• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.1-9
• /
• 2012

These days news about natural disaster caused by earthquake, typhoon is broadcasted frequently. At this moment, structure' healthy is threatened by natural disaster, only way to minimize the casualties and property damage is doing accurate alert. In this research, I designed Expert system to reduce wrong-alert and elevate the accuracy. The expert system put many sensors close to each other as a one group. We focus on elevating reliability of monitoring system by comparing each nearby sensor's state not one single sensor. Providing accurate data which can decide safe to structure manager can minimize current damage by early response, also has advantage that can prevent additional damage can be occur in the future.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.421-428
• /
• 2022

This study analyzes emerging earthquake and space use technologies from the latest Korean and Japanese scientific and technological foresights in 2022 and 2019, respectively. Unlike the earthquake prediction and early warning technologies presented in the 2017 study, the emerging earthquake technologies in 2022 in Korea was described as an earthquake/complex disaster information technology and public data platform. Many detailed future technologies were presented in Japan's 2019 survey, which includes largescale earthquake prediction, induced earthquake, national liquefaction risk, wide-scale stress measurement; and monitoring by Internet of Things (IoT) or artificial intelligence (AI) observation & analysis. The latest emerging space use technology in Korea and Japan were presented in more detail as robotic mining technology for water/ice, Helium-3, and rare earth metals, and manned station technology that utilizes local resources on the moon and Mars. The technological realization year forecasting in 2019 was delayed by 4-10 years from the prediction in 2015, which could be greater due to the Corona 19 epidemic, the declaration of carbon neutrality in Korea and Japan in 2020 and the Russo-Ukrainian War in 2022. However, it is required to more active research on earthquake and space technologies linked to information technology.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.25 no.2
• /
• pp.71-81
• /
• 2021

This paper presents a real-time, false-pick filter based on deep learning to reduce false alarms of an onsite Earthquake Early Warning (EEW) system. Most onsite EEW systems use P-wave to predict S-wave. Therefore, it is essential to properly distinguish P-waves from noises or other seismic phases to avoid false alarms. To reduce false-picks causing false alarms, this study made the EEWNet Part 1 'False-Pick Filter' model based on Convolutional Neural Network (CNN). Specifically, it modified the Pick_FP (Lomax et al.) to generate input data such as the amplitude, velocity, and displacement of three components from 2 seconds ahead and 2 seconds after the P-wave arrival following one-second time steps. This model extracts log-mel power spectrum features from this input data, then classifies P-waves and others using these features. The dataset consisted of 3,189,583 samples: 81,394 samples from event data (727 events in the Korean Peninsula, 103 teleseismic events, and 1,734 events in Taiwan) and 3,108,189 samples from continuous data (recorded by seismic stations in South Korea for 27 months from 2018 to 2020). This model was trained with 1,826,357 samples through balancing, then tested on continuous data samples of the year 2019, filtering more than 99% of strong false-picks that could trigger false alarms. This model was developed as a module for USGS Earthworm and is written in C language to operate with minimal computing resources.

• Journal of the Korea Society for Simulation
• /
• v.19 no.2
• /
• pp.147-155
• /
• 2010

It often occur to nature disaster that like earthquake, typhoon, etc. around KOREA. A Haiti and Chile also metropolitan area of KOREA occur earthquake. in result, People consider nature disaster. Structures of present age are easily affected by nature disaster. So we are important that warn of dangerous situation as soon as possible. On this study, I introduce Integrated Health Monitoring System for Infra-structure. I develop Structure Health Monitoring System on web-site. Administrator always monitor structure on real-time using internet network. As Administrator using mobile device like PDA, Administrator always monitor structure. As using this system, Damage of nature disaster is minimized and is prevented post damage.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.3
• /
• pp.1489-1494
• /
• 2013

Tsunami happens rarely enough to allow a false sense of security, but when they do occur, there may be just minutes or hours for people to reach a safe location. Natural disasters like tsunami are inevitable and it is almost impossible to fully recoup damages caused by the disasters. However, it is possible to minimize the potential risk by developing early warning strategies. GIS modelling with its geoprocessing and analysis capability can play a crucial role in efficient mitigation and management of disaster. This study aims at developing integrated spatial information system processing model supporting tsunami evacuation action planning using geo-information technology such as GIS. The integration process classified into four phases. And in each phase, required input data and GIS processes are decided. The main effort in minimizing casualties in tsunami disaster is to evacuate people from the hazard area before tsunami strikes by means of either horizontal or vertical evacuation. The study provides essential spatial information for local decision making related with people's evacuation in tsunami-prone areas based on a modeling approach transferable to other coastal areas.