Hongying Wang

Dr. Hongying Wang


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
7 August 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
HWHongying Wang
Hongying Wang
PFPeng Fang
Peng Fang
EDEnze Duan
Enze Duan
ZYZhichen Yang
Zhichen Yang
Liangju WangLiangju Wang
Liangju Wang
HWHongying Wang
Hongying Wang
Stacked cage is the main breeding method of the large-scale farm in China. In broiler farms, dead broiler inspection is a routine task in the breeding process. It refers to the manual inspection of all cages and removal of dead broilers in the broiler house by the breeders every day. However, as the total amount of broilers is huge, the inspection work is not only time-consuming but also laborious. Therefore, a dead broiler inspection system is constructed in this study to replace the manual inspection work. It mainly consists of an autonomous inspection platform and a dead broiler detection model. The automatic inspection platform performs inspections at the speed of 0.2 m/s in the broiler house aisle, and simultaneously collects images of the four-layer broilers. The images are sent to a server and processed by a dead broiler detection model, which was developed based on the YOLOv3 network. A mosaic augment, the Swish function, an spatial pyramid pooling (SPP) module, and complete intersection over union (CIoU) loss are used to improve the YOLOv3 performance. It achieves a 98.6% mean average precision (intersection of union (IoU) = 0.5) and can process images at 0.007 s per frame. The dead broiler detection model is robust to broilers of different ages and can adapt to different lighting conditions. It is deployed on the server with a human–machine interface. By observing the processing results using the human–machine interface, the breeders could directly find the cage position of dead broilers and remove them, which could reduce the workload of breeders and promote the intelligent development of poultry breeding.

2 June 2023 in Animals
Verified
Journal Article
Open access
PDF file
SLSheng Luo
Sheng Luo
YMYiming Ma
Yiming Ma
FJFeng Jiang
Feng Jiang
HWHongying Wang
Hongying Wang
QTQin Tong
Qin Tong
Liangju WangLiangju Wang
Liangju Wang
In large-scale laying hen farming, timely detection of dead chickens helps prevent cross-infection, disease transmission, and economic loss. Dead chicken detection is still performed manually and is one of the major labor costs on commercial farms. This study proposed a new method for dead chicken detection using multi-source images and deep learning and evaluated the detection performance with different source images. We first introduced a pixel-level image registration method that used depth information to project the near-infrared (NIR) and depth image into the coordinate of the thermal infrared (TIR) image, resulting in registered images. Then, the registered single-source (TIR, NIR, depth), dual-source (TIR-NIR, TIR-depth, NIR-depth), and multi-source (TIR-NIR-depth) images were separately used to train dead chicken detecting models with object detection networks, including YOLOv8n, Deformable DETR, Cascade R-CNN, and TOOD. The results showed that, at an IoU (Intersection over Union) threshold of 0.5, the performance of these models was not entirely the same. Among them, the model using the NIR-depth image and Deformable DETR achieved the best performance, with an average precision (AP) of 99.7% (IoU = 0.5) and a recall of 99.0% (IoU = 0.5). While the IoU threshold increased, we found the following: The model with the NIR image achieved the best performance among models with single-source images, with an AP of 74.4% (IoU = 0.5:0.95) in Deformable DETR. The performance with dual-source images was higher than that with single-source images. The model with the TIR-NIR or NIR-depth image outperformed the model with the TIR-depth image, achieving an AP of 76.3% (IoU = 0.5:0.95) and 75.9% (IoU = 0.5:0.95) in Deformable DETR, respectively. The model with the multi-source image also achieved higher performance than that with single-source images. However, there was no significant improvement compared to the model with the TIR-NIR or NIR-depth image, and the AP of the model with multi-source image was 76.7% (IoU = 0.5:0.95) in Deformable DETR. By analyzing the detection performance with different source images, this study provided a reference for selecting and using multi-source images for detecting dead laying hens on commercial farms.

