Shuqiang Yang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Shuqiang Yang has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Gang Li
Medical School of Tianjin University, Tianjin, 300072, China; State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin, 300072, China
4 shared publications - Guoquan He
School of Electronic Information Engineering, Yangtze Normal University, Chongqing, China
3 shared publications - Ling Lin
State Key Laboratory of Precision Measuring Technology and Instruments, Tianjin University, Tianjin, 300072, China
3 shared publications - Wenjuan Yan
School of Electronic Information Engineering, Yangtze Normal University, Chongqing, China
3 shared publications - Fulong Liu
Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin, China
2 shared publications - Huafeng Qin
Chongqing Technology and Business University
2 shared publications
Latest Publications
- Open Access
- 7 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 51-56
Lightweight Vein Recognition for Secure IoT Edge Devices: A Channel-wise Attention Approach for Big Data Biometrics
- 7 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 51-56
Open AccessLightweight Vein Recognition for Secure IoT Edge Devices: A Channel-wise Attention Approach for Big Data Biometrics
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition
Eye movement biometrics has received increasing attention thanks to its highly secure identification. Although deep learning (DL) models have succeeded in eye movement recognition, their architectures largely rely on human prior knowledge. Differentiable Neural Architecture Search (DARTS) automates the manual architecture design process with high search efficiency. However, DARTS typically stacks multiple cells to form a convolutional network, which limits the diversity of architecture. Furthermore, DARTS generally searches for architectures using shallower networks than those used in the evaluation, creating a significant disparity in architecture depth between the search and evaluation phases. To address this issue, we propose EM-DARTS, a hierarchical differentiable architecture search algorithm to automatically design the DL architecture for eye movement recognition. First, we define a supernet and propose a global and local alternate Neural Architecture Search method to search the optimal architecture alternately with a differentiable neural architecture search. The local search strategy aims to find an optimal architecture for different cells, while the global search strategy is responsible for optimizing the architecture of the target network. To minimize redundancy, transfer entropy is proposed to compute the information amount of each layer, thereby further simplifying the network search process. Experimental results on three public datasets demonstrate that the proposed EM-DARTS can produce an optimal architecture that leads to state-of-the-art recognition performance. Specifically, the recognition models developed using EM-DARTS achieved the lowest EERs of 0.0453 on the GazeBase dataset, 0.0377 on the JuDo1000 dataset, and 0.1385 on the EMglasses dataset.
- 10 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-16
EM-DARTS: Hierarchical Differentiable Architecture Search for Eye Movement Recognition
Eye movement biometrics has received increasing attention thanks to its highly secure identification. Although deep learning (DL) models have succeeded in eye movement recognition, their architectures largely rely on human prior knowledge. Differentiable Neural Architecture Search (DARTS) automates the manual architecture design process with high search efficiency. However, DARTS typically stacks multiple cells to form a convolutional network, which limits the diversity of architecture. Furthermore, DARTS generally searches for architectures using shallower networks than those used in the evaluation, creating a significant disparity in architecture depth between the search and evaluation phases. To address this issue, we propose EM-DARTS, a hierarchical differentiable architecture search algorithm to automatically design the DL architecture for eye movement recognition. First, we define a supernet and propose a global and local alternate Neural Architecture Search method to search the optimal architecture alternately with a differentiable neural architecture search. The local search strategy aims to find an optimal architecture for different cells, while the global search strategy is responsible for optimizing the architecture of the target network. To minimize redundancy, transfer entropy is proposed to compute the information amount of each layer, thereby further simplifying the network search process. Experimental results on three public datasets demonstrate that the proposed EM-DARTS can produce an optimal architecture that leads to state-of-the-art recognition performance. Specifically, the recognition models developed using EM-DARTS achieved the lowest EERs of 0.0453 on the GazeBase dataset, 0.0377 on the JuDo1000 dataset, and 0.1385 on the EMglasses dataset.
