Imbalanced object classification using a new convolutional neural network and principal component analysis

Key Points

• The new convolutional neural network improves classification accuracy in imbalanced datasets, directly addressing this common challenge.
• Achieved an increase in classification accuracy of over 15% compared to traditional methods, showcasing the effectiveness of the model.
• Analysis employed principal component analysis for feature extraction, enhancing the learning process and model performance.
• Implications highlight the need for advanced algorithms to tackle imbalanced data, a pervasive issue in machine learning tasks.