• Journal of Advanced Navigation Technology
• /
• v.15 no.1
• /
• pp.76-82
• /
• 2011

Most previous work on network selection in heterogeneous wireless networks has concentrated on the quality of the network alone. Therefore, users are not satisfied with network quality based network selection due to different user preferences. To solve this problem, we proposes a QoE-aware network selection algorithm that is based on the consumption patterns of user preferences which is divided into normal user, cost-sensitive user, quality-sensitive user and video quality as well as network quality. As a result of experiments, cost-sensitive user and quality-sensitive user are satisfied with enhanced QoE by 36% and 3% from the proposed network selection algorithm compared to the normal user, respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10b
• /
• pp.277-279
• /
• 1998

비디오와 같은 매체가 결합된 대용량의 멀티미디어 데이터를 보다 효율적으로 저장 및 검색하기 위한 연구가 다양한 분야에 걸쳐 진행중이다. 본 논문에서는 NoD 서비스용 내용-기반 비디오 정보검색을 위해, 미국의 Wisconsin 대학에서 개발한 SHORE(Scalable Heterogeneous Object Repository) 객체-재향 저장 시스템을 이용하여, 멀티미디어 객체 자체의 비디오 스트림 데이터와 그에 따르는 부가적인 색인 정보를 효율적으로 저장하고 관리하기 위한 하부 저장 구조를 설계한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.10c
• /
• pp.289-291
• /
• 2001

그룹 통신 시스템은 결함 감내와 고 가용성을 향상시켜 주는 유용한 메커니즘이다. 그름 통신 시스템을 모바일 인터넷 환경으로 확장하게 될 때 모바일 호스트의 이동성과 단절로 인한 일시적인 그룹 멤버쉽의 비일관성으로 인해 빈번한 그룹 뷰 변경이 발생하고 그를 통신 시스템의 성능 저하를 야기시킨다. 본 논문에서는 이를 해결하고자 계층적 뷰 관리에 로컬 멤버 리스트와 일시적으로 단절된 멤버의 리스트를 추가하여 모바일 환경에서의 확장성 있는 그룹 멥버쉽 서비스를 제안한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2001.04a
• /
• pp.391-393
• /
• 2001

본 논문은 WAP Gateway의 HTML Filter 구현에 대하여 다루고 있다. 웹 콘텐츠를 무선환경에 맞는 WML 문서로 변환하기 위한 HTML Filter 구조를 설계하고 이와 관련된 RuleSet Database, Parsing Engine, Markup Language Translator의 기능을 정의한다. 마지막으로, 확장성 있는 웹 서비스를 위해 실제 웹상의 콘텐츠를 대상으로 한 실험으로 통해 구현된 HTML Filter의 성능 평가의 분석을 수행하여 구현시 고려해야 할 사항 및 향후 연구방향에 대하여 논의한다.

• Journal of KIISE:Information Networking
• /
• v.32 no.5
• /
• pp.561-573
• /
• 2005

As the demand on ubiquitous communication increases, global roaming and vertical handover will be prevailing in the near future. Since this environment is accompanied by the frequent handovers at remote sites, a scalable and fast authentication becomes prerequisite for ubiquitous communication. In this paper, we suggest a framework for scalable and fast authentication, using hierarchical caching based on general trust relationship among domains. At the end, we show that the proposed scheme achieves reduced authentication delay and network overhead through an analytic method with fluid flow model.

• Journal of KIISE:Information Networking
• /
• v.28 no.4
• /
• pp.578-585
• /
• 2001

IP Multicast that provides best-efforts service does not guarantee reliable delivery of multicast packets. In recent years, there are many approaches to support reliable multicast, but those are insufficient for implementing scalable and reliable multicast over Internet. We propose a Reliable Multicast Architecture(RMA) for scalable and reliable multicast. The RMA model guarantees reliability using a receiver initiated retransmission mechanism, and scalability using a feedback suppression mechanism by Multicast Router(MR). Furthermore, it utilizes underlying multicast routing information to minimize the cost of protocol modification and overheads. Our performance analyses show that RMA is much superior to previous works in the point of scalability and compatibility.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2002.11a
• /
• pp.610-613
• /
• 2002

To improve quality of service(QoS) in the current Internet, various QoS providing mechanisms such as RSVP, DiffServ have been proposed. In this paper we propose a more simple but more scalable mechanism which can guarantee end-to-end QoS. The proposed mechanism can provide scalability by minimizing the state information which is needed by router to reserve network resources. Using sender-initiated & soft-state resource reservation, a router does not need to keep the backward data path like RSVP. In this paper we illustrate the proposed resource reservation mechanism with network topology and signaling.

