Jianlong Ye

Jianlong Ye

Auto-generated profile, based on publicly available information

Jianlong Ye

Zhejiang Institute of Communications Co., Ltd., Hangzhou 310030, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
2 April 2024 in Buildings
Verified
Journal Article
Open access
PDF file
JYJianlong Ye
Jianlong Ye
HYHongchuan Yu
Hongchuan Yu
GLGaoyang Liu
Gaoyang Liu
JZJiong Zhou
Jiong Zhou
JSJiangpeng Shu
Jiangpeng Shu
Component identification and depth estimation are important for detecting the integrity of post-disaster structures. However, traditional manual methods might be time-consuming, labor-intensive, and influenced by subjective judgments of inspectors. Deep-learning-based image visual inspection is a new approach to overcome these problems, but repeated modeling is required for different inspection tasks, which limits inspection accuracy and practical deployment efficiency. In this study, it is observed that the matched ratios of pixel pairs between component identification and depth estimation reach a high value, which indicates the dual tasks are highly related. Therefore, the Multi-Scale Task Interaction Network (MTI-Net) is proposed for structural images to simultaneously accomplish both tasks for accurate and efficient structural inspection. It propagates distilled task information from lower to higher scales. Then, it aggregates the refined task features from all scales to produce the final per-task predictions. Experiments show that MTI-Net delivers the full potential of multi-task learning, with a smaller memory footprint and higher efficiency compared to single-task learning. For the evaluation metrics of model performance, the mean Intersection over Union (mIoU) of component identification improves by 2.30, and root mean square error (RMSE) drops by 0.36 m with the aid of the multi-task strategy. The multi-task deep learning framework has great potential value in engineering applications.

17 September 2025 in Buildings
Verified
Journal Article
Open access
PDF file
XLXiang Li
Xiang Li
XCXinran Chen
Xinran Chen
JYJie Yuan
Jie Yuan
Huailei ChengHuailei Cheng
Huailei Cheng
JYJianlong Ye
Jianlong Ye
ZWZengyi Wang
Zengyi Wang
Granite residual soil is widely employed as subgrade fill material, but its tendency to undergo wetting-induced deformation under moisture infiltration poses significant challenges to pavement stability. To address this issue, this study introduces an innovative wetting device capable of precisely controlling moisture content increase, enabling multi-step wetting tests under controlled conditions. Saturated wetting tests were also conducted using both single-line and double-line methods, and the results were compared. Pore size distribution curves for granite residual soil samples with different initial states were measured using Mercury Intrusion Porosimeter (MIP) tests. Results indicate that for both the single-line method and the double-line method, the εV-lgp curve for samples subjected to different compaction efforts remains parallel across varying initial moisture content. The increase in vertical stress will constrain the water adsorption and swelling potential. Whereas an increase in compaction effort leads to greater swelling potential, which is mitigated by an increase in initial moisture content. By integrating the test results of the soil water characteristic (SWCC) curve, the relationship between normalized wetting deformation and matric suction is primarily influenced by the initial state of the soil sample and remains unaffected by vertical stress during multi-step wetting. Based on the test results, an empirical wetting prediction model was formulated, accounting for the influence of vertical stress, initial matric suction, and matric suction after wetting. Fitting results confirmed that the established model achieved high prediction accuracy (R2 > 0.9), supporting its application in practical engineering endeavors.