Search for: All records

In this study, we aimed to evaluate the performance of various machine learning (ML) classifiers to predict mode choice of movement-challenged persons (MCPs) based on data collected through a questionnaire survey of 384 respondents in Dhaka, Bangladesh. The mode choice set consisted of CNG-driven auto-rickshaw, bus, walking, motorized rickshaw, and non-motorized rickshaw, which was found as the most prominent mode used by MCPs. Age, sex, income, travel time, and supporting instrument (as an indicator of the level of disability) utilized by MCPs were explored as predictive variables. Results from the different split ratios with 10-fold cross-validation were compared to evaluate model outcomes. A split ratio of 60% demonstrates the optimum accuracy. It was found that Multi-nominal Logistic Regression (MNL), K-Nearest Neighbors (KNN), and Linear Discriminant Analysis (LDA) show higher accuracy for the split ratio of 60%. Overfitting of bus and walking as a travel mode was found as a source of classification error. Travel time was identified as the most important factor influencing the selection of walking, CNG, and rickshaw for MNL, KNN, and LDA. LDA and KNN depict the supporting instrument as a more important factor in mode choice than MNL. The selection of rickshaw as a mode follows a relatively normal probability distribution, while probability distribution is negatively skewed for the other three modes. 

Crop type information at the field level is vital for many types of research and applications. The United States Department of Agriculture (USDA) provides information on crop types for US cropland as a Cropland Data Layer (CDL). However, CDL is only available at the end of the year after the crop growing season. Therefore, CDL is unable to support in-season research and decision-making regarding crop loss estimation, yield estimation, and grain pricing. The USDA mostly relies on field survey and farmers’ reports for the ground truth to train image classification models, which is one of the major reasons for the delayed release of CDL. This research aims to use trusted pixels as ground truth to train classification models. Trusted pixels are pixels which follow a specific crop rotation pattern. These trusted pixels are used to train image classification models for the classification of in-season Landsat images to identify major crop types. Six different classification algorithms are investigated and tested to select the best algorithm for this study. The Random Forest algorithm stands out among selected algorithms. This study classified Landsat scenes between May and mid-August for Iowa. The overall agreements of classification results with CDL in 2017 are 84%, 94%, and 96% for May, June, and July, respectively. The classification accuracies have been assessed through 683 ground truth data points collected from the fields. The overall accuracies of single date multi-band image classification are 84%, 89% and 92% for May, June, and July, respectively. The result also shows higher accuracy (94–95%) can be achieved through multi-date image classification compared to single date image classification.