Bello-Salau, HOnumanyi, Adeiza JAdebiyi, RFAdedokun, EAHancke, Gp2022-05-062022-05-062021-06Bello-Salau, H., Onumanyi, A.J., Adebiyi, R., Adedokun, E. & Hancke, G. 2021. Performance analysis of machine learning classifiers for pothole road anomaly segmentation. http://hdl.handle.net/10204/12391 .978-1-7281-9023-5978-1-7281-9022-82163-51452163-51452163-5137DOI: 10.1109/ISIE45552.2021.9576214http://hdl.handle.net/10204/12391Recently, machine learning (ML) classifiers are being widely deployed in many intelligent transportation systems towards improving the safety and comfort of passengers as well as to ease and enhance road navigation. However, the comparative performance analyses of different ML classifiers within the confines of road anomaly detection remain unexplored under some specific capture conditions such as bright light, dim light, and hazy image conditions. Consequently, this paper investigates the performance of six different state-of-the-art ML classification algorithms, viz: random forest, JRip, One-R,naive Bayesian, J48, and AdaBoost for segmenting pothole road anomalies under three different environmental conditions viz: bright, dim, and hazy light conditions. The results obtained suggest that either the J48 random forest or JRip classifiers are suitable for classifying pothole anomalies captured under broad day light (bright light) conditions with an average accuracy performance of 95%. On the other hand, the One-R classifier sufficed as more suitable for use under hazy image condition yielding an average accuracy of 73%, whereas the random forest algorithm yielded the best classification accuracy of 55%under dim light conditions. These results are helpful particularly towards determining the best ML classifiers for use towards developing robust artificial intelligence-based real-time algorithms for detecting and characterizing road anomalies effectively in autonomous vehicles.AbstractenImage segmentationMachine learning algorithmsClassification algorithmsPerformance analysisReal-time systemsUnmanned vehiclesConference PresentationBello-Salau, H., Onumanyi, A. J., Adebiyi, R., Adedokun, E., & Hancke, G. (2021). Performance analysis of machine learning classifiers for pothole road anomaly segmentation. http://hdl.handle.net/10204/12391Bello-Salau, H, Adeiza J Onumanyi, RF Adebiyi, EA Adedokun, and Gp Hancke. "Performance analysis of machine learning classifiers for pothole road anomaly segmentation." <i>2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), Kyoto, Japan, 20-23 June 2021</i> (2021): http://hdl.handle.net/10204/12391Bello-Salau H, Onumanyi AJ, Adebiyi R, Adedokun E, Hancke G, Performance analysis of machine learning classifiers for pothole road anomaly segmentation; 2021. http://hdl.handle.net/10204/12391 .TY - Conference Presentation AU - Bello-Salau, H AU - Onumanyi, Adeiza J AU - Adebiyi, RF AU - Adedokun, EA AU - Hancke, Gp AB - Recently, machine learning (ML) classifiers are being widely deployed in many intelligent transportation systems towards improving the safety and comfort of passengers as well as to ease and enhance road navigation. However, the comparative performance analyses of different ML classifiers within the confines of road anomaly detection remain unexplored under some specific capture conditions such as bright light, dim light, and hazy image conditions. Consequently, this paper investigates the performance of six different state-of-the-art ML classification algorithms, viz: random forest, JRip, One-R,naive Bayesian, J48, and AdaBoost for segmenting pothole road anomalies under three different environmental conditions viz: bright, dim, and hazy light conditions. The results obtained suggest that either the J48 random forest or JRip classifiers are suitable for classifying pothole anomalies captured under broad day light (bright light) conditions with an average accuracy performance of 95%. On the other hand, the One-R classifier sufficed as more suitable for use under hazy image condition yielding an average accuracy of 73%, whereas the random forest algorithm yielded the best classification accuracy of 55%under dim light conditions. These results are helpful particularly towards determining the best ML classifiers for use towards developing robust artificial intelligence-based real-time algorithms for detecting and characterizing road anomalies effectively in autonomous vehicles. DA - 2021-06 DB - ResearchSpace DP - CSIR J1 - 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), Kyoto, Japan, 20-23 June 2021 KW - Image segmentation KW - Machine learning algorithms KW - Classification algorithms KW - Performance analysis KW - Real-time systems KW - Unmanned vehicles LK - https://researchspace.csir.co.za PY - 2021 SM - 978-1-7281-9023-5 SM - 978-1-7281-9022-8 SM - 2163-5145 SM - 2163-5145 SM - 2163-5137 T1 - Performance analysis of machine learning classifiers for pothole road anomaly segmentation TI - Performance analysis of machine learning classifiers for pothole road anomaly segmentation UR - http://hdl.handle.net/10204/12391 ER -25409