Low Hong Yi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Low Hong Yi has a total of 2 co-authors. Here are the top co-authors by number of shared publications:
- Abdul Salam Shah
Taylor's University, Malaysia
1 shared publication - Manzoor Hussain
Indus University
1 shared publication
Latest Publications
- Open Access
- 27 May 2026
- Published by MDPI AG in Preprints.org
Analysis of Mild Overfitting, Class-Level Performance, and Future Directions in AI-Driven Fashion
The given research paper describes a CNN model of classifying images belonging to more than two classes on the Fashion-MNIST data. The model performed a test accuracy of 92.44% and test loss of 0.2533 the greatest accuracy as compared to similar studies with similar architectures. The architecture has three convolutional-pooling blocks, a dense layer with dropout regularization (0.3), and a softmax output layer. The analysis of training and validation curves demonstrates mild overfitting of the later epochs, and the validation loss starts growing even though the training loss continues to decrease. In-depth analysis using confusion matrix and classification report identifies certain patterns of misclassification between visually similar categories. The paper also discusses implications on batch normalization, data augmentation as well as Vision Transformer architecture.
- 27 May 2026
- Published by MDPI AG in Preprints.org
Open AccessAnalysis of Mild Overfitting, Class-Level Performance, and Future Directions in AI-Driven Fashion
The given research paper describes a CNN model of classifying images belonging to more than two classes on the Fashion-MNIST data. The model performed a test accuracy of 92.44% and test loss of 0.2533 the greatest accuracy as compared to similar studies with similar architectures. The architecture has three convolutional-pooling blocks, a dense layer with dropout regularization (0.3), and a softmax output layer. The analysis of training and validation curves demonstrates mild overfitting of the later epochs, and the validation loss starts growing even though the training loss continues to decrease. In-depth analysis using confusion matrix and classification report identifies certain patterns of misclassification between visually similar categories. The paper also discusses implications on batch normalization, data augmentation as well as Vision Transformer architecture.