Search

Building extraction aims to extract building pixels from remote sensing imagery, which plays a significant role in urban planning, dynamic urban monitoring, and many other applications. UNet3+ is widely applied in building extraction from remote sensing images. However, it still faces issues such as low segmentation accuracy, imprecise boundary delineation, and the complexity of network models. Therefore, based on the UNet3+ model, this paper proposes a 3D Joint Attention (3DJA) module that effectively enhances the correlation between local and global features, obtaining more accurate object semantic information and enhancing feature representation. The 3DJA module models semantic interdependence in the vertical and horizontal dimensions to obtain feature map spatial encoding information, as well as in the channel dimensions to increase the correlation between dependent channel graphs. In addition, a bottleneck module is constructed to reduce the number of network parameters and improve model training efficiency. Many experiments are conducted on publicly accessible WHU,INRIA and Massachusetts building dataset, and the benchmarks, BOMSC-Net, CVNet, SCA-Net, SPCL-Net, ACMFNet, MFCF-Net models are selected for comparison with the 3DJA-UNet3+ model proposed in this paper. The experimental results show that 3DJA-UNet3+ achieves competitive results in three evaluation indicators: overall accuracy, mean intersection over union, and F1-score. The code will be available at https://github.com/EnjiLi/3DJA-UNet3Plus. [ABSTRACT FROM AUTHOR]

Stone matrix asphalt and asphalt concrete mixture with 13.2 mm nominal maximum aggregate size (named SMA13 and AC13, respectively) are widely used in the surface course of asphalt pavement in China. Generally, the pavement performance of SMA13 is superior to that of AC13, while the cost of the former is significantly higher than that of the latter. The objective of this paper was to develop a new hot mix asphalt (named SMAC13) whose performance and cost are between SMA13 and AC13. A boundary sieve size (BSS) of 2.36 mm was selected between fine and coarse aggregates. Based on the union set of aggregate gradation ranges of SMA13 and AC13, the family of gradation curves in the forms of S shapes were designed in terms of the BSS passing rate. According to the evaluation of the skeleton interlock of coarse aggregate of the gradation curve family, the aggregate gradation range of SMAC13 was determined. Also, the performance of three kinds of asphalt mixtures were compared through laboratory tests. The results indicated that SMA13 shows the best rutting resistance, followed by SMAC13 then AC13, while in terms of low-temperature performance in resistance to cracking, the sequence is SMAC13, AC13, and SMA13. The sequence of water stability is AC13, SMAC13, and SMA13. Furthermore, the cost of SMAC13 is 25% less than that of SMA13. Therefore, SMAC13 can be used as an alternative for the surface course of asphalt pavement in terms of performance and cost. [ABSTRACT FROM AUTHOR]

While the significance of N6-methyladenosine (m 6 A) in viral regulation has been extensively studied, the functions of 5-methylcytosine (m 5 C) modification in viral biology remain largely unexplored. In this study, we demonstrate that m 5 C is more abundant than m 6 A in severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and provide a comprehensive profile of the m 5 C landscape of SARS-CoV-2 RNA. Knockout of NSUN2 reduces m 5 C levels in SARS-CoV-2 virion RNA and enhances viral replication. Nsun2 deficiency mice exhibited higher viral burden and more severe lung tissue damages. Combined RNA-Bis-seq and m 5 C-MeRIP-seq identified the NSUN2-dependent m 5 C-methylated cytosines across the positive-sense genomic RNA of SARS-CoV-2, and the mutations of these cytosines enhance RNA stability. The progeny SARS-CoV-2 virions from Nsun2 deficiency mice with low levels of m 5 C modification exhibited a stronger replication ability. Overall, our findings uncover the vital role played by NSUN2-mediated m 5 C modification during SARS-CoV-2 replication and propose a host antiviral strategy via epitranscriptomic addition of m 5 C methylation to SARS-CoV-2 RNA.