Jun Peng

Prof. Jun Peng


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
29 June 2022 in BMC Bioinformatics
Verified
Journal Article
Open access
PDF file
LYLiang Ying
Liang Ying
YWYanan Wu
Yanan Wu
ZZZequn Zhang
Zequn Zhang
NLNiannian Liu
Niannian Liu
JPJun Peng
Jun Peng
JTJianjun Tang
Jianjun Tang
Background: DNA N4-methylcytosine is part of the restrictive modification system, which works by regulating some biological processes, for example, the initiation of DNA replication, mismatch repair and inactivation of transposon. However, using experimental methods to detect 4mC sites is time-consuming and expensive. Besides, considering the huge differences in the number of 4mC samples among different species, it is challenging to achieve a robust multi-species 4mC site prediction performance. Hence, it is of great significance to develop effective computational tools to identify 4mC sites. Results: This work proposes a flexible deep learning-based framework to predict 4mC sites, called Hyb4mC. Hyb4mC adopts the DNA2vec method for sequence embedding, which captures more efficient and comprehensive information compared with the sequence-based feature method. Then, two different subnets are used for further analysis: Hyb_Caps and Hyb_Conv. Hyb_Caps is composed of a capsule neural network and can generalize from fewer samples. Hyb_Conv combines the attention mechanism with a text convolutional neural network for further feature learning. Conclusions: Extensive benchmark tests have shown that Hyb4mC can significantly enhance the performance of predicting 4mC sites compared with the recently proposed methods.

31 August 2021 in Zeitschrift für Kristallographie - New Crystal Structures
Verified
Journal Article
Open access
PDF file
JGJia Gu
Jia Gu
XSXiu-Ying Song
Xiu-Ying Song
GWGui-Shu Wang
Gui-Shu Wang
JPJun Peng
Jun Peng
XNXuliang Nie
Xuliang Nie
C 12 H 12 O 4 , monoclinic, P 2 1 / c (no. 14), a = 16.071(6) Å, b = 9.424(4) Å, c = 7.640(3) Å, β = 101.861(5)°, V = 1132.4(8) Å 3 , Z = 4, R gt ( F ) = 0.0366, wR ref ( F 2 ) = 0.1043, T = 296(2) K.

5 November 2025 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
LYLe Yang
Le Yang
ZWZizhi Wu
Zizhi Wu
LWLongfei Wang
Longfei Wang
JPJun Peng
Jun Peng
QZQiangqiang Zhou
Qiangqiang Zhou
In the domain of plant morphological studies, three-dimensional scanning technologies have brought about a paradigm shift in the field of leaf structure modelling. Nevertheless, the high cost and operational complexity of these systems act as significant barriers to widespread adoption. To address this issue, a single-image 3D reconstruction pipeline was developed, focusing on potato leaves and optimized for use with mobile phone cameras. The algorithm begins with image preprocessing to enhance quality, followed by leaf instance segmentation to isolate the target leaf. Subsequently, a precise 2D leaf contour is extracted to capture planar geometry. Subsequently, 3D spatial features are recovered from a single image to infer depth information. Contour back-projection is a process that Links the extracted 2D contour to the estimated 3D space. The discretization of the 3D contour is enabled by boundary sampling, thereby facilitating the generation of an initial 3D polygonal mesh. Finally, mesh surface refinement is applied to optimize model accuracy and visual fidelity. The methodology employed in this study successfully reconstructed potato and other crop leaves, demonstrating minimal deviation in key morphological shape descriptors and negligible error in surface area measurements in comparison to the ground truth. The reconstructed models exhibited high geometric congruence with the original leaves. This demonstrates the potential of our technique to broaden the accessibility of conventional modelling approaches and to advance methodologies within the field of crop phenotyping.

21 July 2026 in Sensors
Verified
Journal Article
Open access
PDF file
LLLiting Liao
Liting Liao
HYHaoyuan Yang
Haoyuan Yang
JPJun Peng
Jun Peng
RJRunqiu Jin
Runqiu Jin
With the rapid development of remote sensing technology, high-resolution satellite imagery has been increasingly applied to land resource monitoring, urban planning, and environmental assessment. Automatically assigning semantic labels to remote sensing image patches remains a fundamental challenge due to pronounced intra-class variation and high inter-class visual similarity. To address the trade-off between model capacity and limited labeled data, this paper proposes a remote sensing image scene classification framework based on an improved EfficientNetV2-S architecture. The proposed model integrates a Squeeze-and-Excitation (SE) channel attention module between the final 1 × 1 expansion convolution and the Global Average Pooling layer, where it functions as a late-stage channel gating mechanism that adaptively recalibrates channel-wise responses, though its accuracy benefit is seed-sensitive rather than consistently reproducible at the current dataset scale. A two-stage optimization strategy was evaluated, comprising a fully unfrozen supervised baseline followed by a pseudo-label semi-supervised fine-tuning stage utilizing a strict confidence threshold (τ=0.90). Evaluated on a 10-class subset of the public NWPU-RESISC45 benchmark, the purely supervised SE-EfficientNetV2-S delivers 98.71% independent test accuracy, matching or exceeding the much larger ResNet50 (98.50%, 24.1 M parameters) despite using only 20.4 M parameters. Multi-seed variance analysis further reveals that semi-supervised fine-tuning yields a small test-set improvement for the No-SE configuration that is consistent in sign across all three seeds (+0.46 pp mean) but not statistically significant at this sample size, and an even smaller, likewise non-significant gain for the SE-augmented model (+0.08 pp), suggesting that channel gating moderates pseudo-label effectiveness in small-data regimes.