• Information Systems Review
• /
• v.20 no.2
• /
• pp.111-137
• /
• 2018

Considering the increase in health insurance benefits and the elderly population of the baby boomer generation, the amount consumed by health care in 2020 is expected to account for 20% of US GDP. As the healthcare industry develops, competition among the medical services of hospitals intensifies, and the need of hospitals to manage the quality of medical services increases. In addition, interest in online reviews of hospitals has increased as online reviews have become a tool to predict hospital quality. Consumers tend to refer to online reviews even when choosing healthcare service providers and after evaluating service quality online. This study aims to analyze the effect of sentiment score of healthcare service quality on hospital rating with Yelp hospital reviews. This study classifies large amount of text data collected online primarily into five service quality measurement indexes of SERVQUAL theory. The sentiment scores of reviews are then derived by SERVQUAL dimensions, and an econometric analysis is conducted to determine the sentiment score effects of the five service quality dimensions on hospital reviews. Results shed light on the means of managing online hospital reputation to benefit managers in the healthcare and medical industry.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of Korea Multimedia Society
• /
• v.7 no.2
• /
• pp.211-222
• /
• 2004

By development of wireless mobile communication, many users increased. But, in case of 1st generation or 2nd generation, transfer communication service was not satisfying high speed wireless internet Communication consumer's request such as other multimedia service because serviced based on voice and text basically. Can get through service such as data and transfer multimedia service that is not service of voice putting first in wireless hereafter. Problems by much development of service are happening, because a transmit is exposed, problem point that wireless network is much unlawful stealing use and tapping etc. As is different from this, problem can happen in service side. Can take next time for these example. By user that is not right can happen. Need method to keep away purpose that is enemy of third party in contract between both men as well as problem for document or accounting information which the third user that is enemy of third party is shared. By solution about problems, certification of contents for document and visual point confirmation must it. Applied service or certification of contents service that is rapidly point of time that is using in wire to solve problem that refer in front in this treatise in IMT-2000 to develop hereafter. Way to propose proposed efficient way using individual in IMT-2000 just as it is.

• Archives of design research
• /
• v.17 no.1
• /
• pp.319-328
• /
• 2004

The communication environment made by digital technologies has made it possible to exchange information and deliver messages fast and easily among people of various classes in virtual space beyond time and space. Net-generation, who is accustomed to this virtual space, couldn't be satisfied with the linear text-oriented language any more, and began to make signs by use of computers in order to differentiate itself from others and to express its desires. Among the signs, emoticon created by joint of popular culture and digital communication centering around young generation is a new visual sign and emotional sign that can deliver a sender's feelings contained in a message. This paper has studied social phenomena, their relationships with emoticon and background of its creation through documentary review of media development, changes in the communication environment and popular culture. Furthermore, it has analyzed the meaningful action and roles of emoticon as a sign in terms of semiotics and also, studied a possibility of using emoticon as a new emotional sign. The study results say that emoticon can play the roles of a non-linguistic sign just like general signs that make mutual exchange through meaningful action, and also that it can be used to effectively deliver messages not only in virtual space, but also in advertising, posters, magazines and CI. However, emoticon is better at emotional expressions yet than other textual signs or visual signs, but in order to position itself as a universal and popular sign, emotional expressions should be clear, any difference in understanding messages should be removed, and message delivery should be more efficient.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.3
• /
• pp.439-449
• /
• 2024

Recent rapid advancements in voice generation technology have enabled the natural synthesis of voices using text alone. However, this progress has led to an increase in malicious activities, such as voice phishing (voishing), where generated voices are exploited for criminal purposes. Numerous models have been developed to detect the presence of synthesized voices, typically by extracting features from the voice and using these features to determine the likelihood of voice generation.This paper proposes a new model for extracting voice features to address misuse cases arising from generated voices. It utilizes a deep learning-based audio codec model and the pre-trained natural language processing model BERT to extract novel voice features. To assess the suitability of the proposed voice feature extraction model for voice detection, four generated voice detection models were created using the extracted features, and performance evaluations were conducted. For performance comparison, three voice detection models based on Deepfeature proposed in previous studies were evaluated against other models in terms of accuracy and EER. The model proposed in this paper achieved an accuracy of 88.08%and a low EER of 11.79%, outperforming the existing models. These results confirm that the voice feature extraction method introduced in this paper can be an effective tool for distinguishing between generated and real voices.

