• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2006.06a
• /
• pp.46-66
• /
• 2006

새로운 지능기반사회(ubiquitous society) 패러다임이란 전제 아래 미국을 비롯해 일본, 유럽 등 세계 각국에서는 모바일, 브로드밴드, 극소형 컴퓨터, IPv6의 기술이 창출해 내는 컴퓨팅 혁명의 실체를 유비궈터스 IT로 파악하고 각 국의 걸부, 기업, 연구소들이 주도권을 잡기 위해 많은 노력을 기울이고 있다. 현재 유비쿼터스 IT를 활용한 u-비즈니스를 활성화하고 관련 시장을 선점하기 위한 전 세계적인 경쟁은 매우 치열한 양상을 보이고 있다. 주요 국가들은 서로 지향하는 영역은 다르지만 궁극적으로 지능기반사회 구현이라는 대명제 아래 독자적인 산업 구축을 위해 노력하고 있다. 이러한 이유는 기본적으로 지능기반사회로의 이행과정에서 발생하는 경제적 파급효과, 예컨대 디지털 가전, 이동통신기기, 전자의료기기, 디스플레이, 2차 전지, 보안 등 관련 산업에 미치는 영향 및 새로운 시장 창출의 기회가 있기 때문이다. 기존의 많은 연구 및 문헌에서는 아직도 유비쿼터스 IT에 대한 개념적인 논의에 치중되어 있고 시장 중심적 또는 수요자 중심적 사고의 논의가 부족하다. 성공적으로 유비쿼터스 산업을 육성하기 위해서는 유비쿼터스 IT자체기술 개발사업(tangible service) 뿐만 아니라 비가시적(intangible) 서비스, 그리고 컨버전스(convergence) 서비스에 대한 상용화 모델과 성공적 사업 전개 방법론에 대한 깊은 연구가 수행되어야 한다. 본 연구에서는 먼저 유비쿼터스 IT의 기술동향과 시장 동향 및 산업 규모에 대한 문헌연구를 통해 u-비즈니스의 가능성을 고찰해보고, u-비즈니스 추진 전략을 탐색적으로 제시하고자 한다.되었다. SPME-GC/MS에 의한 휘발성분 분석 결과, 기능성 유지에서 홍국쌀 에탄올 추출물로부터 기인되는 특유의 휘발성분은 관찰되지 않았으나, RT=12.1 min인 hexanal의 함량이 control에 비하여 유의적인 감소 경향을 나타내는 것이 확인되었다(p<0.05).히지 못하여, 이의 기전을 밝히기 위한 추후 연구가 필요하다./TEX>로서 p<0.01 수준에서 현저히 증가하였다. 혈청의 인지질과 콜레스테롤 에스테르의 지방산 조성에서 vitamin C를 혼합 투여한 3,5,7군에서 PUFA 함량이 증가한 반면, SFA 함량은 감소하여 P/S 비율, n-3P/n-6P 비율은 증가하는 경향이었으며 이는 간장의 인지질, 콜레스테롤 에스테르, 총 지질의 지방산조성에서도 같은 경향을 볼 수 있었다.X>$(C_{18:2})$와 n-3계 linolenic acid$(C_{18:3})$가 대부분을 차지하였다. 야생 돌복숭아 과육 중의 지방산 조성은 포화지방산이 16.74%, 단불포화지방산 17.51% 및 다불포화지방산이 65.73%의 함유 비율을 보였는데, 이 중 다불포화지방산인 n-6계 linoleic acid$(C_{18:2})$와 n-3계 linolenic acid$(C_{18:3})$가 지질 구성 총 지방산의 대부분을 차지하는 함유 비율을 나타내었다.했다. 하강하는 약 4일간의 기상변화가 자발성 기흉 발생에 영향을 미친다고 추론할 수 있었다. 향후 본 연구에서 추론된 기상변화와 기흉 발생과의 인과관계를 확인하고 좀 더 구체화하기 위한 연구가 필요할 것이다.게 이루어질 수 있을 것

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.63-71
• /
• 2020

In this paper, we propose a fire detection technology using YOLOv3 and EfficientDet, the most reliable artificial intelligence detection algorithm recently, an alert service that simultaneously transmits four kinds of notifications: text, web, app and e-mail, and an AWS system that links fire detection and notification service. There are two types of our highly accurate fire detection algorithms; the fire detection model based on YOLOv3, which operates locally, used more than 2000 fire data and learned through data augmentation, and the EfficientDet, which operates in the cloud, has conducted transfer learning on the pretrained model. Four types of notification services were established using AWS service and FCM service; in the case of the web, app, and mail, notifications were received immediately after notification transmission, and in the case of the text messaging system through the base station, the delay time was fast enough within one second. We proved the accuracy of our fire detection technology through fire detection experiments using the fire video, and we also measured the time of fire detection and notification service to check detecting time and notification time. Our AI fire detection and notification service system in this paper is expected to be more accurate and faster than past fire detection systems, which will greatly help secure golden time in the event of fire accidents.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.611-618
• /
• 2020

In this paper, we propose a design and implementation method of speed quiz content that can be driven by a social robot capable of interacting with humans, and a method of developing an intelligent module necessary for implementation. In addition, we propose a method of implementing speed quiz content through the process of constructing a map by arranging and connecting intelligent module blocks. Recently, software education has become mandatory and interest in programming is increasing. However, programming is difficult for students without basic knowledge of programming languages to directly access, and interest in block-type programming platforms suitable for beginners is growing. The block-type programming platform used in this paper is a platform that supports immediate and intuitive programming by supporting interactions between humans and robots. In this paper, the intelligent module implemented for the speed quiz content was used by blocking it within a block-type programming platform. In order to implement the scenario of the speed quiz content proposed in this paper, we implement a total of three image-based artificial intelligence modules. In addition to the intelligent module, various functional blocks were placed to implement the speed quiz content. In this paper, we propose a method of designing a speed quiz content scenario and a method of implementing an intelligent module for speed quiz content.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.6
• /
• pp.470-476
• /
• 2020

