• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.201-207
• /
• 2024

Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.12
• /
• pp.1207-1215
• /
• 2008

Satellite generates a complex electromagnetic noise by conducted and radiated coupling effect of the various electrical instruments. This noise may cause serious problems on the satellite system. To minimize the electromagnetic coupling effects and maintain the system safety margin, system noise reduction technique should be applied from the beginning of the system design. The COMS system is evaluated by measuring the conducted noise on system electrical power leads at PSR(Power Supply Regulator) and verifying a 6 dB system safety margin under the complex noise environment with current injection. The radiated noise due to the complex transmit antenna configuration is evaluated by integrating all unit-level RE measurement results, and the RF compatibility between spacecraft and launch vehicle is analyzed with the above estimations. This paper describes the COMS EMC compatibility analysis with respect to each unit level EMC test results, and RF compatibility analysis between spacecraft and launch vehicle. The analyzed results will be reflected on FM(Flight Model) EMC test.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.431-433
• /
• 2022

With the development of IoT technology, various technologies such as artificial intelligence and automation are being grafted into industrial sites, and accordingly, the importance of data processing is increasing. Image denoising is one of the basic processes of image processing, and is used as a preprocessing step in many applications. Various studies have been conducted to remove noise, but various problems arise in the process of noise removal, such as image detail preservation, texture restoration, and special noise removal. In this paper, we propose a digital filter using an extended convolutional mask to preserve image detail during the impulse denoising process. The proposed algorithm uses an extended convolution mask as a filtering mask, and obtains the final output by switching the extension level according to the noise level. Simulation was conducted to evaluate the performance of the proposed algorithm, and the performance was analyzed compared to the existing method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.382-382
• /
• 2020

과거 많은 연구에서 다수의 모형의 결과를 이용한 앙상블 방법론은 인공지능 모형 (artificial neural network)의 예측 능력에 향상을 갖고 온다 논하였다. 본 연구에서는 미계측유역의 저수량(low flow)의 예측을 위하여 Jittering을 기반으로 한 인공지능 모형을 제시하고자 한다. 기본적인 방법론은 설명변수들에게 백색 잡음(white noise)를 삽입하여 훈련되는 자료를 증가시키는 것이다. Jittering을 기반으로 한 인공지능 모형에 대한 효과를 검증하기 위하여 본 연구에서는 Multi-output neural network model을 기반으로 모형을 구축하였다. 다음으로 Jittering을 기반으로 한 앙상블 모형을 variable importance measuring algorithm과 결합시켜서 유역특성치와 예측되는 저수량의 특성치들의 관계를 추론하였다. 본 연구에서 사용되는 방법론들의 효용성을 평가하기 위해서 미동북부에 위치하고 있는 총 207개의 유역을 사용하였다. 결과적으로 본 연구에서 제시한 Jittering을 기반으로 한 인공지능 앙상블 모형은 단일예측모형 (single modeling approach)을 정확도 측면에서 우수한 것으로 확인되었다. 또한, 적은 숫자의 앙상블 모형에서도 그 정확성이 단일예측모형보다 우수한 것을 확인하였다. 마지막으로 본 연구에서는 유역특성치들의 효과가 살펴보고자 하는 저수량의 특성치들에 따라서 일관적으로 영향을 미치거나 그 중요도가 변화하는 것을 확인하였다.

• Journal of Korea Water Resources Association
• /
• v.45 no.12
• /
• pp.1321-1330
• /
• 2012

In this study, the daily inflow at the basin of Chungju dam is predicted using wavelet-artificial neural network for nonlinear model. Time series generally consists of a linear combination of trend, periodicity and stochastic component. However, when framing time series model through these data, trend and periodicity component have to be removed. Wavelet transform which is denoising technique is applied to remove nonlinear dynamic noise such as trend and periodicity included in hydrometeorological data and simple noise that arises in the measurement process. The wavelet-artificial neural network (WANN) using data applied wavelet transform as input variable and the artificial neural network (ANN) using only raw data are compared. As a results, coefficient of determination and the slope through linear regression show that WANN is higher than ANN by 0.031 and 0.0115 respectively. And RMSE and RRMSE of WANN are smaller than those of ANN by 37.388 and 0.099 respectively. Therefore, WANN model applied in this study shows more accurate results than ANN and application of denoising technique through wavelet transforms is expected that more accurate predictions than the use of raw data with noise.

