Multi-scale feature fusion for pavement crack detection based on Transformer.

Automated pavement crack image segmentation presents a significant challenge due to the difficulty in detecting slender cracks on complex pavement backgrounds, as well as the significant impact of lighting conditions. In this paper, we propose a novel approach for automated pavement crack detection using a multi-scale feature fusion network based on the Transformer architecture, leveraging an encoding-decoding structure. In the encoding phase, the Transformer is leveraged as a substitute for the convolution operation, which utilizes global modeling to enhance feature extraction capabilities and address long-distance dependence. Then, dilated convolution is employed to increase the receptive field of the feature map while maintaining resolution, thereby further improving context information acquisition. In the decoding phase, the linear layer is employed to adjust the length of feature sequence output by different encoder block, and the multi-scale feature map is obtained after dimension conversion. Detailed information of cracks can be restored by fusing multi-scale features, thereby improving the accuracy of crack detection. Our proposed method achieves an F1 score of 70.84% on the Crack500 dataset and 84.50% on the DeepCrack dataset, which are improvements of 1.42% and 2.07% over the state-of-the-art method, respectively. The experimental results show that the proposed method has higher detection accuracy, better generalization and better crack detection results can be obtained under both high and low brightness conditions.

Dynamics of Neutral and Charged Nanodiamonds in Aqueous Media Confined between Gold Surfaces under Normal and Shear Loading.

The dynamics of cubo-octahedral nanodiamonds (NDs) with three different surface treatments and confined in aqueous environments between gold surfaces under shear and normal loading conditions have been characterized via molecular dynamics (MD) simulations. The treatments consisted of carboxyl (-COO-) or amino (-NH3 +) groups attached to the NDs, producing either negatively or positively charged NDs, respectively, and hydrogen-terminated surfaces producing neutral NDs. Simulations were performed in the presence and absence of induced image charges to explore the impact of electrostatic interactions on friction and surface deformation. Significant deformation of the gold surfaces was observed for negatively charged NDs placed between gold surfaces under external loads that were sufficient to displace water from the contact. Rolling and relatively high friction levels were also observed for the negatively charged NDs under the same conditions. In contrast, the neutral and positively charged NDs exhibited sliding behavior with only minor deformation of the gold surfaces. The results suggest that the size of the surface functional group plays a major role in determining whether NDs slide or roll on solid contacts. Higher friction levels were also observed in conjunction with induced image charges in the gold contacts. The results demonstrate how surface functionalization and surface-induced charges can work in combination to profoundly influence tribological performance.

Effect of Indoors Artificial Lighting Conditions on Computer-Based Learning Performance.

Lighting condition is essential to human performance. With the widespread use of computer-based learning, the performance measurements become difficult, and the effects of artificial lighting conditions towards the new learning forms are not investigated extensively. The current study conducts a subject-within experiment with a 45-min-long online learning along with electroencephalogram (EEG)-based measurements, and a post-interview under five lighting setups respectively (300 lx, 3000 K; 300 lx, 4000 K; 300 lx, 6500 K; 500 lx, 4000 K; 1000 lx, 4000 K). Attention is chosen as the key factor to represent the learning performance. The results show that the attention of people aged in the 20s is not affected by the experimental lighting conditions. The results also demonstrate that people in high illumination at 1000 lx are more inclined to sustain attention despite the discomfort and dissatisfaction. Taking the EEG-based attention measurements and post-interview answers into consideration, lighting conditions at 300 lx, 4000 K are the recommended set points for university architectures among the investigated conditions, providing a practical basis when adjusting the lighting standard for its advantage in energy saving.

Interdependent Roles of Electrostatics and Surface Functionalization on the Adhesion Strengths of Nanodiamonds to Gold in Aqueous Environments Revealed by Molecular Dynamics Simulations.

Molecular dynamics simulations demonstrate that adhesion strengths as a function of charge for aqueous nanodiamonds (NDs) interacting with a gold substrate result from an interdependence of electrostatics and surface functionalization. The simulations reveal a water layer containing Na+ counterions between a negative ND with surface -COO- functional groups that is not present for a positively charged ND with -NH3+ functional groups. The closer proximity of the positive ND to the gold surface and the lack of cancelation of electrostatic interactions due to counterions and the water layer lead to an electrostatic adhesion force for the positive ND that is nearly three times larger than that of the negative ND. Prior interpretations of experimental tribological studies of ND-gold systems suggested that electrostatics or surface functionalization could be responsible for observed adhesion strength differences. The present work demonstrates how these two effects work together in determining adhesion for this system.