It is not practical to obtain a large number of labeled data to train a supervised learning network in tunnel lining nondestructive testing with ground-penetrating radar (GPR). To decrease the dependence of supervised learning on the number of labeled data, an improved self-supervised learning algorithm—self-attention dense contrastive learning (SA-DenseCL)—is proposed and incorporated with a mask region-convolution neural network (Mask R-CNN), which is trained by unlabeled and labeled GPR data. The proposed SA-DenseCL adds a self-attention-based relevant projection head to the DenseCL architecture of self-supervised learning, capturing the spatially continuing information between adjacent GPR traces. In the workflow, some unlabeled GPR images are used to pre-train the SA-DenseCL network for feature extraction and obtaining the backbone weights, which is superior to the conventional pre-training methods of supervised learning pre-trained by ImageNet images. The weights of the pre-trained backbone are then used to initialize the Mask R-CNN through transfer learning. Subsequently, a limited number of labeled GPR images are used to fine-tune the Mask R-CNN for automatically identifying the locations of the reinforcement bars and voids and estimating the secondary lining thickness. The experimental results show that the average precision reaches 96.70%, 81.04%, and 94.67% in identifying reinforcement bar locations, detecting void defects, and estimating secondary lining thickness, respectively, which outperform the conventional methods that use ImageNet-based supervised learning or GPR image-based DenseCL for initializing the Mask R-CNN backbone weights. It is observed that the improved self-supervised learning-based framework can improve the detection and estimation accuracy in GPR tunnel lining inspection.

Situation awareness (SA) is critical to improving takeover performance during the transition period from automated driving to manual driving. Although many studies measured SA during or after the driving task, few studies have attempted to predict SA in real time in automated driving. In this work, we propose to predict SA during the takeover transition period in conditionally automated driving using eye-tracking and self-reported data. First, a tree ensemble machine learning model, named LightGBM (Light Gradient Boosting Machine), was used to predict SA. Second, in order to understand what factors influenced SA and how, SHAP (SHapley Additive exPlanations) values of individual predictor variables in the LightGBM model were calculated. These SHAP values explained the prediction model by identifying the most important factors and their effects on SA, which further improved the model performance of LightGBM through feature selection. We standardized SA between 0 and 1 by aggregating three performance measures (i.e., placement, distance, and speed estimation of vehicles with regard to the ego-vehicle) of SA in recreating simulated driving scenarios, after 33 participants viewed 32 videos with six lengths between 1 and 20 s. Using only eye-tracking data, our proposed model outperformed other selected machine learning models, having a root-mean-squared error (RMSE) of 0.121, a mean absolute error (MAE) of 0.096, and a 0.719 correlation coefficient between the predicted SA and the ground truth. The code is available at https://github.com/refengchou/Situation-awareness-prediction. Our proposed model provided important implications on how to monitor and predict SA in real time in automated driving using eye-tracking data.

This paper proposes a nondestructive evaluation method based on deep learning using combined ground-penetrating radar (GPR) and electromagnetic induction (EMI) data for autonomic and accurate estimation of the cover thickness and diameter of reinforcement bars. A real-time object detection algorithm—You Only Look Once–version 3 (YOLO v3)—is adopted to automatically identify the reinforcement bar reflected signals from radargrams, with which the range of the cover thickness is roughly predicted. Subsequently, EMI data, accompanied with the cover thickness range, are imported to a one-dimensional convolutional neural network (1D CNN), pretrained by calibrated EMI and GPR data, to simultaneously estimate the cover thickness and reinforcement bar diameter. Testing with the on-site GPR data shows that YOLO v3 is superior to Single Shot Multibox Detector method in GPR hyperbolic signal identification. Testing of 1D CNN with the EMI and GPR data collected in an in-house sand pit experiment shows that the estimation accuracy of the cover thickness and reinforcement bar diameter is, respectively, 96.8% and 90.3% with a permissible error of 1 mm. Further, an experiment with concrete specimens demonstrates that among the 22 estimated values (including the reinforcement bar diameter and cover thickness), there are 17 values accurately estimated, while the inaccurately estimated values have an error up to 2 mm. The experimental results show that the proposed method can autonomically evaluate the reinforcement bar diameter and cover thickness with a high accuracy.