ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Dimensionality Reduction based Classification Using Generative Adversarial Networks Dataset Generation


Affiliations
1 Department of Electronics and Instrumentation Engineering, Annamalai University, India
     

   Subscribe/Renew Journal


The term data augmentation refers to an approach that can be used to prevent overfitting in the training dataset, which is where the issue first manifests itself. This is based on the assumption that extra datasets can be improved by include new information that is of use. It is feasible to create an artificially larger training dataset by utilizing methods such as data warping and oversampling. This will allow for the creation of more accurate models. This idea is demonstrated through the application of a variety of different methods, some of which include neural style transfer, adversarial training, and erasure by random erasure, amongst others. By utilizing oversampling augmentations, it is feasible to create synthetic instances that can be incorporated into the training data. This is made possible by the generation of synthetic instances. There are numerous illustrations of this, including image merging, feature space enhancements, and generative adversarial networks, to name a few (GANs). In this paper, we aim to provide evidence that a Generative Adversarial Network can be used to convert regular images into Hyper Spectral Images (HSI). The purpose of the model is to generate data by including a certain amount of unpredictable noise.

Keywords

Data Augmentation, GAN, Hyper Spectral Images, Classification.
Subscription Login to verify subscription
User
Notifications
Font Size

  • Ian Goodfellow and Yoshua Bengio, “Generative Adversarial Networks”, Communications of the ACM, Vol. 63, No. 11, pp. 139-144, 2020.

  • Z. Xu, Jiawei Luo and Zehao Xiong, “scSemiGAN: A Single-Cell Semi-Supervised Annotation and Dimensionality Reduction Framework based on Generative Adversarial Network”, Bioinformatics, Vol. 83, No. 2, pp. 1-14, 2022.

  • Farajzadeh Zanjani, Maryam, Ehsan Hallaji, Roozbeh Razavi Far and Mehrdad Saif, “Generative Adversarial Dimensionality Reduction for Diagnosing Faults and Attacks in Cyber-Physical Systems”, Neurocomputing, Vol. 440, pp. 101-110, 2021.

  • E. Lin, C. Lin and H.Y. Lane, “Relevant Applications of Generative Adversarial Networks in Drug Design and Discovery: Molecular De Novo Design, Dimensionality Reduction, and De Novo Peptide and Protein Design”, Molecules, Vol. 25, No. 14, pp. 3250-3265, 2020.

  • H. Ding, L. Chen and X. Cui, “Imbalanced Data Classification: A KNN and Generative Adversarial Networks-Based Hybrid Approach for Intrusion Detection”, Future Generation Computer Systems, Vol. 131, pp. 240-254, 2022.

  • S. Chan and A.H. Elsheikh, “Parametrization of Stochastic Inputs using Generative Adversarial Networks with Application in Geology”, Frontiers in Water, Vol. 2, pp. 1-5, 2020.

  • D. Li, C. Du and H. He, “Semi-Supervised Cross-Modal Image Generation with Generative Adversarial Networks”, Pattern Recognition, Vol. 100, pp. 107085-107098, 2020.

  • S. Latif, S., Jurdak and B.W. Schuller, “Augmenting Generative Adversarial Networks for Speech Emotion Recognition”, Proceedings of International Conference on Recent Trends in Computer Science, pp. 1-8, 2020.

  • M. Marouf, P. Machart, V. Bansal, C. Kilian and S. Bonn, “Realistic in Silico Generation and Augmentation of Single-Cell RNA-Seq Data using Generative Adversarial Networks”, Nature Communications, Vol. 11, No. 1, pp. 1-12, 2020.

  • F. Zhu, F. Ye, Y. Fu, Q. Liu and B. Shen, “Electrocardiogram Generation with a Bidirectional LSTM-CNN Generative Adversarial Network”, Scientific Reports, Vol. 9, No. 1, pp. 1-11, 2019.

  • J. Viola, Y. Chen and J. Wang, “FaultFace: Deep Convolutional Generative Adversarial Network (DCGAN) based Ball-Bearing Failure Detection Method”, Information Sciences, Vol. 542, pp. 195-211, 2021.

  • Z. Zhong, J. Li and A. Wong, “Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification”, IEEE Transactions on Cybernetics, Vol. 50, No. 7, pp. 3318-3329, 2019.

  • S. Surana, P. Arora, D. Singh, D. Sahasrabuddhe and J. Valadi, “Pandoragan: Generating Antiviral Peptides using Generative Adversarial Network”, Proceedings of International Conference on Machine Learning, pp. 1-7, 2021.

  • J. Feng, J. Chen, X., Zhang and T. Yu, “Generative Adversarial Networks based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification”, Remote Sensing, Vol. 12, No. 7, pp. 1149- 1162, 2020.

  • H. Nguyen, D. Zhuang, P.Y. Wu and M. Chang, “Autogan-based Dimension Reduction for Privacy Preservation”, Neurocomputing, Vol. 384, pp. 94-103, 2020.

  • W. Zhao, J. Chen and Y. Qu, “Sample Generation with Self-Attention Generative Adversarial Adaptation Network (SaGAAN) for Hyperspectral Image Classification”, Remote Sensing, Vol. 12, No. 5, pp. 843-852, 2020.


Abstract Views: 75

PDF Views: 1




  • Dimensionality Reduction based Classification Using Generative Adversarial Networks Dataset Generation

Abstract Views: 75  |  PDF Views: 1

Authors

G. Narendra
Department of Electronics and Instrumentation Engineering, Annamalai University, India
D. Sivakumar
Department of Electronics and Instrumentation Engineering, Annamalai University, India

Abstract


The term data augmentation refers to an approach that can be used to prevent overfitting in the training dataset, which is where the issue first manifests itself. This is based on the assumption that extra datasets can be improved by include new information that is of use. It is feasible to create an artificially larger training dataset by utilizing methods such as data warping and oversampling. This will allow for the creation of more accurate models. This idea is demonstrated through the application of a variety of different methods, some of which include neural style transfer, adversarial training, and erasure by random erasure, amongst others. By utilizing oversampling augmentations, it is feasible to create synthetic instances that can be incorporated into the training data. This is made possible by the generation of synthetic instances. There are numerous illustrations of this, including image merging, feature space enhancements, and generative adversarial networks, to name a few (GANs). In this paper, we aim to provide evidence that a Generative Adversarial Network can be used to convert regular images into Hyper Spectral Images (HSI). The purpose of the model is to generate data by including a certain amount of unpredictable noise.

Keywords


Data Augmentation, GAN, Hyper Spectral Images, Classification.

References