• 정보처리학회 논문지
• /
• 제13권9호
• /
• pp.404-412
• /
• 2024

클라우드 환경의 도입은 애플리케이션 배포와 관리 방식을 혁신적으로 변화시켰으며, 마이크로서비스 아키텍처와 컨테이너 기술이 그 중심에 자리 잡고 있다. 그러나 이러한 변화는 마이크로서비스와 같은 복잡한 서비스 환경에서 서비스 간 상호작용을 정확히 파악하고 내부 프로세스를 세밀하게 분석해야 하는 새로운 과제를 제기했다. 기존의 모니터링 기법은 이와 같은 복잡한 환경을 충분히 분석하는 데 한계를 보였으며, 이를 해결하기 위해 최근 eBPF(extended Berkeley Packet Filter) 기술이 주목받고 있다. eBPF는 리눅스 커널에서 발생하는 이벤트를 실시간으로 수집하고 분석할 수 있는 강력한 기술로, 커널 영역에서 발생하는 파일 시스템 활동을 비롯한 다양한 이벤트를 모니터링할 수 있다. 본 논문에서는 이러한 eBPF를 기반으로 한 컨테이너 활동 분석 시스템을 제안하며, 이 시스템이 컨테이너와 호스트 시스템의 커널 영역에서 발생하는 이벤트를 실시간으로 모니터링하고, 수집된 데이터를 분석하는 방법을 제시한다. 또한, eBPF를 활용한 대표적인 컨테이너 모니터링 시스템인 Tetragon, Falco, Tracee를 이벤트 탐지 방식, 기본 정책 적용 여부, 이벤트 유형 식별, 시스템 콜 차단 및 경고 생성 기능 측면에서 비교 분석하여 각 시스템의 장단점을 평가하고, 컨테이너 프로세스 감시 및 제한에 필요한 기능을 파악하였다. 나아가, 본 논문에서는 제안된 시스템을 컨테이너 메타데이터 수집, 내부 활동 모니터링, 시스템 메타데이터 연계의 세 가지 측면에서 설명하고 평가하며, 관련 연구와의 비교를 통해 eBPF 기반 모니터링 시스템의 효용성과 향후 발전 가능성에 대해 논의한다.

• Journal of Communications and Networks
• /
• 제17권3호
• /
• pp.286-295
• /
• 2015

Avionic databuses fulfill a critical function in the connection and communication of aircraft components and functions such as flight-control, navigation, and monitoring. Ethernet-based avionic databuses have become the mainstream for large aircraft owning to their advantages of full-duplex communication with high bandwidth, low latency, low packet-loss, and low cost. As a new generation aviation network communication standard, avionics full-duplex switched ethernet (AFDX) adopted concepts from the telecom standard, asynchronous transfer mode (ATM). In this technology, the switches are the key devices influencing the overall performance. This paper reviews the avionic databus with emphasis on the switch architecture classifications. Based on a comparison, analysis, and discussion of the different switch architectures, we propose a new avionic switch design based on a time-division switch fabric for high flexibility and scalability. This also merges the design concept of space-partition switch fabric to achieve reliability and predictability. The new switch architecture, called space partitioned shared memory switch (SPSMS), isolates the memory space for each output port. This can reduce the competition for resources and avoid conflicts, decrease the packet forwarding latency through the switch, and reduce the packet loss rate. A simulation of the architecture with optimized network engineering tools (OPNET) confirms the efficiency and significant performance improvement over a classic shared memory switch, in terms of overall packet latency, queuing delay, and queue size.

