Use of n-Fold Cross-Validation to Evaluate Three Methods to Calculate Heavy Truck Annual Average Daily Traffic and Vehicle Miles Traveled

Abstract

Reliable estimates of heavy-truck volumes in the United States are important in a number of transportation applications including pavement design and management, traffic safety, and traffic operations. Additionally, because heavy vehicles emit pollutants at much higher rates than passenger vehicles, reliable volume estimates are critical to computing accurate inventories of on-road emissions. Accurate baseline inventories are also necessary to forecast future scenarios. The research presented in this paper evaluated three different methods commonly used by transportation agencies to estimate annual average daily traffic (AADT), which is used to determine vehicle miles traveled (VMT). Traffic data from continuous count stations provided by the Iowa Department of Transportation were used to estimate AADT for single-unit and multiunit trucks for rural freeways and rural primary highways using the three methods. The first method developed general expansion factors, which apply to all vehicles. AADT, representing all vehicles, was estimated for short-term counts and was multiplied by statewide average truck volumes for the corresponding roadway type to obtain AADT for each truck category. The second method also developed general expansion factors and AADT estimates. Truck AADT for the second method was calculated by multiplying the general AADT by truck volumes from the short-term counts. The third method developed expansion factors specific to each truck group. AADT estimates for each truck group were estimated from short-term counts using corresponding expansion factors. Accuracy of the three methods was determined by comparing actual AADT from count station data to estimates from the three methods. Accuracy of the three methods was compared using n-fold cross-validation. Mean squared error of prediction was used to estimate the difference between estimated and actual AADT. Prediction error was lowest for the method that developed separate expansion factors for trucks. Implications for emissions estimation using the different methods are also discussed.

Genome-Wide Association Studies of Image Traits Reveal Genetic Architecture of Drought Resistance in Rice

“…All-subset regression was adopted for the modeling of shoot weight, and adjusted R 2 (adjusted determination coefficients), AIC (Akaike's information criterion), MAPE (mean absolute percentage error), and SD APE (the SD of absolute percentage error) were calculated using SAS 9.2 (SAS Institute). To evaluate the prediction performance of a model, we independently performed 5-fold cross-validation (Hallmark et al, 2007;Yang et al, 2014) 10 times. For 5-fold cross-validation, five steps were conducted as follows: (i) the rice accessions were randomly assigned into five groups; (ii) one of the five groups was selected as a testing set and the other four groups were selected as a training set; (iii) MAPE, SD APE , and R 2 of the testing set were calculated; (iv) the final MAPE, SD APE , and R 2 were calculated as the mean values of 10 reruns of 5-fold cross-validation.…”

Machine Learning Approach to Predict the Surface Charge Density of Monodispersed Particles in Gas–Solid Fluidized Beds

“… 43 For small data sets, n -fold cross-validation is frequently used to maximize the use of the data. 44 The principle of n -fold cross-validation is to randomly select and divide the data set into n parts and cycle the use of one of the parts as the test set and the others as the training set. The advantage of this method is that it allows all data points to be rotated as training and test sets, thereby maximizing data usage.…”

“…The reason for not using all of the data points for training and testing is to avoid overfitting, which refers to a training error wherein the model corresponds excessively closely or exactly to a particular set of data, and may therefore fail to fit additional data or predict future observations reliably . For small data sets, n -fold cross-validation is frequently used to maximize the use of the data . The principle of n -fold cross-validation is to randomly select and divide the data set into n parts and cycle the use of one of the parts as the test set and the others as the training set.…”

Importance of Holidays for Short Term Load Forecasting Using Adaptive Neural Fuzzy Inference System

“…Two-fold Cross validation. The Cross validation technique is very commonly used to measure reliability of the testing [17,18]. This method is called "N-fold cross-validation", and fold gets its name from the number of the dividing data set, i.e.…”