Likun Tang
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
Likun Tang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Yong Jia
Chengdu University of Technology
2 shared publications - Chang Gao
SICHUAN SHUDAO NEW SYSTEM RAIL GROUP CO., LTD., China
1 shared publication - Guoqian Yang
Chengdu University of Technology, China
1 shared publication - Jiang Yu
Chengdu University of Technology, China
1 shared publication - Weiping Liu
SICHUAN SHUDAO NEW SYSTEM RAIL GROUP CO., LTD., China
1 shared publication Xiaodong Fan
Chengdu University of Technology,School of Electrical and Mechanical Engineering,Chengdu,Sichuan,China
1 shared publication
Latest Publications
- 8 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17, 409-413
Domain Adaptive Recognition of Defects for Ground Penetrating Radar Images
GPR technology is of significant importance for road maintenance authorities to detect road defect under the road surface, for it helps to monitor the construction process and detect defects early, thus reducing maintenance costs. The high cost of data collection and core verification for underground defects makes the dataset very valuable. In practical applications, different radar types and imaging methods often lead to heterogeneous generated radar images. In addition, there are significant differences between training data and real-world test data, which may lead to ambiguous predictions. This is because as the discrepance in different data domains increase, the transferability of the features extracted by neural networks significantly decreases at higher levels. Therefore, it is important to reduce dataset bias and enhance transferability in specific task layers. This article specifically designs a feature transfer enhancement algorithm for heterogeneous ground penetrating radar data based on deep domain adaptation. Compared with other deep domain adaptation algorithms such as DAN, DANN, and DeepCoral, the proposed method has the best recognition performance on underground defect data of ground penetrating radar.
- 8 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17, 409-413
Domain Adaptive Recognition of Defects for Ground Penetrating Radar Images
GPR technology is of significant importance for road maintenance authorities to detect road defect under the road surface, for it helps to monitor the construction process and detect defects early, thus reducing maintenance costs. The high cost of data collection and core verification for underground defects makes the dataset very valuable. In practical applications, different radar types and imaging methods often lead to heterogeneous generated radar images. In addition, there are significant differences between training data and real-world test data, which may lead to ambiguous predictions. This is because as the discrepance in different data domains increase, the transferability of the features extracted by neural networks significantly decreases at higher levels. Therefore, it is important to reduce dataset bias and enhance transferability in specific task layers. This article specifically designs a feature transfer enhancement algorithm for heterogeneous ground penetrating radar data based on deep domain adaptation. Compared with other deep domain adaptation algorithms such as DAN, DANN, and DeepCoral, the proposed method has the best recognition performance on underground defect data of ground penetrating radar.
- Open Access
- 28 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 106-110
Emitter identification based on multi-class spectrograms in time-frequency domain
In the identification of emitter, there are some problems such as poor identification effect and incomplete feature expression of emitter by using single signal processing method to obtain spectrogram with feature of emitter. In order to solve these problems, a method of emitter identification based on multi-class spectrograms in time-frequency domain is proposed. Specifically, three time-frequency analyses, including short-time Fourier transform (STFT), smoothed pseudo Wigner-Ville distribution (SPWVD) and reduced interference distribution with Hanning kernel (RIDHK), are performed on signal data to obtain the time-frequency spectrograms with different feature expressions. Three convolutional neural networks (CNN) were used to extract the independent features from three classes of spectrograms, and the three features were stacked to obtain more complete features of emitter, to improve the recognition effect. Experimental results show that compared with the single feature recognition method, the proposed method improves the accuracy of emitter identification effectively.
- 28 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 106-110
Open AccessEmitter identification based on multi-class spectrograms in time-frequency domain
In the identification of emitter, there are some problems such as poor identification effect and incomplete feature expression of emitter by using single signal processing method to obtain spectrogram with feature of emitter. In order to solve these problems, a method of emitter identification based on multi-class spectrograms in time-frequency domain is proposed. Specifically, three time-frequency analyses, including short-time Fourier transform (STFT), smoothed pseudo Wigner-Ville distribution (SPWVD) and reduced interference distribution with Hanning kernel (RIDHK), are performed on signal data to obtain the time-frequency spectrograms with different feature expressions. Three convolutional neural networks (CNN) were used to extract the independent features from three classes of spectrograms, and the three features were stacked to obtain more complete features of emitter, to improve the recognition effect. Experimental results show that compared with the single feature recognition method, the proposed method improves the accuracy of emitter identification effectively.