• 한국경영과학회지
• /
• 제36권1호
• /
• pp.39-55
• /
• 2011

Process monitoring has been emphasized for the monitoring of complex system such as chemical processing industries to achieve the efficiency enhancement, quality management, safety improvement. Recently, ICA (Independent Component Analysis) based MSPC (Multivariate Statistical Process Control) was widely used in process monitoring approaches. Moreover, DICA (Dynamic ICA) has been introduced to consider the system dynamics. However, the existing approaches show the limitation that their performances are strongly dependent on the statistical distributions of control variables. To improve the limitation, we propose a novel approach for process monitoring by integrating DICA and LOF (Local Outlier Factor). In this paper, we aim to improve the fault detection rate with the proposed method. LOF detects local outliers by using density of surrounding space so that its performance is regardless of data distribution. Therefore, the proposed method not only can consider the system dynamics but can also assure robust performance regardless of the statistical distributions of control variables. Comparison experiments were conducted on the widely used benchmark dataset, Tennessee Eastman process (TE process), and showed the improved performance than existing approaches.

• 반도체디스플레이기술학회지
• /
• 제18권4호
• /
• pp.81-86
• /
• 2019

According to the needs of many users, motor pumps have been steadily developed and widely used in many industries where fluids are used. Motor pumps are used in a variety of environments, degrading quality and performance. It is becoming important to monitor the condition of motor pumps in order to maintain system performance and increase efficiency. This paper presents the method for effectively monitoring the condition of motor pumps. The designed MMI controller receives the collected data through data logging and output and controls the motor pump with touch screen. Implementing a Wi-Fi monitoring system and SCADA monitoring system based on Ethernet and RS485, user can monitor even if the user is far from the MMI controller without time and space limitation. In addition, by implementing a voice output system, the user can immediately recognize the situation through the sound. Therefore, through the proposed method, multi-monitoring system solves the cause of breakdowns and degradation of motor-pump and gives the possibility of commercialization by providing the convenience of maintenance to users.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1759-1772
• /
• 2023

Chinese named entity recognition (NER) is a challenging work that seeks to find, recognize and classify various types of information elements in unstructured text. Due to the Chinese text has no natural boundary like the spaces in the English text, Chinese named entity identification is much more difficult. At present, most deep learning based NER models are developed using a bidirectional long short-term memory network (BiLSTM), yet the performance still has some space to improve. To further improve their performance in Chinese NER tasks, we propose a new NER model, IDCNN-BiLSTM-Highway, which is a combination of the BiLSTM, the iterated dilated convolutional neural network (IDCNN) and the highway network. In our model, IDCNN is used to achieve multiscale context aggregation from a long sequence of words. Highway network is used to effectively connect different layers of networks, allowing information to pass through network layers smoothly without attenuation. Finally, the global optimum tag result is obtained by introducing conditional random field (CRF). The experimental results show that compared with other popular deep learning-based NER models, our model shows superior performance on two Chinese NER data sets: Resume and Yidu-S4k, The F1-scores are 94.98 and 77.59, respectively.

• 한국항공우주학회지
• /
• 제49권12호
• /
• pp.1027-1035
• /
• 2021

본 논문에서는 한반도 주변의 미세먼지 관측 임무를 위한 3U 큐브위성인 MIMAN 설계안을 제시하였다. MIMAN의 주요 임무 목표는 높은 공간 해상도로 한반도 주변의 미세먼지를 관측하는 것이다. 이를 통해 천리안위성 2B호 데이터에서 구름을 제거할 수 있는 보조 자료를 제공하는 것이 최종 목표이다. 본 연구에서는 임무를 정의하고 임무 요구조건 및 제한 조건을 도출하였다. 운용 개념을 정의하였으며, 안정적인 운용을 위해 통신 안정성을 고려하였다. 위성에 문제가 생겼을 경우, 이를 지상에서 해결할 수 있도록 모든 운용 모드에서 UHF 통신이 가능하도록 설계하였다. 임무와 운용 개념 설계 결과를 바탕으로 시스템 설계안을 도출하였다. 시스템 요구조건을 만족시킬 수 있는 시스템 설계안 및 인터페이스를 제시하였다. 시스템 인터페이스의 경우 각 하드웨어의 데이터 특성을 고려하여 설계하였다. 시스템 버짓 분석을 수행하였으며, 이를 통해 시스템 안정성을 확인하였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.793-794
• /
• 2003

Forest fire monitoring prototype system was developed by National Development Agency of Japan (NASDA) and the Ministry of Agriculture, Forestry and Fisheries of Japan (MAFF) to verify the usefulness of interoperabile system to study new services of Earth observation satellite data distribution for a practical application. In this system, a standard interface of Web based GIS technology, OpenGIS Consortium (OGC) technology, was adopted. This system is also expected to encourage data sharing activities in Digital Asia Network (DAN) as a demonstration system.

