• 반도체디스플레이기술학회지
• /
• 제20권2호
• /
• pp.109-114
• /
• 2021

When we inspect scaffold defect using sight, inspecting performance is decrease and inspecting time is increase. We need for automatically scaffold defect detection method to increase detection accuracy and reduce detection times. In this paper. We produced scaffold defect classification models using densenet, alexnet, vggnet algorithms based on CNN. We photographed scaffold using multi dimension camera. We learned scaffold defect classification model using photographed scaffold images. We evaluated the scaffold defect classification accuracy of each models. As result of evaluation, the defect classification performance using densenet algorithm was at 99.1%. The defect classification performance using VGGnet algorithm was at 98.3%. The defect classification performance using Alexnet algorithm was at 96.8%. We were able to quantitatively compare defect classification performance of three type algorithms based on CNN.

• 정보관리학회지
• /
• 제40권3호
• /
• pp.99-118
• /
• 2023

이 연구의 목적은 기록물의 맥락정보를 담고 있는 메타데이터를 활용하여 기록물 자동분류 과정에서의 성능요소를 파악하는데 있다. 연구를 위해 2022년 중앙행정기관 원문정보 약 97,064건을 수집하였다.수집한 데이터를 대상으로 다양한 분류 알고리즘과 데이터선정방법, 문헌표현기법을 적용하고 그 결과를 비교하여 기록물 자동 분류를 위한 최적의 성능요소를 파악하고자 하였다. 연구 결과 분류 알고리즘으로는 Random Forest가, 문헌표현기법으로는 TF 기법이 가장 높은 성능을 보였으며, 단위과제의 최소데이터 수량은 성능에 미치는 영향이 미미하였고 자질은 성능변화에 명확한 영향을 미친다는 것이 확인되었다.

• 한국경영과학회지
• /
• 제32권1호
• /
• pp.61-75
• /
• 2007

The purpose of this paper is to develop a new group classification method based on genetic algorithm and to com-pare its prediction performance with those of existing methods in the area of bond rating. To serve this purpose, we conduct various experiments with pilot and general models. Specifically, we first conduct experiments employing two pilot models : the one searching for the cluster center of each group and the other one searching for both the cluster center and the attribute weights in order to maximize classification accuracy. The results from the pilot experiments show that the performance of the latter in terms of classification accuracy ratio is higher than that of the former which provides the rationale of searching for both the cluster center of each group and the attribute weights to improve classification accuracy. With this lesson in mind, we design two generalized models employing genetic algorithm : the one is to maximize the classification accuracy and the other one is to minimize the total misclassification cost. We compare the performance of these two models with those of existing statistical and artificial intelligent models such as MDA, ANN, and Decision Tree, and conclude that the genetic algorithm-based group classification method that we propose in this paper significantly outperforms the other methods in respect of classification accuracy ratio as well as misclassification cost.

• 한국멀티미디어학회논문지
• /
• 제21권12호
• /
• pp.1417-1424
• /
• 2018

In order to improve the performance of image classifications using Convolutional Neural Networks (CNN), applying a category hierarchy to the classification can be a useful idea. However, the visual separation of object categories is very different according to the upper and lower category levels and highly uneven in image classifications. Therefore, it is doubtable whether the use of category hierarchies for classification is effective in CNN. In this paper, we have clarified whether the image classification using category hierarchies improves classification performance, and found at which level of hierarchy classification is more effective. For experiments we divided the image classification task according to the upper and lower category levels and assigned image data to each CNN model. We identified and compared the results of three classification models and analyzed them. Through the experiments, we could confirm that classification effectiveness was not improved by reduction of number of categories in a classification model. And we found that only with the re-training method in the last network layer, the performance of lower category classification was not improved although that of higher category classification was improved.

• 산업공학
• /
• 제24권2호
• /
• pp.97-104
• /
• 2011

Research for multi-variate classification has been studied through two kinds of procedures which are feature selection and classification. Feature Selection techniques have been applied to select important features and the other one has improved classification performances through classifier applications. In general, each technique has been independently studied, however consideration of the interaction between both procedures has not been widely explored which leads to a degraded performance. In this paper, through integrating these two procedures, classification performance can be improved. The proposed model takes advantage of KBANN (Knowledge-Based Artificial Neural Network) which uses prior knowledge to learn NN (Neural Network) as training information. Each NN learns characteristics of the Feature Selection and Classification techniques as training sets. The integrated NN can be learned again to modify features appropriately and enhance classification performance. This innovative technique is called ALBNN (Algorithm Learning-Based Neural Network). The experiments' results show improved performance in various classification problems.

• 대한산업공학회지
• /
• 제38권4호
• /
• pp.276-284
• /
• 2012

Classification algorithms generally assume that the data is complete. However, missing values are common in real data sets due to various reasons. In this paper, we propose to use locally linear reconstruction (LLR) for missing value imputation to improve the classification performance when missing values exist. We first investigate how much missing values degenerate the classification performance with regard to various missing ratios. Then, we compare the proposed missing value imputation (LLR) with three well-known single imputation methods over three different classifiers using eight data sets. The experimental results showed that (1) any imputation methods, although some of them are very simple, helped to improve the classification accuracy; (2) among the imputation methods, the proposed LLR imputation was the most effective over all missing ratios, and (3) when the missing ratio is relatively high, LLR was outstanding and its classification accuracy was as high as the classification accuracy derived from the compete data set.

