Flower pollination algorithm for convolutional neural network training in vibration classification
A convolutional neural network (CNN) is among the branches in deep learning (DL) which is a new field of research in machine learning. This model artificially mimics the visual cortex to learn the representation of visuals from low to high levels of abstraction and representation to mining data patt...
| Main Authors: | , , , |
|---|---|
| Format: | Book Section |
| Published: |
Springer Science and Business Media Deutschland GmbH
2022
|
| Subjects: |
| _version_ | 1796866959332081664 |
|---|---|
| author | Md. Esa, Md. Fadil Mustaffa, Noorfa Haszlinna Mohamed Radzi, Nor Haizan Sallehuddin, Roselina |
| author_facet | Md. Esa, Md. Fadil Mustaffa, Noorfa Haszlinna Mohamed Radzi, Nor Haizan Sallehuddin, Roselina |
| author_sort | Md. Esa, Md. Fadil |
| collection | ePrints |
| description | A convolutional neural network (CNN) is among the branches in deep learning (DL) which is a new field of research in machine learning. This model artificially mimics the visual cortex to learn the representation of visuals from low to high levels of abstraction and representation to mining data patterns such as image, sound, text, and signal. Despite the proven CNN advantages in various applications, training this model is challenging especially in complex scenarios. Some methods to optimize CNN training have been proposed, such as stochastic and meta-heuristic algorithms. In this paper, we propose a flower pollination algorithm (FPA) to train CNN. A CWRU bearing dataset is used to ensure the accuracy and efficiency of the proposed method. Moreover, we also compare our proposed method with the original CNN. The results show that the proposed method needs to be refined to achieve the required performance of CNN. |
| first_indexed | 2024-03-05T21:19:59Z |
| format | Book Section |
| id | utm.eprints-100878 |
| institution | Universiti Teknologi Malaysia - ePrints |
| last_indexed | 2024-03-05T21:19:59Z |
| publishDate | 2022 |
| publisher | Springer Science and Business Media Deutschland GmbH |
| record_format | dspace |
| spelling | utm.eprints-1008782023-05-18T04:09:55Z http://eprints.utm.my/100878/ Flower pollination algorithm for convolutional neural network training in vibration classification Md. Esa, Md. Fadil Mustaffa, Noorfa Haszlinna Mohamed Radzi, Nor Haizan Sallehuddin, Roselina QA75 Electronic computers. Computer science A convolutional neural network (CNN) is among the branches in deep learning (DL) which is a new field of research in machine learning. This model artificially mimics the visual cortex to learn the representation of visuals from low to high levels of abstraction and representation to mining data patterns such as image, sound, text, and signal. Despite the proven CNN advantages in various applications, training this model is challenging especially in complex scenarios. Some methods to optimize CNN training have been proposed, such as stochastic and meta-heuristic algorithms. In this paper, we propose a flower pollination algorithm (FPA) to train CNN. A CWRU bearing dataset is used to ensure the accuracy and efficiency of the proposed method. Moreover, we also compare our proposed method with the original CNN. The results show that the proposed method needs to be refined to achieve the required performance of CNN. Springer Science and Business Media Deutschland GmbH 2022 Book Section PeerReviewed Md. Esa, Md. Fadil and Mustaffa, Noorfa Haszlinna and Mohamed Radzi, Nor Haizan and Sallehuddin, Roselina (2022) Flower pollination algorithm for convolutional neural network training in vibration classification. In: Computational Intelligence in Machine Learning Select Proceedings of ICCIML 2021. Lecture Notes in Electrical Engineering, 834 (NA). Springer Science and Business Media Deutschland GmbH, Singapore, pp. 339-346. ISBN 978-981168483-8 http://dx.doi.org/10.1007/978-981-16-8484-5_32 DOI:10.1007/978-981-16-8484-5_32 |
| spellingShingle | QA75 Electronic computers. Computer science Md. Esa, Md. Fadil Mustaffa, Noorfa Haszlinna Mohamed Radzi, Nor Haizan Sallehuddin, Roselina Flower pollination algorithm for convolutional neural network training in vibration classification |
| title | Flower pollination algorithm for convolutional neural network training in vibration classification |
| title_full | Flower pollination algorithm for convolutional neural network training in vibration classification |
| title_fullStr | Flower pollination algorithm for convolutional neural network training in vibration classification |
| title_full_unstemmed | Flower pollination algorithm for convolutional neural network training in vibration classification |
| title_short | Flower pollination algorithm for convolutional neural network training in vibration classification |
| title_sort | flower pollination algorithm for convolutional neural network training in vibration classification |
| topic | QA75 Electronic computers. Computer science |
| work_keys_str_mv | AT mdesamdfadil flowerpollinationalgorithmforconvolutionalneuralnetworktraininginvibrationclassification AT mustaffanoorfahaszlinna flowerpollinationalgorithmforconvolutionalneuralnetworktraininginvibrationclassification AT mohamedradzinorhaizan flowerpollinationalgorithmforconvolutionalneuralnetworktraininginvibrationclassification AT sallehuddinroselina flowerpollinationalgorithmforconvolutionalneuralnetworktraininginvibrationclassification |