Abstract: A method for predicting an on-site seismic feature value using artificial intelligence is disclosed. The method includes the steps of obtaining a plurality of seismic historical data for a local position, wherein each of the seismic historical data includes seismic longitudinal wave information and a corresponding seismic transverse wave feature value, the seismic longitudinal wave information includes a plurality of data related to a vertical direction of ground surface, and the plurality of data include at least an acceleration value, a displacement value, a period and a velocity value; and based on at least the plurality of seismic historical data, obtaining a seismic transverse wave prediction model for the local position via an artificial intelligence calculation module.

Abstract: An earthquake detection method is disclosed. The method comprises the following steps: receiving a first signal and at least a second signal, wherein the first signal is triggered in response to a first vibration state of a main detection site, and the at least a second signal is triggered in response to at least a second vibration state of at least a backup detection site; determining whether a quantity of those being enabled among the at least a second signal satisfies a quantity ratio condition, and determining whether the first signal and the quantity of the at least a second signal are both enabled at a specific time point, wherein the first and the quantity of the at least a second signals respectively have a first and at least a second initial enabled time points; and determining there is a real earthquake event when an interval between the first and the at least a second signal satisfies a time relationship.

Abstract: An earthquake detection system is disclosed. The earthquake detection system includes a main sensor, a first backup sensor, a second backup sensor and a third backup sensor. The main sensor is disposed on a free field. The first backup sensor is disposed on a structure. The second backup sensor is disposed below a ground surface at a depth of at least 20 meters. The third backup sensor is disposed at a remote end relative to the main sensor, and outputs a remote signal through a network so as to avoid misjudging the occurrence of earthquakes because of unnatural factors, and prevent the vibration caused by human activities from interfering with the detector. The earthquake detection system achieves the effect of verification through a plurality of sensors installed in different positions. Only when all the sensors confirm that there is an earthquake, an earthquake warning will be issued to the protected place.

Abstract: In the present invention, an earthquake detection system based on the combination configuration of a free field and remote signal source is provided. The earthquake detection system includes: a host; a main sensor arranged in a free field and connected to the host; and a plurality of backup sensors, which are remotely arranged with respect to the main sensor, wherein each of the backup is connected to the host via the internet and transmits a remote signal to the host so as to avoid misjudging the occurrence of earthquakes because of unnatural factors, and prevent the vibration caused by human activities from interfering with the detector. The earthquake detection system achieves the effect of verification through a plurality of sensors installed in different positions.

Abstract: An information platform for providing an earthquake early warning of a large area is disclosed. The large area includes a plurality of small districts, different sets of the plurality of small districts form different large districts according to geographical locations so as to make up the large area, and the information platform is both connected with a plurality of on-site earthquake early warning stations and the plurality of small districts through a cloud network. The plurality of on-site earthquake early warning stations are located in the large districts respectively, each of the plurality of on-site earthquake early warning stations is configured to obtain a real-time seismic longitudinal wave measurement data, obtain a real-time seismic transverse wave feature prediction value corresponding to the real-time seismic longitudinal wave measurement data, and transmit the real-time seismic transverse wave feature prediction value.