• Smart Structures and Systems
• /
• 제23권1호
• /
• pp.71-79
• /
• 2019

In general, it may be advantageous to measure the pressure pulsation near a valve to detect a valve defect in a linear compressor. However, the acceleration signals are more advantageous for rapid classification in a mass-production line. This paper deals with the performance improvement of fault classification using only the compressor-shell acceleration signal based on the relation between the refrigerant pressure pulsation and the shell acceleration of the compressor. A transfer function was estimated experimentally to take into account the signal noise ratio between the pressure pulsation of the refrigerant in the suction pipe and the shell acceleration. The shell acceleration signal of the compressor was modified using this transfer function to improve the defect classification performance. The defect classification of the modified signal was evaluated in the acceleration signal in the frequency domain using Fisher's discriminant ratio (FDR). The defect classification method was validated by experimental data. By using the method presented, the classification of valve defects can be performed rapidly and efficiently during mass production.

• 한국문헌정보학회지
• /
• 제57권2호
• /
• pp.435-452
• /
• 2023

이 연구는 딥러닝 기법의 전이학습 모형인 BERT를 이용하여 주제명의 자동 분류를 실험하고 그 성능을 평가하였으며, 더 나아가 주제명이 부여된 KDC 분류체계와 주제명의 범주 유형에 따른 성능을 분석하였다. 실험 데이터는 국가서지를 이용하여 주제명의 부여 횟수에 따라 6개의 데이터셋을 구축하고 분류 자질로 서명을 이용하였다. 그 결과, 분류 성능으로 3,506개의 주제명이 포함된 데이터셋(레코드 1,539,076건)에서 마이크로 F1과 매크로 F1 척도가 각각 0.6059와 0.5626 값을 보였다. 또한 KDC 분류체계에 따른 분류 성능은 총류, 자연과학, 기술과학, 그리고 언어 분야에서 좋은 성능을 보이며 종교와 예술 분야는 낮은 성능을 보였다. 주제명의 범주 유형에 따른 성능은 '식물', '법률명', '상품명'이 높은 성능을 보인 반면, '국보/보물' 유형의 주제명에서 낮은 성능을 보였다. 다수의 주제명을 포함하는 데이터셋으로 갈수록 분류기가 주제명을 제대로 부여하지 못하는 비율이 늘어나 최종 성능의 하락을 가져오기 때문에, 저빈도 주제명에 대한 분류 성능을 높이기 위한 개선방안이 필요하다.

• 지능정보연구
• /
• 제26권1호
• /
• pp.23-45
• /
• 2020

기업의 경쟁력 확보를 위해 판별 알고리즘을 활용한 의사결정 역량제고가 필요하다. 하지만 대부분 특정 문제영역에는 적합한 판별 알고리즘이 어떤 것인지에 대한 지식은 많지 않아 대부분 시행착오 형식으로 최적 알고리즘을 탐색한다. 즉, 데이터셋의 특성에 따라 어떠한 분류알고리즘을 채택하는 것이 적합한지를 판단하는 것은 전문성과 노력이 소요되는 과업이었다. 이는 메타특징(Meta-Feature)으로 불리는 데이터셋의 특성과 판별 알고리즘 성능과의 연관성에 대한 연구가 아직 충분히 이루어지지 않았기 때문이며, 더구나 다중 클래스(Multi-Class)의 특성을 반영하는 메타특징에 대한 연구 또한 거의 이루어진 바 없다. 이에 본 연구의 목적은 다중 클래스 데이터셋의 메타특징이 판별 알고리즘의 성능에 유의한 영향을 미치는지에 대한 실증 분석을 하는 것이다. 이를 위해 본 연구에서는 다중 클래스 데이터셋의 메타특징을 데이터셋의 구조와 데이터셋의 복잡도라는 두 요인으로 분류하고, 그 안에서 총 7가지 대표 메타특징을 선택하였다. 또한, 본 연구에서는 기존 연구에서 사용하던 IR(Imbalanced Ratio) 대신 시장집중도 측정 지표인 허핀달-허쉬만 지수(Herfindahl-Hirschman Index, HHI)를 메타특징에 포함하였으며, 역ReLU 실루엣 점수(Reverse ReLU Silhouette Score)도 새롭게 제안하였다. UCI Machine Learning Repository에서 제공하는 복수의 벤치마크 데이터셋으로 다양한 변환 데이터셋을 생성한 후에 대표적인 여러 판별 알고리즘에 적용하여 성능 비교 및 가설 검증을 수행하였다. 그 결과 대부분의 메타특징과 판별 성능 사이의 유의한 관련성이 확인되었으며, 일부 예외적인 부분에 대한 고찰을 하였다. 본 연구의 실험 결과는 향후 메타특징에 따른 분류알고리즘 추천 시스템에 활용할 것이다.

• 품질경영학회지
• /
• 제51권1호
• /
• pp.119-129
• /
• 2023

Purpose: This study proposes a classification model for implementing condition-based maintenance (CBM) by monitoring the real-time status of a machine using acceleration sensor data collected from a vehicle. Methods: The classification model's performance was improved by applying Fourier transform to convert the acceleration sensor data from the time domain to the frequency domain. Additionally, the Generative Adversarial Network (GAN) algorithm was used to augment images and further enhance the classification model's performance. Results: Experimental results demonstrate that the GAN algorithm can effectively serve as an image augmentation technique to enhance the performance of the classification model. Consequently, the proposed approach yielded a significant improvement in the classification model's accuracy. Conclusion: While this study focused on the effectiveness of the GAN algorithm as an image augmentation method, further research is necessary to compare its performance with other image augmentation techniques. Additionally, it is essential to consider the potential for performance degradation due to class imbalance and conduct follow-up studies to address this issue.