Semisupervised SVM by Hybrid Whale Optimization Algorithm and Its Application in Oil Layer Recognition

In many fields, such as oil logging, it is expensive to obtain labeled data, and a large amount of inexpensive unlabeled data are not used. Therefore, necessary use semisupervised learning accurate classification with limited data. The support vector machine (S3VM) the most useful method in learning. Nevertheless, S3VM model performance will degrade when sample number categories even or have lots samples. Thus, new SVM by hybrid whale optimization algorithm (HWOA-S3VM) proposed this paper. Firstly, tradeoff control parameter added deal an uneven category which can cause degrade. Then, (HWOA) used optimize parameters increase accuracy. For HWOA improvement, opposition-based cubic mapping initialize WOA population improve convergence speed, catfish effect help jump out local optimum global ability. experiments, firstly, tested 12 classic benchmark functions CEC2005 four CEC2014 compared other five algorithms. six UCI datasets test HWOA-S3VM Finally, we applied perform layer recognition three well datasets. These experimental results show that (1) has higher speed better searchability than (2) accuracy on algorithms combined, labeled, training dataset. (3) superior recognition.