• Title/Summary/Keyword: 재난망

Search Result 221, Processing Time 0.024 seconds

A study on the application of hydrophone and CNN analysis for the calculation of bed load discharge (소류사량 산정을 위한 하이드로폰의 적용과 CNN 분석에 관한 연구)

  • Min Jin Jung;Kye Won Jun;Chang deok Jang;Sung Uk Kim;Ji Yeol Ryu
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2023.05a
    • /
    • pp.135-135
    • /
    • 2023
  • 우리나라의 전 국토면적 중 약 63% 이상이 산지로 이루어져 있으며 이는 OECD국가 중 4위에 해당할 정도로 매우 높은 비율이다. 광활한 산지 면적의 효율적 이용을 위해 사면개발, 태양광 시설, 관광자원으로써의 활용 등이 이루어져 토양침식에 매우 취약해졌으며, 하천으로의 토사유입량이 증가하고 있다. 따라서 하천으로 유입된 유사량의 조사가 매우 중요하며, 유사량 중 입경이 큰 소류사량을 추정하기 위한 조사 장비 중 간접적 방법인 하이드로폰에 관한 국내·외 연구가 활발히 진행되고 있다. 본 연구에서는 기존 소류사량 추정 방법 중 추정식을 활용한 방법의 추정량이 많아질수록 정확도가 낮아지는 문제를 개선하기 위한 노력으로 인공신경망의 한 종류인 Convolutional Neural Networks(CNN)를 소류사량의 계측에 적용하기 위한 연구를 시도하였으며, 그 결과와 실제 소류사량의 정확도를 비교 및 분석하였다. 실험데이터를 획득하기 위하여 실내수로를 구축하였으며, Labview를 이용하여 소류사량에 대한 충돌음 이미지데이터를 취득한 후 학습을 진행한 결과, 검증데이터에 대한 정확도는 60%이상의 값으로 나타났다. 향후 추가적인 데이터 확보를 통해 정확도 향상을 위한 연구를 진행하고자 한다.

  • PDF

Rapid Self-Configuration and Optimization of Mobile Communication Network Base Station using Artificial Intelligent and SON Technology (인공지능과 자율운용 기술을 이용한 긴급형 이동통신 기지국 자율설정 및 최적화)

  • Kim, Jaejeong;Lee, Heejun;Ji, Seunghwan
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.9
    • /
    • pp.1357-1366
    • /
    • 2022
  • It is important to quickly and accurately build a disaster network or tactical mobile communication network adapting to the field. In configuring the traditional wireless communication systems, the parameters of the base station are set through cell planning. However, for cell planning, information on the environment must be established in advance. If parameters which are not appropriate for the field are used, because they are not reflected in cell planning, additional optimization must be carried out to solve problems and improve performance after network construction. In this paper, we present a rapid mobile communication network construction and optimization method using artificial intelligence and SON technologies in mobile communication base stations. After automatically setting the base station parameters using the CNN model that classifies the terrain with path loss prediction through the DNN model from the location of the base station and the measurement information, the path loss model enables continuous overage/capacity optimization.

Mobile Sensor Relocation to Prolong the Lifetime of Wireless Sensor Networks (무선 센서망의 수명 연장을 위한 센서 재배치)

  • Yoo, Young-Hwan
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.34 no.4B
    • /
    • pp.338-348
    • /
    • 2009
  • The Wireless Sensor Network (WSN) has recently attracted considerable attention due to the low price and ease to deploy it. In particular, in a hostile or harsh regions where sensors cannot be deployed manually, WSNs can be established just by dropping sensors from the air. In this case, however, most likely sensors are not placed at optimal positions, although the location of sensors does have a drastic impact on the WSN performance. Moreover, randomized deployment algorithm can leave holes in terms of coverage in the sensing area. This paper proposes a sensor relocation scheme where mobile sensors move to patch up the holes by appropriate coverage. Simulation results show that the proposed algorithm outperforms prior existing schemes in terms of coverage and lifespan of WSNs.

