• Journal of the Korea Computer Graphics Society
• /
• v.28 no.2
• /
• pp.11-19
• /
• 2022

Recently, various researches on medical image generation have been suggested, and it becomes crucial to accurately evaluate the quality and diversity of the generated medical images. For this purpose, the expert's visual turing test, feature distribution visualization, and quantitative evaluation through IS and FID are evaluated. However, there are few methods for quantitatively evaluating medical images in terms of fidelity and diversity. In this paper, images are generated by learning a chest CT dataset of non-small cell lung cancer patients through DCGAN and PGGAN generative models, and the performance of the two generative models are evaluated in terms of fidelity and diversity. The performance is quantitatively evaluated through IS and FID, which are one-dimensional score-based evaluation methods, and Precision and Recall, Improved Precision and Recall, which are two-dimensional score-based evaluation methods, and the characteristics and limitations of each evaluation method are also analyzed in medical imaging.

• Journal of the Korean Society for information Management
• /
• v.13 no.1
• /
• pp.65-82
• /
• 1996

The aim of this study is to identify how searchers reflect the search goal requirements associated with search questions in process and outcome. One query which has two different search goal requirements was given to subjects, that is, one is to increase high precision and the other is to increase high recall. Using ERIC ONTAP file through DIALOG online search system, 54 subjects conducted online searches twice for the high precision search and for the high recall search. Subjects employed significantly different search strategies, invested significantly different efforts, and achieved significantly different results between the high precision and the high recall search.

• International Journal of Computer Science & Network Security
• /
• v.24 no.1
• /
• pp.119-126
• /
• 2024

Disease caused by the coronavirus (COVID-19) is sweeping the globe. There are numerous methods for identifying this disease using a chest imaging. Computerized Tomography (CT) chest scans are used in this study to detect COVID-19 disease using a pretrain Convolutional Neural Network (CNN) ResNet50. This model is based on image dataset taken from two hospitals and used to identify Covid-19 illnesses. The pre-train CNN (ResNet50) architecture was used for feature extraction, and then fully connected layers were used for classification, yielding 97%, 96%, 96%, 96% for accuracy, precision, recall, and F1-score, respectively. When combining the feature extraction techniques with the Back Propagation Neural Network (BPNN), it produced accuracy, precision, recall, and F1-scores of 92.5%, 83%, 92%, and 87.3%. In our suggested approach, we use a preprocessing phase to improve accuracy. The image was enhanced using the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm, which was followed by cropping the image before feature extraction with ResNet50. Finally, a fully connected layer was added for classification, with results of 99.1%, 98.7%, 99%, 98.8% in terms of accuracy, precision, recall, and F1-score.

• Journal of KIISE
• /
• v.42 no.5
• /
• pp.629-636
• /
• 2015

The types of errors corrected by a Korean spelling and grammar checker can be classified into isolated-term spelling errors and context-sensitive spelling errors (CSSE). CSSEs are difficult to detect and to correct, since they are correct words when examined alone. Thus, they can be corrected only by considering the semantic and syntactic relations to their context. CSSEs, which are frequently made even by expert wiriters, significantly affect the reliability of spelling and grammar checkers. An existing Korean spelling and grammar checker developed by P University (KSGC 4.5) adopts hand-made correction rules for correcting CSSEs. The KSGC 4.5 is designed to obtain very high precision, which results in an extremely low recall. Our overall goal of previous works was to improve the recall without considerably lowering the precision, by generalizing CSSE correction rules that mainly depend on linguistic knowledge. A variety of rule-based methods has been proposed in previous works, and the best performance showed 95.19% of average precision and 37.56% of recall. This study thus proposes a statistics based method using a conditional probability model with dynamic window sizes. in order to further improve the recall. The proposed method obtained 97.23% of average precision and 50.50% of recall.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.11
• /
• pp.1027-1033
• /
• 2012

Semantic-based information retrieval techniques understand the meanings of the concepts that users specify in their queries, but the traditional semantic matching methods based on the ontology tree have three weaknesses which may lead to many false matches, causing the falling precision. In order to improve the matching precision and the recall of the information retrieval, this paper proposes a multi-agent improved semantic similarity matching algorithm based on the ontology tree, which can avoid the considerable computation redundancies and mismatching during the entire matching process. The results of the experiments performed on our algorithm show improvements in precision and recall compared with the information retrieval techniques based on the traditional semantic similarity matching methods.

