Xin Wang

Xin Wang

Auto-generated profile, based on publicly available information

Xin Wang

College of Life Sciences, Northwest University, Xi'an, China

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
8 October 2019 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
Verified
Journal Article
Open access
XSXia Sun
Xia Sun
YGYi Gao
Yi Gao
RSRichard Sutcliffe
Richard Sutcliffe
SGShou-Xi Guo
Shou-Xi Guo
XWXin Wang
Xin Wang
JFJun Feng
Jun Feng
Sentiment classification is a fundamental task in many natural language processing applications. Neural networks have achieved great successes on the sentiment classification task in recent years, since recurrent neural networks and long-short-term memory networks have the ability to deal with sequences of different lengths and to capture contextual semantic information. However, the effectiveness of these methods is limited when used to extract contextual information from relatively long texts. Therefore, in our model, we apply bidirectional gated recurrent units to capture contextual information as far as possible when learning word representations, which may effectively reduce the noise compared to other methods. We also propose a novel loss function namely drop loss (DL) which makes the model focus on the hard examples--examples which are easily classified incorrectly--in order to improve the accuracy of the model. We experiment on four commonly used datasets, and the results show that the proposed method has a good performance on four datasets, and needs fewer parameters compared with recent benchmarks, such as CoVe, ULMFiT, embeddings from language models, and bidirectional encoder representations from transformers. Furthermore, we demonstrate that the classification performance of existing shallow network models can be significantly improved by using DL. In particular, the accuracy of the CNN+LSTM model improves 9% on the IMDB-10 dataset.

6 May 2022 in Frontiers in Medicine
Verified
Journal Article
Open access
YDYankai Dong
Yankai Dong
LLLina Liu
Lina Liu
JHJie Han
Jie Han
LZLianqing Zhang
Lianqing Zhang
YWYi Wang
Yi Wang
XHXiaofei Hu
Xiaofei Hu
Objective: Artemisinin is an organic compound that comes from Artemisia annua. Artemisinin treatment is the most important and effective method for treating malaria. Bibliometric analysis was carried out to identify the global research trends, hot spots, scientific frontiers, and output characteristics of artemisinin from 2000 to 2021.Methods: Publications and their recorded information from 2000 to 2021 were retrieved through the Web of Science Core Collection (WoSCC). Using VOSviewer and Citespace, the hotspots and trends of studies on artemisinin were visualized.Results: A total of 8,466 publications were retrieved, and for the past 22 years, the annual number of publications associated with artemisinin kept increasing. The United States published most papers. The H-index and number of citations of the United States ranked first. The University of Oxford and MALARIA JOURNAL were the most productive affiliation and journal, respectively. A paper written by E.A. Ashley in 2011 achieved the highest global citation score. Keywords, such as “malaria,” “artesunate,” “plasmodium-falciparum,” “in-vitro,” “artemisinin resistance,” “plasmodium falciparum,” “resistance,” and “artemether-lumefantrine,” appeared most frequently. The research on artemisinin includes clinical research and animal and cell experiments.Conclusion: The biosynthesis, drug resistance mechanism, and combination of artemisinin have become more popular than before. Studies on artemisinin treating coronavirus disease 2019 (COVID-19) have been carried out, and good research results have been obtained.