Study on D2D Relay based Interconnection Network of HAM Radio and Wi-Fi for Securing Communication Performance in Satellite Wireless Package Systems (이동단말용 위성 통신 무선 패키지 시스템을 위한 D2D Relay 기반 HAM Radio와 Wi-Fi Network 결합망의 통신 성능 확보 연구)

  • Hwang, Yu Min;Cha, Jae Sang;Kim, Jin Young
    • Journal of Satellite, Information and Communications
    • /
    • v.10 no.1
    • /
    • pp.12-16
    • /
    • 2015
  • In this paper, we introduce a wireless package system based on the amateur radio HR(HAM Radio) and satellite communication as a novel wireless disaster communication system and have configured a interference scenario receiving interference from adjacent base stations and D2D groups in the disaster network. In such interference scenarios, we propose a frequency re-allocation method to avoid interference and communicate with disaster networks by securing the channel capacity required between D2D terminals. As a result of computer simulation, we can find the proposed method has improved BED performance of a gain of 1.5dB and overall system throughput than conventional methods.

Measures to Secure Safety according to Gas pipe Hydrogen Mixing(Carbon Neutral) (가스배관 수소혼입(탄소중립)에 따른 안전확보 방안)

  • Kwak, Che-Sik;Sin, Dong-Il
    • Proceedings of the Korean Society of Disaster Information Conference
    • /
    • 2022.10a
    • /
    • pp.290-291
    • /
    • 2022
  • 본 논문에서는 우리나라 2030년 국가 온실가스 감축목표(NDC*, 291백만톤 감축)달성 및 2050년 탄소중립 목표 달성을 위해 필연적으로 수반되는 천연가스 내 수소 혼입에 따른 안전성확보 방안과 수소혼입에 따른 국민 불안감 해소 및 수용성 제고를 위한 대안을 제시하고, 해외 사례를 연구 하였다. 탄소중립은 온실가스(이산화탄소 등)의 배출량을 최대한 줄이고, 남은 온실가스를 흡수, 제거해서 실질적인 배출량이 "0"이 되는 것을 의미하고, 수소혼입은 도시가스의 주성분인 메탄 연소시 발생하는 CO2를 최소화하기 위해 수소(H2)를 도시가스에 일정비율 혼합하는 것을 말한다. 본 연구에서는 수소 혼입 시 우려되는 수소취성 및 배관내구성 문제와 수소 특성인 작은 입자로 인한 누출 위험성, 고층에서 메탄과 수소가 분리되는 현상 등에 따른 문제를 도출하고 이에 대한 안전관리 방안도 함께 제시하였다. 또한, 도시가스 배관에 수소 혼입시 천연가스 대체를 통한 온실가스 감축 및 기존 배관망 사용을 통한 경제성 분석결과와 국가 온실가스 감축에 어느 정도 기영할 수 있는지도 함께 기술하였다.

  • PDF

Natural Disaster Damage Cost Prediction Model based on Neural Network and Genetic Algorithm (신경망과 유전자 알고리즘을 이용한 자연재해 피해예측 모델 연구)

  • Choi, Seon-Hwa
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2010.06c
    • /
    • pp.380-384
    • /
    • 2010
  • 기후온난화, 국지성 호우 및 대규모 태풍으로 인한 피해가 증대되면서 사회 경제적 손실 또한 날로 증가하고 있어 재해로 인한 피해 발생가능성을 효율적으로 예측하는 모델을 통한 선제적 대응이 필요하다. 재난 재해의 위험성 분석 방법은 주로 확률 통계기법을 기반으로 하는 연구가 주류를 이루었으나, 본 논문에서는 포착된 현상의 데이터를 이용해 그 데이터를 지배하는 경험적 규칙성을 학습하고 획득하는데 다른 기법보다 탁월한 성능을 가진 신경망 모델을 적용하여 자연재해 피해예측 모델을 연구하였다. 1991년부터 2005년 사이에 우리나라에서 발생한 자연재해의 피해자료와 기상개황 자료를 이용하여 지역별 자연재해로 인한 피해를 예측하는 신경망 모델은 우리나라 232개 행정구역에 대하여 누적강우량과 최대풍속, 그리고 재해사상 발생 5일 이내의 선행강우량을 입력변수로 하고 총 피해액을 출력변수로 한다. 또한 학습을 통한 최적의 해를 찾기 위해 신경망의 매개변수 학습률, 모멘텀, 편의값을 유전자알고리즘으로 결정하여 학습을 수행 하였다.

