Wavelet Transform for Feature Extraction to Improve Volume Adjustment Factors for Rural Roads

Abstract

Wavelet transform is a powerful technique for feature extraction from data that are characterized by frequent and large-scale fluctuations. This technique has been studied in recent years for incident detection and intelligent transportation systems data aggregation. Because of its attractive properties, such as time frequency localization, multirate filtering, and scale-space analysis as well as multiresolution analysis, this research explores the potential application of the technique to improve the accuracy of monthly and weekly adjustment factors in rural annual average daily traffic estimation. The technique was applied to data collected from automatic traffic recorder stations in northern Ohio, and the application showed that the technique could separate and filter out the high-frequency data oscillations and trace the changes in the fundamental pattern of traffic. The test results illustrated an impressive improvement, ranging from 10% to 20%, over conventional data estimation at those stations. This success shows that the proposed approach is feasible, and future improvements of the application of the technique can make it an effective tool for traffic volume estimation for rural highways.