• 대한임베디드공학회논문지
• /
• 제11권2호
• /
• pp.57-65
• /
• 2016

In this paper, we propose a system for efficient use of shared memory between CPU and GPU. The system, called Fusion Architecture, assures consistency of the shared memory and minimizes cache misses that frequently occurs on Heterogeneous System Architecture or Unified Virtual Memory based systems. It also maximizes the performance for memory intensive jobs by efficient allocation of GPU cores. To test between architectures on various scenarios, we introduce the Fusion Architecture Analyzer, which compares OpenMP, OpenCL, CUDA, and the proposed architecture in terms of memory overhead and process time. As a result, Proposed fusion architectures show that the Fusion Architecture runs benchmarks 55% faster and reduces memory overheads by 220% in average.

• 한국군사과학기술학회지
• /
• 제11권1호
• /
• pp.85-92
• /
• 2008

An architecture for multiple radar tracking systems can be broadly categorized according to the methods in which the tracking functions are performed : central-level tracking and distributed tracking. In the central-level tracking, target tracking is performed using observations from all radar systems. This architecture provides optimal solution to target tracking. In distributed tracking, tracking is performed at each radar system and the composite track information is formed through track fusion integrating multiple radar-level tracks. Track-to-track fusion and track-to-track association are required to perform in this architecture. In this paper, issues and recent research on the two tracking architectures are surveyed.

• Journal of Information Processing Systems
• /
• 제12권4호
• /
• pp.724-740
• /
• 2016

The performance issues of screening large database compounds and multiple query compounds in virtual screening highlight a common concern in Chemoinformatics applications. This study investigates these problems by choosing group fusion as a pilot model and presents efficient parallel solutions in parallel platforms, specifically, the multi-core architecture of CPU and many-core architecture of graphical processing unit (GPU). A study of sequential group fusion and a proposed design of parallel CUDA group fusion are presented in this paper. The design involves solving two important stages of group fusion, namely, similarity search and fusion (MAX rule), while addressing embarrassingly parallel and parallel reduction models. The sequential, optimized sequential and parallel OpenMP of group fusion were implemented and evaluated. The outcome of the analysis from these three different design approaches influenced the design of parallel CUDA version in order to optimize and achieve high computation intensity. The proposed parallel CUDA performed better than sequential and parallel OpenMP in terms of both execution time and speedup. The parallel CUDA was 5-10x faster than sequential and parallel OpenMP as both similarity search and fusion MAX stages had been CUDA-optimized.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.1791-1796
• /
• 2004

Recently, great improvements have been made in developing autonomous underwater vehicles (AUVs) using stateof- the-art technologies for various kinds of sophisticated underwater missions. To meet increasing demands posed on AUVs, a powerful on-board computer system and an accurate sensor system with an well-organized control system architecture are needed. In this paper, a new control system architecture is proposed for AUV, ORCA (Oceanic Reinforced Cruising Agent) which is being currently developed by Korea Research Institute of Ships and Ocean Engineering (KRISO). The proposed architecture uses a hybrid architecture that combines a hierarchical architecture and a behavior based control architecture with an evaluator for coordinating between the architectures. This paper also proposed a sensor fusion structure based on the definition of 4 categories of sensors called grouping and 5-step data processing procedure. The development of the AUV, ORCA involving the system architecture, vehicle layout, and hardware configuration of on-board system are described.

• 한국자원식물학회지
• /
• 제19권3호
• /
• pp.418-421
• /
• 2006

In this study, we surveyed the influence of IOA (iodoacetamide) and media upon protoplast fusion for the efficient production of the somatic hybrid among S. sisymbriifolium and other Solanum species (S. intergrifolium and S. toxicarium). Regardless of a breed, as the IOA concentration increases, the cell division tends to decrease. As the influence of the media on the colony formation, we could get 5 colonies from the fusion of S. sisymbriifolium and IOA-treated S. integrifolium protoplast, but none was observed in other fusions. As a result of analyzing their IDH isozyme, we found a somatic hybrid in 2 objects.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.76.2-76
• /
• 2001

In this paper, a new fusion architecture consisting of a host filter and a do-correlated compression filter is proposed based on propagated measurement fusion. In the proposed architecture, the host filter estimates the system states in long-term sense based on the measurements from the beginning to the current time. The de-correlated compression filter assists the host filter by providing fusion results in short-term sense based on the measurements within a block of time. The proposed de-correlated compression filter alleviates computational burden of the host filter by reducing the maximum amount of instantaneous computation, and provides an efficient environment for real-time fault detection and estimation.

