Donglai Sun

Dr. Donglai Sun


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
24 October 2023 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
DSDonglai Sun
Donglai Sun
LZLijuan Zhang
Lijuan Zhang
JWJianqiang Wang
Jianqiang Wang
XLXintong Liu
Xintong Liu
ZWZhengbo Wang
Zhengbo Wang
JWJichao Wang
Jichao Wang

6 June 2022 in Wireless Communications and Mobile Computing
Verified
Journal Article
Open access
PDF file
LZLijuan Zhang
Lijuan Zhang
DSDonglai Sun
Donglai Sun
LWLu Wang
Lu Wang
ZWZhengbo Wang
Zhengbo Wang
JWJianqiang Wang
Jianqiang Wang
Target detection is a complex process that is important as an important module in computer vision applications. In particular, in many occasions where the real-time requirements are extremely high, it is very important to achieve fast and accurate detection of targets. But at this stage, there are still many problems in the research on rapid target detection, such as inefficiency and high is the first phase of automatic target recognition (ATR). For the performance of SAR image target detection, this paper proposes a CFAR fast detection algorithm based on Rayleigh. CFAR detection is divided into two steps: horizontal and vertical CFAR detection. The efficiency of parameter estimation is improved by the coincidence of adjacent point reference windows and the distribution characteristics of images. The algorithm in this paper combines the target variance characteristics to reduce the false alarm rate. The experiment was performed on the MSTAR dataset. Fast target detection algorithm based on CFAR and target variance feature has the characteristics of high detection rate, low false alarm, and high speed, and its detection performance is good. The experimental results show that the recognition efficiency of the proposed algorithm is higher than that of the traditional algorithm on different target datasets, the time is shortened by 30%, and the accuracy rate is equal to that of the traditional algorithm.

6 July 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
DSDonglai Sun
Donglai Sun
SHShaoyang Hua
Shaoyang Hua
QCQian Cheng
Qian Cheng
Intelligent fault diagnosis of rotating machinery under varying working conditions remains challenging due to distribution shifts caused by different work conditions. Although unsupervised domain adaptation (UDA) has been widely applied, existing methods often suffer from unreliable pseudo-labeling and limited capability in handling large domain gaps. To address these issues, this paper proposes DCMDNet, a domain adaptation framework based on a ConvNeXt-1D feature extractor. Specifically, to dynamically updated class prototypes, a dynamic center-guided pseudo-labeling (DCGPL) strategy with Exponential Moving Average(EMA) algorithm is developed to assign target pseudo-labels according to geometric proximity. In addition, a source-target MixUp (ST-MixUp) strategy is introduced to generate intermediate-domain samples through signal-level interpolation, forming a continuous domain-transition manifold for improved robustness against domain shifts. In this process, soft-label supervision is incorporated to mitigate pseudo-label noise and stabilize model training. Experimental results demonstrate that the DCGPL strategy yields more reliable pseudo-labels than conventional confidence-based selection, while the cross-domain Mixup interpolation further mitigates pseudo-label noise under large domain discrepancies, thus achieving superior performance over several state-of-the-art UDA methods.

11 November 2025 in Research Square
Verified
Preprint
Open access
PDF file
JWJiChao Wang
JiChao Wang
ZHZhenqiao Hui
Zhenqiao Hui
MLMengyuan Li
Mengyuan Li
DSDonglai Sun
Donglai Sun
SPSicong Pang
Sicong Pang
To address the challenges of detecting winter jujubes in orchard environments—including dense small targets, variable illumination, complex backgrounds, and limited edge deployment capabilities—this paper proposes SF-YOLO11, a lightweight real-time detection model. First, a ternary channel importance metric is proposed that integrates gradient, variance, and task relevance to construct an adaptive pruning strategy. This strategy optimizes C3K2 into PrunedC3K2, achieving 31% model compression. Second, the LightSPPF module is designed through computational graph reconstruction. This module employs a three-stage architecture comprising depthwise separable convolution, adaptive pooling, and dynamic fusion, reducing computational cost by 40%. Finally, we transform multi-scale feature processing into sequence modeling and design the ISSFF module to capture scale dependencies through bidirectional LSTM and multi-head attention mechanisms, thereby improving small target detection accuracy. Experimental results demonstrate that SF-YOLO11 achieves an mAP@0.5 of 92.89%, representing a 3.68% improvement over the baseline. The model contains 1.6M parameters, requires 4.3 GFLOPs of computation, and operates at 128 FPS, achieving optimizations of 38.5%, 33.8%, and 14%, respectively. After INT8 quantization, the model size is reduced to only 1.7 MB, and the FPS increases to 215. In cross-fruit transfer experiments, the model achieves zero-shot mAP@0.5 values of 68.34% and 71.52% on grape and cherry tomato datasets, respectively. After fine-tuning, these values improve to 85.23% and 87.12%, respectively. Robustness tests validate the model's performance under extreme conditions, including strong illumination, low illumination, and occlusion.