Xinbo Liu

Dr. Xinbo Liu


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
28 April 2023 in Processes
Verified
Journal Article
Open access
PDF file
LWLing Wang
Ling Wang
XLXinbo Liu
Xinbo Liu
JMJuntao Ma
Juntao Ma
WSWenzhi Su
Wenzhi Su
HLHan Li
Han Li
Steel surface defect detection is an important issue when producing high-quality steel materials. Traditional defect detection methods are time-consuming and uneconomical and require manually designed prior information or extra supervisors. Surface defects have different representations and features at different scales, which make it challenging to automatically detect the locations and defect types. This paper proposes a real-time steel surface defect detection technology based on the YOLO-v5 detection network. In order to effectively explore the multi-scale information of the surface defect, a multi-scale explore block is especially developed in the detection network to improve the detection performance. Furthermore, the spatial attention mechanism is also developed to focus more on the defect information. Experimental results show that the proposed network can accurately detect steel surface defects with approximately 72% mAP and satisfies the real-time speed requirement.

1 January 2025 in Journal of Industrial and Management Optimization
Verified
Journal Article
Closed access
PDF file
XLXi Liu
Xi Liu
Xin ChenXin Chen
Xin Chen
YZYushan Zhao
Yushan Zhao
XLXinbo Liu
Xinbo Liu
CWChin-Chia Wu
Chin-Chia Wu
WLWin-Chin Lin
Win-Chin Lin
This paper addresses the multi-objective flexible flow shop scheduling problem, aiming to minimize makespan, reduce the ratio of processing delay to enhance customer satisfaction, and lower total electricity costs under a time-of-use pricing structure. Considering this problem's characteristics, the NSGA-Ⅱ is the algorithm chosen to best solve this problem. However, preliminary experiments reveal that NSGA-Ⅱ suffers from premature convergence, crossover between repeated solutions, and a time-consuming selection operator. To address these issues, a hybrid algorithm called HNSGA-Ⅱ, which combines Greedy Random Adaptive Search Procedure (GRASP) and NSGA-Ⅱ is designed, it introduces an adaptive crossover probability based on the similarity of parents to reduce the possibility of the crossover between close relatives, improves the population diversity, and incorporates an electoral selection based on the concept of Pareto to reduce the time cost. The test results demonstrate that the optimized HNSGA-Ⅱ outperforms the other methods in terms of the quality, quantity, and diversity of the Pareto solution set.

1 January 2023 in International Journal of Applied Mathematics and Computer Science
Verified
Journal Article
Open access
PDF file
XLXinbo Liu
Xinbo Liu
WWWen Wang
Wen Wang
Xin ChenXin Chen
Xin Chen
MSMalgorzata Sterna
Malgorzata Sterna
JBJacek Blazewicz
Jacek Blazewicz
We consider the scheduling problem on unrelated parallel machines in order to minimize the total late work. Since the problem is NP-hard, we propose a...

7 February 2022 in Scientific Programming
Verified
Journal Article
Open access
XLXinbo Liu
Xinbo Liu
LWLing Wang
Ling Wang
XCXinyu Chen
Xinyu Chen
YLYuqing Liu
Yuqing Liu
Image superresolution (SR) is a classical issue in computer vision area. Recently, there are elaborated convolutional neural networks (CNNs) demonstrating remarkable effectiveness on image SR. However, most of the previous works lack effective exploration on the structural information, which plays a critical role for image quality. In this paper, we find that the hierarchical design can effectively restore the structural information and devise a multilevel feature exploration network for image SR (MFSR). Specially, we design an encoder-decoder architecture to concentrate on structural information from different levels and devise a spatial attention mechanism to address the inherent correlation among features for effective restoration. Experimental results show the proposed MFSR can restore more correct edges and lines and achieves both better objective and subjective performances than the state-of-the-art methods with higher PSNR/SSIM results, indicating the effectiveness on structural information restoration.

20 June 2022 in Mathematical Problems in Engineering
Verified
Journal Article
Open access
PDF file
XLXiaohui Li
Xiaohui Li
LWLing Wang
Ling Wang
XLXinbo Liu
Xinbo Liu
Image super-resolution (SR) is one of the classical ill-posed image processing issues to generate high-resolution (HR) images from given low-resolution (LR) instances. Recent SR works aim to find an elaborate convolutional neural network (CNN) design and regard it as an end-to-end filter to map the image from LR space to HR space. However, seldom of them concentrate on the mathematical proof of network design or consider the problem from an optimization perspective. In this paper, we investigate the image SR based on the Landweber iteration method, which is an effective optimization method to find a feasible solution for the ill-posed problem. By considering the issue from the optimization perspective, we design a corresponding Landweber iteration-inspired network to adaptively learn the parameters and find the HR results. Experimental results show the proposed network achieves competitive or better subjective and objective performance than other state-of-the-art methods with fewer parameters and computational costs.