Visual extraction system for insulators on power transmission lines from UAV photographs using support vector machine and color models

Zhang, Chi; Gong, Qingjie; Wang, Ting; Koyamada, Koji

doi:10.1007/s12650-020-00672-9

Cited by 3 publications

(1 citation statement)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the direction of iteration is stronger, and the global search ability is improved. Support vector machine algorithm is used to regression analyze the training set, find the best parameters, and then bring the training set into the best parameter model [28][29][30]. In the optimization using the least square method, the fitness parameter is the content that needs to be determined.…”

Section: Journal Of Function Spacesmentioning

confidence: 99%

Application of Optimized Support Vector Machine Model in Tax Forecasting System

Xin

2022

Journal of Function Spaces

View full text Add to dashboard Cite

Tax forecast has an important impact on financial budget and tax plan. The amount of tax data is greatly increased, the difficulty of tax forecast is improved, and the accuracy is always difficult to keep up with the development demand. Analyze the application of optimized support vector machine model in tax prediction system. Based on the simple analysis of the research situation of tax prediction and the research status of data mining algorithm in tax data classification and prediction, this paper constructs a tax prediction model. Aiming at the problem of too many influencing factors of tax prediction, this paper puts forward the use of principal component analysis to extract the main factors, reduce the dimension of tax data, and reduce the difficulty of analysis. Support vector machine is used to realize tax prediction, aiming at the problem of parameter optimization proposed to optimize the parameters. Finally, the prediction accuracy is evaluated by comparing the error between tax prediction value and real value. The results show that the algorithm used in this paper can optimize the parameters of support vector machine. The tax prediction results show that the predicted value is similar to the real value curve. After grid search optimization, the introduction of principal component analysis reduces the redundancy and improves the prediction accuracy.

show abstract

Section: Journal Of Function Spacesmentioning

confidence: 99%