Yating Hu

Dr. Yating Hu

College of Information Technology Jilin Agricultural University
orcid

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
10 January 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
JLJian Li
Jian Li
KLKongyu Liu
Kongyu Liu
YHYating Hu
Yating Hu
HZHongchen Zhang
Hongchen Zhang
Ali Asghar HeidariAli Asghar Heidari
Ali Asghar Heidari
HEHela Elmannai
Hela Elmannai

21 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
LDLuyu Ding
Luyu Ding
CZChongxian Zhang
Chongxian Zhang
YYYuxiao Yue
Yuxiao Yue
CYChunxia Yao
Chunxia Yao
ZLZhuo Li
Zhuo Li
QLQifeng Li
Qifeng Li
Accurate monitoring of animal behaviors enables improved management in precision livestock farming (PLF), supporting critical applications including health assessment, estrus detection, parturition monitoring, and feed intake estimation. Although both contact and non-contact sensing modalities are utilized, wearable devices with embedded sensors (e.g., accelerometers, pressure sensors) offer unique advantages through continuous data streams that enhance behavioral traceability. Focusing specifically on contact sensing techniques, this review examines sensor characteristics and data acquisition challenges, methodologies for processing behavioral data and implementing identification algorithms, industrial applications enabled by recognition outcomes, and prevailing challenges with emerging research opportunities. Current behavior classification relies predominantly on traditional machine learning or deep learning approaches with high-frequency data acquisition. The fundamental limitation restricting advancement in this field is the difficulty in maintaining high-fidelity recognition performance at reduced acquisition rates, particularly for integrated multi-behavior identification. Considering that the computational demands and limited adaptability to complex field environments remain significant constraints, Tiny Machine Learning (Tiny ML) could present opportunities to guide future research toward practical, scalable behavioral monitoring solutions. In addition, algorithm development for functional applications post behavior recognition may represent a critical future research direction.

13 January 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JLJian Li
Jian Li
WZWeijian Zhang
Weijian Zhang
YHYating Hu
Yating Hu
SFShengliang Fu
Shengliang Fu
CLChangyi Liao
Changyi Liao
WYWeilin Yu
Weilin Yu
To improve the obstacle avoidance ability of agricultural unmanned aerial vehicles (UAV) in farmland settings, a three-dimensional space path planning model based on the R5DOS model is proposed in this paper. The direction layer of the R5DOS intersection model is improved, and the RJA-star algorithm is constructed with the improved jump point search A-star algorithm in our paper. The R5DOS model is simulated in MATLAB. The simulation results show that this model can reduce the computational complexity, computation time, the number of corners and the maximum angles of the A-star algorithm. Compared with the traditional algorithm, the model can avoid obstacles effectively and reduce the reaction times of the UAV. The final fitting results show that compared with A-star algorithm, the RJA-star algorithm reduced the total distance by 2.53%, the computation time by 97.65%, the number of nodes by 99.96% and the number of corners by 96.08% with the maximum corners reduced by approximately 63.30%. Compared with the geometric A-star algorithm, the running time of the RJA-star algorithm is reduced by 95.84%, the number of nodes is reduced by 99.95%, and the number of turns is reduced by 67.28%. In general, the experimental results confirm the effectiveness and feasibility of RJA star algorithm in three-dimensional space obstacle avoidance.

