Haiying Hu

Dr. Haiying Hu


Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
5 March 2021 in Optics Express
Verified
Journal Article
Open access
PDF file
ZWZhengyuan Wei
Zhengyuan Wei
HHHaiying Hu
Haiying Hu
HHHuamao Huang
Huamao Huang
To optimize the uniformity of signal-to-noise ratio (SNR) distribution in a visible light communication (VLC) system, the firefly algorithm is improved for joint optimization of location, power allocation and orientation of a light-emitting diode (LED) lamp array. Taking 16 LED lamps as an example, optimizations with a different number of degrees-of-freedom (DOF) are investigated. The orientation-involved optimizations significantly decrease average SNR and average illuminance. However, if the average illuminance is restricted to a large value, the effects of the orientation DOF would be small. With the restriction of illuminance, the optimization with all the three DOFs gives an improvement of 4.18 times in SNR uniformity, compared to the typical square-circle layout. The optimizations are further studied by varying the number of LED lamps.

8 December 2014 in Water
Verified
Journal Article
Open access
PDF file
HHHaiying Hu
Haiying Hu
GHGuoru Huang
Guoru Huang
Understanding the characteristics of non-point sources (NPS) pollutions can provide theoretical support for improving water quality. Siheshui watershed located in south China was selected to explore the characteristics of NPS pollutions in rainfall-runoff process. In this small agricultural watershed, five flood events and one non-flood event were monitored, and the water quantity and quality constituents were measured. The event mean concentrations (EMCs) of pollutant constituents in runoff flows were estimated. It is shown that the EMCs of BOD5, CODMn, TSS, TP, TN, and NH3-N in the flood events are remarkably larger than those in the non-flood event. The antecedent precipitation has a large effect on the output of the pollutant concentration. The pollutant load fluxes of most pollutant constituents change synchronously with the runoff flows, and the synchronization relationship is better than that between the pollutant concentrations and the runoff flows. The Pearson correlation analysis indicates that the EMCs of CODMn, TP, and TSS are significantly correlated with rainfall runoff characteristics in the flood events, while BOD5, TN, and NH3-N show weak correlations. In addition, the mean concentration method was used to estimate the annual NPS pollution load. It is shown that the proportions of the NPS pollution load to the total pollutant load are more than 80% from 2008 to 2010.

29 November 2022 in Horticulturae
Verified
Journal Article
Open access
PDF file
TLTongkai Li
Tongkai Li
HHHuamao Huang
Huamao Huang
YPYangyang Peng
Yangyang Peng
HZHui Zhou
Hui Zhou
HHHaiying Hu
Haiying Hu
MLMing Liu
Ming Liu
As a traditional edible and medicinal fungus in China, Oudemansiella raphanipes has high economic benefits. In order to achieve the automatic classification of Oudemansiella raphanipes into four quality levels using their image dataset, a quality grading algorithm based on neural network models was proposed. At first, the transfer learning strategy and six typical convolution neural network models, e.g., VGG16, ResNet50, InceptionV3, NasNet-Mobile, EfficientNet, and MobileNetV2, were used to train the datasets. Experiments show that MobileNetV2 has good performance considering both testing accuracy and detection time. MobileNetV2 only needs 37.5 ms to classify an image, which is shorter by 11.76%, 28.57%, 46.42%, 59.45%, and 79.73%, respectively, compared with the classification times of InceptionV3, EfficientNetB0, ResNet50, NasNet-Mobile, and VGG16. Based on the original MobileNetV2 model, four optimization methods, including data augmentation, hyperparameter selecting, an overfitting control strategy, and a dynamic learning rate strategy, were adopted to improve the accuracy. The final classification accuracy can reach as high as 98.75%, while the detection time for one image is only 22.5 ms and the model size is only 16.48 MB. This quality grading algorithm based on an improved MobileNetV2 model is feasible and effective for Oudemansiella raphanipes, satisfying the needs in the production line.

