| 1. |
- Lun, Zhao, et al.
(författare)
-
Skip-YOLO : Domestic Garbage Detection Using Deep Learning Method in Complex Multi-scenes
- 2023
-
Ingår i: International Journal of Computational Intelligence Systems. - : Springer Science+Business Media B.V.. - 1875-6891 .- 1875-6883. ; 16:1
-
Tidskriftsartikel (refereegranskat)abstract
- It is of great significance to identify all types of domestic garbage quickly and intelligently to improve people's quality of life. Based on the visual analysis of feature map changes in different neural networks, a Skip-YOLO model is proposed for real-life garbage detection, targeting the problem of recognizing garbage with similar features. First, the receptive field of the model is enlarged through the large-size convolution kernel which enhanced the shallow information of images. Second, the high-dimensional features of the garbage maps are extracted by dense convolutional blocks. The sensitivity of similar features in the same type of garbage increases by strengthening the sharing of shallow low semantics and deep high semantics information. Finally, multiscale high-dimensional feature maps are integrated and routed to the YOLO layer for predicting garbage type and location. The overall detection accuracy is increased by 22.5% and the average recall rate is increased by 18.6% comparing the experimental results with the YOLOv3 analysis. In qualitative comparison, it successfully detects domestic garbage in complex multi-scenes. In addition, this approach alleviates the overfitting problem of deep residual blocks. The application case of waste sorting production line is used to further highlight the model generalization performance of the method. © 2023, Springer Nature B.V.
|
|
| 2. |
- Marcotte, Harold, et al.
(författare)
-
Conversion of monoclonal IgG to dimeric and secretory IgA restores neutralizing ability and prevents Infection of Omicron lineages
- 2024
-
Ingår i: Proceedings of the National Academy of Sciences of the United States of America. - : NATL ACAD SCIENCES. - 0027-8424 .- 1091-6490. ; 121:3
-
Tidskriftsartikel (refereegranskat)abstract
- The emergence of Omicron lineages and descendent subvariants continues to present a severe threat to the effectiveness of vaccines and therapeutic antibodies. We have previ- ously suggested that an insufficient mucosal immunoglobulin A (IgA) response induced by the mRNA vaccines is associated with a surge in breakthrough infections. Here, we further show that the intramuscular mRNA and/or inactivated vaccines cannot suffi- ciently boost the mucosal secretory IgA response in uninfected individuals, particu- larly against the Omicron variant. We thus engineered and characterized recombinant monomeric, dimeric, and secretory IgAl antibodies derived from four neutralizing IgG monoclonal antibodies (mAbs 01A05, rmAb23, DXP-604, and XG014) targeting the receptor-binding domain of the spike protein. Compared to their parental IgG antibod- ies, dimeric and secretory IgAl antibodies showed a higher neutralizing activity against different variants of concern (VOCs), in part due to an increased avidity. Importantly, the dimeric or secretory IgAl form of the DXP-604 antibody significantly outperformed its parental IgG antibody, and neutralized the Omicron lineages BA.1, BA.2, and BA.4/5 with a 25- to 75-fold increase in potency. In human angiotensin converting enzyme 2 (ACE2) transgenic mice, a single intranasal dose of the dimeric IgA DXP-604 conferred prophylactic and therapeutic protection against Omicron BA.5. Thus, dimeric or secre- tory IgA delivered by nasal administration may potentially be exploited for the treatment Iand prevention of Omicron infection, thereby providing an alternative tool for combating immune evasion by the current circulating subvariants and, potentially, future VOCs.
|
|
| 3. |
- Zhao, Lun, et al.
(författare)
-
A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method
- 2021
-
Ingår i: Scanning. - : Wiley-Hindawi. - 0161-0457 .- 1932-8745.
-
Tidskriftsartikel (refereegranskat)abstract
- The scanning electron microscope (SEM) is widely used in the analysis and research of materials, including fracture analysis, microstructure morphology, and nanomaterial analysis. With the rapid development of materials science and computer vision technology, the level of detection technology is constantly improving. In this paper, the deep learning method is used to intelligently identify microcracks in the microscopic morphology of SEM image. A deep learning model based on image level is selected to reduce the interference of other complex microscopic topography, and a detection method with dense continuous bounding boxes suitable for SEM images is proposed. The dense and continuous bounding boxes were used to obtain the local features of the cracks and rotating the bounding boxes to reduce the feature differences between the bounding boxes. Finally, the bounding boxes with filled regression were used to highlight the microcrack detection effect. The results show that the detection accuracy of our approach reached 71.12%, and the highest mIOU reached 64.13%. Also, microcracks in different magnifications and in different backgrounds were detected successfully.
|
|
