Saroch Boonsiripant

Poor road conditions present considerable obstacles for individuals, resulting in asset loss, bodily harm, and time inefficiency. Approximately 1.35 million fatalities are attributable to road traffic incidents. The Department of Public Works and Town & Country Planning conducted road surveys to assess and strategize maintenance efforts. The manual car survey requires additional time and an excessive budget. The automated system of artificial intelligence (AI) is widely recognized. This paper presents a model to detect road surface conditions utilizing video data. Four versions of convolutional neural networks (CNN) were utilized for this work. The model evaluation employed the mean average precision (mAP) measure. The video data was acquired via a smartphone mounted in a vehicle, comprising 10,984 photos for training and 2,198 images for testing. We trained and evaluated four versions of CNN architectures named YOLO, utilizing our data and GPU, with a specific emphasis on identifying cracks, potholes, and the condition of manhole covers. Of the architectures evaluated, YOLO V6 attained the greatest mAP score in comparison YOLO V5 to YOLO V8. The testing results with batch sizes of 4, 8, 16, and 32 are effective. The batch size of 32 yields the highest performance, achieving 87.38% mAP. Conduct the dropout normalization using rates of 0.25, 0.50, 0.75, and 1. The maximum mAP is observed with a dropout rate of 0.25, yielding a mAP of 85.40%. The model indicates that the government conducted road surface inspections with enhanced efficiency, enabling the planning of road repairs for public utility issues, which can lower transportation costs. Additionally, the model can be utilized to identify hazardous road conditions and minimize vehicular accident rates.

Effective road maintenance is critical for ensuring safety, efficiency, and convenience in transportation networks. However, conventional assessment methods, often relying on isolated metrics or visual inspections, fail to capture the complex interplay of pavement condition factors, leading to potential misallocation of maintenance efforts. This study proposes a two-stage framework to enhance road condition assessment and maintenance prioritization by integrating individual performance indices with a unified pavement assessment metric (UPAM) developed through the fuzzy analytic hierarchy process. In the first stage, road segments are pre-screened based on individual indices—the structural condition index, international roughness index, international friction index, and pavement condition index—to identify localized deficiencies. Segments are classified as high or low priority based on threshold performance. In the second stage, segments are systematically ranked within each group using UPAM scores. While individual indices offer detailed diagnostic insights, they lack consistency for ranking; conversely, the UPAM provides standardized prioritization but may obscure critical localized issues. The combined approach improves transparency, reliability, and decision-making effectiveness, offering a comprehensive tool for optimizing pavement maintenance strategies.

Road maintenance is essential for supporting road safety and user comfort. Developing predictive models for road surface conditions enables highway agencies to optimize maintenance planning and strategies. The international roughness index (IRI) is widely used as a standard for evaluating road surface quality. This study compares the performance of deep neural networks (DNNs) and graph convolutional networks (GCNs) in predicting IRI values. A unique aspect of this research is the inclusion of additional predictor features, such as the type and timing of recent roadwork, hypothesized to affect IRI values. Findings indicate that, overall, the DNN model performs similarly to the GCN model across the entire highway network. Given the predominantly linear structure of national highways and their limited connectivity, the dataset exhibits a low beta index, ranging from 0.5 to 0.75. Additionally, gaps in IRI data collection and discontinuities in certain highway segments present challenges for modeling spatial dependencies. The performance of DNN and GCN models was assessed across the network, with results indicating that DNN outperforms GCN when highway networks are sparsely connected. This research underscores the suitability of DNN for low-connectivity networks like highways, while also highlighting the potential of GCNs in more densely connected settings.

Efficient and sustainable transportation is crucial for addressing the environmental and social challenges associated with urban mobility. Accurate estimation of travel time plays a pivotal role in traffic management and trip planning. This study focused on leveraging machine learning models to enhance travel time estimation accuracy on toll roads under diverse traffic conditions. Two models were developed for travel time estimation under a variety of traffic conditions on the Don Muang Tollway, Bangkok, Thailand: a long short-term memory (LSTM) recurrent neural network model and a support vector regression (SVR) model. Missing data were treated using the proposed segment-based data imputation method. Unlike other studies, the effects of missing input data on the travel time model performance were also analyzed. Traffic parameters, such as speed and flow, along with other relevant parameters (time of day, day of the week, holiday indicators, and a missing data indicator), were fed into each model to estimate travel time on each of the four specific routes. The LSTM and SVR results had similar performance levels based on evaluating the all-day pooled data. However, the mean absolute percentage errors were lower for LSTM during peak periods, while SVR performed slightly better during off-peak periods. Additionally, LSTM coped substantially better than SVR with unusual traffic fluctuations. The sensitivity analysis of the missing input data in this study also revealed that the LSTM model was more robust to the high degree of missing data than the SVR model.

With the current popularity of mobile devices with Bluetooth technology, numerous studies have developed methods to analyze the data from such devices to estimate a variety of traffic information, such as travel time, link speed, and origin–destination estimations. However, few studies have comprehensively determined the impact of the penetration rate on the estimated travel time derived from Bluetooth detectors. The objectives of this paper were threefold: (1) to develop a data-processing method to estimate the travel time based on Bluetooth transactional data; (2) to determine the impact of vehicle speeds on Bluetooth detection performance; and (3) to analyze how the Bluetooth penetration rate affected deviations in the estimated travel time. A 28 km toll section in Bangkok, Thailand, was chosen for the study. A number of Bluetooth detectors and microwave radar devices were installed to collect traffic data in October 2020. Five data-processing steps were developed to estimate the travel time. Based on the results, the penetration rate during the day (50 to 90 percent) was higher than during the night (20 to 50 percent). In addition, we found that speed had adverse effects on the MAC address detection capability of the Bluetooth detectors; for speeds greater than 80 km/h, the number of MAC addresses detected decreased. The minimum Bluetooth penetration rate should be at least 1 percent (or 37 vehicles/h) during peak periods and at least 5 percent (or 49 vehicles/h) during the off-peak period.