1016/j.csda.2006.11.025
  17. Zhang, S., Li, J., Shi, L., Ding, M., Nguyen, D. C., Tan, W., ... & Han, Z. (2023). Federated learning in intelligent transportation systems: Recent applications and open problems. IEEE Transactions on Intelligent Transportation Systems.
  18. Nikparvar, B., & Thill, J. C. (2021). Machine learning of spatial data. ISPRS International Journal of Geo-Information, 10(9), 600.
  19. Assent, I. (2012). Clustering high dimensional data. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 2(4), 340-350. https://doi.org/10.1002/widm.1062
  20. Ribeiro, M. T., Singh, S., & Guestrin, C. (2018, April). Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI conference on artificial intelligence (Vol. 32, No. 1).
  21. Cesar, I., Pereira, I., Rodrigues, F., Migueis, V., Nicola, S., & Madureira, A. Exploring multimodal learning applications in marketing: A critical perspective. International Journal of Hybrid Intelligent Systems, (Preprint), 1-18.
  22. Xie, W. B., Liu, Z., Das, D., Chen, B., & Srivastava, J. (2023). Scalable clustering by aggregating representatives in hierarchical groups. Pattern Recognition, 136, 109230.
  23. Kaul, M. (2013). 3D Road Network (North Jutland, Denmark) [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5GP51.