• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.435-437
• /
• 2019

모바일 환경에서 다양한 AI 관련 응용을 수행하기 위해, 정확도에 기반한 크고 깊은 신경망 이외에, 정확도를 비교적 유지하면서 좀더 효율적인 신경망 구조에 대한 다양한 연구가 진행중이다. 본 논문에서는 모바일 딥러닝을 위한 다양한 임베디드 장치 및 모바일 폰에서의 성능 평가를 통해 경량 신경망의 비교 분석에 대한 연구를 담고 있다.

• Proceedings of the KSR Conference
• /
• 2008.11b
• /
• pp.1321-1326
• /
• 2008

According to the conventional train control system, the area of each train is detected by plural track circuits located in a constant distance on railway lines in order to control a distance between trains. The conventional train control system has the difficulty in making use of the substructure thoroughly and transmitting enormous amount of information. To solve those problems, the wireless CBTC system has been a global issue. To apply wireless CBTC system to train system, the following two requirements are preferentially necessary: (1) Dualizing wireless CBTC system to control trains ceaselessly in a system accident, (2) Improving dependency of transmitted information for location and velocity to protect collision and derailment of lightweight trains in advance.

• Journal of Information Processing Systems
• /
• v.14 no.6
• /
• pp.1398-1404
• /
• 2018

High-performance computing (HPC) provides to researchers a powerful ability to resolve problems with intensive computations, such as those in the math and medical fields. When an HPC platform is provided as a service, users may suffer from unexpected obstacles in developing and running applications due to restricted development environments and dependencies. In this context, operating system level virtualization can be a solution for HPC service to ensure lightweight virtualization and consistency in Dev-Ops environments. Therefore, this paper proposes three types of typical HPC structure for container environments built with HPC container and Docker. The three structures focus on smooth integration with existing HPC job framework, message passing interface (MPI). Lastly, the performance of the structures is analyzed with High Performance Linpack benchmark from the aspect of performance degradation in network communications under Docker.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.2
• /
• pp.450-470
• /
• 2023

Traditional cloud computing faces some challenges such as huge energy consumption, network delay and single point of failure. Edge computing is a typical distributed processing platform which includes multiple edge servers closer to the users, thus is more robust and can provide real-time computing services. Although outsourcing data to edge servers can bring great convenience, it also brings serious security threats. In order to provide image retrieval while ensuring users' data privacy, a privacy preserving image retrieval scheme in edge environment is proposed. Considering the distributed characteristics of edge computing environment and the requirement for lightweight computing, we present a privacy-preserving image retrieval scheme in edge computing environment, which two or more "honest but curious" servers retrieve the image quickly and accurately without divulging the image content. Compared with other traditional schemes, the scheme consumes less computing resources and has higher computing efficiency, which is more suitable for resource-constrained edge computing environment. Experimental results show the algorithm has high security, retrieval accuracy and efficiency.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• fall
• /
• pp.106-109
• /
• 2021

본 논문에서는 입력에 따라 합성곱 레이어 간의 잔차 연결을 변화시키는 동적 잔차 연결을 활용해 고해상도 복원 (Super-resolution) 작업을 위한 경량 네트워크를 설계하는 방법을 제안한다. 먼저, 동적 잔차 연결을 입력에 따라 변화시킬 수 있도록 경량화된 (Lightweight) 모듈을 설계하는 방법을 제안한다. 또한 이렇게 설계한 모듈로부터 얻은 잔차 연결에 대한 정보를 토대로 네트워크를 설계하는 방법을 제시한다. 제안된 방법을 통해 설계된 고해상도 복원 작업을 위한 네트워크는 적은 파라미터로도 입력에 따라 적응적으로 네트워크의 구조를 변화시킬 수 있어 효울적으로 다양한 입력 영상을 처리할 수 있다.

• Annual Conference of KIPS
• /
• 2023.05a
• /
• pp.479-481
• /
• 2023

Generative Adversarial Networks (GANs) have facilitated substantial improvement in single-image super-resolution (SR) by enabling the generation of photo-realistic images. However, the high memory requirements of GAN-based SRs (mainly generators) lead to reduced performance and increased energy consumption, making it difficult to implement them onto resource-constricted devices. In this study, we propose an efficient and compressed architecture for the SR-GAN (generator) model using the model compression technique Knowledge Distillation. Our approach involves the transmission of knowledge from a heavy network to a lightweight one, which reduces the storage requirement of the model by 58% with also an increase in their performance. Experimental results on various benchmarks indicate that our proposed compressed model enhances performance with an increase in PSNR, SSIM, and image quality respectively for x4 super-resolution tasks.