In this paper, we present the design of modular replaceable AI server for image deep learning that separates the server from the Edge Device so as to drive the AI block and the method of data transmission and reception. The modular replaceable AI server for image deep learning can reduce the dependency between social robots and edge devices where the robot's platform will be operated to improve drive stability. When a user requests a function from an AI server for interaction with a social robot, modular functions can be used to return only the results. Modular functions in AI servers can be easily maintained and changed by each module by the server manager. Compared to existing server systems, modular replaceable AI servers produce more efficient performance in terms of server maintenance and scale differences in the programs performed. Through this, more diverse image deep learning can be included in robot scenarios that allow human-robot interaction, and more efficient performance can be achieved when applied to AI servers for image deep learning in addition to robot platforms.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.360-366
• /
• 2022

This paper presents a AI model structure for restoring Korean traditional palace photographs, which remain only black-and-white photographs, to color photographs using Pix2Pix, one of the adversarial generative neural network techniques. Pix2Pix consists of a combination of a synthetic image generator model and a discriminator model that determines whether a synthetic image is real or fake. This paper deals with an artificial intelligence model by adjusting a receptive field of the discriminator, and analyzes the results by considering the characteristics of the ancient palace photograph. The receptive field of Pix2Pix, which is used to restore black-and-white photographs, was commonly used in a fixed size, but a fixed size of receptive field is not suitable for a photograph which consisting with various change in an image. This paper observed the result of changing the size of the existing fixed a receptive field to identify the proper size of the discriminator that could reflect the characteristics of ancient palaces. In this experiment, the receptive field of the discriminator was adjusted based on the prepared ancient palace photos. This paper measure a loss of the model according to the change in a receptive field of the discriminator and check the results of restored photos using a well trained AI model from experiments.

• Journal of Intelligence and Information Systems
• /
• v.28 no.4
• /
• pp.211-227
• /
• 2022

Illegal gambling through online gambling sites has become a significant social problem. The development of Internet technology and the spread of smartphones have led to the proliferation of illegal gambling sites, so now illegal online gambling has become accessible to anyone. In order to mitigate its negative effect, the Korean government is trying to detect illegal gambling sites by using self-monitoring agents or reporting systems such as 'Nuricops.' However, it is difficult to detect all illegal sites due to limitations such as a lack of staffing. Accordingly, several scholars have proposed intelligent illegal gambling site detection techniques. Xu et al. (2019) found that fake or illegal websites generally have unique features in the HTML tag structure. It implies that the HTML tag structure can be important for detecting illegal sites. However, prior studies to improve the model's performance by utilizing the HTML tag structure in the illegal site detection model are rare. Against this background, our study aimed to improve the model's performance by utilizing the HTML tag structure and proposes Tag2Vec, a modified version of Doc2Vec, as a methodology to vectorize the HTML tag structure properly. To validate the proposed model, we perform the empirical analysis using a data set consisting of the list of harmful sites from 'The Cheat' and normal sites through Google search. As a result, it was confirmed that the Tag2Vec-based detection model proposed in this study showed better classification accuracy, recall, and F1_Score than the URL-based detection model-a comparative model. The proposed model of this study is expected to be effectively utilized to improve the health of our society through intelligent technology.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.6
• /
• pp.381-389
• /
• 2023

One of the crucial components in building information modeling (BIM) is data. To systematically manage these data, various research studies have focused on the creation of object breakdown structures and property sets. Specifically, crucial data for managing programs and payments involves work breakdown structures (WBSs) and cost breakdown structures (CBSs), which are indispensable for mapping BIM objects. Achieving this requires disassembling CBS quantities based on 3D objects and WBS. However, this task is highly tedious owing to the large volume of CBS and divergent coding practices employed by different organizations. Manual processes, such as those based on Excel, become nearly impossible for such extensive tasks. In response to the challenge of computing quantities that are difficult to derive from BIM objects, this study presents methods for disassembling length-based quantities, incorporating significant portions of the bill of quantities (BOQs). The proposed approach recommends suitable CBS by leveraging the accumulated history of WBS-CBS mapping databases. Additionally, it establishes a unified CBS code, facilitating the effective operation of CBS databases.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.5
• /
• pp.331-337
• /
• 2023

In this paper, we propose a deep learning model to detect lumbar 3 (L3) CT images to determine the occurrence and degree of sarcopenia. In addition, we would like to propose an optimization technique that uses oversampling ratio and class weight as design parameters to address the problem of performance degradation due to data imbalance between L3 level and non-L3 level portions of CT data. In order to train and test the model, a total of 150 whole-body CT images of 104 prostate cancer patients and 46 bladder cancer patients who visited Gangneung Asan Medical Center were used. The deep learning model used ResNet50, and the design parameters of the optimization technique were selected as six types of model hyperparameters, data augmentation ratio, and class weight. It was confirmed that the proposed optimization-based L3 level extraction model reduced the median L3 error by about 1.0 slices compared to the control model (a model that optimized only 5 types of hyperparameters). Through the results of this study, accurate L3 slice detection was possible, and additionally, we were able to present the possibility of effectively solving the data imbalance problem through oversampling through data augmentation and class weight adjustment.