Search for: All records

Road authorities worldwide can leverage the advances in vehicle technology by continuously monitoring their roads’ conditions to minimize road maintenance costs. The existing methods for carrying out road condition surveys involve manual observations using standard survey forms, performed by qualified personnel. These methods are expensive, time-consuming, infrequent, and can hardly provide real-time information. Some automated approaches also exist but are very expensive since they require special vehicles equipped with computing devices and sensors for data collection and processing. This research aims to leverage the advances in vehicle technology in providing a cheap and real-time approach to carry out road condition monitoring (RCM). This study developed a deep learning model using the You Only Look Once, Version 5 (YOLOv5) algorithm that was trained to capture and categorize flexible pavement distresses (FPD) and reached 95% precision, 93.4% recall, and 97.2% mean Average Precision. Using vehicle built-in cameras and GPS sensors, these distresses were detected, images were captured, and locations were recorded. This was validated on campus roads and parking lots using a car featured with a built-in camera and GPS. The vehicles’ built-in technologies provided a more cost-effective and efficient road condition monitoring approach that could also provide real-time road conditions. 

Recent technological developments have attracted the use of machine learning technologies and sensors in various pavement maintenance and rehabilitation studies. To avoid excessive road damages, which cause high road maintenance costs, reduced mobility, vehicle damages, and safety concerns, the periodic maintenance of roads is necessary. As part of maintenance works, road pavement conditions should be monitored continuously. This monitoring is possible using modern distress detection methods that are simple to use, comparatively cheap, less labor-intensive, faster, safer, and able to provide data on a real-time basis. This paper proposed and developed two models: computer vision and sensor-based. The computer vision model was developed using the You Only Look Once (YOLOv5) algorithm for detecting and classifying pavement distresses into nine classes. The sensor-based model combined eight Controller Area Network (CAN) bus sensors available in most new vehicles to predict pavement distress. This research employed an extreme gradient boosting model (XGBoost) to train the sensor-based model. The results showed that the model achieved 98.42% and 97.99% area under the curve (AUC) metrics for training and validation datasets, respectively. The computer vision model attained an accuracy of 81.28% and an F1-score of 76.40%, which agree with past studies. The results indicated that both computer vision and sensor-based models proved highly efficient in predicting pavement distress and can be used to complement each other. Overall, computer vision and sensor-based tools provide cheap and practical road condition monitoring compared to traditional manual instruments. 

The recent development in transportation, such as energy-efficient and autonomous vehicles, defines a condition for the students in transportation engineering. Students in the field of transportation engineering should be ready upon their graduation with new knowledge and skills that are compatible with the need of the industry and sustainable engineering practices. During summers of2018 and 2019, we developed and implemented an eight-week program to increase the knowledge and skills of students coming from multidisciplinary fields related to autonomous vehicles. Problem of “How much will platooning reduce fuel consumption and emissions per vehicle mile traveled?” was instrumentalized in subsequent activities to introduce the comprehensive knowledge structure of autonomous vehicles. The engineering concept of reducing the cost and sustainability was embedded in the leading research question that helped us to develop and implement activities on an overall knowledge structure in autonomous vehicles. The goal of using problem-based learning activities was not to encourage the students to focus on reaching the solution merely. We aimed to introduce the multidisciplinary knowledge and critical skills aspects of learning about disruptive technologies. In this paper, we will discuss how a multidisciplinary research approach was incorporated into a problem-based learning activity. The students were introduced the subjects related to math, physics, computer science, and biology as the integration of the knowledge structure of autonomous vehicles. We will also present the results on students’ use of critical skills such as machine learning and computer programming. 

This research focuses on studying the scattering phenomenon. Scattering electromagnetic waves from a rotating conducting cylinder is investigated when the material of the conducting cylinder is linear, homogeneous, isotropic, and dispersive. This study is an extension of a previous work that investigated the effect of the rotating conducting cylinder on the scattered phase and amplitude, when the material of the conducting cylinder is linear, homogeneous, isotropic, and nondispersive. One of the important result of the previous work is that the Franklin transformation is a proper and more accurate method to calculate the effect of the rotation, and gives more accurate results than Galilean transformation. In this research, the Franklin transformation will be used to investigate the effect of the rotation of the object on the scattered phase and magnitude of the incident waves. The two types of incident waves (E-wave and H-wave) will be considered herein. The simulation results will clearly display the behavior of the scattered phase and magnitude with changes to the incident frequency, the speed of rotation, and the radius of the very good conducting cylinder. Moreover, this result is compared with the result of the previous work (non- dispersive material) to show the behavior of the scattered phase and magnitude when the incident frequency, speed of the rotation and radius of the very good conducting cylinder is changed. 

Many studies have reported associations between respiratory symptoms and resident proximity to traffic. However, only a few have documented information about the relationship between traffic volume and air quality in local areas. This study investigates the impact of traffic volume on air quality at different geographical locations in the state of South Carolina using multilevel linear mixed models and Grey Systems. Historical traffic volume and air quality data between 2006 and 2016 are obtained from the South Carolina Department of Transportation (SCDOT) and the United States Environmental Protection Agency (EPA) monitoring stations. The data are used to develop prediction models that relate Air Quality Index (AQI) to traffic volume for selected counties and schools. For the counties, two models are developed, one with Ozone (O3) and one with PM2:5 as the dependent variable. For the schools, only one model is developed, with O3 as the dependent variable. The number of counties and schools studied are limited by the availability of air monitoring stations dedicated to measuring O3 and PM2:5. Several types of models were investigated. They include linear regression model (LM), linear mixed-effect regression model (LMER), Grey Systems (GM), error corrected GM (EGM), Grey Verhulst (GV), error corrected GV (EGV), and LMER + EGM. The LM model produced the least accurate estimate while the LMER + EGM model produced the most accurate estimate (average RMSE is less than 5%). The models’ estimates suggest that air quality in South Carolina will continue to get worse in the coming years due to increasing AADT. An interesting finding of this study is that some counties and schools will have higher levels of O3 or PM2:5 when AADT decreases. This finding suggests that there are other factors, other than AADT, that influence the air quality in these counties and schools.