KJCKorea
Journal Central

In this paper, we proposes a Convolutional Neural Networks(CNN) equipped with Batch Normalization(BN) for handwritten digit recognition training the MNIST dataset. Aiming to surpass the performance of LeNet-5 by LeCun et al., a 6-layer neural network was designed. The proposed model processes 28x28 pixel images through convolution, Max Pooling, and Fully connected layers, with the batch normalization to improve learning stability and performance. The experiment utilized 60,000 training images and 10,000 test images, applying the Momentum optimization algorithm. The model configuration used 30 filters with a 5x5 filter size, padding 0, stride 1, and ReLU as activation function. The training process was set with a mini-batch size of 100, 20 epochs in total, and a learning rate of 0.1. As a result, the proposed model achieved a test accuracy of 99.22%, surpassing LeNet-5's 99.05%, and recorded an F1-score of 0.9919, demonstrating the model's performance. Moreover, the 6-layer model proposed in this paper emphasizes model efficiency with a simpler structure compared to LeCun et al.'s LeNet-5 (7-layer model) and the model proposed by Ji, Chun and Kim (10-layer model). The results of this study show potential for application in real industrial applications such as AI vision inspection systems. It is expected to be effectively applied in smart factories, particularly in determining the defective status of parts.

In this study, we propose a method to improve the classification accuracy of body mass index (BMI) estimation techniques based on three-dimensional gait data. In previous studies on BMI estimation techniques, the classification accuracy was only about 60%. In this study, we identify the reasons for the low BMI classification accuracy. According to our analysis, the reason is the use of the undersampling technique to address the class imbalance problem in the gait dataset. We propose applying oversampling instead of undersampling to solve the class imbalance issue. We also demonstrate the usefulness of anthropometric and spatiotemporal features in gait data-based BMI estimation techniques. Previous studies evaluated the usefulness of anthropometric and spatiotemporal features in the presence of undersampling techniques and reported that their combined use leads to lower BMI estimation performance than when using either feature alone. However, our results show that using both features together and applying an oversampling technique achieves state-of-the-art performance with 92.92% accuracy in the BMI estimation problem.

This study proposes a novel automation system that integrates Optical Character Recognition (OCR) and Retrieval-Augmented Generation (RAG) technologies to enhance the efficiency of the ESG (Environmental, Social, and Governance) document review process. The proposed system improves text recognition accuracy by applying an ensemble model-based image preprocessing algorithm and hybrid information extraction models in the OCR process. Additionally, the RAG pipeline optimizes information retrieval and answer generation reliability through the implementation of layout analysis algorithms, re-ranking algorithms, and ensemble retrievers. The system's performance was evaluated using certificate images from online portals and corporate internal regulations obtained from various sources, such as the company’s websites. The results demonstrated an accuracy of 93.8% for certification reviews and 92.2% for company regulations reviews, indicating that the proposed system effectively supports human evaluators in the ESG assessment process.