Annual Average Daily Traffic (AADT) is an important parameter for traffic engineering analysis. Departments of Transportation continually collect traffic count using both permanent count stations (i.e., Automatic Traffic Recorders or ATRs) and temporary short-term count stations. In South Carolina, 87% of the ATRs are located on interstates and arterial highways. For most secondary highways (i.e., collectors and local roads), AADT is estimated based on short-term counts. This paper develops AADT estimation models for different roadway functional classes with two machine learning techniques: Support Vector Regression (SVR) and Artificial Neural Network (ANN). The models predict AADT from short-term counts. The results are first compared against each other, using the 2011 ATR data, to identify the best models. Then, the results of the best models are compared against both the regression-based model and factor-based model. The comparison reveals the superiority of the SVR model for AADT estimation for different roadway functional classes over all other methods. Among models for different roadway functional classes, developed with the 2011 ATR data, the SVR-based models show minimum errors in estimating AADT compared to the ANN-based, regression-based, and factor-based models, depicting the superiority of the SVR-based model for all roadway functional classes over other models in terms of AADT estimation accuracy. SVR models are validated for each roadway functional class using the 2016 ATR data and short-term count data collected by the South Carolina Department of Transportation (SCDOT). The validation results show that the SVR-based AADT estimation models can be used by the SCDOT as a reliable option to predict AADT from the short-term counts.

To improve the effectiveness of transportation professionals in their respective jobs and successfully meet changing capability requirements, public agencies often offer online training. This article presents the current practices of design criteria and delivery method of such training through a three-faceted approach: the review of published materials, an online survey of transportation agency professionals, and follow-up telephone interviews. This study revealed that some of the most important considerations of successful online training programs are (a) the inclusion of interactive components within the training modules to keep participants engaged, (b) a short duration for each of the training modules to retain participants’ attentiveness, and (c) the provision of quizzes to assess participants’ understanding of the material.

Efficient training is an essential component of work force development for transportation agencies. The South Carolina Department of Transportation (DOT) recognized one such training need in its management of contracts for professional services consultants. This recognition led to a research effort to identify standardized procedures in the procurement and administration of these contracts, resulting in the development of a training manual and daylong pilot training session. Although the session received positive feedback, it limited the time and location for delivery. This traditional, in-class method is no longer the only available option. Asynchronous online training presents agencies with the option of providing training to employees regardless of their spatial or schedule variabilities while minimizing the need for instructor effort and availability. In light of this change, the South Carolina DOT commissioned a subsequent research effort to study best practices for development, delivery, and assessment of online training and to use these findings to create training modules of the previously completed manual and training session. The focus of this paper is to present the process for developing asynchronous online training employed for the 10 modules, which total roughly 5 h. Although this process is based on best practices, they are not discussed at length; rather, references to findings are made where they pertain. The process, unique lessons learned, and advisable practices are discussed. The paper’s presentation of the online development process can be applied to other transportation agencies intending to implement asynchronous online training for professional development.

The overall goal of this research was to identify proven successful safety programs used in other states and assess the potential for safety improvement if similar programs were implemented in South Carolina. The research team not only sought out engineering solutions, but also expanded the search to include programs for enforcement, education, licensing, legal proceedings, and emergency services—therefore incorporating a wide range of stakeholder groups. South Carolina has, for many years, had one of the highest mileage death rates of any state in the nation—far exceeding the national fatality rate. While South Carolina Department of Transportation has a federal requirement to develop and maintain the Strategic Highway Safety Plan, which identifies the state’s key safety needs and guides investment decisions toward strategies and countermeasures with the most potential to save lives and prevent injuries, South Carolina legislation and state policies have effectively blocked many paths to safety improvements. Tree protection ordinances, limited policies for graduated drivers licensing, bans on camera enforcement, and lack of universal helmet laws continue to undermine efforts to improve motor vehicle safety in the state. Using a data-driven approach to safety program selection will yield support for changes in programs, policies, and standards, and have positive impacts on safety, operational, and economic aspects of the South Carolina roadway system. Further, the implementation of a data-driven safety management program will help to assure that the most appropriate strategies are implemented. The successful implementation of this research would likely result in a substantial reduction in loss of life and injuries associated with motor vehicle crashes in the state of South Carolina.