RISS 학술연구정보서비스

검색
다국어 입력

http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.

변환된 중국어를 복사하여 사용하시면 됩니다.

예시)
  • 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
  • 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
닫기
    인기검색어 순위 펼치기

    RISS 인기검색어

      검색결과 좁혀 보기

      • 좁혀본 항목

      • 좁혀본 항목 보기순서

        • 원문유무
        • 음성지원유무
          • 원문제공처
          • 등재정보
          • 학술지명
          • 주제분류
          • 발행연도
          • 작성언어
          • 저자

        오늘 본 자료

        • 오늘 본 자료가 없습니다.
        더보기
        • 무료
        • 기관 내 무료
        • 유료
        • KCI등재

          Multiple Sliding Surface Control Approach to Twin Rotor MIMO Systems

          Quan Nguyen Van,Chang-Ho Hyun 한국지능시스템학회 2014 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.14 No.3

          In this paper, a multiple sliding surface (MSS) controller for a twin rotor multi-input-multioutput system (TRMS) with mismatched model uncertainties is proposed. The nonlinear terms in the model are regarded as model uncertainties, which do not satisfy the standard matching condition, and an MSS control technique is adopted to overcome them. In order to control the position of the TRMS, the system dynamics are pseudo-decomposed into horizontal and vertical subsystems, and two MSSs are separately designed for each subsystem. The stability of the TRMS with the proposed controller is guaranteed by the Lyapunov stability theory. Some simulation results are given to verify the proposed scheme, and the real time performances of the TRMS with the MSS controller show the effectiveness of the proposed controller.

        • Hadoop-based System for Analysis Big Social Sensor Data

          Van Quan Nguyen,Linh Van Ma,Jinsul Kim 한국정보기술학회 2018 한국정보기술학회지 Vol.2018 No.6

          요즘 많은 분석 데이터가 많은 업무에서 중요 해지고 있습니다. 데이터는 산업 시스템의 과학, 의학, 기상, 금융, 마케팅 또는 센서 데이터 일 수도 있고 소셜 네트워크의 소셜 데이터 일 수도 있습니다. Hadoop 프레임워크는 현재 분산 데이터뿐 아니라 대용량 데이터 처리를위한 최상의 선택이되고 있습니다. 이 백서에서는 Hadoop 분산 파일 시스템 (HDFS)에 MapReduce 기반 아키텍처를 배포하여 여러 사용자가 재난에 대해 수집한 사회적 센서 데이터를 처리합니다. 기상청이 예상하고 예측하고 주민에게 경고문을 게시하려면이 큰 데이터를 실시간으로 수집, 저장 및 처리해야합니다. Nowadays large analysis amount of data has become important for many tasks. Data could be scientific, medical, meteorological, financial, marketing or sensor data from industrial system even social data from the social network. Hadoop framework is currently becoming the best choice for big data processing as well as distributed data. This paper deployed MapReduce based architecture on Hadoop Distributed File System (HDFS) to process social sensor data which is collected from multiple users about the disaster. Real-time collecting, storing and processing of this big data is necessary for the meteorological department to forecast as well as publish the warning to residents.

        • Deep Learning-based Approach to Smart Factory

          Van Quan Nguyen,Linh Van Ma,Jinsul Kim 한국정보기술학회 2018 한국정보기술학회지 Vol.2018 No.6

          스마트 제조는 수집, 분석, 시각화 및 의사 결정에서의 시스템 성능 향상을 의미합니다. 우리는 장치 기반 및 네트워크 기반 기술뿐만 아니라 센서 데이터 조작에 있어 고급 프로세스를 시작하기 위해 기계 학습을 널리 사용하는 것을 목격 해 왔습니다. 이 글에서는 산업용 시스템의 센서 데이터를 분석하기위한 LSTM 아키텍처 기반의 반복적 인 신경망을 제시합니다. 시계열 데이터는 타임 라인에 따라 개체의 상태에 반영되기 때문에 많은 시스템에서 중요한 부분이 되었습니다. 왜 우리가 반복적 인 신경망을 데이터의 순서를 탐색하는 솔루션으로 사용하는지에 대한 주된 이유. LSTM 신경 회로망의 응용을 증명하기 위해 이상 검출 알고리즘을 제안하고 여러 데이터 집합에서 수행한다. Smart manufacturing refers to using advanced techniques in collecting, analyzing, visualization and decision making in management to improve system’s performance. We have been witnessing the widespread of machine learning to launch advanced process in the manipulation of sensor data as well as managing devices and productions based on network technologies. This article presents recurrent neural network with LSTM architecture-based approach to analyzing sensor data for the industrial system. Using time series data has become a critical part of many systems because this explored information reflect the state of objects according to the timeline. This is the major reason why we use Recurrent Neural Networks as a solution to explore the sequence of data. In order to prove the application of LSTM neural network, anomaly detection algorithm is proposed and perform on time series datasets.

        • KCI등재

          Social Media based Real-time Event Detection by using Deep Learning Methods

          Nguyen, Van Quan,Yang, Hyung-Jeong,Kim, Young-chul,Kim, Soo-hyung,Kim, Kyungbaek THE KOREAN INSTITUTE OF SMART MEDIA 2017 스마트미디어저널 Vol.6 No.3

          Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

        • KCI등재

          Vision Sensor-Based Driving Algorithm for Indoor Automatic Guided Vehicles

          Quan Nguyen Van,Hyuk-Min Eum,Jeisung Lee,Chang-Ho Hyun 한국지능시스템학회 2013 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.13 No.2

          In this paper, we describe a vision sensor-based driving algorithm for indoor automatic guided vehicles (AGVs) that facilitates a path tracking task using two mono cameras for navigation. One camera is mounted on vehicle to observe the environment and to detect markers in front of the vehicle. The other camera is attached so the view is perpendicular to the floor, which compensates for the distance between the wheels and markers. The angle and distance from the center of the two wheels to the center of marker are also obtained using these two cameras. We propose five movement patterns for AGVs to guarantee smooth performance during path tracking: starting, moving straight, pre-turning, left/right turning, and stopping. This driving algorithm based on two vision sensors gives greater flexibility to AGVs, including easy layout change, autonomy, and even economy. The algorithm was validated in an experiment using a two-wheeled mobile robot.

