• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2006.05a
• /
• pp.978-980
• /
• 2006

A Next Generation Network (NGN) is a packet-based network able to provide services including Telecommunication Services and able to make use of multiple broadband, QoS-enabled transport technologies and in which service-related functions are independent from underlying transport-related technologies. It offers unrestricted access by users to different service providers. It supports generalized mobility which will allow consistent and ubiquitous provision of services to users In this paper, we explain the trend of standardization activity related with open services in ITU-T SG13(Study Group 13). ITU-T SG13 is responsible for studies .elating to the architecture, evolution and convergence of next generation networks including frameworks and functional architectures, signalling requirements for NGN.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.85-110
• /
• 2018

A chatbot is an interactive assistant that utilizes many communication modes: voice, images, video, or text. It is an artificial intelligence-based application that responds to users' needs or solves problems during user-friendly conversation. However, the current version of the chatbot is focused on understanding and performing tasks requested by the user; its ability to generate personalized conversation suitable for relationship-building is limited. Recognizing the need to build a relationship and making suitable conversation is more important for social chatbots who require social skills similar to those of problem-solving chatbots like the intelligent personal assistant. The purpose of this study is to propose a text analysis method that evaluates relationships between chatbots and users based on content input by the user and adapted to the communication situation, enabling the chatbot to conduct suitable conversations. To evaluate the performance of this method, we examined learning and verified the results using actual SNS conversation records. The results of the analysis will aid in implementation of the social chatbot, as this method yields excellent results even when the private profile information of the user is excluded for privacy reasons.

• Journal of the Korean Society of Radiology
• /
• v.83 no.1
• /
• pp.3-27
• /
• 2022

Cardiac CT has been proven to provide diagnostic and prognostic evaluation of coronary artery disease for cardiovascular risk stratification and treatment decision-making based on rapid technological development and various research evidence. Coronary CT angiography has emerged as a gateway test for coronary artery disease that can reduce invasive angiography due to its high negative predictive value, but the diagnostic specificity is relatively low. However, coronary CT angiography is likely to overcome its limitations through functional evaluation to identify the hemodynamic significance of coronary artery disease by analyzing myocardial perfusion and fractional flow reserve through cardiac CT. Recently, studies have been actively conducted to incorporate artificial intelligence to make this more objective and reproducible. In this review, functional imaging techniques of cardiac computerized tomography are explored.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.61-70
• /
• 2023

Clustering is an unsupervised learning method that involves grouping data based on features such as distance metrics, using data without known labels or ground truth values. This method has the advantage of being applicable to various types of data, including images, text, and audio, without the need for labeling. Traditional clustering techniques involve applying dimensionality reduction methods or extracting specific features to perform clustering. However, with the advancement of deep learning models, research on deep clustering techniques using techniques such as autoencoders and generative adversarial networks, which represent input data as latent vectors, has emerged. In this study, we propose a deep clustering technique based on deep learning. In this approach, we use an autoencoder to transform the input data into latent vectors, and then construct a vector space according to the cluster structure and perform k-means clustering. We conducted experiments using the MNIST and Fashion-MNIST datasets in the PyTorch machine learning library as the experimental environment. The model used is a convolutional neural network-based autoencoder model. The experimental results show an accuracy of 89.42% for MNIST and 56.64% for Fashion-MNIST when k is set to 10.

• Journal of Service Research and Studies
• /
• v.14 no.1
• /
• pp.13-26
• /
• 2024

Multi-modal generation is the process of generating results based on a variety of information, such as text, images, and audio. With the rapid development of AI technology, there is a growing number of multi-modal based systems that synthesize different types of data to produce results. In this paper, we present an AI system that uses speech and text recognition to describe a person and generate a montage image. While the existing montage generation technology is based on the appearance of Westerners, the montage generation system developed in this paper learns a model based on Korean facial features. Therefore, it is possible to create more accurate and effective Korean montage images based on multi-modal voice and text specific to Korean. Since the developed montage generation app can be utilized as a draft montage, it can dramatically reduce the manual labor of existing montage production personnel. For this purpose, we utilized persona-based virtual person montage data provided by the AI-Hub of the National Information Society Agency. AI-Hub is an AI integration platform aimed at providing a one-stop service by building artificial intelligence learning data necessary for the development of AI technology and services. The image generation system was implemented using VQGAN, a deep learning model used to generate high-resolution images, and the KoDALLE model, a Korean-based image generation model. It can be confirmed that the learned AI model creates a montage image of a face that is very similar to what was described using voice and text. To verify the practicality of the developed montage generation app, 10 testers used it and more than 70% responded that they were satisfied. The montage generator can be used in various fields, such as criminal detection, to describe and image facial features.

