APPARATUS AND METHOD FOR PERSONAL IDENTIFICATION BASED ON DEEP NEURAL NETWORK

• Main Authors: KIM SEUNG HYUN, BAN SEONG HYUN, KIM YU SUNG, SHIN SEUNG HWAN, CHAE KEUN HONG
• Format: Patent
• Language: English; Korean
• Published: 20.04.2023
• Subjects: ANALOGOUS ARRANGEMENTS USING OTHER WAVES; CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES; MEASURING; PHYSICS; RADIO DIRECTION-FINDING; RADIO NAVIGATION; TESTING

The present specification relates to a device and a method for personal identification based on a deep neural network. The method for personal identification according to one embodiment of the present specification comprises: a step of receiving, by a wireless signal collection part, a plurality of wireless signals comprising spatial information and identification information of a subject to be identified through a plurality of receivers of different locations; a step of processing, by a manipulation signal generating part, the spatial information through a first deep neural network model learned in advance to generate a manipulation signal from the wireless signal; and a step of identifying, by a personal identification processing part, the subject to be identified of a specific space in which the identification information of the subject to be identified of the manipulation signal is considered as an input of a second deep neural network model. Therefore, the present invention is capable of allowing a large amount of information to be transmitted and received within a short time. 본 명세서는 심층 신경망 기반 개인 식별 장치 및 방법에 관한 것이다. 본 명세서의 일 실시예에 따른 개인 식별 방법은 무선 신호 수집부가 서로 다른 위치의 복수의 수신기를 통해 공간 정보 및 식별 대상 자의 식별 정보를 포함하는 복수의 무선 신호를 수신하는 단계, 조작 신호 생성부가 미리 학습된 제1 심층 신경망 모델을 통해 상기 공간 정보를 가공하여 상기 무선 신호로부터 조작 신호를 생성하는 단계 및 개인 식별 처리부가 상기 조작 신호의 식별 대상자의 식별 정보를 제2 심층 신경망 모델의 입력으로 하여 특정 공간의 식별 대상자를 식별하는 단계를 포함한다.