Dejin Wang

Dejin Wang


Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
7 February 2024 in Agriculture
Verified
Journal Article
Open access
PDF file
JLJianian Li
Jianian Li
LQliu zheng quan
liu zheng quan
DWDejin Wang
Dejin Wang
The precise detection of diseases is crucial for the effective treatment of pear trees and to improve their fruit yield and quality. Currently, recognizing plant diseases in complex backgrounds remains a significant challenge. Therefore, a lightweight CCG-YOLOv5n model was designed to efficiently recognize pear leaf diseases in complex backgrounds. The CCG-YOLOv5n model integrates a CA attention mechanism, CARAFE up-sampling operator, and GSConv into YOLOv5n. It was trained and validated using a self-constructed dataset of pear leaf diseases. The model size and FLOPs are only 3.49 M and 3.8 G, respectively. The mAP@0.5 is 92.4%, and the FPS is up to 129. Compared to other lightweight indicates that the models, the experimental results demonstrate that the CCG-YOLOv5n achieves higher average detection accuracy and faster detection speed with a smaller computation and model size. In addition, the robustness comparison test CCG-YOLOv5n model has strong robustness under various lighting and weather conditions, including frontlight, backlight, sidelight, tree shade, and rain. This study proposed a CCG-YOLOv5n model for accurately detecting pear leaf diseases in complex backgrounds. The model is suitable for use on mobile terminals or devices.

10 September 2021 in Hydrological Processes
Verified
Journal Article
Closed access
PDF file
DWDejin Wang
Dejin Wang
WZWenzhi Zhao
Wenzhi Zhao
HZHong Zhou
Hong Zhou
WLWeicheng Luo
Weicheng Luo
Hu LiuHu Liu
Hu Liu

5 November 2024 in IEEE Sensors Journal
Verified
Journal Article
Closed access
JLJianian Li
Jianian Li
YCYingying Cheng
Yingying Cheng
YMYongzheng Ma
Yongzheng Ma
YLYuecong Li
Yuecong Li
JWJun Wu
Jun Wu
DWDejin Wang
Dejin Wang
Rapid detection of fertilizer solutions is essential for improving water-fertilizer integration systems. However, existing detection methods are hindered by high costs, complexity, and slow response times, making real-time monitoring challenging. To solve these issues, we developed a qualitative-quantitative model that leverages machine learning (ML) algorithms based on the dielectric frequency response to detect the type and concentration of seven fertilizer solutions (N, P, K, PN, PK, NK, and NPK). Each fertilizer had unique dielectric frequency features, with different fluctuation, peak numbers, and maximum peaks. A linear relationship was also observed between the dielectric features (gain or phase shift) and fertilizer concentration within a specific frequency band. Following a "qualitative first, then quantitative" strategy, a qualitative-quantitative model was constructed using these results, including one classification model and seven concentration prediction models. For identifying solution types, the random forests (RF) algorithm was selected as the optimal qualitative model, with an accuracy of 98.57%. For detecting solution concentrations, seven optimal models were identified with R² values exceeding 0.98 and RMSE values below 0.4%, each incorporating the observed linear relationships mentioned above and different ML algorithms. Notably, the least squares support vector machine (LSSVM) and BP regression models outperformed the partial least squares regression (PLSR) model. These results demonstrated that the developed qualitative-quantitative model effectively integrates dielectric features with ML algorithms to accurately detect fertilizer solution components. This model can provide can provide feedback on fertilizer in-formation, supporting rapid online identification of fertilizer components, significantly enhancing their water-fertilizer utilization efficiency.

7 November 2025 in Engineering Research Express
Verified
Journal Article
Closed access
JLJianian Li
Jianian Li
YLYang Luo
Yang Luo
ZLZhengquan Liu
Zhengquan Liu
ZYZhu Yuan
Zhu Yuan
LGLong Gao
Long Gao
DWDejin Wang
Dejin Wang
Precise identification of leaf diseases in time is crucial for improving the yield and quality of Dendrobium officinarum . However, the current approach cannot satisfy the requirement of rapid and accurate detection for Dendrobium leaf diseases in the complex environments.To solve this issue, this study proposed a CSMD-YOLOv5s model, which integrates the CA attention mechanism, Swin Transformer, small-target detection layer, and decoupling head into the YOLOv5s. Compared with the baseline model (YOLOv5s), the improved model performed higher average detection accuracy and faster detection speed, with mAP@0.5 (89.6%), precision (88.3%), and recall (87.3%). Robustness experiments show that the improved model is able to maintain stable detection under interference conditions such as strong light, dark light, occlusion, and rain.The CSMD-YOLOv5s model can accurately identify five prevalent Dendrobium leaf diseases in a complex environment, as well as reduce the missed and false detection rate. The model provides a convenient approach for rapidly and accurately detecting the Dendrobium leaf diseases, which can be used for mobile devices and terminals.

15 January 2021
Verified
Preprint
Open access
PDF file
DWDejin Wang
Dejin Wang
WZWenzhi Zhao
Wenzhi Zhao
ZHZhou Hong
Zhou Hong
WLWeicheng Luo
Weicheng Luo
Desert pavements are critical for maintaining ecological stability and promoting near-surface hydrological cycle in arid regions. However, few studies have reported the desert pavements on ecological on fluvial fans. Although desert pavement surfaces appear to be barren and flat, we found that the surfaces were featured by mosaic pattern of desert pavement (DP) and bare ground (BG). In this study, we investigated the effects of mosaic DP on water infiltration and vegetation distribution at six sites (i.e. one on the hillside and five in the sectors of fluvial fans) along a southwest belt transect on the fluvial fans in the Northern Linze County, in the middle of Hexi Corridor. The results showed that significant differences of Mosaic DP between hillside and sectors of fans were found in pavement thickness, thickness of vesicular horizon (Av thickness), particle composition and bulk density, rather than soil moisture content (SMC), gravel coverage and surface gravel size. The mosaic DP can inhibit water infiltration by pavement layer, where the sorptivity ( S ), initial infiltration rate ( i int ) and steady- state infiltration rate ( i sat ) and infiltration time ( T ) averaged 1.30 cm/min-0.5, 5.03 cm/min, 0.23 cm/min, and 12.76 min respectively. If pavement layer was scalped, the S , i int and i sat increased by 0.75 cm/min-0.5, 2.90 cm/min and 0.13 cm/min, respectively, and the T was shortened by 5.34 min. Water infiltration was mainly controlled by the pavement layer thickness (+), Av thickness (-), surface gravel coverage (-), and fine earth (+) and fine gravel (-) of pavement layer. Mosaic DP grew less shrubs than mosaic BG where distributed plenty of herbs. It can be concluded that desert pavements can keep vegetation stability by self-regulating rainfall. This study would deepen our understanding of the eco-hydrological cycle of pavement landscape in arid regions.

11 September 2025 in Signal, Image and Video Processing
Verified
Journal Article
Closed access
PDF file
JLJianian Li
Jianian Li
ZYZhu Yuan
Zhu Yuan
ZLZhengquan Liu
Zhengquan Liu
YLYang Luo
Yang Luo
LGLong Gao
Long Gao
DWDejin Wang
Dejin Wang