Qiang Fu

Dr. Qiang Fu


Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

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

Representative Publications

View All Publications
1 January 2012
Verified
Book Chapter
Closed access
PDF file
YLYoucheng Lin
Youcheng Lin
NTNan Tong
Nan Tong
MSMajie Shi
Majie Shi
KFKedi Fan
Kedi Fan
DYDi Yuan
Di Yuan
QFQiang Fu
Qiang Fu

4 December 2024 in Sensors
Verified
Journal Article
Open access
PDF file
LTLi Tan
Li Tan
QFQiang Fu
Qiang Fu
JLJing Li
Jing Li
In modern knitted garment production, accurate identification of fabric texture is crucial for enabling automation and ensuring consistent quality control. Traditional manual recognition methods not only demand considerable human effort but also suffer from inefficiencies and are prone to subjective errors. Although machine learning-based approaches have made notable advancements, they typically rely on manual feature extraction. This dependency is time-consuming and often limits recognition accuracy. To address these limitations, this paper introduces a novel model, called the Differentiated Leaning Weighted DenseNet (DLW-DenseNet), which builds upon the DenseNet architecture. Specifically, DLW-DenseNet introduces a learnable weight mechanism that utilizes channel attention to enhance the selection of relevant channels. The proposed mechanism reduces information redundancy and expands the feature search space of the model. To maintain the effectiveness of channel selection in the later stages of training, DLW-DenseNet incorportes a differentiated learning strategy. By assigning distinct learning rates to the learnable weights, the model ensures continuous and efficient channel selection throughout the training process, thus facilitating effective model pruning. Furthermore, in response to the absence of publicly available datasets for fabric texture recognition, we construct a new dataset named KF9 (knitted fabric). Compared to the fabric recognition network based on the improved ResNet, the recognition accuracy has increased by five percentage points, achieving a higher recognition rate. Experimental results demonstrate that DLW-DenseNet significantly outperforms other representative methods in terms of recognition accuracy on the KF9 dataset.

22 May 2018 in Journal of Lightwave Technology
Verified
Journal Article
Closed access
WCWeiwei Chen
Weiwei Chen
TYTianjun Yang
Tianjun Yang
PWPengjun Wang
Pengjun Wang
JZJie Zhang
Jie Zhang
QFQiang Fu
Qiang Fu
JYJianyi YANG
Jianyi YANG
In this paper, a kind of integrated flexible-grid wavelength-selective switch composed of reconfigurable add-drop silicon microring resonators with interferometric couplers is described in detail. Owing to tunable interferometric couplers, the proposed device is capable of realizing an increase in adjustable channel spacing for a given field coupling coefficient. By carefully controlling the path phase differences and tunable interferometric couplers, the transmission spectra of adjacent channels can be selectively combined to form adjustable bandwidths as desired. As an example, an integrated flexible-grid 1-2 wavelength-selective switch is designed and theoretically analyzed. The channel spacing can increase from 0.1 to 0.8 nm. When the channel spacing is selected to be 0.8 nm, the bandwidth varies from 0.36 to 2.91 nm and a minimum extinction ratio of 14.8 dB is obtained.

15 September 2023 in Biomimetics
Verified
Journal Article
Open access
PDF file
LHLin Huang
Lin Huang
QFQiang Fu
Qiang Fu
NTNan Tong
Nan Tong
Aimed at the problems of the Harris Hawks Optimization (HHO) algorithm, including the non-origin symmetric interval update position out-of-bounds rate, low search efficiency, slow convergence speed, and low precision, an Improved Harris Hawks Optimization (IHHO) algorithm is proposed. In this algorithm, a circle map was added to replace the pseudo-random initial population, and the population boundary number was reduced to improve the efficiency of the location update. By introducing a random-oriented strategy, the information exchange between populations was increased and the out-of-bounds position update was reduced. At the same time, the improved sine-trend search strategy was introduced to improve the search performance and reduce the out-of-bound rate. Then, a nonlinear jump strength combining escape energy and jump strength was proposed to improve the convergence accuracy of the algorithm. Finally, the simulation experiment was carried out on the test function and the path planning application of a 2D grid map. The results show that the Improved Harris Hawks Optimization algorithm is more competitive in solving accuracy, convergence speed, and non-origin symmetric interval search efficiency, and verifies the feasibility and effectiveness of the Improved Harris Hawks Optimization in the path planning of a grid map.

21 May 2019 in IEEE Photonics Journal
Verified
Journal Article
Open access
PWPengjun Wang
Pengjun Wang
JDJian Ding
Jian Ding
WCWeiwei Chen
Weiwei Chen
SLShiqi Li
Shiqi Li
BZBohao Zhang
Bohao Zhang
JYJianyi YANG
Jianyi YANG
In this paper, a plasmonic Feynman gate based on suspended graphene nano-ribbon waveguides at THz wavelengths is proposed and numerically investigated. The proposed plasmonic Feynman gate is composed of two cascaded microring resonators. The resonant states of microring resonators are flexibly controlled by tuning chemical potentials of graphene in rings and thus the logic operation results of Feynman gate can be performed successfully. Compared to the plasmonic Feynman gate based on graphene nano-ribbons deposited on the Si substrate and the plasmonic Feynman gate based on graphene nano-ribbons deposited on the SiO2/Si substrate, our designed plasmonic Feynman gate can have better extinction ratio and crosstalk. Calculation results exhibit that the extinction ratio is larger than 15.39 dB and the crosstalk is lower than -15.55 dB when input logic states of our designed device are '00', '01', '10', and '11'.

17 April 2026 in Journal of King Saud University Computer and Information Sciences
Verified
Journal Article
Open access
PDF file
JLJiajun Liu
Jiajun Liu
QFQiang Fu
Qiang Fu
JLJing Li
Jing Li
ZWZhiping Wu
Zhiping Wu
Fabric defect detection is critical for ensuring textile quality in industrial manufacturing. However, existing methods face significant challenges when dealing with complex texture backgrounds, high similarity between defects and normal patterns, extreme aspect ratios, and small defect sizes. To address these issues, we propose ASCR-DETR, an enhanced Detection Transformer specifically designed for fabric defect detection. First, we propose an Adaptive Spatial Geometric Convolution (ASGC) module, which dynamically adjusts sampling locations and modulation parameters through a Tri-Dimensional Cooperative Attention (TDCA) mechanism, enabling effective modeling and accurate capture of irregular defect geometries. Second, we design a Context-Guided Spatial Reconstruction Feature Pyramid Fusion Network (CSRFPN) that implements a progressive three-stage "calibration-reconstruction-fusion" framework. This network establishes cross-scale semantic correlations by aggregating multi-resolution contextual information, performs fine-grained spatial reconstruction to enhance local discriminability at each pyramid level, and achieves progressive top-down feature aggregation through dynamic interpolation and gated fusion mechanisms, effectively preserving small defect details while suppressing background interference across multiple scales. Third, we incorporate Coordinate Attention (CA) mechanisms to enhance global contextual representation, and introduce Dynamic Range Histogram Self-Attention (DRHS-AIFI) for intra-scale feature interaction, effectively suppressing background interference through value-domain statistical modeling. Extensive experiments on public and industrial datasets demonstrate that ASCR-DETR achieves 85.3% mAP@50(+7.1%) and 45.9% mAP@50:95(4.9%), outperforming state-of-the-art CNN-based and Transformer-based detectors while maintaining real-time performance, validating its effectiveness and deployment potential for industrial fabric inspection systems. The source code is available at:https://github.com/justDo000/ASCR-DETR.