• Proceedings of the Safety Management and Science Conference
• /
• 2004.05a
• /
• pp.233-239
• /
• 2004

현재 국내 인체 이식용 전자 의료기의 이식건수는 매년 약 1800 여건으로 해마다 증가하고 있으며 그 연령대도 다양한 작업환경에 노출되는 청장년층으로 급속히 확대되어 가고 있다. 이러한 이식용 의료기는 인공 심장 박동기, 이식형 제세동기, 진통억제를 위한 이식형 전기 펄스 발생기, 이식형 약물주입기 등을 포함한다. 그러한 기기들은 미세한 생체 신호에 따라 반응하기 때문에 생체 신호이외의 잡음에 의한 오동작은 절대적으로 피해져야 하며 경우에 따라 생명위협과도 직결된다. 본 논문에서는 현재사용 중인 이식형 전자의료기들의 구조와 동작원리, 다양한 작업 환경 하에서 잡음의 영향을 고찰하고, 잡음에 의한 오동작의 방지 방안을 고찰함으로써 전자의료기 인체 삽입자의 작업환경에 따른 안전문제를 제고하고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.11a
• /
• pp.208-210
• /
• 2014

본 논문에서는 HEVC 동영상 표준 부호화 방식의 Intra 압축 모드를 이용해 영상을 압축할 때 잡음이 압축 알고리즘에 미치는 영향에 대해 논하고, 이를 분리하여 영상 압축의 성능을 높이는 방안을 제안한다. 먼저, 인공적으로 발생시킨 잡음을 영상에 추가한 후 이를 제거했을 때 압축 성능의 변화를 살펴본다. 그리고, 실제로 카메라를 사용해 취득한 영상에서 같은 결과가 나타나는지 확인하고, 이 결과를 바탕으로 가능한 한 화질을 유지하면서 압축 성능을 제고하는 방안을 제시하고자 한다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.44 no.5
• /
• pp.416-422
• /
• 2016

This paper presents preliminary performance analysis of a satellite formation flying testbed, which is under development by Astrodynamics and Control Laboratory, Department of Astronomy, Yonsei University. A model reference adaptive controller (MRAC) with a first-order reference model is chosen to enhance the response of reaction wheel system which is subject to uncertainties caused by unmodelled dynamics and measurement noise. In addition, an on-line parameter estimation (OPE) technique based on the least square is combined to eliminate the effect of angular measurement noise by estimating the moment of inertia. Both numerical simulations and hardware experiments with MRAC support the effectiveness and applicability of the adaptive control scheme, which maintains the tracking error below $0.25^{\circ}$ for the entire time span. However, the high frequency control input generated in hardware experiment strongly suggests design modifications to reduce the effect of deadzone.

• Journal of Advanced Navigation Technology
• /
• v.26 no.6
• /
• pp.487-495
• /
• 2022

This paper describes the design and development of a high-power transmit receive module(TRM) for mounting on X-band synthetic aperture radar(SAR) of the NEXTSat-2. The TRM generates a high-power pulse signal with a bandwidth of 100 MHz in the target frequency range of X-band and amplifies a low-noise on the received signal. Tx. path of the TRM has output signal level of more than 200 watts (53.01 dB), pulse droop of 0.35 dB, signal strength change of 0.04 dB during transmission signal output, and phase change of 1.7 ˚. Rx. path has noise figure of 3.99 dB and gain of 37.38 ~ 37.46 dB. It was confirmed the TRM satisfies all requirements. The TRM mounted on the NEXTSat-2 flight model(FM) which will be launched using the KSLV-II (Nuri).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.407-409
• /
• 2021

Under the influence of the 4th industrial revolution, various technologies such as artificial intelligence and automation are being grafted into industrial sites, and accordingly, the importance of data processing is increasing. Digital images may generate noise due to various reasons, and may affect various systems such as image recognition and classification and object tracking. To compensate for these shortcomings, we propose an image restoration algorithm based on pattern information of non-noise pixels. According to the distribution of non-noise pixels inside the filtering mask, the proposed algorithm switched the filtering process by dividing the interpolation method into a pattern that can be applied, a pattern based on region division, and a randomly arranged pixel pattern. preserves and restores the image. The proposed algorithm showed superior performance compared to the existing impulse noise removal algorithm.