Yawen Wang

Ms. Yawen Wang

Department of Business Administration

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
3 May 2020 in Carbon Management
Verified
Journal Article
Closed access
WSWei Sun
Wei Sun
YWYawen Wang
Yawen Wang
With the development of China’s carbon market, there has been a growing interest in research on carbon prices. Using analysis and prediction, the mechanism of the carbon market could be improved and correct guidance from relevant policies might be provided. To improve the accuracy of prediction, a hybrid model based on factor analysis, empirical mode decomposition, improved particle swarm optimization, and the least squares support vector machine is proposed in this article to use when considering the historical carbon price and external factors affecting the carbon price. First, factor analysis is conducted to extract special factors as input variables. Then, the original carbon price sequences are decomposed by empirical mode decomposition. Ultimately, the least squares support vector machine optimized by improved particle swarm optimization is employed to calculate each sequence, and the final predicted result is integrated by the forecasting results of each sequence. Based on three typical carbon markets in China, the results show that the hybrid model is more accurate than comparable models when forecasting carbon prices combined with various factors.

16 April 2021 in Polish Journal of Environmental Studies
Verified
Journal Article
Closed access
WSWei Sun
Wei Sun
YWYawen Wang
Yawen Wang
With the rapid increase in CO2 emissions, there is a profound impact on global climate change, seriously hindering the sustainable development of the low-carbon economy. Therefore, it is particularly significant to predict CO2 emissions. To improve the accuracy and robustness, a new hybrid model (KPCA-CEEMDAN-AWOA-RELM) is proposed when considering multiple factors about historical CO2 emissions, energy consumption, economic and social. First, factors are determined by Pearson doubly significant test, and the principal component is extracted by kernel principal component analysis (KPCA) to realize nonlinear dimension reduction. Then, the CO2 emissions sequence is decomposed by the ensemble empirical model with adaptive noise (CEEMDAN) model to reduce noise interference and abate reconstruction error. Finally, CO2 emissions can be predicted via the extreme learning machine with regularization parameter modification optimized by an improved input weight matrix and the deviation matrix of the adaptive optimization whale algorithm (AWOA-RELM). Taking Hebei and China as examples, it is found that the selected model is better than other comparative models.

15 October 2021
Verified
Conference Paper
Closed access
YWYawen Wang
Yawen Wang
JCJiang Dr. Chen
Jiang Dr. Chen
JHJunhua Hu
Junhua Hu
NXNing Xu
Ning Xu
YWYuan Wang
Yuan Wang
GMGuo-Ming Ma
Guo-Ming Ma
Transformer is an indispensable main electrical equipment in power transmission and distribution system. A large number of typical quality event analysis reports are accumulated in daily operation and maintenance, most of which are unstructured descriptive text data. The records have distinct personal characteristics, and it is difficult to understand or analyze by means of automation. For solving the above problem, this paper proposed an analysis method for labeling transformer quality event features based on Bidirectional Encoder Representation from Transformers(BERT). Firstly, the transformer quality event manually extracted feature label is used as input for text vectorization, and the model parameters are obtained by repeatedly using the text get into BERT pre-training model. Then, a training method that changes each learning rate by gradual attenuation is proposed to optimize the model. K-means++ clustering algorithm was used to analysis and Figure out all kinds of quality events. Finally, an example analysis based on 452 actual transformer quality event analysis reports was conducted. The example results showed that the method proposed in this paper achieved a good correspondence between the feature labels of transformer quality events, and the accuracy reached 90%, which is which is at least 4.2% higher than that of the traditional machine learning text data mining technology.