19 June 2024 in Ultrasonics Sonochemistry
Verified
Journal Article
Open access
YZYongxuan Zuo
Yongxuan Zuo
Fanglei ZouFanglei Zou
Fanglei Zou
MYMiao Yang
Miao Yang
GXGuangfei Xu
Guangfei Xu
JWJunhua Wu
Junhua Wu
HWHongying Wang
Hongying Wang
In this study, corn starch was used as the raw material, and modified starch was prepared using a method combining plasma-activated water and ultrasound treatment (PUL). This method was compared with treatments using plasma-activated water (PAW) and ultrasound (UL) alone. The structure, thermal, physicochemical, pasting, and functional properties of the native and treated starches were evaluated. The results indicated that PAW and UL treatments did not alter the shape of the starch granules but caused some surface damage. The PUL treatment increased the starch gelatinization temperature and enthalpy (from 11.22 J/g to 13.13 J/g), as well as its relative crystallinity (increased by 0.51 %), gel hardness (increased by 16.19 %) compared to untreated starch, without inducing a crystalline transition. The PUL treatment resulted in a whitening of the samples. The dual treatment enhanced the thermal stability of the starch paste, which can be attributed to the synergistic effect between PAW and ultrasound (PAW can modify the starch structure at a molecular level, while ultrasound can further disrupt the granule weak crystalline structures, leading to improved thermal properties). Furthermore, FTIR results suggested significant changes in the functional groups related to the water-binding capacity of starch, and the order of the double-helical structure was disrupted. The findings of this study suggest that PUL treatment is a promising new green modification technique for improving the starch structure and enhancing starch properties. However, further research is needed to tailor the approach based on the specific properties of the raw material.

15 May 2024 in International Journal of Biological Macromolecules
Verified
Journal Article
Closed access
Fanglei ZouFanglei Zou
Fanglei Zou
TSTharushi S. Shinali
Tharushi S. Shinali
MYMiao Yang
Miao Yang
YZYuanliang Zhong
Yuanliang Zhong
JWJunhua Wu
Junhua Wu
HWHongying Wang
Hongying Wang

24 April 2022 in Sustainability
Verified
Journal Article
Open access
PDF file
RLRangling Li
Rangling Li
HWHongying Wang
Hongying Wang
HSHui Sun
Hui Sun
Liangju WangLiangju Wang
Liangju Wang
HWHongying Wang
Hongying Wang
This study investigated composted rabbit manure as an organic matrix to replace peat for manufacturing horticultural growing media, where three kinds of rabbit manures were composted with temperatures > 50 °C lasting > 7 days, with a germination index > 70%. The heavy metal contents in rabbit manure were far lower than the thresholds in Chinese standards for safe use as horticultural growing media. Then, different ratios of compost and peat were mixed with perlite and vermiculite to manufacture growing media, which were evaluated in a 28-day seedling experiment with cabbage. The manufactured growing media characteristics could satisfy the seedlings’ requirements; air spaces in particular were improved from 15.7% to up to 28.7% by mixing composted manure. Seedling emergence percentages > 90% and good seedling qualities (including enhanced root length, seedling height, and chlorophyll content) indicated that composted rabbit manure could effectively replace peat to manufacture horticultural growing media. The best seedling performance was obtained with the following ratio of composted manure, peat, perlite, and vermiculite: 3:3:2:2. However, the mixing ratio could be further optimized, and other methods to reduce the salinity may be required for the different requirements of specific crops in further research.

13 December 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
HHHongyun Hao
Hongyun Hao
PFPeng Fang
Peng Fang
Wei JiangWei Jiang
Wei Jiang
XSXianqiu Sun
Xianqiu Sun
Liangju WangLiangju Wang
Liangju Wang
HWHongying Wang
Hongying Wang
The feeding behavior of laying hens is closely related to their health and welfare status. In large-scale breeding farms, monitoring the feeding behavior of hens can effectively improve production management. However, manual monitoring is not only time-consuming but also reduces the welfare level of breeding staff. In order to realize automatic tracking of the feeding behavior of laying hens in the stacked cage laying houses, a feeding behavior detection network was constructed based on the Faster R-CNN network, which was characterized by the fusion of a 101 layers-deep residual network (ResNet101) and Path Aggregation Network (PAN) for feature extraction, and Intersection over Union (IoU) loss function for bounding box regression. The ablation experiments showed that the improved Faster R-CNN model enhanced precision, recall and F1-score from 84.40%, 72.67% and 0.781 to 90.12%, 79.14%, 0.843, respectively, which could enable the accurate detection of feeding behavior of laying hens. To understand the internal mechanism of the feeding behavior detection model, the convolutional kernel features and the feature maps output by the convolutional layers at each stage of the network were then visualized in an attempt to decipher the mechanisms within the Convolutional Neural Network(CNN) and provide a theoretical basis for optimizing the laying hens’ behavior recognition network.