Technology for analyzing abnormal behavior using deep learning-based system and data imaging
AssigneeCtilab Co., Ltd.
InventorsHong Yeon Cho, Tae Yang Oh, Won Woo Park
Life of this patent
Estimating the term…
Abstract
Disclosed is a method of analyzing abnormal behavior by using data imaging, including: receiving data to be analyzed as an input, wherein the data to be analyzed is related to a state of a system to be analyzed; converting the inputted data to be analyzed into image data; training a neural network unit with the converted image data as an input; and detecting or predicting abnormal behavior in the system to be analyzed, at the neural network unit, which has received the image data converted from the data to be analyzed as the input and completed training.
Claims12
A method of analyzing abnormal behavior by using data imaging, comprising:
- a step of receiving data to be analyzed as an input, wherein the data to be analyzed is related to a state of a system to be analyzed;
- a step of converting the inputted data to be analyzed into image data;
- a step of training a neural network unit with the converted image data as an input;
- and
- at the neural network unit, which has received the image data converted from the data to be analyzed as the input and completed training, a step of detecting or predicting abnormal behavior in the system to be analyzed,
- wherein the neural network unit trained and performs classification of the image data converted from the data to be analyzed, by using a neural network algorithm applied with a deep learning technique.
A system for analyzing abnormal behavior by using data imaging, comprising:
- an input unit that receives data to be analyzed as an input, wherein the data to be analyzed is related to a state of a system to be analyzed;
- a data processing unit that converts the inputted data to be analyzed into image data;
- and
- a neural network unit that receives the converted image data for training, and after completing the training, receives the image data converted from the data to be analyzed to detect abnormal behavior in the system to be analyzed,
- wherein the neural network unit performs the training and classification of the image data converted from the data to be analyzed, by using a neural network algorithm applied with a deep learning technique.
Dependencies are inferred from the claim text.