More bridges today require maintenance with age, owing to increasing structural loads from traffic and natural disasters. Routine inspection for damages, including in the aftermath of special events, is conducted by experts. To address the limitations of human inspection, deep-learning-based analysis of bridge damage is being actively conducted. However, such models exhibit deteriorated performance in classifying multiple classes. Most existing algorithms do not use in situ images. Hence, the results of the model training do not accurately reflect the actual damage. This study utilizes an extant method and proposes a new model of combination training by bridge member. By integrating the two approaches, we propose a bridge damaged-object-detection deep-combination framework (BDODC-F). To ensure variety in the type of damaged objects and enhanced model performance, a deep-learning-based super-resolution module is employed. For performance improvement and optimization, a deep-learning combination model based on individual training by bridge member is proposed. The BDODC-F improved the mean average precision by 191.6% and 112.21% in the combination model. We expect the framework to aid engineers in the automated detection and identification of bridge damage.

The quality of road pavements is highly impacted by environmental variables, such as temperature, humidity, and weather; and construction-related variables, such as material quality and time. In this paper, an advanced data collection and analysis system based on big data/cloud was proposed for the use of IoT location-based smart platforms for pavement quality big data at road pavement sites. For the big data platform, a relational database management system (RDBMS) for a general alphanumeric data-based infrastructure for IoT-based systems was designed based on distributed/parallel processing to enable rapid and big data collection and analysis. The structure was established based on a NoSQL-based database to enable real-time high-speed collection and analysis, and the big data platform was developed as a data collection and visualization infrastructure. When the big data system was studied using data analysis methods, the proposed system demonstrated improvements in data collection performance and analysis speed, indicating that analysis results could be derived in real time. Specifically, the data collection processing (create) speed of the NoSQL-based system (0.405 ms) was significantly higher than that of the compared existing system (21.146 ms). Real-time processing capacity was also verified based on quality big data generated on actual road pavements, and the proposed system was proven suitable for the real-time monitoring (the data collection processing) of road pavement quality big data.

In recent years, active research has been conducted using deep learning to evaluate damage to aging bridges. However, this method is inappropriate for practical use because its performance deteriorates owing to numerous classifications, and it does not use photos of actual sites. To this end, this study used image data from an actual bridge management system as training data and employed a combined learning model for each member among various instance segmentation models, including YOLO, Mask R-CNN, and BlendMask. Meanwhile, techniques such as hyperparameter tuning are widely used to improve the accuracy of deep learning, and this study aimed to improve the accuracy of the existing model through this. The hyperparameters optimized in this study are DEPTH, learning rate (LR), and iterations (ITER) of the neural network. This technique can improve the accuracy by tuning only the hyperparameters while using the existing model for bridge damage identification as it is. As a result of the experiment, when DEPTH, LR, and ITER were set to the optimal values, mAP was improved by approximately 2.9% compared to the existing model.

Advanced driver-assistance systems (ADAS) are primarily known for their positive impact in improving the safety of drivers. Previous studies primarily analyzed the positive effects of ADAS with short-term experiments and accident data without considering the long-term changes in drivers’ safety perception. The human factor is the most dominant among factors that cause traffic accidents, and safety effect evaluation should be performed considering changes in human errors. To this end, this study classified the safety effect of ADAS-forward collision warning (FCW) on taxi drivers in Seoul into behavioral control and attitude change to perform analysis on respective factors. With regard to behavioral control, virtual driving simulation was used to analyze the reaction time of drivers and deceleration rate, and for attitude change, autoregressive integrated moving average (ARIMA) time series analysis was employed to predict the long-term perception change of drivers. The analysis results indicated that, in terms of behavioral control, ADAS-FCW reduces the cognitive reaction time of drivers in risk situations on the road, similar to the findings in previous studies. However, in terms of attitude change, ADAS-FCW has the adverse long-term effect of increasing violations in maintaining safety distance in the case of nighttime-drivers under 60 years old. As can be seen from these results, new technologies in the road safety arena can have a short-term effect of improving safety with behavioral control but may have a negative impact in the long term. The results of this study are expected to provide a theoretical basis for reference in the safety evaluation of ADAS and traffic safety facilities.

Currently, damage in aging bridges is assessed visually, leading to significant personnel, time, and cost expenditures. Moreover, the results depend on the subjective judgment of the inspector. Machine-learning-based approaches, such as deep learning, can solve these problems. In particular, instance-segmentation models have been used to identify different types of bridge damage. However, the value of deep-learning-based damage identification may be reduced by insufficient training data, class imbalance, and model-reliability issues. To overcome these limitations, this study utilized photographic data from real bridge-management systems for the inspection and assessment of bridges as the training dataset. Six types of damage were considered. Moreover, the performances of three representative deep learning models—Mask R-CNN, BlendMask, and SWIN—were compared in terms of loss–function values. SWIN showed the best performance, achieving a loss value of 0.000005 after 269,939 training iterations. This shows that bridge-damage-identification performance can be maximized by setting an appropriate learning rate and using a deep learning model with a minimal loss value.