• 음성과학
• /
• 제10권4호
• /
• pp.107-115
• /
• 2003

In this paper we tried to classify the pathological voice signal with severe noise component based on two different parameters, the spectral slope and the ratio of energies in the harmonic and noise components (HNR), The spectral slope is obtained by using a curve fitting method and the HNR is computed in cepstrum quefrency domain. Speech data from normal peoples and patients are collected, diagnosed and divided into three different classes (normal, relatively less noisy and severely noisy data), The mean values and the standard deviations of the spectral slope and the HNR are computed and compared with in the three kinds of data to characterize and classify the severely noisy pathological voice signals from others.

• 한국음향학회지
• /
• 제38권6호
• /
• pp.687-696
• /
• 2019

기존의 지진파 분류 특징은 강진에 초점이 맞추어져 있어서 미소지진과 같은 지진파는 다소 적합하지 않다. 본 연구에서는 강진과 더불어 미소지진, 인공지진, 잡음 분류에 적합한 특징 추출을 위해 주파수-시간 공간 내에서 히스토그램과 주성분 기반 특징 추출방법을 제안한다. 제안된 방법은 지진파의 주파수 관련 정보와 시간 관련 정보를 결합하는 방법을 적용한 히스토그램 기반 특징 추출방법과 주성분 기반 특징 추출방법을 이용하여 지진(강진, 미소지진, 인공지진)과 잡음, 미소지진과 잡음, 미소지진과 인공지진을 이진 분류한다. 2017년~2018년 최근 국내지진 자료와 분류 성능을 토대로 제안한 특징 추출방식의 효용성을 비교 평가한다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2011년도 추계학술대회 논문집
• /
• pp.664-666
• /
• 2011

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.691-692
• /
• 2013

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2001년도 하계종합학술대회 논문집(5)
• /
• pp.65-68
• /
• 2001

In the rehabilitation robotic arm systems for the disabled with spinal code injury, EMG signals are used in the control of the robotic arm. EMG signals are corrupted by many kinds of noises such as ECG signal, power noise and contact noise of electrode. Noise rejection improves the performance of the EMG pattern classification. In this paper, a variable bandwidth filter (VBF) and wavelet transform are used for the noise rejection of EMG signals and the comparison of SNR is given. Also, some statistical characteristics of features are investigated.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2005년도 춘계학술대회논문집
• /
• pp.367-371
• /
• 2005

Social noise survey on multiple residential noises such as nut impact, air-borne, bathroom, drainage and traffic noises was conducted to investigate major variables affecting the overall satisfaction for noise environment The effect of individual noise perception on the evaluation of the overall noise environment was investigated through a questionnaire survey on annoyance, disturbance and noise sensitivity. Auditory experiments was also undertaken to determine noise level according to the percent of satisfaction for individual noise source. As a result of survey, it was found that satisfaction for floor impact noise most greatly affects the overall satisfaction for noise environment and annoyance most greatly affects the satisfaction for individual noise sources. Result of auditory experiment showed that the noise level of floor impact noise by bang machine, airborne, drainage and traffic noise corresponding to 50% satisfaction is 44dB($L_{i,Fmax,AW}$) and 40dBA, respectively.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 춘계학술대회논문집
• /
• pp.712-717
• /
• 2004

Recently, the concern for the environmental noise has increased due to the growing of the living standard. The environmental noise regulations based on the equivalent noise level are widely used. However, the noise level, which Is based mainly on the magnitude with A-weighting, the important characteristics of noises in frequency and time domains and the impulsive nature cannot be assessed properly. These can have substantial effects on how human respond to noise. Therefore, the noise evaluation methodology based on the sound quality rather than the equivalent noise level can be more suitable to represent human response to the environmental noise. This paper describes the study on environmental noise quality analysis for various noises. A cluster analysis was carried out and the noises were classified into several clusters using the values of sound quality metrics. The classification was confirmed by comparing time and frequency characteristics of the noises. And then the result of Jury testing was analysis.

• 한국음향학회지
• /
• 제14권3호
• /
• pp.71-81
• /
• 1995

본 논문에서는 수중에서 발생되는 전이 신호의 자동 식별을 위하여 특징벡타를 추출하는 기법과 식별 알고리즘에 대하여 논한다. 특징벡타 추출기법으로 적은 계수로도 우수한 성능을 보이는 wavelet 변환을 사용한 방법을 제안하고 기종의 고전적인 방법들과 비교한다. 자동식별을 위해서는 MLP (Multilayer Perceptron), RBF (radial Basis Function), MLP-클래스 등 세 종류의 신경회로망을 사용하고, 성능 및 신뢰성을 높이기 위해서 두가지 특징벡타 및 세 식별기를 결합하는 방법을 사용한다. Traco의 표준 천이 데이터 집합 (standard transient data set) I과 모의 실험 데이터를 사용하여, 주어진 천이신호가 배경잡음에 비하여 충분히 에너지가 크고, 유한개의 소음원이 존재하며, 동시에 둘 이상의 소음원이 존재하지 않는다는 가정하에서 제안된 특징벡타 추출기법과 식별 알고리즘의 우수성을 확인한다.

• Journal of Electrical Engineering and Technology
• /
• 제10권4호
• /
• pp.1886-1898
• /
• 2015

In today’s era of advanced technological developments, the threats to the authenticity and integrity of digital images, in a nutshell, the threats to the Image Forensics Research communities have also increased proportionately. This happened as even for the ‘non-expert’ forgers, the availability of image processing tools has become a cakewalk. This image forgery poses a great problem for judicial authorities in any context of trade and commerce. Block matching based image cloning detection system is widely researched over the last 2-3 decades but this was discouraged by higher computational complexity and more time requirement at the algorithm level. Thus, for reducing time need, various dimension reduction techniques have been employed. Since a single technique cannot cope up with all the transformations like addition of noise, blurring, intensity variation, etc. we employ multiple techniques to a single image. In this paper, we have used Fuzzy logic approach for decision making and getting a global response of all the techniques, since their individual outputs depend on various parameters. Experimental results have given enthusiastic elicitations as regards various transformations to the digital image. Hence this paper proposes Fuzzy based cloning detection and classification system. Experimental results have shown that our detection system achieves classification accuracy of 94.12%. Detection accuracy (DAR) while in case of 81×81 sized copied portion the maximum accuracy achieved is 99.17% as regards subjection to transformations like Blurring, Intensity Variation and Gaussian Noise Addition.