Tong Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tong Li has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Changhong Liang
National Laboratory of Science and Technology on Antennas and Microwaves, Xidian University, Xi’an 710071, Shaanxi, China
1 shared publication- Guihong Li
Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
1 shared publication - Huiqing Zhai
National Key Laboratory of Radar Detection and Sensing and the School of Electronic Engineering, Xidian University, Xian, China
1 shared publication Jun Ma
China Mobile Group Shaanxi Company Limited Shaanxi China
1 shared publication- Xiaoyan Ma
School of Materials Science and Engineering, Chang’an University, Xi’an 710064, China
1 shared publication Yanling Zhang
State Key Laboratory of Integrated Services Xidian University Shaanxi China
1 shared publication
Latest Publications
- 14 February 2022
- Published by Wiley in Internet Technology Letters
- Vol. 6 (5) , e354
AI-based Abstractive Text Summarization towards AIoT and Edge Computing
The task of text summarization has been widely concerned in the fields of news, document indexing and literature retrieval. Recently, due to the rise of mobile Internet devices, natural language processing for AIoT and edge computing has become a hot spot. This paper focuses on the research of text summarization for AIoT and edge computing. For a long time, abstractive summarization is limited to academic research due to the lack of controllability of the generated content. Recently, the appearance of Transformer has changed the current situation of abstractive text summarization. Transformer follows encoder‐decoder architecture, including attention mechanism and feed‐forward network. The encoder encodes the semantic information of source text, and decoder adaptively selects the effective context information through the attention mechanism to generate a coherent summary. To extract more semantic information and control the generated text better, this paper proposes multi‐scale semantic information Transformer (MSIT). Specifically, we introduce depth‐wise separable convolution to the encoder to extract more local semantic information, so that the attention mechanism can make better use of contextual semantic information. Additionally, we combine the encoding vector of encoder and target summary as the input to the attention layer of the decoder, and introduce time series mechanism so that the decoder can consider context information when generating text. Experiments on CNN‐Daily Mail Dataset show that this model is superior to other methods.
- 14 February 2022
- Published by Wiley in Internet Technology Letters
- Vol. 6 (5) , e354
AI-based Abstractive Text Summarization towards AIoT and Edge Computing
The task of text summarization has been widely concerned in the fields of news, document indexing and literature retrieval. Recently, due to the rise of mobile Internet devices, natural language processing for AIoT and edge computing has become a hot spot. This paper focuses on the research of text summarization for AIoT and edge computing. For a long time, abstractive summarization is limited to academic research due to the lack of controllability of the generated content. Recently, the appearance of Transformer has changed the current situation of abstractive text summarization. Transformer follows encoder‐decoder architecture, including attention mechanism and feed‐forward network. The encoder encodes the semantic information of source text, and decoder adaptively selects the effective context information through the attention mechanism to generate a coherent summary. To extract more semantic information and control the generated text better, this paper proposes multi‐scale semantic information Transformer (MSIT). Specifically, we introduce depth‐wise separable convolution to the encoder to extract more local semantic information, so that the attention mechanism can make better use of contextual semantic information. Additionally, we combine the encoding vector of encoder and target summary as the input to the attention layer of the decoder, and introduce time series mechanism so that the decoder can consider context information when generating text. Experiments on CNN‐Daily Mail Dataset show that this model is superior to other methods.
- 22 April 2014
- Published by Taylor & Francis in Journal of Electromagnetic Waves and Applications
- Vol. 28 (10) , 1212-1220
Design of a CPW-fed slot antenna with small size and ultra-broadband circularly polarized radiation
In this research, a coplanar waveguide (CPW)-fed slot antenna is proposed with a compact size and an ultra-broadband circularly polarized (CP) radiation. The proposed antenna, just with a small size of 40 mm × 40 mm × 1 mm in overall configuration, achieves an ultra-broad CP bandwidth of 68.1% from 3.05 to 6.2 GHz, suitable for both WiMAX (3.3–3.8 GHz) and WLAN (5.15–5.35 GHz/5.725–5.825 GHz) systems. The presented antenna proposes two linked rectangular slots in the ground to obtain CP radiations. The linked slots can also be considered as a square slot with two perturbations in the corners. The perturbations can split the fundamental resonant mode into two near-degenerate modes, leading to CP waves. The adjacent excited CP modes are merged for ultra-wideband CP radiation. With a symmetric series impedance line connected to CPW feedline, broadband input impedance matching from 2.65 to 6.8 GHz can be obtained. The proposed design has been verified by the simulated and measured results. The future MIMO potential of the proposed CP antenna has also been studied.
- 22 April 2014
- Published by Taylor & Francis in Journal of Electromagnetic Waves and Applications
- Vol. 28 (10) , 1212-1220
Design of a CPW-fed slot antenna with small size and ultra-broadband circularly polarized radiation
In this research, a coplanar waveguide (CPW)-fed slot antenna is proposed with a compact size and an ultra-broadband circularly polarized (CP) radiation. The proposed antenna, just with a small size of 40 mm × 40 mm × 1 mm in overall configuration, achieves an ultra-broad CP bandwidth of 68.1% from 3.05 to 6.2 GHz, suitable for both WiMAX (3.3–3.8 GHz) and WLAN (5.15–5.35 GHz/5.725–5.825 GHz) systems. The presented antenna proposes two linked rectangular slots in the ground to obtain CP radiations. The linked slots can also be considered as a square slot with two perturbations in the corners. The perturbations can split the fundamental resonant mode into two near-degenerate modes, leading to CP waves. The adjacent excited CP modes are merged for ultra-wideband CP radiation. With a symmetric series impedance line connected to CPW feedline, broadband input impedance matching from 2.65 to 6.8 GHz can be obtained. The proposed design has been verified by the simulated and measured results. The future MIMO potential of the proposed CP antenna has also been studied.