13 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
YHYating Hu
Yating Hu
ZWZhi Wang
Zhi Wang
XLXiaofeng Li
Xiaofeng Li
LLLei Li
Lei Li
Xigang WangXigang Wang
Xigang Wang
YWYanlin Wei
Yanlin Wei
Mildew of maize seeds may affect their germination rates and reduce crop quality. It is crucial to classify maize seeds efficiently and without destroying their original structure. This study aimed to establish hyperspectral datasets using hyperspectral imaging (HSI) of maize seeds with different degrees of mildew and then classify them using spectral characteristics and machine learning algorithms. Initially, the images were processed with Otus and morphological operations. Each seed’s spectral features were extracted based on its coding, its edge, region of interest (ROI), and original pixel coding. Random forest (RF) models were optimized using the sparrow search algorithm (SSA), which is incapable of escaping the local optimum; hence, it was optimized using a modified reverse sparrow search algorithm (JYSSA) strategy. This reverse strategy selects the top 10% as the elite group, allowing us to escape from local optima while simultaneously expanding the range of the sparrow search algorithm’s optimal solution. Finally, the JYSSA-RF algorithm was applied to the validation set, with 96% classification accuracy, 100% precision, and a 93% recall rate. This study provides novel ideas for future nondestructive detection of seeds and moldy seed selection by combining hyperspectral imaging and JYSSA algorithms based on optimized RF.

18 July 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XZXiaopeng Zhang
Xiaopeng Zhang
YHYating Hu
Yating Hu
XLXiaofeng Li
Xiaofeng Li
PWPing Wang
Ping Wang
SGSike Guo
Sike Guo
XGXue Ge
Xue Ge
Accurate estimation of rice leaf nitrogen content (LNC) is essential for optimizing nitrogen management in precision agriculture. However, challenges such as spectral saturation and canopy structural variations across different growth stages complicate this task. This study proposes a robust framework for LNC estimation that integrates both spectral and texture features extracted from UAV-based multispectral imagery through the development of novel Spectral–Texture Fusion Indices (STFIs). Field data were collected under nitrogen gradient treatments across three critical growth stages: heading, early filling, and late filling. A total of 18 vegetation indices (VIs), 40 texture features (TFs), and 27 STFIs were derived from UAV images. To optimize the feature set, a two-stage feature selection strategy was employed, combining Pearson correlation analysis with model-specific embedded selection methods: Recursive Feature Elimination with Cross-Validation (RFECV) for Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and Sequential Forward Selection (SFS) for Support Vector Regression (SVR) and Deep Neural Networks (DNNs). The models—RFECV-RF, RFECV-XGBoost, SFS-SVR, and SFS-DNN—were evaluated using four feature configurations. The SFS-DNN model with STFIs achieved the highest prediction accuracy (R2 = 0.874, RMSE = 2.621 mg/g). SHAP analysis revealed the significant contribution of STFIs to model predictions, underscoring the effectiveness of integrating spectral and texture information. The proposed STFI-based framework demonstrates strong generalization across phenological stages and offers a scalable, interpretable approach for UAV-based nitrogen monitoring in rice production systems.

19 June 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
LDLuyu Ding
Luyu Ding
CZChongxian Zhang
Chongxian Zhang
YYYuxiao Yue
Yuxiao Yue
CYChunxia Yao
Chunxia Yao
ZLZhuo Li
Zhuo Li
RGRonghua Gao
Ronghua Gao
Accurate, efficient, and timely monitoring of animal behaviors is of great significance to precision livestock farming (PLF). Behavioral monitoring serves as a valuable tool for daily production management for farmers. It can be utilized for assessing animal health, detecting estrus, monitoring parturition, and even estimating feed intake. Non-contact machine vision and contact sensors (such as accelerometers, pressure sensors and position sensors) embedded in wearable devices represent the forefront of current research in behavior monitoring. Due to the continuity and traceability in the contact sensing of wearable sensors, this study focused on contact sensing techniques and reviewed the characteristics of various sensing methods. It addressed challenges in data sorting, advancements in identification algorithms, potential industrial applications following behavior recognition, and the associated challenges and prospects. Current behavior classification algorithms primarily rely on traditional machine learning or deep learning approaches, which exhibit the limitations such as high-frequency data acquisition, complex processing requirements, and low adaptability to the intricate scenarios encountered by wearable devices. As a new frontier in machine learning that is adaptable to application scenarios with limited computational resources, the potential use of Tiny Machine Learning (Tiny ML) in behavior recognition was also analyzed to provide guidance for subsequent research and applications.