• Journal of Digital Convergence
• /
• v.11 no.2
• /
• pp.263-269
• /
• 2013

This research paper is applying Writing Supporting System on the previous research study about writing tool data model on interactive storytelling about family Story. Family story writing supporting system enables users to create text, images, videos and digital contents based on experimental knowledge collected from the first and second generations. The paper about studies on writing tool system on family story, aims to create documentary based high quality contents about each family members and family history. At the same time, overcome generation gaps and the lack of creation infrastructures. Throughout this process, the author will contribute to the expansion of creation devices which can be applied in other researches and writing tools.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.337-340
• /
• 2004

The exactly reproduced prosody of a TTS system is one of the key factors that affect the naturalness of synthesized speech. In general, rules about prosody had been gathered either from linguistic knowledge or by analyzing the prosodic information from natural speech. But these could not be perfect and some of them could be incorrect. So we proposed artificial neural network(ANN)s that can be trained to team the prosody of natural speech and generate it. In learning phase, let ANNs learn the pitch and energy contour of center phoneme by applying a string of phonemes in a sentence to ANNs and comparing the output pattern with target pattern and making adjustment in weighting values to get the least mean square error between them. In test phase, the estimation rates were computed. We saw that ANNs could generate the prosody of a sentence.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.10
• /
• pp.361-372
• /
• 2016

Identity Privacy issues such as exposures of IMSIs(International Mobile Subscriber Identities) in access network have been consistently raised throughout GSM, UMTS, LTE in 3GPP. The 3GPP specification uses temporary identities instead of IMSI to ensure anonymity of the user. Even if temporary identities are disclosed, Identity Privacy may be maintained at a safe level by security policies such as no linkability and periodic update. But in case of IMSI, it cannot be changed even though it is exposed. There still exist some situations that IMSI is used in clear text for the authentication. Therefore, a protective mechanism for the identity confidentiality is needed. In this paper we propose a protocol based on IBE(Identity-based Encryption) to protect permanent identities in access network. By simplifying the scheme, this protocol has minimized the system impact on current 3GPP environment. And this scheme can be applied to all kind of permanent identities and 3GPP AKA(Authentication and Key Agreement) protocols in access network.

• The Journal of the Korea Contents Association
• /
• v.17 no.7
• /
• pp.358-370
• /
• 2017

This thesis discusses the emerging system of value and structure of feeling in today's Chinese society through analyzing Chinese main theme TV series. The 2000s' Chinese main theme TV series represents Chinese's anger and nervousness into the structure of narrative, and they try to form a bond of sympathy with the audience by various characters which represent the common people. Main characters are no longer revolutionists who internalize ideas of socialism and collectivism, but they put emphasis on individuals' thoughts, tastes, and values, and freely express them. Individualism, which was negatively represented and excluded in main theme TV series before 2000s, are compromised and included in today's Chinese dramas. Even though dramas represent the superiority of communism, individuals' choice of various value and faith is positively and flexibly considered. There is a new phenomenon where female figures are no longer passive and dependent, but they are portrayed with given with unique roles and status. Although main theme TV series are directed under the state and government's supervision, they exist in the relation where market, state, drama text, and audience interact.

• Journal of Microbiology and Biotechnology
• /
• v.27 no.6
• /
• pp.1163-1170
• /
• 2017

Clostridium difficile releases two exotoxins, toxin A and toxin B, which disrupt the epithelial cell barrier in the gut to increase mucosal permeability and trigger inflammation with severe diarrhea. Many studies have suggested that enteric nerves are also directly involved in the progression of this toxin-mediated inflammation and diarrhea. C. difficile toxin A is known to enhance neurotransmitter secretion, increase gut motility, and suppress sympathetic neurotransmission in the guinea pig colitis model. Although previous studies have examined the pathophysiological role of enteric nerves in gut inflammation, the direct effect of toxins on neuronal cells and the molecular mechanisms underlying toxin-induced neuronal stress remained to be unveiled. Here, we examined the toxicity of C. difficile toxin A against neuronal cells (SH-SY5Y). We found that toxin A treatment time- and dose-dependently decreased cell viability and triggered apoptosis accompanied by caspase-3 activation in this cell line. These effects were found to depend on the up-regulation of reactive oxygen species (ROS) and the subsequent activation of p38 MAPK and induction of $p21^{Cip1/Waf1}$. Moreover, the N-acetyl-$\text\tiny L$-cysteine (NAC)-induced down-regulation of ROS could recover the viability loss and apoptosis of toxin A-treated neuronal cells. These results collectively suggest that C. difficile toxin A is toxic for neuronal cells, and that this is associated with rapid ROS generation and subsequent p38 MAPK activation and $p21^{Cip1/Waf1}$ up-regulation. Moreover, our data suggest that NAC could inhibit the toxicity of C. difficile toxin A toward enteric neurons.