• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10a
• /
• pp.592-594
• /
• 2001

두 문자열의 부분배치(local alignment)를 찾는 대표적인 알고리즘인 Smith-Waterman 알고리즘(SW 알고리즘)은 정규화된 최적부분배치를 찾지 못하는 단점이 있다. 최근에 fractional programming 기법을 이용하여 여러 번의 SW 알고리즘을 수행함으로써 정규화된 최적부분배티를 찾는 알고리즘이 제시되었지만 이는 매우 많은 시간이 걸린다. 본 논문에서는 fractional programming 기법을 이용하여 정규화된 최적부분배치를 찾는 알고리즘에, 완전매치(Exact Match)을 이용한 휴리스틱 기법인 Banded SW 알고리즘을 적용하여, 낮은 오차를 가지면서 실용적으로 매우 빠른 정규화된 최적부분배치를 찾는 알고리즘을 제시하고 이 알고리즘과 제시하고 이 알고리즘과 기존의 알고리즘을 직접 구현하여 실험한 결과를 비교 분석한다.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.35-42
• /
• 2018

Deep learning is known as a method of high accuracy among several methods for image classification. In this paper, we propose a method of enhancing the accuracy of image classification using CNN with a batch normalization method for classification of images using deep CNN (Convolutional Neural Network). In this paper, we propose a method to add a batch normalization layer to existing neural networks to enhance the accuracy of image classification. Batch normalization is a method to calculate and move the average and variance of each batch for reducing the deflection in each layer. In order to prove the superiority of the proposed method, Accuracy and mAP are measured by image classification experiments using five image data sets SHREC13, MNIST, SVHN, CIFAR-10, and CIFAR-100. Experimental results showed that the CNN with batch normalization is better classification accuracy and mAP rather than using the conventional CNN.

• Korean Journal of Remote Sensing
• /
• v.36 no.2_1
• /
• pp.199-215
• /
• 2020

A seagrass that is marine vascular plants plays an important role in the marine ecosystem, so periodic monitoring ofseagrass habitatsis being performed. Recently, the use of dronesthat can easily acquire very high-resolution imagery is increasing to efficiently monitor seagrass habitats. And deep learning based on a convolutional neural network has shown excellent performance in semantic segmentation. So, studies applied to deep learning models have been actively conducted in remote sensing. However, the segmentation accuracy was different due to the hyperparameter, various deep learning models and imagery. And the normalization of the image and the tile and batch size are also not standardized. So,seagrass habitats were segmented from drone-borne imagery using a deep learning that shows excellent performance in this study. And it compared and analyzed the results focused on normalization and tile size. For comparison of the results according to the normalization, tile and batch size, a grayscale image and grayscale imagery converted to Z-score and Min-Max normalization methods were used. And the tile size isincreased at a specific interval while the batch size is allowed the memory size to be used as much as possible. As a result, IoU was 0.26 ~ 0.4 higher than that of Z-score normalized imagery than other imagery. Also, it wasfound that the difference to 0.09 depending on the tile and batch size. The results were different according to the normalization, tile and batch. Therefore, this experiment found that these factors should have a suitable decision process.

• Journal of KIISE:Computer Systems and Theory
• /
• v.27 no.12
• /
• pp.988-995
• /
• 2000

각 모듈들의 위치가 배치 알고리즘에 의해 결정된 후에도 모듈들을 종축 또는 횡축을 중심으로 뒤집거나 회전시킴으로써 회로의 효율성과 연결성을 향상시킬 수 있다. 고집적 회로설계의 한 단계인 모듈방향 결정 문제는 모듈간에 연결된 선의 길이의 합이 최소가 되도록 각 모듈의 방향을 결정하는 문제이다. 최근에 평균장 어닐링 방법이 조합적 최적화 문제에 사용되어 좋은 결과를 보여 주고 있다. 평균장 어닐링은 신경회로망의 따른 수렴 특성과 시뮬레이티드 어닐링의 우수한 해를 생성하는 특성이 결합된 방법이다. 본 논문에서는 정규화된 평균장 어닐링을 사용해서 모듈 방향 결정 문제를 해결하였고 실험을 통해 기존의 Hopfield 네트워크 방법과 시뮬레이티드 어닐링과 그 결과를 비교하였다. 시뮬레이티드 어닐링, 정규화된 평균장 어닐링과 Hopfield 네트워크의 총 길이 감소율은 각각 19.86%, 19.85%, 19.03%였으며, 정규화된 평균장 어닐링의 실행 시간은 Hopfield 네트워크보다는 1.1배, 시뮬레이티드 어닐링보다는 11.4배 정도 빨랐다.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.9
• /
• pp.1-7
• /
• 2024

