• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.132-141
• /
• 2019

The necessity of transmitting video data over a narrow-bandwidth exists steadily despite that video service over broadband is common. In this paper, we propose a scalable video coding framework for low-resolution video transmission over a very narrow-bandwidth network by super-resolution of decoded frames of a base layer using a convolutional neural network based super resolution technique to improve the coding efficiency by using it as a prediction for the enhancement layer. In contrast to the conventional scalable high efficiency video coding (SHVC) standard, in which upscaling is performed with a fixed filter, we propose a scalable video coding framework that replaces the existing fixed up-scaling filter by using the trained convolutional neural network for super-resolution. For this, we proposed a neural network structure with skip connection and residual learning technique and trained it according to the application scenario of the video coding framework. For the application scenario where a video whose resolution is $352{\times}288$ and frame rate is 8fps is encoded at 110kbps, the quality of the proposed scalable video coding framework is higher than that of the SHVC framework.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.92-92
• /
• 2023

본 연구에서는 대한민국 도시 유역에 대하여 딥러닝 네트워크 기반의 분산형 수문 모형을 개발하였다. 개발된 모형은 완전연결계층(Fully Connected Layer)으로 연결된 여러 개의 장단기 메모리(LSTM-Long Short-Term Memory) 은닉 유닛(Hidden Unit)으로 구성되었다. 개발된 모형을 사용하여 연구 지역인 중랑천 유역을 분석하기 위해 1km² 해상도의 239개 모델 격자 셀에서 10분 단위 레이더-지상 합성 강수량과 10분 단위 기온의 시계열을 입력으로 사용하여 10분 단위 하도 유량을 모의하였다. 모형은 보정과(2013~2016년)과 검증 기간(2017~2019년)에 대한 NSE 계수는각각 0.99와 0.67로 높은 정확도를 보였다. 본 연구는 모형을 추가적으로 심층 분석하여 다음과 같은 결론을 도출하였다: (1) 모형을 기반으로 생성된 유출-강수 비율 지도는 토지 피복 데이터에서 얻은 연구 지역의 불투수율 지도와 유사하며, 이는 모형이 수문학에 대한 선험적 정보에 의존하지 않고 입력 및 출력 데이터만으로 강우-유출 분할과정을 성공적으로 학습하였음을 의미한다. (2) 모형은 연속 수문 모형의 필수 전제 조건인 토양 수분 의존 유출 프로세스를 성공적으로 재현하였다; (3) 각 LSTM 은닉 유닛은 강수 자극에 대한 시간적 민감도가 다르며, 응답이 빠른 LSTM 은닉 유닛은 유역 출구 근처에서 더 큰 출력 가중치 계수를 가졌는데, 이는 모형이 강수 입력에 대한 직접 유출과 지하수가 주도하는 기저 흐름과 같이 응답 시간의 차이가 뚜렷한 수문순환의 구성 요소를 별도로 고려하는 메커니즘을 가지고 있음을 의미한다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.2
• /
• pp.65-72
• /
• 2021

Recently, attacks on the network environment have been rapidly escalating and intelligent. Thus, the signature-based network intrusion detection system is becoming clear about its limitations. To solve these problems, research on machine learning-based intrusion detection systems is being conducted in many ways, but two problems are encountered to use machine learning for intrusion detection. The first is to find important features associated with learning for real-time detection, and the second is the imbalance of data used in learning. This problem is fatal because the performance of machine learning algorithms is data-dependent. In this paper, we propose the HSF-DNN, a network intrusion detection model based on a deep neural network to solve the problems presented above. The proposed HFS-DNN was learned through the NSL-KDD data set and performs performance comparisons with existing classification models. Experiments have confirmed that the proposed Hybrid Feature Selection algorithm does not degrade performance, and in an experiment between learning models that solved the imbalance problem, the model proposed in this paper showed the best performance.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1282-1289
• /
• 2017

Since the study of deep convolutional neural network became prevalent, one of the important discoveries is that a feature map from a convolutional network can be extracted before going into the fully connected layer and can be used as a saliency map for object detection. Furthermore, the model can use features from each different layer for accurate object detection: the features from different layers can have different properties. As the model goes deeper, it has many latent skip connections and feature maps to elaborate object detection. Although there are many intermediate layers that we can use for semantic segmentation through skip connection, still the characteristics of each skip connection and the best skip connection for this task are uncertain. Therefore, in this study, we exhaustively research skip connections of state-of-the-art deep convolutional networks and investigate the characteristics of the features from each intermediate layer. In addition, this study would suggest how to use a recent deep neural network model for semantic segmentation and it would therefore become a cornerstone for later studies with the state-of-the-art network models.

