• Journal of Multimedia Information System
• /
• v.9 no.1
• /
• pp.69-72
• /
• 2022

Extraction of a salient chromagram is utmost important for cover song identification. Cover song refers to a live performance, a remix, or a new recording of a previously recorded track. This paper utilizes the Savitzky-Golay filters in chromagram extraction for suppressing timber-related components of a music signal, which is not preserved while generating cover songs. By removing the timber-related components, the discriminative tonal components, which are conducive for cover song identification, are emphasized in chromagram. Experiments on cover song identification over two datasets show that the Savitzky-Golay filters are more effective in reducing timber effects in chromagram than other types of filters.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.268-268
• /
• 2020

토양수분량은 수문연구에 있어 중요한 인자 중의 하나이며, 그 필요성이 점차 강조되고 있다. 국내에서도 최근 새로운 관측기기의 도입이나 수자원위성의 개발 등에 관한 연구가 점차 활발하게 이뤄지고 있으나, 토양수분량 자료의 생산, 품질관리 및 배포 시스템에 관한 연구 및 개발이 부족한 실정이다. 반면에 해외에서는 International Soil Moisture Network(ISMN)을 통해 토양수분량 자료의 품질관리 및 배포가 활발하게 이루어지고 있는데, ISMN에서는 토양특성, 강우에 대한 반응, 토양온도, 시계열특성을 이용해 토양수분량 관측 자료를 품질관리 하고 있다. 본 연구에서는 ISMN의 spike 검출 알고리즘에서 그래프 평활화(smoothing)를 위해 이용되는 Savitzky-Golay 필터의 window size와 polynomial order(filter order)를 다양하게 변화시키고, 이를 설마천 관측소에서 측정한 토양수분량 원시자료에 적용하여 window size와 polynomial order별로 편의(bias), 변동(variation), 평균 제곱근 오차(Root Mean Square Error, RMSE)를 산정하였다. 통계산정 결과 원시자료와의 bias는 window size가 3이고 polynomial order가 2인 필터를 적용했을 때 가장 작은 것으로 나타났으며, variance는 window size가 3이고 polynomial order가 2인 필터를 이용했을 때가 원시자료와 가장 유사한 것으로 나타났다. 또한, RMSE는 window size가 5이고 polynomial order가 3일 때 가장 작은 것으로 나타났다. 이는 추후 토양수분량 품질관리를 수행하기 위해 적절한 필터 계수 값을 제시할 수 있는 논문으로 사료된다.

• Journal of the Korean Geographical Society
• /
• v.51 no.4
• /
• pp.509-523
• /
• 2016

The soil prediction can provide quantitative soil information for sustainable mountainous ecosystem management. Visible near infrared spectroscopy, one of soil prediction methods, has been applied to predict several soil properties with effective costs, rapid and nondesctructive analysis, and satisfactory accuracy. Spectral preprocessing is a essential procedure to correct noisy spectra for visible near infrared spectroscopy. However, there are no attempts to evaluate various spectral preprocessing methods. We tested 5 different pretreatments, namely continuum removal, Savitzky-Golay filter, discrete wavelet transform, 1st derivative, and 2nd derivative to predict soil carbon(C) and nitrogen(N). Partial least squares regression was used for the prediction method. The total of 153 soil samples was split into 122 samples for calibration and 31 samples for validation. In the all range, absorption was increased with increasing C contents. Specifically, the visible region (650nm and 700nm) showed high values of the correlation coefficient with soil C and N contents. For spectral preprocessing methods, continuum removal had the highest prediction accuracy(Root Mean Square Error) for C(9.53mg/g) and N(0.79mg/g). Therefore, continuum removal was selected as the best preprocessing method. Additionally, there were no distinct differences between Savitzky-Golay filter and discrete wavelet transform for visual assessment and the methods showed similar validation results. According to the results, we also recommended Savitzky-Golay filter that is a simple pre-treatment with continuum removal.

• Journal of information and communication convergence engineering
• /
• v.20 no.2
• /
• pp.125-130
• /
• 2022

In modern society, as many data are used for research or commercial purposes, the value of data is gradually increasing. In related fields, research is being actively conducted to collect valuable data, but it is difficult to collect proper data because the value of collection is determined according to the performance of existing sensors. To solve this problem, a method to effectively reduce noise has been proposed, but there is a point in which performance is degraded due to damage caused by noise. In this paper, a device capable of collecting time series data was designed to correct such data noise, and a correction technique was performed by giving an error value based on the representatively collected ultrafine dust data, and then comparing before and after Compare performance. For the correction method, Kalman, LPF, Savitzky-Golay, and Moving Average filter were used. Savitzky-Golay filter and Moving Average Filter showed excellent correction rate as an experiment. Through this, the performance of the sensor can be supplemented and it is expected that data can be effectively collected.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.4
• /
• pp.639-642
• /
• 2012

Optical coherence tomography(OCT) can provide real-time and non-invasive subsurface imaging with ultra-high resolution of micrometer scale. However, conventional OCT systems generally have a limited imaging depth range within a depth of only 1-2 mm. To overcome the limitation, we have proposed an active surface tracking algorithm used in common-path Fourier-domain OCT system in order to extend the imaging depth range. The surface tracking algorithm based on the threshold and Savitzky-Golay filter of A-scan data was applied to real-time tracking. The algorithm has controlled a moving stage according to the sample's surface variance in real time. An OCT image obtained by the algorithm clearly show an extended imaging depth range. Consequently, the proposed algorithm demonstrated the potential for improving the conventional OCT systems with limitary depth range.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.17-26
• /
• 2023