22 October 2022 in Water
Verified
Journal Article
Open access
PDF file
FWFangyi Wang
Fangyi Wang
HHHaiying Hu
Haiying Hu
LYLuo YunRu
Luo YunRu
XLXiang Dong LEI
Xiang Dong LEI
DWDi Wu
Di Wu
JJJie Jiang
Jie Jiang
During accelerated urbanization, the lack of attention to environmental protection and governance led to the formation of black-odor water. The existence of urban black-odor water not only affects the cityscape, but also threatens human health and damages urban ecosystems. The black-odor water bodies are small and hidden, so they require large-scale and high-resolution monitoring which offers a temporal and spatial variation of water quality frequently, and the unmanned aerial vehicle (UAV) with a multispectral instrument is up to the monitoring task. In this paper, the Nemerow comprehensive pollution index (NCPI) was introduced to assess the pollution degree of black-odor water in order to avoid inaccurate identification based on a single water parameter. Based on the UAV-borne multispectral data and NCPI of sampling points, regression models for inverting the parameter indicative of water quality were established using three artificial intelligence algorithms, namely extreme gradient boosting (XGBoost), random forest (RF), and support vector regression (SVR). The result shows that NCPI is qualified to evaluate the pollution level of black-odor water. The XGBoost regression (XGBR) model has the highest fitting accuracy on the training dataset (R2 = 0.99) and test dataset (R2 = 0.94), and it achieved the best retrieval effect on image inversion in the shortest time, which made it the best-fit model compared with the RF regression (RFR) model and the SVR model. According to inversion results based on the XGBR model, there was only a small size of mild black-odor water in the study area, which showed the achievement of water pollution treatment in Guangzhou. The research provides a theoretical framework and technical feasibility for the application of the combination of algorithms and UAV-borne multispectral images in the field of water quality inversion.

16 September 2020 in Atmosphere
Verified
Journal Article
Open access
PDF file
HSHaowei Sun
Haowei Sun
HHHaiying Hu
Haiying Hu
Zhaoli WangZhaoli Wang
Zhaoli Wang
CLC. Lai
C. Lai
In recent decades, the severe drought across agricultural regions of China has had significant impact on agriculture. The standardized precipitation evapotranspiration index (SPEI) has been widely used for drought analyses; however, SPEI is prone to be affected by potential evapotranspiration (PET). We thus examined the correlations between soil moisture anomalies and the SPEI calculated by the Thornthwaite, Hargreaves, and Penman–Monteith (PM) equations to select the most suitable for drought research. Additionally, the Mann–Kendall and wavelet analysis were used to investigate drought trends and to analyze and the impact of atmospheric circulation on drought in China from 1961 to 2018. The results showed that (1) PET obtained from the PM equation is the most suitable for SPEI calculation; (2) there were significant wetting trends in Northern China and the whole Chinese mainland and most of the wetting mutation points occurred in the 1970s and 1980s and the significant inter-annual oscillations period in the Chinese mainland was 2–4 years; (3) the Chinese mainland and Northern China are strongly influenced by West Pacific Trade Wind, while Western Pacific Subtropical High Intensity and Pacific Subtropical High Area have primary impact on Southern China.

6 March 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
FWFangyi Wang
Fangyi Wang
Zhaoli WangZhaoli Wang
Zhaoli Wang
Xushu WuXushu Wu
Xushu Wu
DWDi Wu
Di Wu
HHHaiying Hu
Haiying Hu
YZYan Zhou
Yan Zhou
The accurate detection and monitoring of levee cracks is critical for maintaining the structural integrity and safety of flood protection infrastructure. Yet at present the application of using UAV to achieve an automatic, rapid detection of levee cracks is still limited and there is a lack of effective deblurring methods specifically tailored for UAV-based levee crack images. In this study, we present E2S, a novel two-stage framework specifically designed for UAV-based levee crack segmentation, which leverages an unsupervised deblurring technique to enhance image quality. In the first stage, we introduce an Improved CycleGAN model that mainly performs motion deblurring on UAV-captured images, effectively enhancing crack visibility and preserving crucial structural details. The enhanced images are then fed into the second stage, where an Attention U-Net is employed for precise crack segmentation. The experimental results demonstrate that the E2S framework significantly outperforms traditional supervised models, achieving an F1-score of 81.3% and a crack IoU of 71.84%, surpassing the best-performing baseline, Unet++. The findings confirm that the integration of unsupervised image enhancement can substantially benefit downstream segmentation tasks, providing a robust and scalable solution for automated levee crack monitoring.