• Korean Journal of Soil Science and Fertilizer
• /
• v.35 no.4
• /
• pp.243-252
• /
• 2002

To develop indicators for soil health evaluation, biological characteristics of native soils from the different parent materials were studied. Survival rate of fluorescent Pseudomonas in soils was the lowest as 0.1% while those of thermophilic Bacillus and alkaliphilic bacteria were over the 90% by the soil drying stress. There was positive relationship between soil microbial biomass and organic carbon exudated from the microbial biomass by the treatment. The average air-drying effect of soils was 39.7% with ranges of 9.7~95.0%. The propagules of mesophilic Bacillus and Gram negative bacteria were increased by the re-wetting of dried soils. Soil pH affected positively to the recovering rate of microbial number. Average recovering rate of microbes was 65.3%, and there was positive relationship between microbial biomass recovery and fluorescent Pseudomonas population.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.2
• /
• pp.119-133
• /
• 2022

Due to the improvement of surveying, mapping and communication techniques, various apps for road direction guides and vehicle navigations have been developed. Although such a development has impacted on walking and driving, there is a limit to improving the daily convenience of the socially impaired people. This is mainly due to the fact that the software have been developed for normal pedestrians and drivers. Therefore, visually impaired people still have problems with the confusion of direction and/or non-provision of risk factors in walking. This study aimed to propose a scheme which constructs data for mobility-impaired or traffic-impaired people based on various geospatial information. The factors and components related to walking for the visually impaired are selected by geospatial data and a walking route guidance network that can be applied to a commercial software. As a result, it was confirmed that road direction guidance would be possible if additional contents, such as braille blocks (dotted/linear), sound signals, bus stops, and bollards are secured. In addition, an initial version of the application software was implemented based on the suggested data model and its usefulness was evaluated to a visually impaired person. To advance the stability of the service in walking for the visually impaired people, various geospatial data obtained by multiple institutes are necessary to be combined, and various sensors and voice technologies are required to be connected and utilized through ICT (Information and Communications Technologies) technology in near future.

• Journal of the HCI Society of Korea
• /
• v.7 no.2
• /
• pp.49-56
• /
• 2012

The camera-based mobile applications such as color, pattern and object reading can improve the living quality of blind people. However currently available camera-based applications are uncomfortable for the blind, since these applications do not reflect accessibility requirements of the blind especially on touch screen. We investigated accessibility requirements about rapidly growing camera-based mobile applications on touch screen devices for the blind. In order to identify accessibility requirements, we conducted a usability testing for color reading applications with three different types of interfaces on Android OS. The results of the usability testing were as follows: (1) users preferred short depth of menu hierarchy, (2) the initial audio help was more useful than just-in-time help, (3) users needed both manual and automatic camera shooting modes although they preferred manual to automatic mode, (4) users wanted the OS supported screen reader function to be turned off during the color reading application was running, and (5) users required tactile feedback to identify touch screen boundary. We designed a new user interface for blind people by applying the identified accessibility requirements. From a usability testing of the new user interface with 10 blind people, we showed that the identified accessibility requirements were very useful accessibility guidelines for camera-based mobile applications.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2016.02a
• /
• pp.261-261
• /
• 2016

