• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.29-38
• /
• 2022

Although image compression is one of the essential technologies to transmit image data on a variety of surveillance and mobile healthcare applications, it causes unnecessary compression artifacts such as blocking and ringing artifacts by the lossy compression in the limited network bandwidth. Recently, image restoration methods using convolutional neural network (CNN) show the significant improvement of image quality from the compressed images. In this paper, we propose Image Denoising Convolutional Neural Networks (IDCNN) to reduce the compression artifacts for the purpose of improving the performance of object classification. In order to evaluate the classification accuracy, we used the ImageNet test dataset consisting of 50,000 natural images and measured the classification performance in terms of Top-1 and Top-5 accuracy. Experimental results show that the proposed IDCNN can improve Top-1 and Top-5 accuracy as high as 2.46% and 2.42%, respectively.

• 한국컴퓨터정보학회논문지
• /
• 제23권4호
• /
• pp.147-153
• /
• 2018

In this paper, we propose an efficient WBC 14-Diff classification which performs using the WBC-ResNet-152, a type of CNN model. The main point of view is to use Super-pixel for the segmentation of the image of WBC, and to use ResNet for the classification of WBC. A total of 136,164 blood image samples (224x224) were grouped for image segmentation, training, training verification, and final test performance analysis. Image segmentation using super-pixels have different number of images for each classes, so weighted average was applied and therefore image segmentation error was low at 7.23%. Using the training data-set for training 50 times, and using soft-max classifier, TPR average of 80.3% for the training set of 8,827 images was achieved. Based on this, using verification data-set of 21,437 images, 14-Diff classification TPR average of normal WBCs were at 93.4% and TPR average of abnormal WBCs were at 83.3%. The result and methodology of this research demonstrates the usefulness of artificial intelligence technology in the blood cell image classification field. WBC-ResNet-152 based morphology approach is shown to be meaningful and worthwhile method. And based on stored medical data, in-depth diagnosis and early detection of curable diseases is expected to improve the quality of treatment.

• 한국측량학회지
• /
• 제27권3호
• /
• pp.331-345
• /
• 2009

본 연구의 목적은 공간데이터 구축공정에 표준으로 적용 가능한 관리방법론을 연구하는데 있다. 우리나라는 아직까지 구축공정 및 품질관리에 대한 체계적인 기준인 정립되지 않은 실정이어서 국가예산이 낭비될 우려의 소지가 있다. 또한 현재 공간데이터 구축과 관련된 법규는 기준이 명확하지 않은 경우가 있어서 공간데이터의 품질에 대한 신뢰성이 부족한 실정이다. 공간데이터의 제작 및 품질검사와 관련이 있는 법규, 국토지리정보원에서 수행한 공간데이터의 품질관련 연구 등 각종 문헌자료, 지방자치단체의 지리정보시스템을 구축한 경험이 있는 주요 업체의 공간데이터 제작공정 및 작업방법에 대하여 조사, 분석하였다. 분석한 내용을 기반으로 GPS에 의한 기준점 측량, 수준측량, 항공사진촬영, 수치지도 제작, 지형도 제작, 수치표고자료 제작, 항공사진 DB 구축, 정사영상지도 제작 등 8개 사업을 대상으로 선정하고 표준화된 관리방법론을 제시하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2004년도 Proceedings of ISRS 2004
• /
• pp.10-13
• /
• 2004

Hyperspectral data has a great advantage to classify various surface materials that are spectrally similar. In this study, we attempted to classify man-made materials in urban area using Hyperion data. Hyperion imagery of Seoul was initially processed to minimize radiometric distortions caused by sensor and atmosphere. Using color aerial photographs. we defined seven man-made surfaces (concrete, asphalt road. railroad, buildings, roof, soil, shadow) for the classification in Seoul. The hyperspectral data showed the potential to identify those manmade materials that were difficult to be classified by multispectral data. However. the classification of road and buildings was not quite satisfactory due to the relatively low spatial resolution of Hyperion image. Further, the low radiometric quality of Hyperion sensor was another limitation for the application in urban area.

• Journal of Information Processing Systems
• /
• 제16권2호
• /
• pp.329-342
• /
• 2020

In recent years, emotional text classification is one of the essential research contents in the field of natural language processing. It has been widely used in the sentiment analysis of commodities like hotels, and other commentary corpus. This paper proposes an improved W-LDA (weighted latent Dirichlet allocation) topic model to improve the shortcomings of traditional LDA topic models. In the process of the topic of word sampling and its word distribution expectation calculation of the Gibbs of the W-LDA topic model. An average weighted value is adopted to avoid topic-related words from being submerged by high-frequency words, to improve the distinction of the topic. It further integrates the highest classification of the algorithm of support vector machine based on the extracted high-quality document-topic distribution and topic-word vectors. Finally, an efficient integration method is constructed for the analysis and extraction of emotional words, topic distribution calculations, and sentiment classification. Through tests on real teaching evaluation data and test set of public comment set, the results show that the method proposed in the paper has distinct advantages compared with other two typical algorithms in terms of subject differentiation, classification precision, and F1-measure.

