Yunhe Zhang

Dr. Yunhe Zhang


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
17 June 2022 in Machines
Verified
Journal Article
Open access
PDF file
YGYuhao Ge
Yuhao Ge
LSlin seng
lin seng
YZYunhe Zhang
Yunhe Zhang
ZLZuolin Li
Zuolin Li
HCHongtai Cheng
Hongtai Cheng
Wu zedong ZedongWu zedong Zedong
Wu zedong Zedong
To realize tomato growth period monitoring and yield prediction of tomato cultivation, our study proposes a visual object tracking network called YOLO-deepsort to identify and count tomatoes in different growth periods. Based on the YOLOv5s model, our model uses shufflenetv2, combined with the CBAM attention mechanism, to compress the model size from the algorithm level. In the neck part of the network, the BiFPN multi-scale fusion structure is used to improve the prediction accuracy of the network. When the target detection network completes the bounding box prediction of the target, the Kalman filter algorithm is used to predict the target’s location in the next frame, which is called the tracker in this paper. Finally, calculate the bounding box error between the predicted bounding box and the bounding box output by the object detection network to update the parameters of the Kalman filter and repeat the above steps to achieve the target tracking of tomato fruits and flowers. After getting the tracking results, we use OpenCV to create a virtual count line to count the targets. Our algorithm achieved a competitive result based on the above methods: The mean average precision of flower, green tomato, and red tomato was 93.1%, 96.4%, and 97.9%. Moreover, we demonstrate the tracking ability of the model and the counting process by counting tomato flowers. Overall, the YOLO-deepsort model could fulfill the actual requirements of tomato yield forecast in the greenhouse scene, which provide theoretical support for crop growth status detection and yield forecast.

15 November 2022 in Machines
Verified
Journal Article
Open access
PDF file
TXTongyu Xu
Tongyu Xu
XQXiangyu Qi
Xiangyu Qi
LSlin seng
lin seng
YZYunhe Zhang
Yunhe Zhang
YGYuhao Ge
Yuhao Ge
XYXin Yang
Xin Yang
In recent years, convolutional neural networks have made many advances in the field of computer vision. In smart greenhouses, using robots based on computer vision technology to pollinate flowers is one of the main methods of pollination. However, due to the complex lighting environment and the influence of leaf shadow in the greenhouse, it is difficult for the existing object detection algorithms to have high recall rate and accuracy. Based on this problem, from the perspective of application, we proposed a Yolov5s-based tomato flowering stage detection method named FlowerYolov5, which can well identify the bud phase, blooming phase and first fruit phase of tomato flowers. Firstly, in order to reduce the loss of tomato flower feature information in convolution and to strengthen the feature extraction of the target, FlowerYolov5 adds a new feature fusion layer. Then, in order to highlight the information of the object, the Convolutional Block Attention module (CBAM) is added to the backbone layer of FlowerYolov5. In the constructed tomato flower dataset, compared with YOLOv5s, the mAP of FlowerYolov5 increased by 7.8% (94.2%), and the F1 score of FlowerYolov5 increased by 6.6% (89.9%). It was found that the overall parameter of FlowerYolov5 was 23.9 Mbyte, thus achieving a good balance between model parameter size and recognition accuracy. The experimental results show that the FlowerYolov5 has good robustness and more accurate precision. At the same time, the recall rate has also been greatly improved. The prediction results of the proposed algorithm can provide more accurate flower positioning for the pollination robot and improve its economic benefits.

27 December 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
ZWZhibin Wang
Zhibin Wang
YWYaNa Wei
YaNa Wei
CMCuixia Mu
Cuixia Mu
YZYunhe Zhang
Yunhe Zhang
XQXiaojun Qiao
Xiaojun Qiao
Rice is a staple food for almost half of the world’s population, and the stability and sustainability of rice production plays a decisive role in food security. Diseases are a major cause of loss in rice crops. The timely discovery and control of diseases are important in reducing the use of pesticides, protecting the agricultural eco-environment, and improving the yield and quality of rice crops. Deep convolutional neural networks (DCNNs) have achieved great success in disease image classification. However, most models have complex network structures that frequently cause problems, such as redundant network parameters, low training efficiency, and high computational costs. To address this issue and improve the accuracy of rice disease classification, a lightweight deep convolutional neural network (DCNN) ensemble method for rice disease classification is proposed. First, a new lightweight DCNN model (called CG-EfficientNet), which is based on an attention mechanism and EfficientNet, was designed as the base learner. Second, CG-EfficientNet models with different optimization algorithms and network parameters were trained on rice disease datasets to generate seven different CG-EfficientNets, and a resampling strategy was used to enhance the diversity of the individual models. Then, the sequential least squares programming algorithm was used to calculate the weight of each base model. Finally, logistic regression was used as the meta-classifier for stacking. To verify the effectiveness, classification experiments were performed on five classes of rice tissue images: rice bacterial blight, rice kernel smut, rice false smut, rice brown spot, and healthy leaves. The accuracy of the proposed method was 96.10%, which is higher than the results of the classic CNN models VGG16, InceptionV3, ResNet101, and DenseNet201 and four integration methods. The experimental results show that the proposed method is not only capable of accurately identifying rice diseases but is also computationally efficient.