- 10 June 2020
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 74 (8) , 883-893
Recognition of Heterogeneous Edges in Multiwavelength Transmission Images Based on the Weighted Constraint Decision Method
Multiwavelength light transmission imaging provides a possibility for early detection of breast cancer. However, due to strong scattering during the transmission process of breast tissue analysis, the transmitted image signal is weak and the image is blurred and this makes heterogeneous edge detection difficult. This paper proposes a method based on the weighted constraint decision (WCD) method to eliminate the erosion and checkerboard effects in image histogram equalization (HE) enhancement and to improve the recognition of heterogeneous edge. Multiwavelength transmission images of phantom are acquired on the designed experimental system and the mask image with high signal-to-noise ratio (SNR) is obtained by frame accumulation and an Otsu thresholding model. Then, during image enhancement the image is divided into low-gray-level (LGL) and high-gray-level (HGL) regions according to the distribution of light intensity in image. And the probability density distribution of gray level in the LGL and HGL regions are redefined respectively according to the WCD method. Finally, the reconstructed image is obtained based on the modified HE. The experimental results show that compared with traditional image enhancement methods, the WCD method proposed in this paper can greatly improve the contrast between heterogeneous region and normal region. Moreover, the correlation between the original image data is maintained to the greatest extent, so that the edge of the heterogeneity can be detected more accurately. In conclusion, the WCD method not only accurately identifies the edge of heterogeneity in multiwavelength transmission images, but it also could improve the clinical application of multiwavelength transmission images in the early detection of breast cancer.
- 10 June 2020
- Published by SAGE Publications in Applied Spectroscopy
- Vol. 74 (8) , 883-893
Recognition of Heterogeneous Edges in Multiwavelength Transmission Images Based on the Weighted Constraint Decision Method
Multiwavelength light transmission imaging provides a possibility for early detection of breast cancer. However, due to strong scattering during the transmission process of breast tissue analysis, the transmitted image signal is weak and the image is blurred and this makes heterogeneous edge detection difficult. This paper proposes a method based on the weighted constraint decision (WCD) method to eliminate the erosion and checkerboard effects in image histogram equalization (HE) enhancement and to improve the recognition of heterogeneous edge. Multiwavelength transmission images of phantom are acquired on the designed experimental system and the mask image with high signal-to-noise ratio (SNR) is obtained by frame accumulation and an Otsu thresholding model. Then, during image enhancement the image is divided into low-gray-level (LGL) and high-gray-level (HGL) regions according to the distribution of light intensity in image. And the probability density distribution of gray level in the LGL and HGL regions are redefined respectively according to the WCD method. Finally, the reconstructed image is obtained based on the modified HE. The experimental results show that compared with traditional image enhancement methods, the WCD method proposed in this paper can greatly improve the contrast between heterogeneous region and normal region. Moreover, the correlation between the original image data is maintained to the greatest extent, so that the edge of the heterogeneity can be detected more accurately. In conclusion, the WCD method not only accurately identifies the edge of heterogeneity in multiwavelength transmission images, but it also could improve the clinical application of multiwavelength transmission images in the early detection of breast cancer.
- Open Access
- 31 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 3980-3986
Systematic Proportional Method for Improving the Measurement Accuracy of Passive Sensor Measurement System
The accuracy and stability of excitation source determine the measurement accuracy of passive sensor measurement system, but the implementation of high-precision excitation source (especially AC excitation source) is difficult or costly in design and process. For this purpose, this paper proposes a systematic proportional method. In this method, the DC voltage converted by the excitation signal is taken as the reference voltage of the ADC used in this system. And then the ratio of the measured signal to the excitation signal is obtained by using the transmission characteristics of the ADC, therefore the amplitude fluctuation of the excitation signal is compensated. The method can greatly suppress the measurement error caused by the amplitude fluctuation of the excitation signal and the fluctuation of the ADC reference voltage, and effectively improve the measurement accuracy of the measurement system. To verify the effectiveness of the proposed method, the Wheatstone bridge measurement circuit is designed. The experimental results show that when the amplitude of the excitation signal changes 50%, the measurement result of the measurement system using non-proportional method changes about 50%, while that of the measurement system using proportional method only changes about 1%. To further improve the measurement accuracy, the DC bias voltage compensation circuit is added, and the maximum variation error of the measurement result after compensation is only 0.3%. More importantly, the method can also be extended to other linear measurement systems with excitation source in principle, which has greater application value.
