wendou WU

Mr. wendou WU


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
ZWZejun Wang
Zejun Wang
SZShihao Zhang
Shihao Zhang
LCLijiao Chen
Lijiao Chen
WWwendou WU
wendou WU
后王后巧 王
后巧 王
BWBaijuan Wang
Baijuan Wang
Pest infestations in tea gardens are one of the common issues encountered during tea cultivation. This study introduces an improved YOLOv8 network model for the detection of tea pests to facilitate the rapid and accurate identification of early-stage micro-pests, addressing challenges such as small datasets and the difficulty of extracting phenotypic features of target pests in tea pest detection. Based on the original YOLOv8 network framework, this study adopts the SIoU optimized loss function to enhance the model’s learning ability for pest samples. AKConv is introduced to replace certain network structures, enhancing feature extraction capabilities and reducing the number of model parameters. Vision Transformer with Bi-Level Routing Attention is embedded to provide the model with a more flexible computation allocation and improve its ability to capture target position information. Experimental results show that the improved YOLOv8 network achieves a detection accuracy of 98.16% for tea pest detection, which is a 2.62% improvement over the original YOLOv8 network. Compared with the YOLOv10, YOLOv9, YOLOv7, Faster RCNN, and SSD models, the improved YOLOv8 network has increased the mAP value by 3.12%, 4.34%, 5.44%, 16.54%, and 11.29%, respectively, enabling fast and accurate identification of early-stage micro pests in tea gardens. This study proposes an improved YOLOv8 network model based on deep learning for the detection of micro-pests in tea, providing a viable research method and significant reference for addressing the identification of micro-pests in tea. It offers an effective pathway for the high-quality development of Yunnan’s ecological tea industry and ensures the healthy growth of the tea industry.

27 February 2025 in Foods
Verified
Journal Article
Open access
PDF file
JXJiayi Xu
Jiayi Xu
XDXiujuan Deng
Xiujuan Deng
YWYamin Wu
Yamin Wu
MZMiao Zhou
Miao Zhou
CDCen Du
Cen Du
BWBaijuan Wang
Baijuan Wang
To investigate the flavour evolution mechanism of raw Pu-erh tea (RPT) during storage, the volatile and non-volatile compounds of RPT with different storage years (1–10 years) from the same raw material origin, manufacturer, and storage location in Wenshan Prefecture, Yunnan Province, were systematically analysed by HPLC, HS-SPME-GC-MS, and OAV. The results showed that both cluster analyses based on non-volatile and volatile compounds could classify RPT of different storage years into three ageing cycles, with key turning points in the third and eighth years of storage, which is also accompanied by the colour changing from green to orange or brown, the aroma changing from a faint scent to woody and ageing, the astringency diminishing, and the sweet and mellow increasing. Theophylline was identified as the potential marker of RPT stored 1–3 years, while (−)-catechin gallate, (−)-gallocatechin gallate, quercetin, and rutin as those for a storage of 9–10 years. The volatile compounds indicate a general trend of an initial increase followed by a decrease. Forty-four key aroma compounds (OAV ≥ 1) were identified. Eucalyptol, β-Caryophyllene, 2-Amylfuran, Copaene, Estragole, and α-Terpinene originated as potential markers for RPT stored 1–3 years, while (Z)-Linalool oxide (furanoid), α-Terpineol, Terpinen-4-ol, and cis-Anethol were for RPT stored 8–10 years. This study revealed the flavour characteristics and quality changes of RPT over the course of storage, and constructed a sensory flavour wheel, providing theoretical underpinnings for the quality control and assessment of RPT.

15 May 2025 in Scientific Reports
Verified
Journal Article
Open access
GPGuoquan Pei
Guoquan Pei
XQXueying Qian
Xueying Qian
BZBing Zhou
Bing Zhou
ZLZigao Liu
Zigao Liu
WWwendou WU
wendou WU
Agricultural diseases pose significant challenges to plant production. With the rapid advancement of deep learning, the accuracy and efficiency of plant disease identification have substantially improved. However, conventional convolutional neural networks that rely on multi-layer small-kernel structures are limited in capturing long-range dependencies and global contextual information due to their constrained receptive fields. To overcome these limitations, this study proposes a plant disease recognition method based on RepLKNet, a convolutional architecture with large kernel designs that significantly expand the receptive field and enhance feature representation. Transfer learning is incorporated to further improve training efficiency and model performance. Experiments conducted on the Plant Diseases Training Dataset, comprising 95,865 images across 61 disease categories, demonstrate the effectiveness of the proposed method. Under five-fold cross-validation, the model achieved an overall accuracy (OA) of 96.03%, an average accuracy (AA) of 94.78%, and a Kappa coefficient of 95.86%. Compared with ResNet50 (OA: 95.62%) and GoogleNet (OA: 94.98%), the proposed model demonstrates competitive or superior performance. Ablation experiments reveal that replacing large kernels with 3×3 or 5×5 convolutions results in accuracy reductions of up to 1.1% in OA and 1.3% in AA, confirming the effectiveness of the large kernel design. These results demonstrate the robustness and superior capability of RepLKNet in plant disease recognition tasks.