• Journal of Broadcast Engineering
• /
• v.9 no.3
• /
• pp.225-235
• /
• 2004

In this paper, we propose a new stereoscopic video coding approach for heterogeneous consumer devices by exploiting the concept of spatio-temporal scalability. The proposed method uses MPEG-2 standard for coding the left or main sequence and an enhanced compatible coding scheme for predicting the P- and B-type of frames of the right or auxiliary sequence. The enhanced compatible coding scheme predicts matching block by interpolating both two forward and backward motion predicted macroblocks and disparity predicted macroblock. To provide flexible stereo video service, we define both a temporally scalable layer and a spatially scalable layer for each eye-view. The experimental results show the efficiency of proposed coding scheme by comparison with already known methods and the advantages of disparity estimation in terms of scalability overhead. According to the experimental results, we expect the proposed functionalities will play a key role in establishing highly flexible stereo video service for ubiquitous computing environment where devices and network connections are heterogeneous.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.10
• /
• pp.722-733
• /
• 2006

In scalable streaming application, there are two important knobs to tune to effectively exploit the underlying network resource and to maximize the user perceivable quality of service(QoS): layer selection and packet scheduling. In this work, we propose Semantics Aware Packet Scheduling (SAPS) algorithm to address these issues. Using packet dependency graph, SAPS algorithm selects a layer to maximize QoS. We aim at minimizing distortion in selecting layers. In inter-frame coded video streaming, minimizing packet loss does not imply maximizing QoS. In determining the packet transmission schedule, we exploit the fact that significance of each packet loss is different dependent upon its frame type and the position within group of picture(GOP). In SAPS algorithm, each packet is assigned a weight called QoS Impact Factor Transmission schedule is derived based upon weighted smoothing. In simulation experiment, we observed that QOS actually improves when packet loss becomes worse. The simulation results show that the SAPS not only maximizes user perceivable QoS but also minimizes resource requirements.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.11a
• /
• pp.8-11
• /
• 2020

4 차 산업혁명 시대의 도래와 함께 AI, ICT 기술의 융합이 진행됨에 따라, 유저 레벨의 디바이스에서도 AI 서비스의 요청이 실현되었다. 이미지 처리와 관련된 AI 서비스는 피사체 판별, 불량품 검사, 자율주행 등에 이용되고 있으며, 특히 Deep Convolutional Neural Network (DCNN)은 이미지의 특색을 파악하는 데 뛰어난 성능을 보여준다. 하지만, 이미지의 크기가 커지고, 신경망이 깊어짐에 따라 연산 처리에 있어 낮은 데이터 지역성과 빈번한 메모리 참조를 야기했다. 이에 따라, 기존의 계층적 시스템 구조는 DCNN 을 scalable 하고 빠르게 처리하는 데 한계를 보인다. 본 연구에서는 DCNN 의 scalable 하고 빠른 처리를 위해 3 차원 메모리 구조의 Processing-In-Memory (PIM) 가속기를 제안한다. 이를 위해 기존 3 차원 메모리인 Hybrid Memory Cube (HMC)에 하드웨어 및 소프트웨어 모듈을 추가로 구성하였다. 구체적으로, Processing Element (PE)간 데이터를 공유할 수 있는 공유 캐시 및 소프트웨어 스택, 파이프라인화된 곱셈기 및 듀얼 프리페치 버퍼를 구성하였다. 이를 유명 DCNN 알고리즘 LeNet, AlexNet, ZFNet, VGGNet, GoogleNet, RestNet 에 대해 성능 평가를 진행한 결과 기존 HMC 대비 40.3%의 속도 향상을 29.4%의 대역폭 향상을 보였다.