- 31 December 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 3980-3986
Open AccessSystematic Proportional Method for Improving the Measurement Accuracy of Passive Sensor Measurement System
The accuracy and stability of excitation source determine the measurement accuracy of passive sensor measurement system, but the implementation of high-precision excitation source (especially AC excitation source) is difficult or costly in design and process. For this purpose, this paper proposes a systematic proportional method. In this method, the DC voltage converted by the excitation signal is taken as the reference voltage of the ADC used in this system. And then the ratio of the measured signal to the excitation signal is obtained by using the transmission characteristics of the ADC, therefore the amplitude fluctuation of the excitation signal is compensated. The method can greatly suppress the measurement error caused by the amplitude fluctuation of the excitation signal and the fluctuation of the ADC reference voltage, and effectively improve the measurement accuracy of the measurement system. To verify the effectiveness of the proposed method, the Wheatstone bridge measurement circuit is designed. The experimental results show that when the amplitude of the excitation signal changes 50%, the measurement result of the measurement system using non-proportional method changes about 50%, while that of the measurement system using proportional method only changes about 1%. To further improve the measurement accuracy, the DC bias voltage compensation circuit is added, and the maximum variation error of the measurement result after compensation is only 0.3%. More importantly, the method can also be extended to other linear measurement systems with excitation source in principle, which has greater application value.
- Open Access
- 20 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 168371-168381
A Fusion Method in Frequency Domain for Multi-Wavelength Transmission Image
Multi-wavelength transmission imaging provides a possibility for early breast cancer detection. However, due to the strong scattering effect of light source in the transmission process of biological tissue, there exist many difficulties in the heterogeneous identification of multi-wavelength images. In this paper, a multi-wavelength images frequency fusion method based on regional variance significance and regional space energy weighting is proposed to improve the accuracy of heterogeneous detection. Firstly, the acquisition experiment of phantom multi-wavelength transmission images is designed. And R three-channel wavelength images are extracted from multi-wavelength images as an example to realize subsequent image fusion. Secondly, frame accumulation technique and second-order Butterworth filter are used to improve the signal-to-noise ratio of images and suppress the noise of images. Then, after homomorphic filtering, it is found that the same frequency domain of images is connected, which is not conducive to the recognition of heterogeneity in image. In order to break the connectivity of images in the same frequency domain and improve the accuracy of heterogeneous detection, the regional variance significance and the regional space energy weighting fusion strategies are used to reconstruct the low-frequency and high-frequency fusion images respectively. Finally, the heterogeneous detection results of the proposed image fusion method and the state-of-the-art methods in the multi-wavelength image are compared. The experimental results show that compared with the state-of-the-art image fusion methods, the fusion method proposed in this paper can identify the location of heterogeneous region more accurately and significantly improve the contrast between heterogeneous region and normal region in the fusion image. In conclusion, the fusion algorithm not only effectively realizes the recognition of heterogeneity in multi-wavelength images, but also promotes the potential application of multi-wavelength transmission image in early breast cancer detection.
