Earthquake Detection Using SVC Waveform Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
On-site earthquake warning systems often experience false alarms due to non-earthquake events, leading to inaccurate classification and increased costs with conventional methods that require multiple sensors for verification.
Innovation Solution
A method utilizing a support vector classification (SVC) approach to establish an earthquake determination model based on initial wave characteristics, such as cumulative absolute velocity, integral of absolute velocity, and integral of absolute displacement, to differentiate between earthquake and non-earthquake events, reducing the need for multiple sensors and enhancing accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple earthquake sensors are installed at different locations for verification, then the accuracy of earthquake classification is improved, but the cost and device complexity increase
Solution Approach 1:
The patent transforms the classification problem from a spatial verification approach (multiple sensors) to a parameter-based approach (waveform characteristics analysis). By extracting and analyzing parameters such as initial wave amplitude, duration, and spectral characteristics, the system achieves accurate earthquake classification using a single sensor, thereby resolving the contradiction between classification accuracy and device complexity
Solution Approach 2:
The patent replaces the mechanical approach of deploying multiple physical sensors with a computational approach using signal processing and machine learning algorithms. The SVC classifier processes waveform parameters to achieve classification, substituting the need for multiple physical verification sensors with intelligent algorithms that analyze the characteristics of waves detected by a single sensor
2Reliability
If multiple earthquake sensors are installed at different locations for verification, then the reliability of earthquake detection is improved, but the installation and maintenance difficulty increase
Solution Approach 1:
The patent enables the single sensor system to perform self-verification through waveform characteristic analysis. The SVC classifier uses the inherent properties of earthquake waves (initial wave characteristics) to automatically distinguish true earthquakes from non-earthquake events, making the system self-sufficient without requiring additional sensors for cross-verification, thus improving ease of installation and maintenance while maintaining reliability
3Ease of operation
If conventional classification methods are used, then the system is simple to implement, but false alarms occur due to non-earthquake events
Solution Approach 1:
The patent applies preliminary action by pre-training the SVC classifier with extensive earthquake and non-earthquake waveform data before deployment. The system learns and stores the characteristic patterns of both earthquake and non-earthquake events during the training phase, enabling it to accurately classify new events without complex real-time adjustments, thus maintaining ease of operation while significantly reducing false alarms
Data Source
AI summary
A method of determining an earthquake event for an earthquake detecting system includes retrieving at least one initial wave characteristic related to each earthquake data among a plurality of earthquake data; utilizing a support vector classification (SVC) method to establish an earthquake determination model according to the initial wave characteristic; and determining whether new earthquake data belong to an earthquake event or a non-earthquake event according to the earthquake determination model when the new earthquake data are received.