Enhancing DCNN model performance: Experimental analysis based on data augmentation
- 16 April 2025
- journal article
- Published by World Scientific Pub Co Pte Ltd in Analysis and Applications
- Vol. 23 (05) , 635-654
Abstract
Deep Convolutional Neural Networks (DCNNs), as a state-of-the-art machine learning technique, have attracted significant attention due to their remarkable performance in data classification, clustering, and pattern recognition. Owing to the DCNN model’s ability to utilize convolution kernels for feature extraction from input data while effectively exploiting local correlations enables it to achieve optimal prediction results, particularly when forecasting large datasets. However, practical scenarios often involve small sample sizes, which significantly diminishes model accuracy. In response to this limitation, this study introduces three data augmentation algorithms aimed at enhancing DCNN precision in contexts with limited sample data. Notably, the Generative Adversarial Network (GAN) augmentation algorithm not only expands the dataset but also incorporates a discriminator to assess the authenticity of generated samples in comparison to the original ones. This methodology ensures that the augmented data closely approximates real samples, thereby facilitating superior predictive performance by the DCNN model. By integrating three oversampling methods with DCNN and applying them to the identification of acid radical ion ligand binding sites, we trained the DCNN using augmented datasets produced through various oversampling techniques. The predictive model derived from the training dataset was independently validated on the test set, revealing that the outcomes achieved with the GAN-DCNN algorithm were optimal and surpassed previous predictions. This finding underscores the exceptional effectiveness of GAN-DCNN in addressing small sample classification challenges.Keywords
Funding Information
- Natural Science Foundation of China (61961032)
- the Natural Science Foundation of Inner Mongolia of China (2024MS06027)
- the Operation expenses basic scientific research of Inner Mongolia of China (JY20230067)
This publication has 25 references indexed in Scilit:
- Probing ion-binding at a protein interface: Modulation of protein properties by ionic liquidsJournal of Colloid and Interface Science, 2023
- Metal3D: a general deep learning framework for accurate metal ion location prediction in proteinsNature Communications, 2023
- Recognizing protein-metal ion ligands binding residues by random forest algorithm with adding orthogonal propertiesComputational Biology and Chemistry, 2022
- Importance of interface and surface areas in protein-protein binding affinity prediction: A machine learning analysis based on linear regression and artificial neural networkBiophysical Chemistry, 2022
- Reveal training performance mystery between TensorFlow and PyTorch in the single GPU environmentScience China Information Sciences, 2021
- Logistic matrix factorisation and generative adversarial neural network-based method for predicting drug-target interactionsMolecular Diversity, 2021
- SciANN: A Keras/TensorFlow wrapper for scientific computations and physics-informed deep learning using artificial neural networksComputer Methods in Applied Mechanics and Engineering, 2021
- Evaluating Learning Algorithms2011
- Transport, binding, and metabolism of sulfate conjugates in the liverChemico-Biological Interactions, 1994
- Statistical analysis of the physical properties of the 20 naturally occurring amino acidsThe Protein Journal, 1985