• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.539-548
• /
• 2020

Deep learning technology is currently being used and applied in many different fields. Convolution neural network (CNN) is a method of artificial neural networks in deep learning, which is commonly used for analyzing different types of images through classification. In the conventional classification of histopathology images of prostate carcinomas, the rating of cancer is classified by human subjective observation. However, this approach has produced to some misdiagnosing of cancer grading. To solve this problem, CNN based classification method is proposed in this paper, to train the histological images and classify the prostate cancer grading into two classes of the benign and malignant. The CNN architecture used in this paper is based on the VGG models, which is specialized for image classification. However, color normalization was performed based on the contrast enhancement technique, and the normalized images were used for CNN training, to compare the classification results of both original and normalized images. In all cases, accuracy was over 90%, accuracy of the original was 96%, accuracy of other cases was higher, and loss was the lowest with 9%.

• Journal of Korean Neurosurgical Society
• /
• v.62 no.5
• /
• pp.526-535
• /
• 2019

Objective : While the risk of aneurysmal rebleeding induced by catheter cerebral angiography is a serious concern and can delay angiography for a few hours after a subarachnoid hemorrhage (SAH), current angiographic technology and techniques have been much improved. Therefore, this study investigated the risk of aneurysmal rebleeding when using a recent angiographic technique immediately after SAH. Methods : Patients with acute SAH underwent immediate catheter angiography on admission. A four-vessel examination was conducted using a biplane digital subtraction angiography (DSA) system that applied a low injection rate and small volume of a diluted contrast, along with appropriate control of hypertension. Intra-angiographic aneurysmal rebleeding was diagnosed in cases of extravasation of the contrast medium during angiography or increased intracranial bleeding evident in flat-panel detector computed tomography scans. Results : In-hospital recurrent hemorrhages before definitive treatment to obliterate the ruptured aneurysm occurred in 11 of 266 patients (4.1%). Following a univariate analysis, a multivariate analysis using a logistic regression analysis revealed that modified Fisher grade 4 was a statistically significant risk factor for an in-hospital recurrent hemorrhage (p=0.032). Cerebral angiography after SAH was performed on 88 patients ${\leq}3$ hours, 74 patients between 3-6 hours, and 104 patients >6 hours. None of the time intervals showed any cases of intra-angiographic rebleeding. Moreover, even though the DSA ${\leq}3$ hours group included more patients with a poor clinical grade and modified Fisher grade 4, no case of aneurysmal rebleeding occurred during erebral angiography. Conclusion : Despite the high risk of aneurysmal rebleeding within a few hours after SAH, emergency cerebral angiography after SAH can be acceptable without increasing the risk of intra-angiographic rebleeding when using current angiographic techniques and equipment.

• Anatomy & Biological Anthropology
• /
• v.31 no.4
• /
• pp.133-142
• /
• 2018

3D histology is a imaging system for the 3D structural information of cells or tissues. The synchrotron radiation propagation phase contrast micro-CT has been used in 3D imaging methods. However, the simple phase contrast micro-CT did not give sufficient micro-structural information when the specimen contains soft elements, as is the case with many biomedical tissue samples. The purpose of this study is to develop a new technique to enhance the phase contrast effect for soft tissue imaging. Experiments were performed at the imaging beam lines of Pohang Accelerator Laboratory (PAL). The biomedical tissue samples under frozen state was mounted on a computer-controlled precision stage and rotated in $0.18^{\circ}$ increments through $180^{\circ}$. An X-ray shadow of a specimen was converted into a visual image on the surface of a CdWO4 scintillator that was magnified using a microscopic objective lens(X5 or X20) before being captured with a digital CCD camera. 3-dimensional volume images of the specimen were obtained by applying a filtered back-projection algorithm to the projection images using a software package OCTOPUS. Surface reconstruction and volume segmentation and rendering were performed were performed using Amira software. In this study, We found that synchrotron phase contrast imaging of frozen tissue samples has higher contrast power for soft tissue than that of non-frozen samples. In conclusion, synchrotron radiation propagation phase contrast cryo-microCT imaging offers a promising tool for non-destructive high resolution 3D histology.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.10 no.2
• /
• pp.27-38
• /
• 2008

In the 21st century, the development of technology overturned the paradigm of the entire society and culture, and the term 'high-tech' became generally accepted around the world by the momentous advances of technology. The purpose of this study is to define the concept of high-tech fashion by clarifying the characteristics of high-tech fashion, and to propose the proper approach toward the coming fashion. Hussein Chalayan shows the experimental and futuristic designs based on the cultural context of architecture and sculpture. Moreover, the scope of this study has been limited into Hussein Chalayan's recent works after the year 2000 up to 2007. High-tech architecture has been, in some ways, a response to pow technology a new aesthetic in contrast with standard modern architecture. High-tech architecture aimed to achieve a new industrial aesthetic, spurred on by the renewed faith in the progression of technology. However, no matter how prominent the industrial look appeared, the functional element of modern architecture has been very much retained. The characteristics of high-tech architecture that had been extracted by analyzing the antecedent studies were: technocism, transformability, and dynamism. Furthermore, the characteristics of high-tech fashion has been explained based on the characteristics of high-tech architecture. First, technocism is expressed either by the new technologized materials, and advanced digital technology. Second, transformability is expressed in the transformable clothing, which performs various functions. Third, dynamism is displayed in dynamic forms influenced by the technology of engineering. High-tech will be the dominant influence in fashion, and the designers will be enamored with the technologies of the new millenium. Architecture and fashion share the characteristics of high-tech, and their common cultural features is confirmed again.

