Unsupervised domain adaptation using fuzzy rules and stochastic hierarchical convolutional neural networks

Abstract

Unsupervised domain adaptation (UDA) describes a set of techniques for using previously acquired knowledge from labeled original data to support task completion in comparable but unlabeled target data. Existing UDA methods often use two classifiers to detect misaligned local areas between the original and prey vocations, resulting in poor implementation. To address this issue, we propose a fuzzy rules and stochastic classifier-based domain adaptation framework called SH-CNN+SMTEOA. Initially, the cross-domain mixed sampling approach is used to test the original and prey data. After that, the Principal Component Analysis is used to extract the characteristics, and fuzzy criteria are used to choose the suitable characteristics. Finally, we introduce the Stochastic Hierarchical Convolutional Neural Network for classification and the Selective Multi-Threshold Entropy Optimization Algorithm for judging a target instance's dependability based on its predictive multi-threshold values. Investigations on UDA benchmark datasets reveal that the proposed method outperforms other methods in classification.