• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.323-332
• /
• 2022

As various services using AI technology are being developed, much attention is being paid to AI service production. Recently, AI technology is acknowledged as one of ICT services, a lot of research is being conducted for general-purpose AI service production. In this paper, I describe the research results in terms of systems for AI service production, focusing on the distribution and production of machine learning models, which are the final steps of general machine learning development procedures. Three different Ubuntu systems were built, and experiments were conducted on the system, using data from 2017 validation COCO dataset in combination of different AI models (RFCN, SSD-Mobilenet) and different communication methods (gRPC, REST) to request and perform AI services through Tensorflow serving. Through various experiments, it was found that the type of AI model has a greater influence on AI service inference time than AI machine communication method, and in the case of object detection AI service, the number and complexity of objects in the image are more affected than the file size of the image to be detected. In addition, it was confirmed that if the AI service is performed remotely rather than locally, even if it is a machine with good performance, it takes more time to infer the AI service than if it is performed locally. Through the results of this study, it is expected that system design suitable for service goals, AI model development, and efficient AI service production will be possible.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.10
• /
• pp.363-372
• /
• 2022

Since the recent COVID-19 Pandemic, the ransomware fandom has intensified along with the expansion of remote work. Currently, anti-virus vaccine companies are trying to respond to ransomware, but traditional file signature-based static analysis can be neutralized in the face of diversification, obfuscation, variants, or the emergence of new ransomware. Various studies are being conducted for such ransomware detection, and detection studies using signature-based static analysis and behavior-based dynamic analysis can be seen as the main research type at present. In this paper, the frequency of ".text Section" Opcode and the Native API used in practice was extracted, and the association between feature information selected using K-means Clustering algorithm, Cosine Similarity, and Pearson correlation coefficient was analyzed. In addition, Through experiments to classify and detect worms among other malware types and Cerber-type ransomware, it was verified that the selected feature information was specialized in detecting specific ransomware (Cerber). As a result of combining the finally selected feature information through the above verification and applying it to machine learning and performing hyper parameter optimization, the detection rate was up to 93.3%.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.267-279
• /
• 2023

This research assessed the feasibility of using high-resolution aerial images and deep learning algorithms for estimating the land-use and land-cover areas at the Approach 3 level, as outlined by the Intergovernmental Panel on Climate Change. The results from different sampling densities of high-resolution (51 cm) aerial images were compared with the land-cover map, provided by the Ministry of Environment, and analyzed to estimate the accuracy of the land-use and land-cover areas. Transfer learning was applied to the VGG16 architecture for the deep learning model, and sampling densities of 4 × 4 km, 2 × 4 km, 2 × 2 km, 1 × 2 km, 1 × 1 km, 500 × 500 m, and 250 × 250 m were used for estimating and evaluating the areas. The overall accuracy and kappa coefficient of the deep learning model were 91.1% and 88.8%, respectively. The F-scores, except for the pasture category, were >90% for all categories, indicating superior accuracy of the model. Chi-square tests of the sampling densities showed no significant difference in the area ratios of the land-cover map provided by the Ministry of Environment among all sampling densities except for 4 × 4 km at a significance level of p = 0.1. As the sampling density increased, the standard error and relative efficiency decreased. The relative standard error decreased to ≤15% for all land-cover categories at 1 × 1 km sampling density. These results indicated that a sampling density more detailed than 1 x 1 km is appropriate for estimating land-cover area at the local level.

• Journal of Convergence for Information Technology
• /
• v.12 no.3
• /
• pp.286-293
• /
• 2022

Recently, the importance of elemental technologies constituting smart factories is increasing due to the 4th Industrial Revolution, and simulation is widely used as a tool to learn these technologies. In particular, PID control is an automatic control technique used in various fields, and most of them analyze mathematical models in certain situations or research on application development with built-in controllers. In actual educational environment requires PID simulator training as well as PID control principles. In this paper, we propose a model that enables education and practice of various PID controls through 3D simulation. The proposed model implemented virtual balls and Fan and implemented PID control by configuring a system so that the force can be lifted by the air pressure generated in the Fan. At this time, the height of the ball was expressed in a graph according to each gain value of the PID controller and then compared with the actual system, and through this, satisfactory results sufficiently applicable to the actual class were confirmed. Through the proposed model, it is expected that the rapidly increasing elemental technology of smart factories can be used in various ways in a remote classroom environment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.246-246
• /
• 2021

