US Patent Application 18341996. METHOD AND APPARATUS FOR PERFORMING ANOMALY DETECTION USING NEURAL NETWORK simplified abstract
Contents
METHOD AND APPARATUS FOR PERFORMING ANOMALY DETECTION USING NEURAL NETWORK
Organization Name
Inventor(s)
Sangjoon Kim of Hwaseong-si (KR)
METHOD AND APPARATUS FOR PERFORMING ANOMALY DETECTION USING NEURAL NETWORK - A simplified explanation of the abstract
- This abstract for appeared for US patent application number 18341996 Titled 'METHOD AND APPARATUS FOR PERFORMING ANOMALY DETECTION USING NEURAL NETWORK'
Simplified Explanation
This abstract describes a method and device that use a neural network to detect anomalies. The device extracts input features from a data signal, processes them through the neural network to obtain output features, calculates an error based on the input and output features, and determines if the input data signal is abnormal by comparing the error to a threshold.
Original Abstract Submitted
A method and apparatus for performing anomaly detection by using a neural network are provided. The apparatus is configured to extract input features of an input data signal, obtain output features of the neural network by processing the input features through the neural network, obtain an error based on the input features and the output features, and determine whether the input data signal indicates an abnormal signal based on the error and a threshold.
