• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.289-293
• /
• 2000

We propose two new algorithms for parallelism-independent scheduling. The machine code generated from the compiler using these algorithms in its scheduling phase is parallelism-independent code, executable in minimum time regardless of the number of the processors in the parallel computer. Our new algorithms have the following phases: finding the minimum number of processors on which the program can be executed in minimal time, scheduling by an heuristic algorithm for this predefined number of processors, and serialization of the parallel schedule according to the earliest start time of the tasks. At run time tasks are taken from the serialized schedule and assigned to the processor which allows the earliest start time of the task. The order of the tasks decided at compile time is not changed at run time regardless of the number of the available processors which means there is no out-of-order issue and execution. The scheduling is done predominantly at compile time and dynamic scheduling is minimized and diminished to allocation of the tasks to the processors. We evaluate the proposed algorithms by comparing them in terms of schedule length to the CP/MISF algorithm. For performance evaluation we use both randomly generated DAGs (directed acyclic graphs) and DACs representing real applications. From practical point of view, the algorithms we propose can be successfully used for scheduling programs for in-order superscalar processors and shared memory multiprocessor systems. Superscalar processors with any number of functional units can execute the parallelism-independent code in minimum time without necessity for dynamic scheduling and out-of-order issue hardware. This means that the use of our algorithms will lead to reducing the complexity of the hardware of the processors and the run-time overhead related to the dynamic scheduling.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.372-380
• /
• 2022

This study proposes a distributed parallel processing system, called the Fast Analysis System for remote sensing daTa(FAST), for large-scale satellite image processing and analysis. FAST is a system that designs jobs in vertices and sequences, and distributes and processes them simultaneously. FAST manages data based on the Hadoop Distributed File System, controls entire jobs based on Apache Spark, and performs tasks in parallel in multiple slave nodes based on a docker container design. FAST enables the high-performance processing of progressively accumulated large-volume satellite images. Because the unit task is performed based on Docker, it is possible to reuse existing source codes for designing and implementing unit tasks. Additionally, the system is robust against software/hardware faults. To prove the capability of the proposed system, we performed an experiment to generate the original satellite images as ortho-images, which is a pre-processing step for all image analyses. In the experiment, when FAST was configured with eight slave nodes, it was found that the processing of a satellite image took less than 30 sec. Through these results, we proved the suitability and practical applicability of the FAST design.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2004.04a
• /
• pp.275-278
• /
• 2004

The geo-referencing of satellite imagery is a key task in remote sensing. GCPs are points the position of which is known both in the image and in the supporting maps. Mapping function makes the determination of map coordinates of all image pixels possible. Generally manual operations are done to identify image points corresponding to the points on a digital topographic map. In order to accurately measure ground coordinates of GCPs, differential global positioning system (DGPS) surveying are used. To acquire the sufficient number of well distributed GCPs is one of the most time-consuming and cost-consuming tasks. This paper describes the procedure of automatically extracting GCOs using GCP database. GCP image chips and image matching technique are used for automatic extraction of GCPs. We developed image processing tool for making image chip GCPs and Web Server for management of GCPs.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10a
• /
• pp.17-17
• /
• 1996

An experimental research is a useful approach for realizing autonomous mobile robots to work in real environment. We are developing an autonomous mobile robot platform named "Yamabico" as a tool for experimental real world robotics research. The architecture of Yamabico is based on the concept of centralized decision making and functionally modularization. Yamabico robot has two level structure with behavior and function levels, and its hardware and software are functionally distributed for providing incremental development and good maintenancibility. We are using many Yamabico robots in our laboratory to realize the robust navigation technology for autonomous robots. The methodology for experimental and task-oriented approach of mobile robotics will be presented. And some experimental results of real world navigation in indoor and outdoor environment will be shown. be shown.

