Wi-Fi Method and Apparatus of Intrusion Detection forWi-Fi NetworkBased on Weight-Selected Neural Networks
Presented are a method and a system of intrusion detection for Wi-Fi based on weight selection for neural network. The method proposed in the present invention comprises the steps of: selecting strong points using a decision tree and artificial neural network based on a weight according to data stan...
Saved in:
Main Authors | , , , |
---|---|
Format | Patent |
Language | English Korean |
Published |
26.07.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Presented are a method and a system of intrusion detection for Wi-Fi based on weight selection for neural network. The method proposed in the present invention comprises the steps of: selecting strong points using a decision tree and artificial neural network based on a weight according to data standardization and threshold adjustment; classifying the strong points selected by using the decision tree and artificial neural network using an artificial neural network classification unit; and calculating IDS matrix for the classified strong points and testing an actual network using the classified strong points.
신경망에 대한 가중치 선택 기반 Wi-Fi 침입 탐지 방법 및 시스템이 제시된다. 본 발명에서 제안하는 신경망에 대한 가중치 선택 기반 Wi-Fi 침입 탐지 방법은 데이터 표준화 및 임계값 조정에 따른 가중치에 기초하고, 결정 트리 및 인공신경망을 이용하여 특장점을 선택하는 단계, 결정 트리 및 인공신경망을 이용하여 선택된 특장점을 인공신경망 분류부를 이용하여 분류하는 단계 및 분류된 특장점에 대하여 IDS 행렬을 계산하고, 상기 분류된 특장점을 이용하여 실제 네트워크로 테스트 하는 단계를 포함한다. |
---|---|
Bibliography: | Application Number: KR20180006369 |