lina Zhang

Prof. lina Zhang

orcid

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
19 October 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
SQShiZheng Qu
ShiZheng Qu
HLHuan Liu
Huan Liu
YXYinghang Xu
Yinghang Xu
LWLu Wang
Lu Wang
YLYunfei Liu
Yunfei Liu
ZLZhuoshi Li
Zhuoshi Li
The Whale Optimization Algorithm (WOA) is regarded as a classic metaheuristic algorithm, yet it suffers from limited population diversity, imbalance between exploitation and exploration, and low solution accuracy. In this paper, we propose the Spiral-Enhanced Whale Optimization Algorithm (SEWOA), which incorporates a nonlinear time-varying self-adaptive perturbation strategy and an Archimedean spiral structure into the original WOA. The Archimedean spiral structure enhances the diversity of the solution space, aiding the algorithm in escaping local optima. The nonlinear time-varying self-adaptive optimization dynamic perturbation strategy improves the algorithm’s local search capability and enhances solution accuracy. The effectiveness of the proposed algorithm is validated from multiple perspectives using CEC2014 test functions, CEC2017 test functions, and 23 benchmark test functions. The experimental results demonstrate that the enhanced Whale Optimization Algorithm significantly improves population diversity, balances global and local search, and enhances solution accuracy. Additionally, SEWOA exhibits excellent performance in solving three engineering design problems, showcasing its value and wide range of potential applications.

29 May 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
Helong YuHelong Yu
Helong Yu
CLChunliu Liu
Chunliu Liu
LZlina Zhang
lina Zhang
CWChengwen Wu
Chengwen Wu
GLGuoxi Liang
Guoxi Liang
OGOsama A. Ghoneim
Osama A. Ghoneim

30 January 2024 in Scientific Reports
Verified
Journal Article
Open access
PDF file
HQHepeng Qu
Hepeng Qu
KLKun Liu
Kun Liu
LZlina Zhang
lina Zhang
Improving the quality of medical images is crucial for accurate clinical diagnosis; however, medical images are often disrupted by various types of noise, posing challenges to the reliability and diagnostic accuracy of the images. This study aims to enhance the Black Widow optimization algorithm and apply it to the task of denoising medical images to improve both the quality of medical images and the accuracy of diagnostic results. By introducing Tent mapping, we refined the Black Widow optimization algorithm to better adapt to the complex features of medical images. The algorithm's denoising capabilities for various types of noise were enhanced through the combination of multiple filters, all without the need for training each time to achieve preset goals. Simulation results, based on processing a dataset containing 1588 images with Gaussian, salt-and-pepper, Poisson, and speckle noise, demonstrated a reduction in Mean Squared Error (MSE) by 0.439, an increase in Peak Signal-to-Noise Ratio (PSNR) by 4.315, an improvement in Structural Similarity Index (SSIM) by 0.132, an enhancement in Edge-to-Noise Ratio (ENL) by 0.402, and an increase in Edge Preservation Index (EPI) by 0.614. Simulation experiments verified that the proposed algorithm has a certain advantage in terms of computational efficiency. The improvement, incorporating Tent mapping and a combination of multiple filters, successfully elevated the performance of the Black Widow algorithm in medical image denoising, providing an effective solution for enhancing medical image quality and diagnostic accuracy.

15 December 2023 in PLOS ONE
Verified
Journal Article
Open access
PDF file
BYbo yang
bo yang
LZlina Zhang
lina Zhang
JHJinping He
Jinping He
Spatial Pyramid Pooling (SPP) is important in capturing remote contextual information for pixel-level prediction tasks in scene-resolved detection of rice diseases. In this paper, the detection objects of the rice disease dataset used in this paper have almost the same target size and do not need to be passed through different filters to obtain different receptive fields of view. Therefore, this paper proposed a new pooling structure, SPPFCSPC-G, which split the feature vector into 2 channels for processing. One channel was processed using grouped 1×1 Conv, while the other channel mainly used multiple filters with the same parallel structure (5×5 MaxPool). Additionally, multiple 1×1 and 3×3 grouped convolutions were concatenated in series in that branch (Group-Conv) to extract more complex features in rice. Finally, the 2 parts were connected (Concat) together, with each convolutional layer Conv divided into 4 groups as a way to reduce the amount of computation in the model. The project team incorporated SPPFCSPC-G into the Backbone of YOLOv5 and trained it on NVIDIA Tesla T4 (GPU). The experimental results showed that the performance of the method used in this paper improved, including Precision, Recall, mAP, and training speed, while reducing the size of computational parameters (Parameters), computational volume (GFLOPs), and model size (Param.). The project team carried out the trained YOLOv5 model on Intel Core i5 (CPU) for inference detection of rice leaves in real scenarios, and the experiments showed that both pre-inference and actual inference were faster. Moreover, the consumption of computational resources was almost minimized, and the model effectively identified rice diseases.