• Journal of Institute of Control, Robotics and Systems
• /
• v.9 no.10
• /
• pp.789-797
• /
• 2003

An implementation scheme and some improvements are proposed to adopt public-licensed operating system, Linux and de-facto world-wide network standard, TCP/IP into the field of behavior-based autonomous mobile robots. To demonstrate the needs of scheme and the improvement, an analysis is performed on a server/client communication problem with real time Linux previously proposed, and another analysis is also performed on interactions among TCP/IP communications and the performance of Linux system using them. Implementation of behavior-based control architecture on real time Linux is proposed firstly. Revised task-scheduling schemes are proposed that can enhance the performance of server/client communication among local tasks on a Linux platform. A new method of TCP/IP packet flow handling is proposed that prioritizes TCP/IP software interrupts with aperiodic server mechanism as well. To evaluate the implementation scheme and the proposed improvements, performance enhancements are shown through some simulations.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1162-1167
• /
• 2003

This paper presents a simple sensor network consists of a group of sensors, RF components, and microprocessors, to perform a distributed sensing and information transmission using wireless links. In the proposed sensor network, though each sensor node has a limited capability and a simple signal-processing engine, a group of sensor nodes can perform a various tasks through coordinated information sharing and wireless communication in a large working area. Using the capability of self-localization and tracking, we show the sensor network can be applied to localization and navigation of mobile robot in which the robot has to be coordinated effectively to perform given task in real time.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1051-1055
• /
• 2003

Policies are collections of general principles specifying the desired behavior and state of a system. Network management is mainly carried out by following policies about the behavior of the resources in the network. Policy-based (PB) network management supports to manage distributed system in a flexible and dynamic way. This paper focuses on configuration management based on Internet Engineering Task Force (IETF) standards. Network security approaches include the usage of intrusion detection system to detect the intrusion, building firewall to protect the internal systems and network. This paper presents how the policy-based framework is collaborated among the network security systems (intrusion detection system, firewall) and intrusion detection systems are cooperated to detect the intrusions.

• Proceedings of the CALSEC Conference
• /
• 1997.11a
• /
• pp.127-132
• /
• 1997

본 논문의 연구방향은 객체지향방법론을 이용하여 PDM에서의 워크플로우를 재설계하는 것이다. 기존의 방법론들은 워크플로우 엔진과 작업자 사이의 흐름에 중점을 두었으나 본 논문에서는 프로세스와 작업에 중점을 두고 이를 각각의 객체로 설계하는 방안을 연구하고자 한다. 시스템의 설계를 위하여 Rumbaugh의 OMT(Object Modeling Technique) 방법론을 기본모델링 방법론으로 사용한다. 연구내용은 object model을 통한 정적 구조 설계, dynamic model을 이용한 시간에 따른 동적 구조 설계, 그리고 functional model에서의 데이터의 전이 및 시스템간의 연계의 설계이다. 특히 object model에서의 작업설계 및 dynamic model에서의 상태변화에 중점을 두고 DCOM(Distributed Component Object Model)을 사용하여 작업(task)을 중심으로 한 분산환경을 구현한다.

• Journal of the Korea Computer Graphics Society
• /
• v.1 no.2
• /
• pp.213-225
• /
• 1995

3 차원 볼륨 데이터를 시각화(visualization)하기 위해서는 많은 계산 량과 메모리 량을 필요로 한다. 단일컴퓨터에서 순차 알고리즘을 이용하여 데이터를 시각화하고 분석하는 것은 실시간 응용 프로그램에는 부적합하다. 기존의 병렬 볼륨 렌더링에서의 데이터 분할 방법은 대부분 정적 로드 밸런싱(static load balancing)에 기반하고 있다. 동적 로드 밸런싱에 기반한 기존의 방법들은 불륨 데이터의 정규성(regularity)을 이용할 수 없다는 단점이 있다. 본 연구에서는 3 차원 볼륨 데이터에 대하여 로컬 태스크 큐(local task queue) 기법에 기반한 새로운 로드밸런싱 알고리즘을 제안한다. 제안한 방법은 계산에 참여할 노드(node)들을 PVM(parallel virtual machine)의 동적 프로세스 그룹(dynamic process group: DPG)을 이용하여 정적으로 그룹화(grouping)한다. 각각의 DPG들은 로컬 태스크 큐를 기반으로 단위 서브-블록에 대하여 동적 로드 밸런싱을 수행한다. 최적화된 레이 캐스팅 알고리즘들을 분산 환경에 새롭게 적용함으로써 로드 밸런싱으로 생길 수 있는 오버 헤드를 최소화하였다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.347-353
• /
• 2001

A stable TSK -type FLC can be designed by the method of Parallel Distributed Compensation (PDC) [2] but in this case, solving the LMI problem is not a trivial task. To overcome such a difficulty, a Time-Delay based FLC (TDFLC) is proposed. TSK -type TDFLC consists of Time-Delay Control (TDC) and Sliding Mode Control (SMC) schemes, which result in a robust controller based upon an integral sliding surface. Finally, simulation study is conducted for a mass-spring-damper system.