In this paper, we propose a several smoothing techniques are compared and applied to increase the application of the LSTM-based learning model and its effectiveness. The applied smoothing technique is Savitky-Golay, exponential smoothing, and weighted moving average. Through this study, the LSTM algorithm with the Savitky-Golay filter applied in the preprocessing process showed significant best results in prediction performance than the result value shown when applying the LSTM model to Bitcoin data. To confirm the predictive performance results, the learning loss rate and verification loss rate according to the Savitzky-Golay LSTM model were compared with the case of LSTM used to remove complex factors from Bitcoin price prediction, and experimented with an average value of 20 times to increase its reliability. As a result, values of (3.0556, 0.00005) and (1.4659, 0.00002) could be obtained. As a result, since crypto-currencies such as Bitcoin have more volatility than stocks, noise was removed by applying the Savitzky-Golay in the data preprocessing process, and the data after preprocessing were obtained the most-significant to increase the Bitcoin prediction rate through LSTM neural network learning.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.84-89
• /
• 2023

In water resource management, data prediction is performed using artificial intelligence, and companies, governments, and institutions continue to attempt to efficiently manage resources through this. LSTM is a model specialized for processing time series data, which can identify data patterns that change over time and has been attempted to predict groundwater level data. However, groundwater level data can cause sen-sor errors, missing values, or outliers, and these problems can degrade the performance of the LSTM model, and there is a need to improve data quality by processing them in the pretreatment stage. Therefore, in pre-dicting groundwater data, we will compare the LSTM model with the MSE and the model after normaliza-tion through distribution, and discuss the important process of analysis and data preprocessing according to the comparison results and changes in the results.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.30 no.1
• /
• pp.16-30
• /
• 1997

Application of digital filter to the wave analysis is studied using the observed data by wave gauge. Sea wave data obtained from wave gauge always include long wave frequency components. In order to estimate the sea wave parameters, we must re-analyzed wave data by using a digital filter and the concept of mean sea level correction method. By the wave by wave analysis and spectral methods, sea wave parameters on the basis of wave data obtained by the conventional method and digital filter are compared. The best-fitted design filter determined by the necessary conditions of frequency responses, can be obtained by calculating various transfer functions. Thus, to get the best the digital filter design, both Butterworth filter and Savitzky-Golay filter of digital filter are used in the frequency and time domain, respectively. Three cases of observation wave data are calculated by applying digital filter. The components of different frequency bands in the surf zone are coexisted in three cases. The wave data for wind wave components is computed using the digital filter the surf zone and off-surf zone, and based on the filtered data, wave parameters are calculated by the spectral analysis and wave by wave analysis methods, respectively. As a results, when sea wave data observed by wave gauge are analyzed, the Savitzky-Golay method is recommended which can well appear cut-off frequency by experimental choosing filter length in the time domain. The better mean sea level correction method is the Butterworth filter in the frequency domain.

• Korean Journal of Remote Sensing
• /
• v.31 no.2
• /
• pp.149-160
• /
• 2015

A comparative study was conducted for alternative consecutive procedures of detection of cloud-contaminated pixels and gap-filling and smoothing of time-series data to produce high-quality gapless satellite vegetation index (i.e. Normalized Difference Vegetation Index, NDVI). Performances of five alternative methods for detecting cloud contaminations were tested with ground-observed cloudiness data. The data gap was filled with a simple linear interpolation and then, it was applied two alternative smoothing methods (i.e. Savitzky-Golay and Wavelet transform). Moderate resolution imaging spectroradiometer (MODIS) data were used in this study. Among the alternative cloud detection methods, a criterion of MODIS Band 3 reflectance over 10% showed best accuracy with an agreement rate of 85%, which was followed by criteria of MODIS Quality assessment (82%) and Band 3 reflectance over 20% (81%), respectively. In smoothing process, the Savitzky-Golay filter was better performed to retain original NDVI patterns than the wavelet transform. This study demonstrated an operational framework of gapdetection, filling, and smoothing to produce high-quality satellite vegetation index.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.05b
• /
• pp.614-618
• /
• 2005

수문시계열 분석과 예측은 대부분 ARMA(AutoRegressive Moving Average) 형태의 선형적인 추계학적인 모형을 이용하였으나 자현현상이 복잡해지고 비선형적인 특성을 가짐에 따라 선형적인 해석은 수문시계열의 분석과 예측에 있어서 많은 오류를 내포하고 있다. 이와 같은 문제를 해결하기 위한 시도로 Chaos이론이란 개념이 사용되기 시작하였으며, 수자원분야에서는 1980년대 후반부터 물수지 방정식 및 강우유출에 대한 카오스적 특성분석 등 많은 연구가 진행되었다. 본 연구에서는 영산강유역의 본류를 대표하는 나주지점을 대상으로 2003년 1월 1일 00시부터 2004년 12월 31일 23시까지 17,544개의 시수위 자료에 대하여 해당 년도의 Rating-Curve식을 적용 환산한 유출량자료에 데한 카오스적 특성을 분석하였다. 카오스적 특성을 분석하기에 앞서 원자료에 대하여 이동평균법과 Savitzky-Golay Filter를 적용하여 잡음을 제거하였으며, 1차원의 단일변량의 자료에 대한 상태공간(Phase Space)의 재건을 통하여 비교검토 하였다. 이러한 일련의 과정을 거친 자료에 대하여 상관차원법을 이용하여 영산강 유역의 나주지점의 시유출량 자료에 대한 카오스적 특성을 분석한 결과 저차원의 수렴으로 카오스 특성을 가졌다.