• Annual Conference of KIPS
• /
• 2008.05a
• /
• pp.1108-1111
• /
• 2008

홈네트워크 기술은 통신과 방송 융합, 유비쿼터스 사회로의 빠른 이동 등 IT 전반적인 환경에서 빠른 변화와 함께 사용자의 특성을 고려해야함으로, 다양한 분야의 기술들이 융합되어 IT 분야 통합과 같은 성격을 가지고 있다. 최근 들어 디바이스 인증기능을 추가하여 유효한 디바이스를 통해서만 서비스를 제공 받을 수 있게 하는 한 단계 강화된 보안의 필요성이 제기되고 있으나, 이를 위해 먼저 보안 고려 사항을 선행하여 점검해야 한다. 또한 유비쿼터스 홈네트워크로의 진화는 다양한 서비스 도메인에서 홈디바이스 이동이 증가될 것이며, 홈디바이스간의 협업에 의한 새로운 홈서비스가 증가할 것이다. 이와 같은 기술의 진화에 따라 유비쿼터스 환경에서 안전한 이동과 seamless한 서비스를 제공할 수 있도록 경량화된 홈디바이스 인증/인가 기술이필요하다. 따라서 홈네트워크 구성 요소들의 여러 가지 사항들을 고려하여, 댁내와 댁외 모두 사용할 수 있도록 안전하고 효율성있는 경량화된 디바이스 인증 및 인가 기술을 제안하였다.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.3
• /
• pp.374-380
• /
• 2017

The Internet of Things (IoT) refers to intelligent technologies and services that connect all things to the internet so they can interactively communicate with people, other things, and other systems. The development of the IoT environment accompanies advances in network protocols applicable to more lightweight and intelligent sensors, and lightweight and diverse environments. The development of those elemental technologies is promoting the rapid progress in smart car environments that provide safety features and user convenience. These developments in smart car services will bring a positive effect, but can also lead to a catastrophe for a person's life if security issues with the services are not resolved. Although smart cars have various features with different types of communications functions to control the vehicles under the existing platforms, insecure features and functions may bring various security threats, such as bypassing authentication, malfunctions through illegitimate control of the vehicle via data forgery, and leaking of private information. In this paper, we look at types of smart car services in the IoT, deriving the security threats from smart car services based on various scenarios, suggesting countermeasures against them, and we finally propose a safe smart car application plan.

• Fire Science and Engineering
• /
• v.20 no.1 s.61
• /
• pp.23-27
• /
• 2006

With the development of the today's advanced industry civilization, We are always inhering a safety frigidity about disasters of various kinds when and where we may happen. The fires and disasters to be enlarged day by day are reported everyday through the mass communication. Therefore, a prevention countermeasure about the every kind fire and disaster is above all important along the social and the days requirement. As a kind of such countermeasure, this paper is proposed about automatic transmission system of disasters alarm by using wire and wireless communication network. The automatic transmission system prevents the unexpected fire or disaster from a sudden occurrence at the house, industrial field or at the place without the human. The proposed system has the characteristic of high precision and high response speed comparing with conventional system. Also, as the proposed system is small size and lightweight, the users have economic advantage and simply install the system.

• Smart Media Journal
• /
• v.12 no.3
• /
• pp.49-59
• /
• 2023

Optical Camera Communication (OCC), known as the next-generation wireless communication technology, is currently under extensive research. The performance of OCC technology is affected by the communication environment, and various strategies are being studied to improve it. Among them, the most prominent method is applying convolutional neural networks (CNN) to the receiver of OCC using deep learning technology. However, in most studies, CNN is simply used to detect the transmitter. In this paper, we experiment with applying the convolutional neural network not only for transmitter detection but also for the Rx demodulation system. We hypothesize that, since the data images of the OCC system are relatively simple to classify compared to other image datasets, high accuracy results will appear in most CNN models. To prove this hypothesis, we designed and implemented an OCC system to collect data and applied it to 12 different CNN models for experimentation. The experimental results showed that not only high-performance CNN models with many parameters but also lightweight CNN models achieved an accuracy of over 99%. Through this, we confirmed the feasibility of applying the OCC system in real-time on mobile devices such as smartphones.