Dongfang Li

Dr. Dongfang Li


Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
24 July 2025 in Sensors
Verified
Journal Article
Open access
PDF file
SKShilu Kang
Shilu Kang
DLDongfang Li
Dongfang Li
JXJiaxin Xu
Jiaxin Xu
AMAokun Mei
Aokun Mei
HHHua Huo
Hua Huo
Accurate classification of chest X-ray (CXR) images is crucial for diagnosing lung diseases in medical imaging. Existing deep learning models for CXR image classification face challenges in distinguishing non-lung features. In this work, we propose a new segmentation-assisted fusion-based classification method. The method involves two stages: first, we use a lightweight segmentation model, Partial Convolutional Segmentation Network (PCSNet) designed based on an encoder–decoder architecture, to accurately obtain lung masks from CXR images. Then, a fusion of the masked CXR image with the original image enables classification using the improved lightweight ShuffleNetV2 model. The proposed method is trained and evaluated on segmentation datasets including the Montgomery County Dataset (MC) and Shenzhen Hospital Dataset (SH), and classification datasets such as Chest X-Ray Images for Pneumonia (CXIP) and COVIDx. Compared with seven segmentation models (U-Net, Attention-Net, SegNet, FPNNet, DANet, DMNet, and SETR), five classification models (ResNet34, ResNet50, DenseNet121, Swin-Transforms, and ShuffleNetV2), and state-of-the-art methods, our PCSNet model achieved high segmentation performance on CXR images. Compared to the state-of-the-art Attention-Net model, the accuracy of PCSNet increased by 0.19% (98.94% vs. 98.75%), and the boundary accuracy improved by 0.3% (97.86% vs. 97.56%), while requiring 62% fewer parameters. For pneumonia classification using the CXIP dataset, the proposed strategy outperforms the current best model by 0.14% in accuracy (98.55% vs. 98.41%). For COVID-19 classification with the COVIDx dataset, the model reached an accuracy of 97.50%, the absolute improvement in accuracy compared to CovXNet was 0.1%, and clinical metrics demonstrate more significant gains: specificity increased from 94.7% to 99.5%. These results highlight the model’s effectiveness in medical image analysis, demonstrating clinically meaningful improvements over state-of-the-art approaches.

9 September 2026 in Aerospace
Verified
Journal Article
Open access
PDF file
LBLei Bao
Lei Bao
DLDongfang Li
Dongfang Li
CLChaolong Li
Chaolong Li
XGXianzhong Gao
Xianzhong Gao
In contemporary manned–unmanned teaming (MUM-T) systems, the accurate detection of aircraft in Synthetic Aperture Radar (SAR) imagery is crucial for battlefield surveillance and target identification. However, challenges such as background clutter, significant scale variations, and limitations in existing feature extraction methods hinder detection accuracy. To address these issues, this study proposes CCS-Net, a lightweight Cooperative Context-aware Sensing Network designed specifically for SAR aircraft detection. CCS-Net enhances image contrast through Contrast-Limited Adaptive Histogram Equalization (CLAHE) preprocessing and employs a novel C2F_LK module combined with a Multi-scale Context Aggregation (MSCA) module to improve multi-scale feature representation with minimal parameters. An FPN-PAN structure adaptively fuses these features, while the Spatial Coordinate Attention Head (SCA-Head) integrates spatial and coordinate attention mechanisms to emphasize key aircraft regions. Optimized with label smoothing, our model achieves a 96.6% mAP@0.5 and 93.5% precision on the SAR-Aircraft-1.0 dataset with only 0.97M parameters. It generalizes well on the SADD aircraft dataset and cross-domain HRSID and SSDD ship benchmarks, outperforming state-of-the-art methods in both accuracy and lightweight design.

8 September 2026 in Electronics
Verified
Journal Article
Open access
PDF file
LBLei Bao
Lei Bao
HTHE Ting
HE Ting
DLDongfang Li
Dongfang Li
XGXianzhong Gao
Xianzhong Gao
To address the challenge of limited evaluations of expensive high-complexity functions in surrogate modeling, this paper proposes a methodological framework that integrates multi-fidelity Gaussian process (MFGP) regression, sequential active sampling, and global sensitivity analysis, using a radar angle tracking accuracy (ATA)-inspired synthetic function as the validation benchmark. An autoregressive MFGP model with composite kernel functions is constructed to capture the complex nonlinear characteristics of the synthetic response surface. A sequential active sampling strategy based on the maximum uncertainty criterion, combined with fixed resource allocation and a neighboring sample avoidance mechanism, is designed to achieve efficient sample collection under a limited evaluation budget. Sobol global sensitivity analysis is then performed on the trained MFGP surrogate model to quantify the main and interaction effects of each input parameter on the synthetic ATA function. Experimental results demonstrate that with the complete sequential sampling procedure, the proposed MFGP model achieves an R2 of 0.8515 and an RMSE of 0.0850 on the test set, significantly outperforming the single-fidelity GP model that relies solely on high-complexity samples. Sobol analysis identifies the Jamming-to-Signal Ratio (JSR) and lateral distance as the most critical influencing factors within the synthetic benchmark. The proposed framework substantially improves sample efficiency under limited evaluation budgets, providing an effective methodological reference for surrogate modeling in similar high-cost computational scenarios.