본 연구는 강우 발생시 유량을 추정하는 것에 목적이 있다. 이를 위해 본 연구는 선행연구의 모형 개발방법론에서 벗어나 딥러닝 알고리즘 중 하나인 합성곱 신경망 (convolution neural network)과 수문학적 이미지 (hydrological image)를 이용하여 강우 발생시 유량을 추정하였다. 합성곱 신경망은 일반적으로 분류 문제 (classification)을 해결하기 위한 목적으로 개발되었기 때문에 불특정 연속변수인 유량을 모의하기에는 적합하지 않다. 이를 위해 본 연구에서는 합성곱 신경망의 완전 연결층 (Fully connected layer)를 개선하여 연속변수를 모의할 수 있도록 개선하였다. 대부분 합성곱 신경망은 RGB (red, green, blue) 사진 (photograph)을 이용하여 해당 사진이 나타내는 것을 예측하는 목적으로 사용하지만, 본 연구의 경우 일반 RGB 사진을 이용하여 유출량을 예측하는 것은 경험적 모형의 전제(독립변수와 종속변수의 관계)를 무너뜨리는 결과를 초래할 수 있다. 이를 위해 본 연구에서는 임의의 유역에 대해 2차원 공간에서 무차원의 수문학적 속성을 갖는 grid의 집합으로 정의되는 수문학적 이미지는 입력자료로 활용했다. 합성곱 신경망의 구조는 Convolution Layer와 Pulling Layer가 5회 반복하는 구조로 설정하고, 이후 Flatten Layer, 2개의 Dense Layer, 1개의 Batch Normalization Layer를 배열하고, 다시 1개의 Dense Layer가 이어지는 구조로 설계하였다. 마지막 Dense Layer의 활성화 함수는 분류모형에 이용되는 softmax 또는 sigmoid 함수를 대신하여 회귀모형에서 자주 사용되는 Linear 함수로 설정하였다. 이와 함께 각 층의 활성화 함수는 정규화 선형함수 (ReLu)를 이용하였으며, 모형의 학습 평가 및 검정을 판단하기 위해 MSE 및 MAE를 사용했다. 또한, 모형평가는 NSE와 RMSE를 이용하였다. 그 결과, 모형의 학습 평가에 대한 MSE는 11.629.8 m3/s에서 118.6 m3/s로, MAE는 25.4 m3/s에서 4.7 m3/s로 감소하였으며, 모형의 검정에 대한 MSE는 1,997.9 m3/s에서 527.9 m3/s로, MAE는 21.5 m3/s에서 9.4 m3/s로 감소한 것으로 나타났다. 또한, 모형평가를 위한 NSE는 0.7, RMSE는 27.0 m3/s로 나타나, 본 연구의 모형은 양호(moderate)한 것으로 판단하였다. 이에, 본 연구를 통해 제시된 방법론에 기반을 두어 CNN 모형 구조의 확장과 수문학적 이미지의 개선 또는 새로운 이미지 개발 등을 추진할 경우 모형의 예측 성능이 향상될 수 있는 여지가 있으며, 원격탐사 분야나, 위성 영상을 이용한 전 지구적 또는 광역 단위의 실시간 유량 모의 분야 등으로의 응용이 가능할 것으로 기대된다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.13 no.3
• /
• pp.9-15
• /
• 2013

Recently, Intrusion detection system is an important technology in computer network system because of has seen a dramatic increase in the number of attacks. The most of intrusion detection methods do not detect intrusion on real-time because difficult to analyze an auditing data for intrusions. A network intrusion detection system is used to monitors the activities of individual users, groups, remote hosts and entire systems, and detects suspected security violations, by both insider and outsiders, as they occur. It is learns user's behavior patterns over time and detects behavior that deviates from these patterns. In this paper has rule-based component that can be used to encode information about known system vulnerabilities and intrusion scenarios. Integrating the two approaches makes Intrusion Detection System a comprehensive system for detecting intrusions as well as misuse by authorized users or Anomaly users (unauthorized users) using RFM analysis methodology and monitoring collect data from sensor Intrusion Detection System(IDS).

• Journal of The Korean Association of Information Education
• /
• v.3 no.2
• /
• pp.120-127
• /
• 2000

All possible efforts have been done to adapt to the information-oriented society throughout the whole area of education. Especially, it is strongly demanded that teachers should effectively apply information communication and disposal to all the educational activities of instruction-learning, students management, school affairs, and administrative affairs. In this thesis, we chose as educational contents the information technology which is necessary in an educational site to increase the capability of applying information of teachers and developed remote training materials. In addition, we developed measurement instruments to evaluate the capability of applying information of teachers and gave grades to them. Grading System of the Capability of Applying Information of Teachers will be a standard of the capability of applying information.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.1
• /
• pp.108-116
• /
• 2005

Synchronizations of intra${\cdot}$intermedia for the lecture presentation in distributed multimedia environments are difficult to guarantee accurate temporal relationship between media, due to the asynchronous errors such as the delay or loss of transferred data or the transmission characteristics of each media. The jitter phenomenon occurs when the network delay has the media arrival rate abnormal because the intra-media synchronization reflects the presentation rate. And the cumulative effective of jitters on a per media stream basis results in a skew. This phenomenon cause confusion to contents recognition of learners due to network delay and can not provide effective interaction of sender and receiver in the distance education. Therefore, this paper can be solution to problems due to network delay by maintaining the requirements of temporal relationship between more than one media. And this paper enables to suggest the inter-media synchronization method that is subject to be influenced by presentation rate, and to implement lecture presentation system for distance education.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.155-160
• /
• 2003

This paper presents a multiple face detector based on a robust pupil detection technique. The pupil detector uses active illumination that exploits the retro-reflectivity property of eyes to facilitate detection. The detection range of this method is appropriate for interactive desktop and kiosk applications. Once the location of the pupil candidates are computed, the candidates are filtered and grouped into pairs that correspond to faces using heuristic rules. To demonstrate the robustness of the face detection technique, a dual mode face tracker was developed, which is initialized with the most salient detected face. Recursive estimators are used to guarantee the stability of the process and combine the measurements from the multi-face detector and a feature correlation tracker. The estimated position of the face is used to control a pan-tilt servo mechanism in real-time, that moves the camera to keep the tracked face always centered in the image.

• Archives of design research
• /
• v.11 no.3
• /
• pp.79-88
• /
• 1998

This research was carried out with emphasis on merits of computers as an education medum. Network technologies make collaboration as easy as they work in the same space. It is generally considered that education should be done with adequate contents and effective methods. But, the methods used in computer graphics education are not different from others, and this fact makes a low efficiency. To improve the education environments, design education program is developed. This is designed on the basis of LAN, and partially on the web. The library where design materials for study are stored and the gallery where design works done by students are exhibited are modules that utilize web technologies. Communication between students will become easy by using whiteboard and feedback from various kinds of user will be done by uploading design works on the web. But the program can be used only in the computer oriented subjects now, so further study should be carried out to broaden the scope of design education.