Automatic recognition of damaged town buildings caused by earthquake using remote sensing information: Taking the 2001 Bhuj, India, earthquake and the 1976 Tangshan, China, earthquake as examples

In the high-resolution images, the undamaged buildings generally show a natural textural feature, while the dam- aged or semi-damaged buildings always exhibit some low-grayscale blocks because of their coarsely damaged sections. If we use a proper threshold to classify the grayscale of image, some independent holes will appear in the damaged regions. By using such statistical information as the number of holes in every region, or the ratio between the area of holes and that of the region, etc, the damaged buildings can be separated from the undamaged, thus automatic detection of damaged buildings can be realized. Based on these characteristics, a new method to auto- matically detect the damage buildings by using regional structure and statistical information of texture is presented in the paper. In order to test its validity, 1-m-resolution iKonos merged image of the 2001 Bhuj earthquake and grayscale aerial photos of the 1976 Tangshan earthquake are selected as two examples to automatically detect the damaged buildings. Satisfied results are obtained.

Vision-based multi-level synthetical evaluation of seismic damage for RC structural components: a multi-task learning approach

Recent studies for computer vision and deep learning-based,post-earthquake inspections on RC structures mainly perform well for specific tasks,while the trained models must be fine-tuned and re-trained when facing new tasks and datasets,which is inevitably time-consuming.This study proposes a multi-task learning approach that simultaneously accomplishes the semantic segmentation of seven-type structural components,three-type seismic damage,and four-type deterioration states.The proposed method contains a CNN-based encoder-decoder backbone subnetwork with skip-connection modules and a multi-head,task-specific recognition subnetwork.The backbone subnetwork is designed to extract multi-level features of post-earthquake RC structures.The multi-head,task-specific recognition subnetwork consists of three individual self-attention pipelines,each of which utilizes extracted multi-level features from the backbone network as a mutual guidance for the individual segmentation task.A synthetical loss function is designed with real-time adaptive coefficients to balance multi-task losses and focus on the most unstably fluctuating one.Ablation experiments and comparative studies are further conducted to demonstrate their effectiveness and necessity.The results show that the proposed method can simultaneously recognize different structural components,seismic damage,and deterioration states,and that the overall performance of the three-task learning models gains general improvement when compared to all single-task and dual-task models.

Eukaryotic nucleotide excision repair： from understanding mechanisms to influencing biology

Repair of bulky DNA adducts by the nucleotide excision repair （NER） pathway is one of the more versatile DNA repair pathways for the removal of DNA lesions. There are two subsets of the NER pathway, global genomic-NER （GG- NER） and transcription-coupled NER （TC-NER）, which differ only in the step involving recognition of the DNA lesion. Following recognition of the damage, the sub-pathways then converge for the incision/excision steps and subsequent gap filling and ligation steps. This review will focus on the GGR sub-pathway of NER, while the TCR sub-pathway will be covered in another article in this issue. The ability of the NER pathway to repair a wide array of adducts stems, in part, from the mechanisms involved in the initial recognition step of the damaged DNA and results in NER impacting an equally wide array of human physiological responses and events. In this review, the impact of NER on carcinogenesis, neurological function, sensitivity to environmental factors and sensitivity to cancer therapeutics will be discussed. The knowledge generated in our understanding of the NER pathway over the past 40 years has resulted from advances in the fields of animal model systems, mammalian genetics and in vitro biochemistry, as well as from reconstitution studies and structural analyses of the proteins and enzymes that participate in this pathway. Each of these avenues of research has contributed significantly to our understanding of how the NER pathway works and how alterations in NER activity, both positive and negative, influence human biology.