A supervised machine learning model for imputing missing boarding stops in smart card data.

Public transport has become an essential part of urban existence with increased population densities and environmental awareness. Large quantities of data are currently generated, allowing for more robust methods to understand travel behavior by harvesting smart card usage. However, public transport datasets suffer from data integrity problems; boarding stop information may be missing due to imperfect acquirement processes or inadequate reporting. This study introduces a supervised machine learning method to impute missing boarding stops based on ordinal classification using GTFS timetable, smart card, and geospatial datasets. A new metric, Pareto Accuracy, is suggested to evaluate algorithms where classes have an ordinal nature. The results are based on a case study in the city of Beer Sheva, Israel, consisting of one month of smart card data. We show that our proposed method is robust to irregular travelers and significantly outperforms well-known imputation methods without the need to mine any additional datasets. The data validation from another Israeli city using transfer learning shows the presented model is general and context-free. The implications for transportation planning and travel behavior research are further discussed.

Noise estimation model development using high-resolution transportation and land use regression.

Noise pollution is a common phenomenon of the 21st century. Noise prediction models tend to estimate noise levels mainly from road traffic sources (such as cars, public transportation etc.). This paper describes the adoption of land use regression (LUR) modeling methodology to assess noise pollution in two periods of the day (rush hour and off-peak), in two major cities in Israel (Tel Aviv and Beer Sheva). For both rush hour and off-peak times, 20 min short term measurements were used to develop a LUR noise estimation model. We used GIS-based predictors alongside commonly used traffic predictors. The findings show good fits for our model, with rush hour "out of sample" ten folds cross-validated R² of 0.79 (Tel Aviv) and 0.52 (Beer Sheva). The Tel Aviv model performance was also tested with independent monitoring data in an adjacent city (Bat Yam), presenting a good performance as well (R² of 0.93). The findings demonstrate the viability of using a LUR approach for applying high-resolution spatial data to estimate and map noise pollution for environmental noise assessment.