플래시 메모리 (flash memory)는 DRAM(dynamic racdom access memory)이나 SRAM(static random access memory)에 비해 소자의 구조가 매우 단순하기 때문에 집적도가 높아서 기기의 소형화가 가능하다는 점과 제조비용이 낮다는 장점을 가지고 있다. 또한, 전원을 차단하면 정보가 사라지는 DRAM이나 SRAM과 달리 전원이 꺼지더라도 저장된 정보가 지워지지 않는다는 특징을 가지고 있어서 ROM(read only memory)과 정보의 입출력이 자유로운 RAM의 장점을 동시에 가지기 때문에 활용도가 크다. 또한, 속도가 빠르고 소비전력이 작아서 USB 드라이브, 디지털 TV, 디지털 캠코더, 디지털 카메라, 휴대전화, 개인용 휴대단말기, 게임기 및 MP3 플레이어 등에 널리 사용되고 있다. 특히, 낸드(NAND)형의 플래시 메모리는 고집적이 가능하며 하드디스크를 대체할 수 있어 고집적 음성이나 화상 등의 저장용으로 많이 쓰이며 일정량의 정보를 저장해두고 작업해야 하는 휴대형 기기에도 적합하며 가격도 노어(NOR)형에 비해 저렴하다는 장점을 가진다. 최근에는 smart watch, wearable device 등과 같은 차세대 디스플레이 소자에 대한 관심이 증가함에 따라 투명하고 유연한 메모리 소자에 대한 연구가 다양하게 진행되고 있으며 유리나 플라스틱과 같은 기판 위에서 투명한 플래시 메모리를 형성하는 기술에 대한 관심이 높아지고 있다. 전하트랩형 (charge trap type) 플래시 메모리는 플로팅 게이트형 플래시 메모리와는 다르게 정보를 절연막 층에 저장하므로 인접 셀간의 간섭이나 소자의 크기를 줄일 수 있기 때문에 투명하고 유연한 메모리 소자에 적용이 가능한 차세대 플래시 메모리로 기대되고 있다. 전하트랩형 플래시메모리는 정보를 저장하기 위하여 tunneling layer, trap layer, blocking layer의 3층으로 이루어진 게이트 절연막을 가진다. 전하트랩 플래시 메모리는 게이트 전압에 따라서 채널의 전자가 tunnel layer를 통해 trap layer에 주입되어 정보를 기억하게 되는데, trap layer에 주입된 전자가 다시 채널로 빠져나가는 charge loss 현상이 큰 문제점으로 지적된다. 따라서 tunnel layer의 막질향상을 위한 다양한 열처리 방법들이 제시되고 있으며, 기존의 CTA (conventional thermal annealing) 방식은 상대적으로 높은 온도와 긴 열처리 시간을 가지고, RTA (rapid thermal annealing) 방식은 매우 높은 열처리 온도를 필요로 하기 때문에 플라스틱, 유리와 같은 다양한 기판에 적용이 어렵다. 따라서 본 연구에서는 기존의 열처리 방식보다 에너지 전달 효율이 높고, 저온공정 및 열처리 시간을 단축시킬 수 있는 마이크로웨이브 열처리(microwave irradiation, MWI)를 도입하였다. Tunneling layer, trap layer, blocking layer를 가지는 MOS capacitor 구조의 전하트랩형 플래시 메모리를 제작하여 CTA, RTA, MWI 처리를 실시한 다음, 전기적 특성을 평가하였다. 그 결과, 마이크로웨이브 열처리를 실시한 메모리 소자는 CTA 처리한 소자와 거의 동등한 정도의 우수한 전기적인 특성을 나타내는 것을 확인하였다. 따라서, MWI를 이용하면 tunnel layer의 막질을 향상시킬 뿐만 아니라, thermal budget을 크게 줄일 수 있어 차세대 투명하고 유연한 메모리 소자 제작에 큰 기여를 할 것으로 예상한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.10
• /
• pp.1994-2005
• /
• 2015

Voice over IP (VoIP) is a technology for the delivery of voice communications and multimedia sessions over Internet Protocol (IP) networks. Instead of being transmitted over a circuit-switched network, however, the digital information is packetized, and transmission occurs in the form of IP packets over a packet-switched network which consist of several layers of computers. VoIP Service that used the various techniques has many advantages such as a voice Service, multimedia and additional service with cheap cost and so on. But the various frauds arises using VoIP because VoIP has the existing vulnerabilities at the Internet and based on complex technologies, which in turn, involve different components, protocols, and interfaces. According to research results, during in 2012, 46 % of fraud calls being made in VoIP. The revenue loss is considerable by fraud call. Among we will analyze for Toll Bypass Fraud by the SIM Box that occurs mainly on the international call, and propose the measures that can detect. Typically, proposed solutions to detect Toll Bypass fraud used DPI(Deep Packet Inspection) based on a variety of detection methods that using the Signature or statistical information, but Fraudster has used a number of countermeasures to avoid it as well. Particularly a Fraudster used countermeasure that encrypt VoIP Call Setup/Termination of SIP Signal or voice and both. This paper proposes the solution that is identifying equipment of Toll Bypass fraud using those countermeasures. Through feature of Voice traffic analysis, to detect involved equipment, and those behavior analysis to identifying SIM Box or Service Sever of VoIP Service Providers.