• Journal of Korea Game Society
• /
• v.12 no.6
• /
• pp.83-94
• /
• 2012

Employing in-depth interview, this study sought to explore the meaning of game play among those adolescent game addicts. Recent evolution of game text and rapid diffusion of smart media contributed to their addictive game use. Stronger relationship-building with their peer group through game play was also more important for them. In addition, alienation from family, school and society apparently led those adolescents to evaluate the virtual experience to be more valuable and meaningful. Lack of proper parental mediation and intervention from the school authority caused them to spend more time in the virtual world. Without understanding the complex social context surrounding the adolescents, a systematic approach to attenuate the problem of game addiction is hardly attainable.

• Journal of Digital Convergence
• /
• v.12 no.5
• /
• pp.501-515
• /
• 2014

The enforcement of the digital switch been two years, but more than half of the viewers are still not enjoying the benefits of it. Therefore, the government proposed that 8VSB transmission method so that majority of the viewer is able to enjoy the benefits of a digital switch. However, the claim has been suggested that 8VSB transmission method will have negative impacts on broadcast market feedback. In this regard, this study verified the effect of 8VSB and the method of minimization on the broadcast market. This study has conducted in-depth interviews concerned experts to achieve this purpose. Results of an interview revealed that the negative impact on the market of content and platforms, network is very small. In other words, the majority of the experts argued that the policy of government about 8VSB transmission are inadequate and it is improved to broaden the choice of the broadcast consumer.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.5
• /
• pp.13-22
• /
• 2011

Network Intrusion Detection Systems use regular expression to represent malicious packets and hardware-based pattern matching is required for fast deep packet inspection. Although hardware architectures for implementing constraint repetition operators such as {10} were recently proposed, they have some limitation. In this paper, we propose hardware architecture supporting constraint repetitions of general regular expression sub-patterns with lower logic complexity. The subpatterns supported by the proposed contraint repetition architecture include general regular expression patterns as well as a single character and fixed length patterns. With the proposed building block, we can implement more efficiently regular expression pattern matching hardwares.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1437-1444
• /
• 2020

With the development of computer vision systems, many advances have been made in the fields of surveillance, biometrics, medical imaging, and autonomous driving. In the field of autonomous driving, in particular, the object detection technique using deep learning are widely used, and the paved road detection is a particularly crucial problem. Unlike the ROI detection algorithm used in general object detection, the structure of paved road in the image is heterogeneous, so the ROI-based object recognition architecture is not available. In this paper, we propose a deep neural network architecture for atypical paved road detection using Semantic segmentation network. In addition, we introduce the multi-scale semantic segmentation network, which is a network architecture specialized to the paved road detection. We demonstrate that the performance is significantly improved by the proposed method.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.55-61
• /
• 2021

The character motion control based on physics simulation using reinforcement learning continue to being carried out. In order to solve a problem using reinforcement learning, the network structure, hyperparameter, state, action and reward must be properly set according to the problem. In many studies, various combinations of states, action and rewards have been defined and successfully applied to problems. Since there are various combinations in defining state, action and reward, many studies are conducted to analyze the effect of each element to find the optimal combination that improves learning performance. In this work, we analyzed the effect on reinforcement learning performance according to the state representation, which has not been so far. First we defined three coordinate systems: root attached frame, root aligned frame, and projected aligned frame. and then we analyze the effect of state representation by three coordinate systems on reinforcement learning. Second, we analyzed how it affects learning performance when various combinations of joint positions and angles for state.

• Asia Marketing Journal
• /
• v.8 no.3
• /
• pp.75-99
• /
• 2006

Inje University, a nonprofit-oriented educational institution, was ranked second in the nation and first in all the local universities in the 2001 Comprehensive Evaluation of the Universities in 25 years since it was founded. In order to find out the reason for this high reputation, we had an interview with the chairman and an in-depth interview with other school authorities, interviewed the students and the residents in the community, and collected related data for the second time. We revealed that Inje University had been performing public marketing in the areas of its management philosophy, function, form, and performance. Our interview with the chairman confirmed that Inje University's management philosophy is the frontier spirits that 'contribute to the moor, attracting nobody's attention, in the name of public interest.' It was also revealed that this management philosophy made the function of the university differ from that of the others. Inje University had been focusing on forming a public network for its community, the nation, and the world, not just for its students. Furthermore, we also found out that the university had its unique separate organizations to take care of this business. An excellent on-campus network for the student and the school, a network between off-campus industries, and an international Inje exchange network had been formed. We have concluded that Inje University is a strong nonprofit-oriented hidden champion. The healing art, easily ignored but essential to human beings, and its commitment to education with all its property invested have contributed to Inje University's social status, reputation, and achievements today.