Search

Your search keyword '"Shi, Xiaojun"' showing total 1,097 results
Start Over Author "Shi, Xiaojun"
1,097 results on '"Shi, Xiaojun"'

2. Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification

Author

Liu, Xueyi, Hou, Rui, Gan, Yanglei, Luo, Da, Li, Changlin, Shi, Xiaojun, and Liu, Qiao

Subjects
Computer Science - Computation and Language, Computer Science - Artificial Intelligence, I.2.7
Abstract

Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its context. Previous works have made remarkable progress in leveraging attention mechanism to extract opinion words for different aspects. However, a persistent challenge is the effective management of semantic mismatches, which stem from attention mechanisms that fall short in adequately aligning opinions words with their corresponding aspect in multi-aspect sentences. To address this issue, we propose a novel Aspect-oriented Opinion Alignment Network (AOAN) to capture the contextual association between opinion words and the corresponding aspect. Specifically, we first introduce a neighboring span enhanced module which highlights various compositions of neighboring words and given aspects. In addition, we design a multi-perspective attention mechanism that align relevant opinion information with respect to the given aspect. Extensive experiments on three benchmark datasets demonstrate that our model achieves state-of-the-art results. The source code is available at https://github.com/AONE-NLP/ABSA-AOAN., Comment: 8 pages, 5 figure, ECAI 2023

Published
2023

30. Adaptive Distributed Laser Charging for Efficient Wireless Power Transfer

Author

Zhang, Qingqing, Shi, Xiaojun, Liu, Qingwen, Wu, Jun, Xia, Pengfei, and Liao, Yong

Subjects
Electrical Engineering and Systems Science - Systems and Control, Electrical Engineering and Systems Science - Signal Processing
Abstract

Distributed laser charging (DLC) is a wireless power transfer technology for mobile electronics. Similar to traditional wireless charging systems, the DLC system can only provide constant power to charge a battery. However, Li-ion battery needs dynamic input current and voltage, thus power, in order to optimize battery charging performance. Therefore, neither power transmission efficiency nor battery charging performance can be optimized by the DLC system. We at first propose an adaptive DLC (ADLC) system to optimize wireless power transfer efficiency and battery charging performance. Then, we analyze ADLC's power conversion to depict the adaptation mechanism. Finally, we evaluate the ADLC's power conversion performance by simulation, which illustrates its efficiency improvement by saving at least 60.4% of energy, comparing with the fixed-power charging system., Comment: 5 pages, 9 figures

Published
2020
Full Text
View/download PDF

45. Fault line selection method for coal mine power grid based on RCMDE and KFCM

Author

HAN Guoguo, SHI Xiaojun, WANG Hui, CHENG Weijian, and MU Yanxiang

Subjects
resonant grounding system, coal mine power grid, single-phase-to-ground fault, fault line selection, refined composite multiscale dispersion entropy, kernel-fuzzy c-means clustering, transient zero-sequence current, Mining engineering. Metallurgy, TN1-997
Abstract

It is difficult to accurately select the fault line when the single-phase ground fault occurs in the coal mine power grid with the widely used resonant grounding system. In order to solve the above problem, a fault line selection method of the coal mine power grid based on the refined composite multiscale dispersion entropy (RCMDE) and the kernel fuzzy C-means clustering (KFCM) is proposed. The limitations of using amplitude, polarity and waveform similarity as line selection characteristic quantities: the applicability of the line selection method based on amplitude and polarity difference is limited. If the polarity of the zero sequence current transformer in the line is reversed, the method based on polarity will directly fail. When the sampling is not synchronized, the line selection method based on waveform similarity is difficult to obtain correct results. In order to overcome the above limitations, RCMDE is introduced to measure the complexity and irregularity of the transient zero sequence current signal of each line. RCMDE is used as the characteristic quantity of line selection. The KFCM algorithm is used to cluster the RCMDE to realize the automatic identification of fault lines. The bus fault and feeder fault are distinguished by judging whether the contour coefficient exceeds the threshold value. Finally, the feeder line with the fault point is judged through the membership degree matrix obtained by clustering. The simulation results show the following points. ① The RCMDE curve of the fault line is different from that of the non-fault line, and the curves can be divided into two types. RCMDE can be used as the fault characteristic index of fault line. ② When the bus fault occurs, there are clusters with an average contour coefficient less than the threshold value in the clustering results. However, when feeder fault occurs, the contour coefficients of the clustering results are all greater than the threshold value. Under various fault scenarios, the coal mine power grid fault line selection method based on RCMDE and KFCM can realize correct line selection. The results show that its accuracy is not affected by factors such as fault line, fault location, fault closing angle and grounding resistance. ③ Under the conditions of noise disturbance, the fault line selection method based on RCMDE and KFCM can realize correct line selection in the case of low resistance grounding or high resistance grounding. And the method has a strong anti-interference capability. ④ Under the conditions of asynchronous sampling and reverse polarity of zero-sequence current transformer in the fault line, the method based on RCMDE and KFCM can still realize correct line selection. And the line selection result has high robustness.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results