        • KCI등재

          LSTM-based Anomaly Detection on Big Data for Smart Factory Monitoring

          Van Quan Nguyen,Linh Van Ma,Jinsul Kim(김진술) 한국디지털콘텐츠학회 2018 한국디지털콘텐츠학회논문지 Vol.19 No.4

          이 논문에서는 이러한 산업 단지 시스템에서의 비정상적인 동작이 일어날 때, 시간 계열의 데이터를 분석하기 위하여 Big 데이터를 이용한 접근을 기반으로 하는 머신 러닝을 보여줍니다. Long Short-Term Memory (LSTM) 네트워크는 향상된 RNN버전으로서 입증되었으며 많은 작업에 유용한 도움이 되었습니다. 이 LSTM 기반 모델은 시간적 패턴뿐만 아니라 더 높은 레벨의 시간적 특징을 학습 한 다음, 미래의 데이터를 예측하기 위해 예측 단계에 사용됩니다. 예측 오차는 예측 인자에 의해 예측 된 결과와 실제 예상되는 값의 차이입니다. 오차 분포 추정 모델은 가우스 분포를 사용하여 관찰 스코어의 이상을 계산합니다. 이러한 방식으로, 우리는 하나의 비정상적 데이터의 개념에서 집단적인 비정상적 데이터 개념으로 바뀌어 갑니다. 이 작업은 실패를 최소화하고 제조품질을 향상시키는 Smart Factory의 모니터링 및 관리를 지원할 수 있습니다. This article presents machine learning based approach on Big data to analyzing time series data for anomaly detection in such industrial complex system. Long Short-Term Memory (LSTM) network have been demonstrated to be improved version of RNN and have become a useful aid for many tasks. This LSTM based model learn the higher level temporal features as well as temporal pattern, then such predictor is used to prediction stage to estimate future data. The prediction error is the difference between predicted output made by predictor and actual in-coming values. An error-distribution estimation model is built using a Gaussian distribution to calculate the anomaly in the score of the observation. In this manner, we move from the concept of a single anomaly to the idea of the collective anomaly. This work can assist the monitoring and management of Smart Factory in minimizing failure and improving manufacturing quality.

        • KCI등재후보

          Social Media based Real-time Event Detection by using Deep Learning Methods

          Van Quan Nguyen,Hyung-Jeong Yang,Young-chul Kim,Soo-hyung Kim,Kyungbaek Kim 한국스마트미디어학회 2017 스마트미디어저널 Vol.6 No.3

          '스콜라' 이용 시 소속기관이 구독 중이 아닌 경우, 오후 4시부터 익일 오전 7시까지 원문보기가 가능합니다.

          Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

        • KCI등재

          Landscapes and Ecosystems of Tropical Limestone: Case Study of the Cat Ba Islands, Vietnam

          Quan Nguyen Van,Thanh Tran Duc,Huy Dinh Van 한국생태학회 2010 Journal of Ecology and Environment Vol.33 No.1

          The Cat Ba Islands in Hai Phong City, northern Vietnam, consist of a large limestone island with a maximum height of 322 m above sea level and 366 small limestone islets with a total area of about 180 km2. The islands are relicts of karst limestone mountains that became submerged during the Holocene transgression 7000 – 8000 year ago. The combination of the longtime karst process and recent marine processes in the monsoonal tropical zone has created a very diversity landscape on the Cat Ba Islands that can be divided into 3 habitat types with 16 forms. The first habitat type is the karst mountains and hills, including karst mountains and hills, karst valleys and dolines, karst lakes, karst caves, and old marine terraces. The second habitat type is the limestone island coast, including beaches, mangrove marshes, tidal flats, rocky coasts, marine notch caves, marine karst lakes, and bights. The third habitat type is karst plains submerged by the sea, including karst cones (fengcong) and towers (fengling), bedrock exposed on the seabed, sandy mud seabed, and submerged channels. Like the landscape, the biodiversity is also high in ecosystems composed of scrub cover – bare hills,rainy tropical forests, paddy fields and gardens, swamps, caves, beaches, mangrove forests, tidal flats, rocky coasts, marine krast lakes, coral reefs, hard bottoms, seagrass beds and soft bottoms. The ecosystems on the Cat Ba Islands that support very high species biodiversity include tropical evergreen rainforests, soft bottoms; coral reefs, mangrove forests, and marine karst lakes. A total of 2,380 species have been recorded in the Cat Ba Islands, included 741 species of terrestrial plants; 282 species of terrestrial animals; 30 species of mangrove plants; 287 species of phytoplankton; 79 species of seaweed; 79 species of zooplankton; 196 species of marine fishes; 154 species of corals; and 538 species of zoobenthos. Many of these species are listed in the Red Book of Vietnam as endangered species, included the white-headed or Cat Ba langur (Trachypithecus poliocephalus), a famous endemic species. Human activities have resulted in significantly changes to the landscape end ecosytems of the Cat Ba islands; however, many natural aspects of the islandsd have been preserved. For this reason, the Cat Ba Islands were recognized as a Biological Reserved Area by UNESCO in 2004.

        맨 위로 스크롤 이동