18 January 2024 in Atmosphere
Verified
Journal Article
Open access
PDF file
RWRunyu Wang
Runyu Wang
YZYunhe Zhang
Yunhe Zhang
LJLeizi Jiao
Leizi Jiao
ZXZhao Xiande
Zhao Xiande
ZGZhen Gao
Zhen Gao
DDDaming Dong
Daming Dong
Sterile medical masks are essential in preventing infectious diseases. However, the ethylene oxide contained within these masks is a class I carcinogen. The standard method for measuring ethylene oxide is gas chromatography-mass spectrometry, which is not fit with the dynamic process of human inhalation. Thus, the amount of ethylene oxide volatilized from masks and inhaled by users is unknown. In this work, ethylene oxide was detected by using proton-transfer-reaction mass spectrometry, which can measure volatile quantities in milliseconds. We found that ethylene oxide was volatilized from masks during use. Within the first minute, the ethylene oxide concentration decreased by 84.65%, and then the rate of reduction gradually slowed. After 5 min, all ethylene oxide was effectively volatilized, and the average mass of ethylene oxide inhaled was 299.02 μg. We investigated three methods to reduce the concentration of ethylene oxide in masks before use: natural airing, shaking the mask, and blowing the mask with a hair dryer. The hair dryer method produced the best results: the ethylene oxide concentration decreased by 88.3% after only 10 s. The natural airing method was the least effective: the ethylene oxide concentration decreased by 60.7% even after 3 h.

26 November 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
YZYunhe Zhang
Yunhe Zhang
YWYing Wang
Ying Wang
JCJinshi Chen
Jinshi Chen
YZYu Zhang
Yu Zhang
Soil disinfection is of great significance in reducing soil pests and weeds, overcoming the problem of crop continuous cropping obstacles, and ensuring the quality and safety of agricultural products. Soil flame disinfection technology, as a supplementary soil disinfection method that can be incorporated into an integrated plant protection system, has attracted much attention in recent years due to its characteristics of low resistance, greenness, environmental friendliness, and high efficiency. However, soil flame disinfection can also have a certain impact on soil organic matter and microbial communities, which is a core challenge that limits the promotion of flame disinfection technology. Clarifying the mechanism and temperature distribution of flame disinfection, accurately controlling flame disinfection parameters, can not only kill harmful organisms in soil, but also minimize damage to soil organic matter and microbial communities is the current research focus. This paper presents a comprehensive summary and discussion of the research progress regarding the mechanism of soil flame disinfection technology, the distribution of temperature fields, and the precise control technology for disinfection machines. It thoroughly elaborates on the efficacy of flame in eliminating typical soil-borne diseases and pests, the destructive impact of flame on soil organic matter and beneficial microbial communities, as well as the current status of research and development on soil flame disinfection devices. Additionally, it explores the pressing technical challenges that remain to be addressed. The article then discusses the future market prospects of soil flame disinfection equipment, focusing on key technological breakthroughs and opportunities, providing theoretical support for the next research, optimization and promotion of soil flame disinfection technology.

6 February 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
YZYunhe Zhang
Yunhe Zhang
JWJisheng Wang
Jisheng Wang
YZYu Zhang
Yu Zhang
YWYuansheng Wang
Yuansheng Wang
ZJZhiwei Jia
Zhiwei Jia
This study developed a heat transfer model and systematically simulated heat conduction behavior during flame disinfection to optimize surface flame disinfection (SFD) technology targeting Bradysia odoriphaga larvae. By determining pest mortality rates at various temperatures, we identified 40 °C as the critical threshold. When temperature increased from 30 °C to 65 °C, the time required to achieve 50% (LT50, median lethal time, represents the baseline threshold for control efficacy) mortality dropped sharply from 131 s to merely 6 s, while the time to reach 95% mortality (LT95, i.e., 95% lethal time, represents the standard for complete control in the field) decreased from 279 s to 12 s. The model demonstrated that higher surface temperatures enabled heat to penetrate deeper into the soil. For every 20 °C increase in temperature, lethal depth increased by 2.1 cm, and heat conduction depth increased by 1.2 cm. Soil thickness exhibited a dual effect; although deeper soil could increase lethal depth, it also created thermal resistance that slowed heat penetration. In practical applications, heating a 20 cm thick soil layer to 163 °C could achieve effective pest control at a depth of 32.5 cm. This framework provides support for achieving precise flame disinfection and promotes sustainable pest management with reduced chemical pesticide use.