  • PDF

Bio-AdHoc Sensor Networks for Disaster Emergency Management Systems (재난 관리용 시스템을 위한 센서 탑재 바이오 애드 혹 네트워크)

  • Lee, Dong-Eun;Lee, Goo-Yeon
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.44 no.2
    • /
    • pp.29-36
    • /
    • 2007
  • Ad hoc network does not need any preexisting network infrastructure, and it has been developed as temporal networks in the various fields. Infostation is an efficient system to transfer information which does not have delay sensitive characteristics. In this paper, we propose a disaster emergency management system using sensor attached animals' mobility combined with infostation system. We also analyze the performance of the proposed system by simulation. From the performance analysis results, we expect that the proposed system will be very useful to early detect big forest fires which occurs frequently in Korea mountain areas.

A Study on Safety Management of Day Care Center using disaster management system (재난관리스템을 이용한 어린이집 안전관리에 관한 연구)

  • Jeong, Chang-sik;Kwon, Mee-Rhan
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.18 no.1
    • /
    • pp.29-35
    • /
    • 2018
  • Safety accidents are frequently occurring in day care centers in recent years. The number of types of safety accidents is bumping into, falling, burning, school bus accident, insertion... etc., and the number of children who have died due to such accidents is increasing steadily every year. Therefore, it is urgent to prevent accidents at day care centers. IoT (Internet of Things) is managed by connecting various sensors and related products from the living space to the Internet in order to prevent them from being dangerous. In particular, IoT products can be automatically controlled by smart phones and sensors anytime and anywhere, thus saving energy, time, convenience and prompt accuracy. This paper proposes a research model to prevent and respond to disasters by using SK LoRa communication network and Arduino, which are Internet access networks for building disaster management in schools, kindergartens and day care centers. And various sensors needed for building disaster management express various safety states in the building and suggests a system that can control the residential environment by transmitting and receiving data to smart phone.

A Study of the Application of Earthquake Early Warning System for the Enhancements in Protective Action by Korea National Park (국립공원의 지진 대응 체계 개선을 위한 지진 조기경보 시스템의 적용에 관한 연구)

  • Yang, Eomzi;Ha, Seong Jun;Kim, Won Kyung;Yun, Tae Sup
    • KSCE Journal of Civil and Environmental Engineering Research
    • /
    • v.38 no.3
    • /
    • pp.439-448
    • /
    • 2018
  • Conventional Earthquake Early Warning System (EEWS) detects the propagated P-wave from epicenter which should be achieved within 5 seconds to provide seconds to minutes of warning, allowing people to prepare for protective actions. EEWS in Korea is currently capable of providing a warning within 50 seconds after the primary P-wave detection, however, it is well-known that earthquake warning systems operating around Korean National Parks (KNP) have limited capability to fully monitor earthquake events. This study, therefore, presents a strategy to quantify the potential vulnerability to earthquake hazards by superimposing the distribution of Korea Integrated Seismic System (KISS) and the discretized map of KNP. Total 22 national parks are evaluated, and the results suggest that the improvement of the on-site systems should be necessitated for Gyoengju, Gyeryongsan, Songnisan, Gayasan, and Deogyusan national parks, whereas enhancement of regional systems is required for Bukhansan national park.

Transmission Performance Evaluation of MPR-based Wireless Communication System Applying for Disaster Investigation (재난조사 활용을 위한 MPR기반 무선통신 전송 성능 평가)

  • Kim, Seong Sam;Shin, Dong Yoon;Noh, Hyun Ju
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.22 no.3
    • /
    • pp.754-762
    • /
    • 2021
  • Seamless wireless communication network access technology enables users to guarantee service continuity. Hence, it is necessary for disaster situations in which network service may be interrupted. The Multi-path router is a technology to improve network stability and strengthen field operability, particularly in a disaster environment where network failure can occur by providing high-performance data transmission using multi-communication networks and network security by VPN-based wireless IP. In this paper, a prototype system for an MPR-based wireless communication network was proposed to improve the operation performance for disaster field investigation applications. A comparative experiment was performed on various data transmission performances with the existing single wireless communication network. In addition, another experiment was conducted by measuring the data packet transmission and receiving performance in the existing/new wireless communication system first and then assessing the UDP transmission performance in a single router environment to understand the transmission capability of the new MPR. The experimental results showed that the sending and receiving performance was improved by approximately double that of the existing single wireless communication system. The proposed prototype system is expected to allow users to share and disseminate collected on-site data more quickly and efficiently during a disaster site investigation.