15 January 2025 in Agriculture
Verified
Journal Article
Open access
PDF file
LZlina Zhang
lina Zhang
ZHZiyi Huang
Ziyi Huang
ZYZhiyin Yang
Zhiyin Yang
BYbo yang
bo yang
圣俞圣鹏 俞
圣鹏 俞
Helong YuHelong Yu
Helong Yu
In response to the structural changes of tomato seedlings, traditional image techniques are difficult to accurately quantify key morphological parameters, such as leaf area, internode length, and mutual occlusion between organs. Therefore, this paper proposes a tomato point cloud stem and leaf segmentation framework based on Elite Strategy-based Improved Red-billed Blue Magpie Optimization (ES-RBMO) Algorithm. The framework uses a four-layer Convolutional Neural Network (CNN) for stem and leaf segmentation by incorporating an improved swarm intelligence algorithm with an accuracy of 0.965. Four key phenotypic parameters of the plant were extracted. The phenotypic parameters of plant height, stem thickness, leaf area and leaf inclination were analyzed by comparing the values extracted by manual measurements with the values extracted by the 3D point cloud technique. The results showed that the coefficients of determination (R2) for these parameters were 0.932, 0.741, 0.938 and 0.935, respectively, indicating high correlation. The root mean square error (RMSE) was 0.511, 0.135, 0.989 and 3.628, reflecting the level of error between the measured and extracted values. The absolute percentage errors (APE) were 1.970, 4.299, 4.365 and 5.531, which further quantified the measurement accuracy. In this study, an efficient and adaptive intelligent optimization framework was constructed, which is capable of optimizing data processing strategies to achieve efficient and accurate processing of tomato point cloud data. This study provides a new technical tool for plant phenotyping and helps to improve the intelligent management in agricultural production.

1 January 2023 in Forestry Research
Verified
Journal Article
Open access
PDF file
Kewei CaiKewei Cai
Kewei Cai
QZQiushuang Zhao
Qiushuang Zhao
HLHanxi Li
Hanxi Li
QZQinhui Zhang
Qinhui Zhang
YLYan Li
Yan Li
XZXiyang Zhao
Xiyang Zhao
Tilia amurensis is a significant ornamental and economically-important tree species, known for its fragrant flowers, which are a source of high-quality honey production. However, the regulatory mechanisms involved in aroma formation during flower development in T. amurensis remains limited. The current study revealed the detection of plant hormones at every assessed stage of flower development. Among them, auxin and brassinosteroid contents significantly increased at stage 3, potentially regulating crucial functions during T. amurensis flower development. Moreover, the study examined the levels and change patterns of secondary metabolites and employed a combination of transcriptomics and metabolomics to comprehensively assess essential structural genes implicated in the biosynthesis pathways of terpenoid and phenylpropanoid. A comprehensive set of 89,526 differentially expressed genes (DEGs) was uncovered, including candidate structural genes ACAT, HDS, TPS, 4CL, CAD, and CCOAMT, which are specifically involved in the biosynthesis of terpenoids and phenylpropanoids. Maslinic acid, 2α,3α-dihydroxyursolic acid, and betulinic acid were accumulated in the terpenoid biosynthesis pathway. In contrast, metabolites with differential accumulation, such as phenylalanine, coniferyl alcohol, and cinnamic acid, were specifically enriched in the phenylpropanoid biosynthesis pathway. The C2H2, MYB, and NAC transcription factor families are crucially associated with the terpenoid and phenylpropanoid biosynthesis pathways. Two transcription factors, C2H2-17 and MYB-24, exhibited strong co-expression with structural genes in two networks, and were identified as central regulatory factors. These findings establish a solid groundwork for elucidating the generation of floral fragrance and provide comprehensive genetic and metabolic information for further studies on T. amurensis.