- 20 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 168371-168381
Open AccessA Fusion Method in Frequency Domain for Multi-Wavelength Transmission Image
Multi-wavelength transmission imaging provides a possibility for early breast cancer detection. However, due to the strong scattering effect of light source in the transmission process of biological tissue, there exist many difficulties in the heterogeneous identification of multi-wavelength images. In this paper, a multi-wavelength images frequency fusion method based on regional variance significance and regional space energy weighting is proposed to improve the accuracy of heterogeneous detection. Firstly, the acquisition experiment of phantom multi-wavelength transmission images is designed. And R three-channel wavelength images are extracted from multi-wavelength images as an example to realize subsequent image fusion. Secondly, frame accumulation technique and second-order Butterworth filter are used to improve the signal-to-noise ratio of images and suppress the noise of images. Then, after homomorphic filtering, it is found that the same frequency domain of images is connected, which is not conducive to the recognition of heterogeneity in image. In order to break the connectivity of images in the same frequency domain and improve the accuracy of heterogeneous detection, the regional variance significance and the regional space energy weighting fusion strategies are used to reconstruct the low-frequency and high-frequency fusion images respectively. Finally, the heterogeneous detection results of the proposed image fusion method and the state-of-the-art methods in the multi-wavelength image are compared. The experimental results show that compared with the state-of-the-art image fusion methods, the fusion method proposed in this paper can identify the location of heterogeneous region more accurately and significantly improve the contrast between heterogeneous region and normal region in the fusion image. In conclusion, the fusion algorithm not only effectively realizes the recognition of heterogeneity in multi-wavelength images, but also promotes the potential application of multi-wavelength transmission image in early breast cancer detection.
- Open Access
- 22 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 97732-97744
Classification of Heterogeneity on Multi-Spectral Transmission Image Based on Modulation-Demodulation-Frame Accumulation and Pattern Recognition
Multi-spectral transmission image provides a possibility for the detection of early breast cancer. However, in the process of acquiring multi-spectral transmission images, the recognition of heterogeneities has many difficulties due to the image blur caused by the scattering effect of light source in biological tissues and weak transmission signals. This paper proposes a combination method of modulation-demodulation-frame accumulation technique and pattern recognition to achieve heterogeneous classification. First, the acquisition experiment of the phantom multi-spectral images is designed. Then, the signal-to-noise ratio (SNR) of the image is improved by the modulation-demodulation and frame accumulation technique, and the 14-dimensional feature information (firmness, angular second-order distance, contrast, gray-scale correlation, entropy, inverse gap, smoothness, dissimilarity, consistency, center of gravity, area, perimeter, long diameter of irregular image, and short diameter of irregular image) of the heterogeneous region are extracted from the image with high SNR. Finally, the heterogeneous classification accuracy of different models is compared. The results show that: compared with the classification accuracy of the traditional multi-spectral image classification models, random forest (RF) and extreme learning machine (ELM) models have better classification effect when subdividing the four types of heterogeneity based on the data set of this paper. Among them, the RF and ELM models established by the dataset of four-wavelength combination have the best classification effect, and the classification accuracy rate reaches 100%, second, it is the three-wavelength combined model. The single-wavelength model has the worst classification effect. And the operating efficiency of ELM is significantly higher than RF. In conclusion, the image quality is improved by modulation-demodulation and frame accumulation technique. And compared with the classification accuracy of the traditional multi-spectral image classification models, the RF and ELM models established in this paper have better classification effect, which may promote the application of multi-spectral transmission imaging in early screening of breast tumors.
- 22 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 7, 97732-97744
Open AccessClassification of Heterogeneity on Multi-Spectral Transmission Image Based on Modulation-Demodulation-Frame Accumulation and Pattern Recognition
Multi-spectral transmission image provides a possibility for the detection of early breast cancer. However, in the process of acquiring multi-spectral transmission images, the recognition of heterogeneities has many difficulties due to the image blur caused by the scattering effect of light source in biological tissues and weak transmission signals. This paper proposes a combination method of modulation-demodulation-frame accumulation technique and pattern recognition to achieve heterogeneous classification. First, the acquisition experiment of the phantom multi-spectral images is designed. Then, the signal-to-noise ratio (SNR) of the image is improved by the modulation-demodulation and frame accumulation technique, and the 14-dimensional feature information (firmness, angular second-order distance, contrast, gray-scale correlation, entropy, inverse gap, smoothness, dissimilarity, consistency, center of gravity, area, perimeter, long diameter of irregular image, and short diameter of irregular image) of the heterogeneous region are extracted from the image with high SNR. Finally, the heterogeneous classification accuracy of different models is compared. The results show that: compared with the classification accuracy of the traditional multi-spectral image classification models, random forest (RF) and extreme learning machine (ELM) models have better classification effect when subdividing the four types of heterogeneity based on the data set of this paper. Among them, the RF and ELM models established by the dataset of four-wavelength combination have the best classification effect, and the classification accuracy rate reaches 100%, second, it is the three-wavelength combined model. The single-wavelength model has the worst classification effect. And the operating efficiency of ELM is significantly higher than RF. In conclusion, the image quality is improved by modulation-demodulation and frame accumulation technique. And compared with the classification accuracy of the traditional multi-spectral image classification models, the RF and ELM models established in this paper have better classification effect, which may promote the application of multi-spectral transmission imaging in early screening of breast tumors.
