• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.399-401
• /
• 2022

A definitive diagnosis to classify the breast malignancy status may be achieved by microscopic analysis using surgical open biopsy. However, this procedure requires experts in the specializing of histopathological image analysis directing to time-consuming and high cost. To overcome these issues, deep learning is considered practically efficient to categorize breast cancer into benign and malignant from histopathological images in order to assist pathologists. This study presents a pre-trained convolutional neural network model architecture with a 100% fine-tuning scheme and Adagrad optimizer to classify the breast cancer histopathological images into benign and malignant using a 40× magnification BreaKHis dataset. The pre-trained architecture was constructed using the InceptionResNetV2 model to generate a modified InceptionResNetV2 by substituting the last layer with dense and dropout layers. The results by demonstrating training loss of 0.25%, training accuracy of 99.96%, validation loss of 3.10%, validation accuracy of 99.41%, test loss of 8.46%, and test accuracy of 98.75% indicated that the modified InceptionResNetV2 model is reliable to predict the breast malignancy type from histopathological images. Future works are necessary to focus on k-fold cross-validation, optimizer, model, hyperparameter optimization, and classification on 100×, 200×, and 400× magnification.

• Journal of Digital Contents Society
• /
• v.7 no.2
• /
• pp.95-102
• /
• 2006

To meet the high demand of the experts in the multimedia industry, many colleges opened the subject related to multimedia technology and pre-learning has been rapidly increasing among the students. However, most instructor is still appling the traditional teaching model rather than the one customized for the pre-learner of multimedia. This paper is to reveal the pre-learner's strong desire in detail and suggest the characteristics of the teaching model and teaching materials. We applied the new paradigm, constructivism and problem-based learning, which rising in the educational literature to suggest and design the lecture model to bring up the experts in the multimedia industry.

• Journal of Korea Multimedia Society
• /
• v.14 no.11
• /
• pp.1491-1499
• /
• 2011

Now a days, to make good use of tags is a general tendency when users need to upload or search some multimedia data such as images and videos on the Web. In this paper, we introduce an approach to calculate semantic importance of tags and to make re-ranking with them on tagged Web image retrieval. Generally, most photo images stored on the Web have lots of tags added with user's subjective judgements not by the importance of them. So they become the cause of precision rate decrease with simple matching of tags to a given query. Therefore, if we can select semantically important tags and employ them on the image search, the retrieval result would be enhanced. In this paper, we propose a method to make image retrieval re-ranking with the key tags which share more semantic information with a query or other tags based on Wikipedia-based semantic relatedness. With the semantic relatedness calculated by using huge on-line encyclopedia, Wikipedia, we found the superiority of our method in precision and recall rate as experimental results.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.2
• /
• pp.465-470
• /
• 2024

The advancement of AI-based image generation technology has resulted in the creation of various images, emphasizing the need for technology capable of accurately discerning them. The amount of generated image data is limited, and to achieve high performance with a limited dataset, this study proposes a model for discriminating generated images using transfer learning. Applying pre-trained models from the ImageNet dataset directly to the CIFAKE input dataset, we reduce training time cost followed by adding three hidden layers and one output layer to fine-tune the model. The modeling results revealed an improvement in the performance of the model when adjusting the final layer. Using transfer learning and then adjusting layers close to the output layer, small image data-related accuracy issues can be reduced and generated images can be classified.

• The Journal of the Korea Contents Association
• /
• v.15 no.5
• /
• pp.47-54
• /
• 2015

The following research analyzes that the level of self-monitoring have an influence on user experience about website. For this research, university students participated in a survey where they evaluated user experience -usability, aesthetics, pleasure- about the new screen images of two homepages of differences in brand recognizability. The "self-monitoring(high/low, except for middle)" and the "brand recognizability(high/low, except for middle)" were set as independent variables and the "usability | deviation |", the "aesthetics | deviation |", the "pleasure | deviation |" were set as the dependent variables. Results, as with new screen images of homepage, there were significant differences in the usability and aesthetics based on the level in self-monitoring. Especially, when level of brand recognizability is low, there was more differences in the usability and aesthetics based on the level in self-monitoring. However, the influence of pleasure on self-monitoring was insignificant.