9 January 2026 in npj Science of Food
Verified
Journal Article
Open access
PDF file
GPGuoquan Pei
Guoquan Pei
BZBing Zhou
Bing Zhou
XQXueying Qian
Xueying Qian
BWBaijuan Wang
Baijuan Wang
WCWei Chen
Wei Chen
WWwendou WU
wendou WU
Accurate identification of the geographical origin of tea leaves is crucial for ensuring quality assurance and traceability within the tea industry. This study introduces Origin-Tea, a novel lightweight convolutional neural network that innovatively combines depthwise separable convolutions with squeeze-and-excitation (SE) attention mechanisms to effectively capture subtle phenotypic variations while minimizing computational costs. Unlike prior approaches that depend on heavy architectures or handcrafted features, Origin-Tea is explicitly designed for efficiency and interpretability in agricultural applications. Comprehensive ablation studies confirm the significant contribution of each architectural component to the model’s robust performance. The dataset comprises 900 high-resolution RGB images of Yunkang 10 tea leaves, independently collected from seven distinct regions in Yunnan Province. A 10-fold stratified nested cross-validation (CV) was employed, with one-fold designated for testing, one for validation, and the remaining eight for training in each iteration. Data augmentation techniques, including flipping, rotation, and exposure adjustments, were applied solely to the training set to enhance model robustness without compromising the intrinsic phenotypic features. Origin-Tea achieved an average overall accuracy (OA) of 0.92 ± 0.03 and a Kappa coefficient of 0.90 ± 0.03, outperforming the best-performing baseline, CoAtNet (OA = 0.89 ± 0.03), by 3.37% accuracy while reducing parameters by over 90% (1.7 M versus 17 M). Furthermore, in an independent test on 1788 scanner-captured images from four villages, Origin-Tea demonstrated excellent generalization with an OA of 0.97. These results highlight the model’s potential as a scalable, field-deployable solution for intelligent tea provenance verification and precision phenotyping.

23 July 2024 in Research Square
Verified
Preprint
Open access
PDF file
GPGuoquan Pei
Guoquan Pei
WWwendou WU
wendou WU
BZBing Zhou
Bing Zhou
ZLZigao Liu
Zigao Liu
PLPeiyao Li
Peiyao Li
HYHongxin Yang
Hongxin Yang
Agriculture diseases are unavoidable problems in agricultural production. With the extensive adoption of deep learning in agricultural diseases, the impact of diseases on crops has been effectively reduced. Many existing disease recognition models use multi-level small kernel convolutional structures, but small kernel convolution is not conducive to extracting global information and cannot capture the relationship between distant pixels. To solve this problem, this paper adopts the large kernel convolutional network RepLKNet to identify the Plant Diseases Training Dataset, and the large kernel convolutional network can effectively increase the receptive field and extract long-term dependencies. Improving model accuracy and training speed using transfer learning techniques. In this paper, experiments were conducted at Plant Diseases Training Dataset and the overall accuracy of the model was 93.6%, with an average accuracy of 91.9% and a Kappa coefficient of 93.3%, which proves its validity and reliability in the identification of agricultural diseases.

8 October 2025 in Agronomy
Verified
Journal Article
Open access
PDF file
WWwendou WU
wendou WU
GPGuoquan Pei
Guoquan Pei
ZLZiqiang Lu
Ziqiang Lu
BZBing Zhou
Bing Zhou
XQXueying Qian
Xueying Qian
LYLinnan Yang
Linnan Yang
Accurate estimation of chlorophyll and nitrogen content in tea leaves is essential for effective nutrient management. This study introduces a proof-of-concept dual-view RGB regression framework developed under controlled scanner conditions. Paired adaxial and abaxial images of Yun Kang 10 tea leaves were collected from four villages in Lincang, Yunnan, alongside corresponding soil and plant analyzer development (SPAD) and nitrogen measurements. A lightweight dual-input CoAtNet backbone with streamlined Bneck modules was designed, and three fusion strategies, Pre-fusion, Mid-fusion, and Late-fusion, were systematically compared. Ten-fold cross-validation revealed that Mid-fusion delivered the best performance (R2 = 94.19% ± 1.75%, root mean square error (RMSE) = 3.84 ± 0.65, MAE = 3.00 ± 0.45) with only 1.92 M parameters, outperforming both the single-view baseline and other compact models. Transferability was further validated on a combined smartphone–scanner dataset, where the framework maintained robust accuracy. Overall, these findings demonstrate a compact and effective system for non-destructive biochemical trait estimation, providing a strong foundation for future adaptation to field conditions and broader crop applications.