• 한국화재소방학회:학술대회논문집
• /
• 한국화재소방학회 1997년도 International Symposium on Fire Science and Technology
• /
• pp.282-288
• /
• 1997

The purpose of this paper is to predict the situation of leak in closed space using an Artificial Neural Network (ANN). The existing system can't monitor the whole He situations with on/off signals. Especially the first stage of data determines the leak spot and intensity is disregarded in gas accidents. To complement these faults, a new prototype of monitoring system is proposed. Ihe system is composed of'sensing systenL data acquisition system computer, and ANN implemented in software and is capable of identifying the leak spot and intensity in closed space. The concentration of gas is measured at the 4 different places. The network has 3 layers that are composed of 4 input Processing Element (PE),24 hidden PEs, md 4 output PEs. The ANN has optimum condition through several experiments and as a consequence the recognition rate of93.75% is achieved finally

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권11호
• /
• pp.3544-3564
• /
• 2022

With the development of the NB-IoT (Narrow band Internet of Things) and smart cities, coupled with the emergence of smart smoke sensors, new requirements and issues have been introduced to study on the deployment of sensors in large spaces. Previous research mainly focuses on the optimization of wireless sensors in some monitoring environments, including three-dimensional terrain or underwater space. There are relatively few studies on the optimization deployment problem of smart smoke sensors, and leaving large spaces with obstacles such as libraries out of consideration. This paper mainly studies the deployment issue of smart smoke sensors in large spaces by considering the fire probability of fire areas and the obstacles in a monitoring area. To cope with the problems of coverage blind areas and coverage redundancy when sensors are deployed randomly in large spaces, we proposed an optimized deployment strategy of smart smoke sensors based on the PSO (Particle Swarm Optimization) algorithm. The deployment problem is transformed into a multi-objective optimization problem with many constraints of fire probability and barriers, while minimizing the deployment cost and maximizing the coverage accuracy. In this regard, we describe the structure model in large space and a coverage model firstly, then a mathematical model containing two objective functions is established. Finally, a deployment strategy based on PSO algorithm is designed, and the performance of the deployment strategy is verified by a number of simulation experiments. The obtained experimental and numerical results demonstrates that our proposed strategy can obtain better performance than uniform deployment strategies in terms of all the objectives concerned, further demonstrates the effectiveness of our strategy. Additionally, the strategy we proposed also provides theoretical guidance and a practical basis for fire emergency management and other departments to better deploy smart smoke sensors in a large space.

• 천문학회보
• /
• 제39권2호
• /
• pp.112.2-112.2
• /
• 2014

We propose simultaneous monitoring observations of 22 GHz $H_2O$ and 43/86/129 GHz SiO masers toward ~15 evolved stars in order to investigate spatial structure and dynamical effect from SiO to $H_2O$ maser regions including mass-loss process and development of asymmetry in circumstellar envelopes. We also aim at investigating mutual association and difference between SiO and $H_2O$ masers for establishing SiO and $H_2O$ maser models coupled to hydrodynamical model of circumstellar envelope. In addition, the correlation and difference of SiO maser properties among J=1-0, J=2-1, and J=3-2 transition masers are traced according to different type of stars for constraining SiO pumping models. These scientific goals and target sources were determined based on KVN single dish and VLBI feasibility test observations at 4 bands. As a total observing time of every 2 month monitoring, about 90 and 360 hours (in average per year) are required for single dish and VLBI observations, respectively. From the 2014B observing season, these monitoring observations will be derived as one of KVN key science programs.