• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권5호
• /
• pp.1755-1777
• /
• 2022

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.

• 대한전자공학회논문지TC
• /
• 제43권2호
• /
• pp.39-43
• /
• 2006

본 논문은 잡음이 존재하는 미지 시스템 출력 신호의 3차 통계치인 cumulant를 이용한 AR 식별에 관한 것이다. 미지 시스템 식별을 위한 알고리즘에서는 Parametric Modeling 기법중에서 Global Convergence 보장 및 시스템의 진폭과 위상 정보를 모두 표현할 수 있는 Cumulant를 이용한 AR (Auto Regressive) 식별 방법을 적용하였다. 식별 과정에서 미지 시스템을 하나의 AR 시스템으로 간주하였고 입력 신호를 발생하여 이를 통과시킨 후 잡음이 부가된 출력 신호를 얻어 이를 이용하였다. 신호대 잡음비의 변화에따른 AR 시스템의 식별을 수행한 결과 원래의 시스템 출력치와 유사한 양호한 식별 결과를 얻을 수 있었고 극점이 z 변환의 단위원내에 존재함을 확인하였다.

• 대한의용생체공학회:의공학회지
• /
• 제16권3호
• /
• pp.317-324
• /
• 1995

A need exists for the accurate identification of time series models having time varying parameters, as is important in the case of real time identification of nonstationary EMG signal. Thls paper describes real time identification and muscle fatigue monitoring method of nonstationary EMG signal. The method is composed of the efficient identifier which estimates the autoregressive parameters of nonstationary EMG signal model, and its real time implementation by using T805 parallel processing computer. The method is verified through experiment with real EMG signals which are obtained from surface electrode. As a result, the proposed method provides a new approach for real time Implementation of muscle fatigue monitoring and the execution time is 0.894ms/sample for 1024Hz EMG signal.

• 한국임상수의학회지
• /
• 제13권2호
• /
• pp.171-176
• /
• 1996

In this study, dldctronic identification system of individual dairy cow was developed for autocatization of stoxkvreeding management. To automize the breeding management, it is necessary to obtain and analyze the individual information distinguished from others perferentially. Electronic identification system can distinguish individual livestock from others with electromagnetic wave signal recognition system. Electoronic identification system consists of transmitter transmitting the oscillated signal and receiver set. The transmitted signal from transmitter clung to individual livestock is received from the receiving antenna and the signal in different according to the established value of the register. By distinct signal recieved from the reciever, wi can distinguish the identity of a livestock from others clearly. This system can manage $2^{12}$ individuals with a reciever theoretically. However in order to reduce the errors by analogous signal, this system uses only triple number and can manage 1365 individuals with a reciever practically. This system can be connevtted to Max 232 and microcomputer for the breeding management efficiently.

• 한국산업정보학회논문지
• /
• 제25권6호
• /
• pp.1-13
• /
• 2020

본 논문에서는 원전 비상 상황 발생 시 다수의 신호 오류가 발생했을 때 어떤 신호에 오류가 발생했는지를 추정하는 신호 오류 식별 (Fault identification) 방법론을 개발하였다. 변분 오토인 코더 (Variational autoencoder; VAE) 기반 모델은 기존의 이상 탐지 방법론과 같이 정상 신호 데이터만을 이용하여 훈련이 진행되며, 이후 각 신호에 대한 복원 오차 (Reconstruction error)와 복원 오차를 입력의 특정 부분으로 미분한 값을 이용하여 어떤 부분에 오류가 포함되어 있는지를 예측한다. 데이터 취득을 위하여 시뮬레이션을 수행하였으며, 일련의 실험으로부터 제시한 신호 오류 식별 방법이 적절한 오차 범위 내에서 오류가 발생한 신호를 특정할 수 있음을 확인하였다.