• Journal of Biomedical Engineering Research
• /
• v.43 no.1
• /
• pp.45-51
• /
• 2022

The purpose of this study is to improve the classification accuracy compared to the existing InceptionV3 model by proposing a new model modified with the fully connected hierarchical structure of InceptionV3, which showed excellent performance in medical image classification. The data used for model training were trained after data augmentation on a total of 1026 chest X-ray images of patients diagnosed with normal heart and Cardiomegaly at Kyungpook National University Hospital. As a result of the experiment, the learning classification accuracy and loss of the InceptionV3 model were 99.57% and 1.42, and the accuracy and loss of the proposed model were 99.81% and 0.92. As a result of the classification performance evaluation for precision, recall, and F1 score of Inception V3, the precision of the normal heart was 78%, the recall rate was 100%, and the F1 score was 88. The classification accuracy for Cardiomegaly was 100%, the recall rate was 78%, and the F1 score was 88. On the other hand, in the case of the proposed model, the accuracy for a normal heart was 100%, the recall rate was 92%, and the F1 score was 96. The classification accuracy for Cardiomegaly was 95%, the recall rate was 100%, and the F1 score was 97. If the chest X-ray image for normal heart and Cardiomegaly can be classified using the model proposed based on the study results, better classification will be possible and the reliability of classification performance will gradually increase.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.6
• /
• pp.609-616
• /
• 2016

This paper is proposed a customized market analysis method using SVM and collaborative filtering. The proposed customized market analysis scheme is consists of DC(Data Classification) module, ICF(Improved Collaborative Filtering) module, and CMA(Customized Market Analysis) module. DC module classifies the characteristics of on-line and off-line shopping mall and traditional markets into price, quality, and quantity using SVM. ICF module calculates the similarity by adding age weight and job weight, and generates network using the similarity of purchased item each users, and makes a recommendation list of neighbor nodes. And CMA module provides the result of customized market analysis using the data classification result of DC module and the recommendation list of ICF module. As a result of comparing the proposed customized recommendation list with the existing user based recommendation list, the case of recommendation list using the existing collaborative filtering scheme, precision is 0.53, recall is 0.56, and F-measure is 0.57. But the case of proposed customized recommendation list, precision is 0.78, recall is 0.85, and F-measure is 0.81. That is, the proposed customized recommendation list shows more precision.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.637-641
• /
• 2009

In this paper, we propose a line composition based searching system which retrieves compositionally similar photo from the DB of the line-compositional photos. To develop the measure of compositional similarity, we carried out a survey to find which feature is discriminative for retrieving. Based on the results of the survey, we developed the measure of compositional similarity and it was applied the proposed searching system. We also show the results of the recall and the precision to evaluate the performance of the proposed system.

• Journal of Korean Library and Information Science Society
• /
• v.27
• /
• pp.457-483
• /
• 1997

This study was intended to compare the effectiveness of the Savvy search and Metacrawler in terms of the total number of relevant documents retrieved, precision, recall, and the number of deadlines. In addition, this study measured whether the Meta-search engine and general web search engines retrieved different web documents. As a result, Savvy search produced a higher precision and recall as compared with motacrawler search engine while the metacrawler had lower deadlines ration than savvy search, Also, Meta search engine was more effective than the general web search engine, The results show that the hybrid methodology of integrating a variety of web search engines can help solve retrieval effectiveness problems on the Internet.

• The Journal of the Korea Contents Association
• /
• v.4 no.1
• /
• pp.76-82
• /
• 2004

In this paper, we used query evaluation method through thesaurus for retrieving Components having concept relation with any classes in a query. Queries are presented in boolean and expanded by similar table. Query expansion by thesaurus is the solution of the term mismatching and it enhanced precision and recall of the components retrieval. For efficiency evaluation of query expansion, we defined most critical value through a simulation and compared precision and recall each other.