• Journal of Global Scholars of Marketing Science
• /
• v.11
• /
• pp.59-78
• /
• 2003

Thus the purpose of this study is to determine how the brand equity is formed in the psychological process of customers by reviewing previous studies of relations between marketing factors influencing the formation and elements for the formation. Results of the study and their suggestions can be summarized as follows. First, among precedent factors required for the formation of the brand equity, advertisement was found having positive effects on both brand awareness and brand image irrespective of the two groups, or high and low involvement groups. Sales promotion did not have any effects on both brand awareness and brand image in the low involvement group while positively affecting brand awareness in the high involvement group. Distribution intensity was found having effects on both brand awareness and brand image in all of the two groups. Second, relations between brand awareness and brand image showed that the former has effects on the latter in both high and low involvement groups. This suggests that brand awareness plays a role in associating brand image. Third, relations among brand awareness, brand image and brand preference showed that both of the former twos influence the other in the high involvement group and that brand awareness cannot influence brand preference in the low involvement group. Fourth, relations between brand preference and brand loyalty showed that the former has effects on the former in both high and low involvement groups. This suggests that there is little possibility for consumers preferring specific brands to turn to other brands which have advantages such as price discount and gift presentation.

• Journal of the Korean School Mathematics Society
• /
• v.8 no.2
• /
• pp.203-222
• /
• 2005

The purpose of this study is to investigate students' understanding of functions based on concept image and concept definition suggested by Vinner, For the study a graphing calculator was provided as a tool for students to use for their exploration. Three students participated in the study using the qualitative research method to identify their processes of understanding functions. The student with previous experiences of the functions had various concept images about the functions and did not have many opportunities to modify their images because the student did not want to depend on the calculator. However, the student who did not have many chances to study about the functions before used the calculator effectively for developing the concept definition on the functions. The calculator played an important role in connecting different representations and finding relationships between these representations supported by dynamic exploration.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.3
• /
• pp.471-476
• /
• 2017

It is very useful to use the mnemonic-system to remember numbers easily. In the mnemonic-system associated with these numbers, the utilization of the corresponding images helps to identify numbers easily. In previous studies related to mnemonic-system, we suggested a method that gave the automatic array function that resulted in a simplified array algorithm and an array of image algorithms arranged in relation to the array of images. This methodology has found that the user has a long way to take the time to familiarize themselves with the image and the number of responses. In this study, we suggest dividing the numbers based on the size and color of the scale, based on the size of the images determined to improve these shortcomings.

• Journal of Intelligence and Information Systems
• /
• v.8 no.1
• /
• pp.27-39
• /
• 2002

A locating text technique capable of locating and extracting text blocks in various Web images is presented here. Until now this area of work has been ignored by researchers even if this sort of text may be meaningful for internet users. The algorithms associated with the technique work without prior knowledge of the text orientation, size or font. In the work presented in this research, our text extraction algorithm utilizes useful edge detection followed by histogram analysis on the genuine characteristics of letters defined by text clustering region, to properly perform extraction of the text region that does not depend on font styles and sizes. By a number of experiments we have showed impressively acceptable results.

• Convergence Security Journal
• /
• v.16 no.1
• /
• pp.81-87
• /
• 2016

In this paper, we propose a forgery/falsification detection technique of web site using the images. The proposed system captures images of the web site when a user accesses to the forgery/falsification web site that has the financial information deodorizing purpose. The captured images are compared with those of normal web site images to detect forgery/falsification. The proposed system calculates similarity factor of normal site image with captured one to detect whether the site is normal or not. If it is determined as normal, analysis procedure is finished. But if it is determined as abnormal, a message informs the user to prevent additional financial information spill and further accidents from the forgery web site.