Yan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yan Wang has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Bing Niu
School of Life Sciences, Shanghai University, Shanghai 200444, China
1 shared publication - Dengke Zhong
Department of Animal Science and Technology, Shanghai Vocational College of Agriculture and Forestry, Shanghai 201699, China
1 shared publication - Jianchao Wei
Shanghai Veterinary Research Institute, Chinese Academy of Agricultural Sciences, Shanghai, China
1 shared publication - Jiayang Zheng
Shanghai Veterinary Research Institute, Chinese Academy of Agricultural Sciences, Shanghai 200241, China
1 shared publication - Jingwen Ji
School of Life Sciences, Shanghai University, Shanghai 200444, China
1 shared publication - Kaiwen Guo
School of Life Sciences, Shanghai University, Shanghai 200444, China
1 shared publication
Latest Publications
- Open Access
DSCF-DET: An RT-DETR-Based Framework for Fine-Grained Detection of Musk Deer and Visually Similar Artiodactyls
Musk deer are forest-dwelling artiodactyls of high conservation value, but their wild populations remain under severe conservation pressure due to poaching driven by the demand for natural musk, together with habitat fragmentation and habitat loss. Efficient non-invasive image-based monitoring is therefore important for musk deer conservation; however, fine-grained detection of musk deer and visually similar artiodactyls in ecological images remains difficult because of background camouflage, vegetation occlusion, and high inter-class similarity. In this study, a fine-grained wildlife image dataset was constructed, and an RT-DETR-based framework, termed DSCF-DET, was proposed for automated detection in complex natural scenes. DSCF-DET integrates three task-oriented modules: DRPBlock for receptive-field-aware feature extraction, SASTE for sparse spatial encoding, and CBAFusion for cross-level feature fusion. On the constructed dataset, DSCF-DET achieved 91.4% precision, 86.2% recall, 88.7% F1-score, and 86.4% mAP50. Compared with RT-DETR-r18, it improved these metrics by 8.6, 12.1, 10.5, and 12.4 percentage points, respectively, while maintaining moderate model complexity. Visualization results showed more target-focused feature responses and reduced background-related activations. Cross-dataset experiments on an independent public wildlife dataset further suggested potential applicability to broader wildlife detection scenarios. These results indicate that DSCF-DET provides a computationally balanced approach for ecological image screening and intelligent musk deer monitoring.
Open AccessDSCF-DET: An RT-DETR-Based Framework for Fine-Grained Detection of Musk Deer and Visually Similar Artiodactyls
Musk deer are forest-dwelling artiodactyls of high conservation value, but their wild populations remain under severe conservation pressure due to poaching driven by the demand for natural musk, together with habitat fragmentation and habitat loss. Efficient non-invasive image-based monitoring is therefore important for musk deer conservation; however, fine-grained detection of musk deer and visually similar artiodactyls in ecological images remains difficult because of background camouflage, vegetation occlusion, and high inter-class similarity. In this study, a fine-grained wildlife image dataset was constructed, and an RT-DETR-based framework, termed DSCF-DET, was proposed for automated detection in complex natural scenes. DSCF-DET integrates three task-oriented modules: DRPBlock for receptive-field-aware feature extraction, SASTE for sparse spatial encoding, and CBAFusion for cross-level feature fusion. On the constructed dataset, DSCF-DET achieved 91.4% precision, 86.2% recall, 88.7% F1-score, and 86.4% mAP50. Compared with RT-DETR-r18, it improved these metrics by 8.6, 12.1, 10.5, and 12.4 percentage points, respectively, while maintaining moderate model complexity. Visualization results showed more target-focused feature responses and reduced background-related activations. Cross-dataset experiments on an independent public wildlife dataset further suggested potential applicability to broader wildlife detection scenarios. These results indicate that DSCF-DET provides a computationally balanced approach for ecological image screening and intelligent musk deer monitoring.
- Open Access
Rapid Detection of Getah Virus Antibodies in Horses Using a Recombinant E2 Protein-Based Immunochromatographic Strip
The prevalence and impact of Getah virus (GETV) are significant concerns in China. GETV can infect a wide range of animals, including horses, pigs, sheep, cattle, birds, and humans, resulting in substantial losses in the livestock and agricultural industries. GETV infection can cause the development of ulcers and inflammation in the mouth and gums of horses, which result in pain and discomfort and lead to symptoms such as reduced appetite, drooling, and difficulty chewing. As a result, there is a pressing need for efficient and rapid disease diagnosis methods. However, the currently available diagnostic methods have limitations in terms of operational time, equipment, and the experience of the individuals using them. In this study, a rapid, specific, and sensitive detection method was developed using a colloidal gold-based immunochromatographic strip (ICS) for the detection of antibodies against GETV in horses. To prepare the ICS, the antigen domain of the E2 glycoprotein of GETV was expressed using the Escherichia coli expression system after analysis with DNAstar v7.1 software. The nitrocellulose membrane was coated with rE2 protein or SPA to form the test line and control line, respectively. After optimizing the reaction conditions, the sensitivity, specificity, and repeatability of the strip were verified. The results showed that the test strip had a detection limit of up to 1:320 dilutions for GETV-positive serum, with no cross-reactivity observed with other equine-susceptible pathogens such as equine arteritis virus (EAV), equine herpesvirus-1 (EHV-I), equine infectious anemia virus (EIAV), equine influenza virus (EIV), African horse sickness virus (AHSV), and Japanese encephalitis virus (JEV). Furthermore, the ICS exhibited a concordance rate of 94.0% when testing 182 clinical serum samples compared to the virus neutralization test. Overall, this ICS diagnosis method will be an effective tool for the rapid detection of GETV in the field.
Open AccessRapid Detection of Getah Virus Antibodies in Horses Using a Recombinant E2 Protein-Based Immunochromatographic Strip
The prevalence and impact of Getah virus (GETV) are significant concerns in China. GETV can infect a wide range of animals, including horses, pigs, sheep, cattle, birds, and humans, resulting in substantial losses in the livestock and agricultural industries. GETV infection can cause the development of ulcers and inflammation in the mouth and gums of horses, which result in pain and discomfort and lead to symptoms such as reduced appetite, drooling, and difficulty chewing. As a result, there is a pressing need for efficient and rapid disease diagnosis methods. However, the currently available diagnostic methods have limitations in terms of operational time, equipment, and the experience of the individuals using them. In this study, a rapid, specific, and sensitive detection method was developed using a colloidal gold-based immunochromatographic strip (ICS) for the detection of antibodies against GETV in horses. To prepare the ICS, the antigen domain of the E2 glycoprotein of GETV was expressed using the Escherichia coli expression system after analysis with DNAstar v7.1 software. The nitrocellulose membrane was coated with rE2 protein or SPA to form the test line and control line, respectively. After optimizing the reaction conditions, the sensitivity, specificity, and repeatability of the strip were verified. The results showed that the test strip had a detection limit of up to 1:320 dilutions for GETV-positive serum, with no cross-reactivity observed with other equine-susceptible pathogens such as equine arteritis virus (EAV), equine herpesvirus-1 (EHV-I), equine infectious anemia virus (EIAV), equine influenza virus (EIV), African horse sickness virus (AHSV), and Japanese encephalitis virus (JEV). Furthermore, the ICS exhibited a concordance rate of 94.0% when testing 182 clinical serum samples compared to the virus neutralization test. Overall, this ICS diagnosis method will be an effective tool for the rapid detection of GETV in the field.