A comparative study to examine principal component analysis and kernel principal component analysis-based weighting layer for convolutional neural networks
| Autor: | Amir Mehrabinezhad, Mohammad Teshnehlab, Arash Sharifi |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2024 |
| Předmět: | |
| Zdroj: | Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, Vol 12, Iss 1 (2024) |
| Druh dokumentu: | article |
| ISSN: | 21681163 2168-1171 2168-1163 |
| DOI: | 10.1080/21681163.2024.2379526 |
| Popis: | In the recent decay, the focus on processing signal data processing such as time series, images, and videos increased. The purpose of this processing is mainly forecasting, classification, and regression. The development of machine learning methods, on the other hand, caused the introduction of novel machine learning-based signal processor models. Convolutional neural networks (CNNs) are the best-known models widely used for signal processing. This work introduces a novel approach by combining PCA with CNNs for signal processing, offering the potential for improved performance in tasks like forecasting, classification, and regression. A comparative analysis of traditional architectures will be crucial in evaluating the effectiveness of the proposed model. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|