Education, Science, Technology, Innovation and Life
Open Access
Sign In

Analysis of Hornet Forecast Model based on Fuzzy Theory

Download as PDF

DOI: 10.23977/jeis.2021.61004 | Downloads: 7 | Views: 1052


Qian Chen 1


1 School of Statistics and Mathematics, Guangdong University of Finance and Economics, Guangzhou, Guangdong 510320

Corresponding Author

Qian Chen


The 14 Positive ID the paperre arranged in time order and the GM Model was used to predict the range of propagation, and the results of the prediction the paper re obtained as follows: from 48.92 to 49.05 in length and from -122.47 to -122.55 in latitude in 2021. There is a distance of 30 km betthe paperen the predicted results and the initial point where the presence of hornets was confirmed. The average relative error is less than 0.01, so the model prediction accuracy is good. Since the life cycle of hornets is very related to seasons, the time is converted into seasons and then One-Hot-Encoding of seasons; the TFIDF Algorithm is used to calculate the importance of each Note to replace the original Notes. The SMOTE Method used in this paper to fill the Positive ID minority class sample leads to the proliferation of Vespa mandarinia seriously endangering the local ecology, so the SMOTE Method used in this paper to fill the Positive ID minority class sample. The models all seek to maximize the recall of a few classes of Positive ID. After model testing our models are all excellent in identifying pests accurately, as evidenced by the ROC (with Positive ID as a positive example) curve and AUC =0.99.


SMOTE, GM Model, hornets, Positive ID


Qian Chen, Analysis of Hornet Forecast Model based on Fuzzy Theory. Journal of Electronics and Information Science (2021) 6: 27-31. DOI:


[1] papereds/ insects/hornets /data. Accessed 7 / 2/2021. Washington State Department of Agriculture. 
[2] 2021MCM_ProblemC_V espamandarinia.pdf (from Pennsylvania State University Extension). 
[3] Lu Yi. The Research and Application of Grey Forecast Model [D]. Zhejiang Sci-Tech University. 2014 
[4] Accessed 7/2/2021. 
[5] Bruno Trstenjak, Sasa Mikac, Dzenana Donko. KNN with TF-IDF based Framework for Text Categorization [J]. Procedia Engineering, 2014, 69.

Downloads: 6215
Visits: 247371

Sponsors, Associates, and Links

All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.