- 1 August 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 120-125
A Joint Model for Sentence Semantic Similarity Learning
Sentence similarity is a fundamental task to measure the degree of the likelihood between two sentences. It plays an important role in both NLP and IR communities. The current sentence semantic similarity measurements can be divided into two categories: the model based on feature engineering and the model based on deep learning. These two categories all have their own advantages and disadvantages. The feature captured based on deep learning may not get the deep meaning of the sentence. And the feature exacted based on feature engineering may not be comprehensive. The algorithm proposed recently usually use one of these two models. In this paper, we proposed a new model that combine the deep learning model and the feature engineering model together. Our model enables two methods to complement each other, making the feature extraction more comprehensive: not only take the global semantic information into account, but also further refine the semantic information at the word level. The experiment shows that our model performs better than models only use one category.
- 1 August 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 120-125
A Joint Model for Sentence Semantic Similarity Learning
Sentence similarity is a fundamental task to measure the degree of the likelihood between two sentences. It plays an important role in both NLP and IR communities. The current sentence semantic similarity measurements can be divided into two categories: the model based on feature engineering and the model based on deep learning. These two categories all have their own advantages and disadvantages. The feature captured based on deep learning may not get the deep meaning of the sentence. And the feature exacted based on feature engineering may not be comprehensive. The algorithm proposed recently usually use one of these two models. In this paper, we proposed a new model that combine the deep learning model and the feature engineering model together. Our model enables two methods to complement each other, making the feature extraction more comprehensive: not only take the global semantic information into account, but also further refine the semantic information at the word level. The experiment shows that our model performs better than models only use one category.
- 20 June 2015
- Published by Springer Nature
- p. 189-196
A Method of Evaluating Distributed Storage System Reliability
- 20 June 2015
- Published by Springer Nature
- p. 189-196
A Method of Evaluating Distributed Storage System Reliability
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 792-797
Partial query optimization techniques for partitioned tables
With the emerging of large database and the explosion of mass data, people need to extract useful information, knowledge from huge database, and to improve the utilization rate of the information further. Partitioning technologies allows users to divisive a big table into some smaller and can manage partitions easier, so it can solve some of the problems of mass data. This paper discussed the Partial-MAX/MIN query optimization for the partitioned tables. We introduce the Rank Bisection Partition Tree (RBP-T) structure to improving the efficiency of this class of query. The experimental results show that our method to solve the Partial-MAX/MIN query in the mass data cases is effective.
- 1 May 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 792-797
Partial query optimization techniques for partitioned tables
With the emerging of large database and the explosion of mass data, people need to extract useful information, knowledge from huge database, and to improve the utilization rate of the information further. Partitioning technologies allows users to divisive a big table into some smaller and can manage partitions easier, so it can solve some of the problems of mass data. This paper discussed the Partial-MAX/MIN query optimization for the partitioned tables. We introduce the Rank Bisection Partition Tree (RBP-T) structure to improving the efficiency of this class of query. The experimental results show that our method to solve the Partial-MAX/MIN query in the mass data cases is effective.
- 1 January 2006
- Published by Springer Nature
- p. 122-132
DRO+: A Systemic and Economical Approach to Improve Availability of Massive Database Systems
- 1 January 2006
- Published by Springer Nature
- p. 122-132
DRO+: A Systemic and Economical Approach to Improve Availability of Massive Database Systems