We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
基于 GA 优化 SVM 参数的白酒分类识别方法 应用研究.
- Authors
刘 鑫; 韩 强; 周永帅; 庹先国
- Abstract
In order to improve the accuracy of the Support Vector Machine algorithm in the classification prediction of Baijiu brands, the Genetic Algorithm was used to optimize the SVM parameters and the SVM Baijiu brand classification prediction model with optimal parameters was established. After the characteristic information of Baijiu of several brands to be tested was collected by array sensors (electronic tongues),the data of the extracted characteristic information were stored as a sample data set after pre-processing (outlier processing, normalization operation, etc.).The sample data was divided into training samples and test samples, and the training samples were used to train the SVM Baijiu brand classification prediction model with optimal parameters, and the test samples were used to predict the classification of the model. After experimental validation, the recognition rate of the model for classification of Baijiu brands reached 97.83%,which is faster and more effective than traditional classification algorithms such as SVM, and significantly improves the accuracy, and the implementation process of the improved method is also relatively simple. Therefore, the prediction model of Baijiu brand classification based on GA optimized SVM parameters has better practicality and high efficiency.
- Publication
Packaging & Food Machinery, 2022, Vol 40, Issue 2, p64
- ISSN
1005-1295
- Publication type
Article
- DOI
10.3969/j.issn.1005-1295.2022.02.012