• 한국산학기술학회논문지
• /
• 제16권5호
• /
• pp.3491-3498
• /
• 2015

본 연구는 건축 도시 분야의 시장 전망과, 건축 도시 상품 패러다임 변화, 융복합 교육수요 증가에 기초하여 경력자 실무자들을 대상으로 융복합 교육 수요, 교육방법, 교육과정 운영체계 등에 대한 요구를 파악하는데 목적을 두었다. 건축 도시분야의 융복합 교육에 대한 수요자의 전반적인 요구 식별을 위해, 건설분야와 비건설분야 재직자 실무자를 대상으로 온라인 설문을 실시하였다. 교육수요 조사결과는 세 가지로 요약될 수 있다. 첫 번째, 단기적 관점에서 실무환경과 밀접한 연계성을 가진 학문(세부전공 빈도증가율: 금융(716.7%), 경영(633.3%), 기획 및 마케팅(454.5%))과 기존 학문을 융합하는 것이 중요하다. 두 번째, 융복합 교육에 적합한 운영방식에 대한 설문결과가 온 오프라인을 병행해야 한다는 의견이 79%를 차지했다. 이에 따라 오프라인 대학과 사이버 대학의 장점을 상호 보완한 새로운 교육방법이 요구된다. 세 번째, 융복합 교과과정내 교육수요자의 교과과목 선택방식은 한정 자유형이 70.9%로 나타났다. 교육과정 운영체계는 건설 실무의 흐름에 맞추어 직무관련 교과과목을 배치하고, 융복합 교과과목은 선택적으로 수강할 수 있게 구성하는 것이 필요하다.

• 한국항행학회논문지
• /
• 제26권5호
• /
• pp.325-330
• /
• 2022

항공기에 탑재된 센서들은 임무 수행에 필수 요소이며 센서들을 통해 얻어진 데이터의 융합은 임무 효율을 높이고 조종사의 부담을 줄이기 위해 적용되고 있다. 센서들로부터 얻어진 데이터를 특정 대상에 대해 일관되고 보다 정리된 형태로 조종사에게 제공하기 위해 데이터 융합이 적용되어 발전하고 있다. 현재 운용되고 있는 군용 항공기는 Link-16 과 같은 전술데이터링크에 연동하여 향상된 전술 상황을 조종사에게 전시하여 임무 효율을 높이고 있다. 항공기에 탑재된 센서가 고성능화 되면서 얻어진 정확도가 향상된 센서 데이터와 전술데이터링크를 통해 수신한 전술상황정보를 융합하여 조종사에게 고신뢰성의 전술상황 및 임무 환경을 제공하고 효율적인 임무 수행과 높은 생존성을 기대할 수 있다. 본 논문에서는 항공기 실시간 센서 데이터와 전술데이터링크를 통해 얻어지는 데이터를 종합된 정보 형태로 제공하기 위한 융합 구조를 보인다.

• 한국정보디스플레이학회:학술대회논문집
• /
• 한국정보디스플레이학회 2008년도 International Meeting on Information Display
• /
• pp.1627-1630
• /
• 2008

We have demonstrated a flexible and full-color OTFT-OLED display. The display has a top-emitting pixel structure with a resolution of 80 ppi, which can be achieved by developed integration architecture of OTFTs. The 0.3-mm-thick flexible display exhibits peak brightness over 100 nit with a contrast ratio greater than 1000:1.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 1999년도 가을 학술발표논문집 Vol.26 No.2 (2)
• /
• pp.551-553
• /
• 1999

This paper explores the utility of a new classifier fusion approach to discrimination. Multiple classifier fusion, a popular approach in the field of pattern recognition, uses estimates of each individual classifier's local accuracy on training data sets. In this paper we investigate the effectiveness of fusion methods compared to individual algorithms, including the artificial neural network and k-nearest neighbor techniques. Moreover, we propose an efficient meta-classifier architecture based on an approximation of the posterior Bayes probabilities for learning the oracle.