• Journal of Digital Convergence
• /
• v.12 no.7
• /
• pp.123-132
• /
• 2014

This study examines the influence of the physical environment on tourist's emotional response and behavioral intention in the tourist destination. The research was mainly performed in leading tourist destinations of Busan Metropolitan City (Haeundae, Gwanganri & Songjeong area) by the sampling survey method in April-May 2013. The results demonstrate as follows. Firstly, the tourist's convenience and amenity in physical environments have significant impacts on the negative feeling of emotional response, but attractiveness did not influence in negative feeling. By contrast, the attractiveness and amenity the a of physical environments give significant impacts on the positive feeling of emotional response but convenience did not work in positive response. Secondly, both positive and negative feeling of emotional responses give meaningful impacts on Tourist's behavior intention. According to the meaningful relationship between physical environment and emotional response, the regional characteristics and effective marketing management of tourism resource and preparedness should be considered in setting up tourist facilities.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.2
• /
• pp.101-108
• /
• 2024

AI-OCR (Artificial Intelligence Optical Character Recognition) combines OCR technology with Artificial Intelligence to overcome limitations that required human intervention. To enhance the performance of AI-OCR, training on diverse data sets is essential. However, the recognition rate declines when image colors have similar brightness levels. To solve this issue, this study employs Homomorphic filtering as a preprocessing step to clearly differentiate color levels, thereby increasing text recognition rates. While Homomorphic filtering is ideal for text extraction because of its ability to adjust the high and low frequency components of an image separately using a gamma value, it has the downside of requiring manual adjustments to the gamma value. This research proposes a range for gamma threshold values based on tests involving image contrast, brightness, and entropy. Experimental results using the proposed range of gamma values in Homomorphic filtering suggest a high likelihood for effective AI-OCR performance.

• Journal of radiological science and technology
• /
• v.15 no.2
• /
• pp.17-23
• /
• 1992

Simple chest radiography is the most frequently performed examination in radiologic practice. However, with transmitted dose through chest which has the problem of wide variations in absorption, conventional Film/Screen Combinations Method make it difficult to delineate lung field mediastinum & cardia portion and subdiaphragmatic structures. In order to overcome this problem, we have been tried several methods as follows. High Kilovoltage Technique, Rare Earth Screen/Wide Lattitude Film, Use of Compensating Filter and Digital Beam Attenuator and recently Insigh System has been developed. In this paper, we'd like to discuss Insight film through apperciation by measuring the difference of contrast. In order to evaluate insight film. We have done experiments using Insight System with Simple Phase, Picker 550. We could get an result which was able to overcome the limitted dynamic range of conventional Film/Screen System remarkably.

• International Journal of Contents
• /
• v.11 no.2
• /
• pp.20-30
• /
• 2015

We propose a new method that specifies objective image quality factors by evaluating an image quality measurement model using random images. In other words, No-Reference variables are used to evaluate the quality of an original image without using any reference for comparison. 1000 portrait images were collected from a web gallery with votes constituting over 30 recommendation values. The bottom-up data collecting process was used to calculate the following image quality factors: total range, average, standard deviation, normalized distribution, z-score, preference percentage. A final grade is awarded out of 100 points, and this method ranks and grades the final estimated image quality preference in terms of total image quality factors. The results of the proposed image quality evaluation model consist of the specific dynamic range, skin tone R, G, B, L, A, B, and RSC contrast. We can present the total for the expected preference points as the average of the objective image qualities. Our proposed image quality evaluation model can measure the preferences for an actual image using a statistical analysis. The results indicate that this is a practical image quality measurement model that can extract a subject's preferred image quality.

• Journal of Distribution Science
• /
• v.19 no.1
• /
• pp.89-103
• /
• 2021

Purpose: This study is to explore how Netflix Customers' Engagement was influenced by Instagram Content, Perceived Price, Exclusivity, and Motivation in the context of Media Streaming and the role of Willingness to Subscribe as the mediating variable. This study underlines millennial's willingness to engage and the form of engagement. Research design, data, and methodology: The data for this research were collected from 100 Netflix's Millennials subscribers who follow @netflixid Instagram. All the results were analyzed and verified using SEM-PLS. Results: Research findings indicated that Willingness to Subscribe, Exclusivity, Motivation, and Instagram Content positively influenced Customer Engagement among Netflix millennials' subscribers. In contrast, Perceived Price had a negative effect on Customer Engagement. Conclusions: As a consequence, the exclusivity that Netflix offers to its audience by a recommendation algorithm has been proven to increase the engagement. This study also disclosed that the most definite form of positive engagement shown by Netflix millennials' subscribers is a behavioral aspect, where they positively recommend Netflix (word of mouth). The study findings can be a reference for the media streaming industry in their efforts to strengthen the engagement with their customers, especially the millennials, and provide knowledge about consumer behavior in digital technology.

• The Journal of Asian Finance, Economics and Business
• /
• v.10 no.1
• /
• pp.49-55
• /
• 2023

Business is an important entity in every economy with its role in job creation, budget contribution, and national output. It can be said that enterprises are also one of the leading units that play a key role in implementing digital transformation, grasping science and technology, and improving labor productivity. Developing a team of enterprises that are both strong in quantity and strong in quality is an urgent requirement in many countries, including Vietnam. Vietnam is a developing country and home to many textile and garment enterprises operating due to the advantages of cheap labor and a large market, the textile and garment industry is capable of creating many jobs for the economy. Studying the factors affecting corporate financial performance across 250 textile and garment enterprises in Hanoi capital and Bac Ninh province, the research results show that when enterprises have the ability to mobilize capital, the cost is cheap, appropriate, and optimal, most businesses often achieve higher business efficiency and financial performance. In contrast, enterprises that are difficult to raise capital in the economy often achieve low financial efficiency and financial performance. The study also confirms the role of human capital in enterprises, enterprises with high human capital often achieve high profits.