• Smart Structures and Systems
• /
• 제15권1호
• /
• pp.209-225
• /
• 2015

Compared to ambient vibration testing, impact testing has the merit to extract not only structural modal parameters but also structural flexibility. Therefore, structural deflections under any static load can be predicted from the identified results of the impact test data. In this article, a signal processing procedure for structural flexibility identification is first presented. Especially, practical issues in applying the proposed procedure for structural flexibility identification are investigated, which include sensitivity analyses of three pre-defined parameters required in the data pre-processing stage to investigate how they affect the accuracy of the identified structural flexibility. Finally, multiple-reference impact test data of a three-span reinforced concrete T-beam bridge are simulated by the FE analysis, and they are used as a benchmark structure to investigate the practical issues in the proposed signal processing procedure for structural flexibility identification.

• 센서학회지
• /
• 제25권5호
• /
• pp.337-343
• /
• 2016

In this paper, we newly introduce a wireless identification system using a solar cell and RF transceivers. The reader sends interrogating signal to a transponder using LED visible light, and the transponder responds to the reader using RF signal. The transponder consists of a solar cell, an amplifier, a microprocessor, and an RF transmitter. The solar cell receives the visible light from the reader and generates current to supply electric power to the other devices in the transponder. At the same time, the solar cell detects interrogating signal in the reader light. The microprocessor senses the interrogating signal and generates a responding signal. The RF transmitter radiates the responding signal to the reader. The transponder is a passive circuit because it operates without external power. In experiments, the maximum read distance between a reader and a transponder was about 1.6 meter.

• 센서학회지
• /
• 제30권4호
• /
• pp.196-203
• /
• 2021

In this study, an optical identification system was developed, wherein visible light is used to transmit the interrogating signal, and infrared is used to send the response signal. In the reader, visible light from a light emitting diode (LED) array was modulated via modified pulse width modulation for flicker-free illumination and dimming control. Moreover, the duty factor of the dimming control time was employed to control the illumination from the LED. In the transponder, the spike signal in the output of the high-pass filter was utilized to recover the interrogating signal while preventing interference from the 120-Hz noise from adjacent lighting lamps. The illumination was controlled in 26-86% range of the constant wave LED illumination by changing the duty factor from 20% to 90%. This configuration is advantageous for the construction of optical identification systems for automatic security check and car fare calculation at toll gates or parking facilities.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제5권1호
• /
• pp.76-82
• /
• 2005

Speech signal has various features of speakers. This feature is extracted from speech signal processing. The speaker is identified by the speaker identification system. In this paper, we propose the speaker identification system that uses the incremental learning based on neural network. Recorded speech signal through the microphone is blocked to the frame of 1024 speech samples. Energy is divided speech signal to voiced signal and unvoiced signal. The extracted 12 orders LPC cpestrum coefficients are used with input data for neural network. The speakers are identified with the speaker identification system using the neural network. The neural network has the structure of MLP which consists of 12 input nodes, 8 hidden nodes, and 4 output nodes. The number of output node means the identified speakers. The first output node is excited to the first speaker. Incremental learning begins when the new speaker is identified. Incremental learning is the learning algorithm that already learned weights are remembered and only the new weights that are created as adding new speaker are trained. It is learning algorithm that overcomes the fault of neural network. The neural network repeats the learning when the new speaker is entered to it. The architecture of neural network is extended with the number of speakers. Therefore, this system can learn without the restricted number of speakers.

• 센서학회지
• /
• 제20권6호
• /
• pp.412-419
• /
• 2011

In this paper, we used the inter-bit noise detection method in order to reduce the effects of noise light in a visible light identification system that uses a visible LED as a carrier source. A visible light identification system consists of a reader and a transponder. When the enable signal from the reader is detected, the transponder encodes the response data in RZ(Return-to-Zero) bit stream and sends response signal by modulating a visible LED. The reader detects the response signal mixed with noise light, samples the noise voltage in each blank low time between data bits of the RZ signal, and recovers the original data by subtracting the sampled noise from the received signal. In experiments, we improved the signal-to-noise ratio by 20dB using the inter-bit noise detection method.