• Asia pacific journal of information systems
• /
• 제29권4호
• /
• pp.789-816
• /
• 2019

Text classification is a challenging task, especially when dealing with a huge amount of text data. The performance of a classification model can be varied depending on what type of words contained in the document corpus and what type of features generated for classification. Aside from proposing a new modified version of the existing algorithm or creating a new algorithm, we attempt to modify the use of data. The classifier performance is usually affected by the quality of learning data as the classifier is built based on these training data. We assume that the data from different domains might have different characteristics of noise, which can be utilized in the process of learning the classifier. Therefore, we attempt to enhance the robustness of the classifier by injecting the heterogeneous data artificially into the learning process in order to improve the classification accuracy. Semi-supervised approach was applied for utilizing the heterogeneous data in the process of learning the document classifier. However, the performance of document classifier might be degraded by the unlabeled data. Therefore, we further proposed an algorithm to extract only the documents that contribute to the accuracy improvement of the classifier.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 하계종합학술대회 논문집(1)
• /
• pp.171-174
• /
• 2004

Packet classification is an essential architectural component in implementing the quality-of-service (QoS) in today's Internet which provides a best-effort service to ail of its applications. Multiple header fields of incoming packets are compared against a set of rules in packet classification, the highest priority rule among matched rules is selected, and the packet is treated according to the action of the rule. In this Paper, we proposed a new packet classification scheme based on parallel multiple hashing on tuple spaces. Simulation results using real classifiers show that the proposed scheme provides very good performance on the required number of memory accesses and the memory size compared with previous works.

• 한국문헌정보학회지
• /
• 제34권1호
• /
• pp.181-205
• /
• 2000

본 연구는 한국십진분류표와 듀이십진분류표의 최근 판을 비교 분석하여 앞으로 이루어질 한국십진분류표의 개정 방안을 제시하고자 하였다. 두 분류표의 형태서지적 측면, 배열, 보조표와 개요표, 주기, 주제의 표현, 상관색인, 편집 체재, 개정 과정을 구체적인 예를 통해 비교하면서 문제점을 지적하였고 이를 바탕으로 한국십진분류표의 개선되어야할 사항을 제시하였다.

• 농촌계획
• /
• 제14권1호
• /
• pp.33-41
• /
• 2008

The main entrance is even disappeared nowadays when the component type is changed, because it loses the actual function. On the other hand, the type of main entrance is changed variously depended on the materials for house and method of construction. Eleven points in the Chungyang-Gun where the environment of rural villages is well maintained was choosed researched to make data. These data of visual component elements were analysed by using the SPSS 12.0 Windows. Cluster Analysis and Factor Analysis was performed to analyze the different types of main entrance in the rural villages. From the above research, we could conclude below results. Research result, The whole quality of the farming village gate with fine feeling and constant temperature characteristic order appeared with the fact that preference quality is highest, in afterwords was analyzed. Also the research which sees led and the result which appears from the landscape quality analysis which the residential gates are general and type by landscape quality analysis the result which appears with the comparative analysis overcomes the limit which the residential gates are general and type by landscape quality analysis the result which appears with the comparative analysis overcomes the limit which the abstractive landscape image has. Like this research result judges currently the research which is meaning which provides a planning standards and the guideline which the governmental department and the rural village improvement enterprising public opinion rural village residential enterprise which is propelling from oneself are detailed. Specially about landscape quality of the residential gate that presents a type classification and preference quality from the actual condition where the research is insufficient the hereafter rural village improvement enterprise specially, sees with the fact that will be the possibility of affecting is meaning to residential section the succeeding researches actively, there being could be advanced, wishes.

• 경영정보학연구
• /
• 제3권2호
• /
• pp.245-260
• /
• 2001

While past knowledge management researches have focused on conceptualization and strategic implications, knowledge asset researches attempt to provide practical guidelines for companies. However, each research classifies knowledge asset from its own perspective, and thus it is not a trivial task to leverage consistent and inclusive criteria in managing corporate knowledge asset. The objective of this paper is to develop a knowledge asset classification schema on the basis of the three business functions: customer relationship management, product innovation, and infrastructure management. To demonstrate the feasibility of our schema, it has been applied to 9 Korean corporations. Knowledge assets are evaluated according to core capabilities, which are main drivers of sustainable competitive advantages. The results of case study show that the leveraged classification schema reflects current knowledge asset management and characteristics of corporations. Our finding is that most top-quality knowledge management corporations are likely to develop well-balanced knowledge asset.