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 28×28 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 5×5 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.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.319-328
• /
• 2022

Bearing plays an important role in the operation of most machinery, Therefore, when a defect occurs in the bearing, a fatal defect throughout the machine is generated. In this reason, bearing defects should be detected early. In this paper, we describe a method using Convolutional Neural Networks (SN-CNNs) based on continuous wavelet transformations and Switchable normalization for bearing defect detection models. The accuracy of the model was measured using the Case Western Reserve University (CWRU) bearing dataset. In addition, batch normalization methods and spectrogram images are used to compare model performance. The proposed model achieved over 99% testing accuracy in CWRU dataset.

• Annual Conference of KIPS
• /
• 2021.11a
• /
• pp.899-902
• /
• 2021

본 논문은 이미지 저작권 유무 판별을 분류 문제로 정의하고 기계학습과 합성곱 신경망 모델을 적용하여 해결한다. 학습을 위해 입력 데이터를 고정된 크기로 변환하고 정규화 과정을 수행하여 학습 데이터셋을 준비한다. 저작권 유무 판별 실험에서 SVM, k-NN, 랜덤포레스트, VGG-Net 모델의 분류 성능을 비교 분석한다. VGG-Net C 모델의 결과가 다른 알고리즘과 비교 시 10.65% 높은 성능을 나타냈으며 배치 정규화 층을 이용하여 과적합 현상을 개선했다.

• Journal of the Korea Convergence Society
• /
• v.11 no.10
• /
• pp.45-51
• /
• 2020

Recently, many games provide data related to the users' game play, and there have been a few studies that predict opponent move by combining machine learning methods. This study predicts opponent move using match data of a real-time strategy game named ClashRoyale and a multi-label classification based on machine learning. In the initial experiment, binary card properties, binary card coordinates, and normalized time information are input, and card type and card coordinates are predicted using random forest and multi-layer perceptron. Subsequently, experiments were conducted sequentially using the next three data preprocessing methods. First, some property information of the input data were transformed. Next, input data were converted to nested form considering the consecutive card input system. Finally, input data were predicted by dividing into the early and the latter according to the normalized time information. As a result, the best preprocessing step was shown about 2.6% improvement in card type and about 1.8% improvement in card coordinates when nested data divided into the early.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.75-80
• /
• 2017

In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.

• Journal of Korean Library and Information Science Society
• /
• v.55 no.1
• /
• pp.123-143
• /
• 2024

In this study, we analyzed the trends in staffing changes in academic libraries over the past ten years and surveyed staff working there to assess their perceptions of staffing levels and the current criteria for staffing allocation in academic libraries. We utilized statistical data from academic libraries to analyze staffing changes from 2014 to 2023. The survey was conducted through an online questionnaire targeting library staff, and responses from 216 respondents from 4-year universities and junior colleges were analyzed. The analysis of staffing changes revealed a decrease in the average number of employees in large 4-year universities and junior colleges, with a decrease in regular positions and an increase in non-regular positions. Survey results suggest causes such as declining school-age population and admissions quotas, budget shortages in universities, and structural adjustments. The perception of staff from 4-year universities and junior colleges regarding the criteria for staffing allocation was mainly negative, suggesting improvements such as increasing and refining criteria numbers, specifying standards for full-time librarians, clarifying criteria for compliance, and enhancing enforcement of standards. The results of this study can enhance understanding of staffing situations in academic libraries and serve as fundamental data for improving staffing criteria in the future, based on an understanding of librarians' perceptions on the ground.