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.

This study develops an early warning system (EWS) to prevent the banking crisis. The proposed system incorporates both the perspective of crises and fundamental characteristics of the banking system in each economy. A fuzzy logic method with data from 1990-2009 is employed to construct the EWS of banking crisis based on 21 pre-determined variables from the aspect of total economy, financial and banking sectors. Our results show: Firstly, South Korea recorded higher probability to have a banking crisis in 1997 as there was large foreign debt in dollars. Secondly, China, Australia and New Zealand banking systems appear to be vulnerable to the crisis in 2007. The surge of China export, FDIs and booming stock market were signs of a heated economy. Australia with high commodity prices was also vulnerable to crisis. Thirdly, Australia, China, Japan and New Zealand banking systems appear to be exposed to the higher chance of a crisis in 2010. Japan with deflation coupled with expensive yen did not augur well for its export. Overall, the findings show that in Asian Financial Crisis 1997/98 and Global Financial Crisis 2008/09, many economies are exposed to a higher probability of having the crisis and this shows an urgent need of having surveillance in these economies.

Now a days, the monitoring system based on high technology and brand new IT which is being used in a facility for the purpose of monitoring the concentration of hazard chemicals and deformation such as crack has reached a significant level. However, the operating and maintenance cost for monitoring system is critical and therefore, it is unsuitable to use for monitoring urban local disaster and integrated emergency management, including indications of NEMA, and for the application of disaster management. For the past 10 years, the main cause for the fire and explosive accident was human error, and the accident rate was more the than 35% in South Korea. This sentence proves the fact that even if the safety device is well equipped, there are high possibilities to occur the disaster by simple human mistakes and it is impossible to neglect the accident. In order to minimize the disaster, comprehensive accident prevention system is required where it could operate and produce all the information needed for accident and accident prevention.In this study, we have considered above conditions, and tried to come up with integrated monitoring system where it could response to both hazard material and collapse threats. First, we divided the disaster area into two parts which are hazard material and collapse with deformation, and then proceed the development separately. Our purpose was to combine both toxic gas monitoring system and collapse monitoring system into one. trough our 3 years of research, the two different types of sensors have been developed and by using these sensors, the integrated early-warning system for monitoring of disaster symptom has been constructed and also the response manual has been made to improve the efficiency. With our integrated early-warning system, we provide the prototype of emergency plan and system for both chemical and contractual disaster, and we expect to be commercialized so that it will minimize the casualties whenever unexpected accident occurs.