• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.24-33
• /
• 2017

Multitemporal MODIS vegetation index (VI) data are widely used in vegetation monitoring research into environmental and climate change, since they provide a profile of vegetation activity. However, MODIS data inevitably contain disturbances caused by the presence of clouds, atmospheric variability, and instrument problems, which impede the analysis of the NDVI time series data and limit its application utility. For this reason, preprocessing to reduce the noise and reconstruct high-quality temporal data streams is required for VI analysis. In this study, a data reconstruction method for MODIS NDVI is proposed to restore bad or missing data based on the statistical properties of the oscillations in the NDVI temporal dynamics. The first derivatives enable us to examine the monotonic properties of a function in the data stream and to detect anomalous changes, such as sudden spikes and drops. In this approach, only noisy data are corrected, while the other data are left intact to preserve the detailed temporal dynamics for further VI analysis. The proposed method was successfully tested and evaluated with simulated data and NDVI time series data covering Baekdu Mountain, located in the northern part of North Korea, over the period of interest from 2006 to 2012. The results show that it can be effectively employed as a preprocessing method for data reconstruction in MODIS NDVI analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.10
• /
• pp.165-172
• /
• 2010

There are two method of error correction in vocabulary recognition system. one error pattern matting base on method other vocabulary mean pattern base on method. They are a failure while semantic of key-word problem for error correction. In improving, in this paper is propose system of key-word error correction using algorithm of syllable restoration. System of key-word error correction by processing of semantic parse through recognized phoneme meaning. It's performed restore by algorithm of syllable restoration phoneme apply fluctuation before word. It's definitely parse of key-word and reduced of unrecognized. Find out error correction rate using phoneme likelihood and confidence for system parse. When vocabulary recognition perform error correction for error proved vocabulary. system performance comparison as a result of recognition improve represent 2.3% by method using error pattern learning and error pattern matting, vocabulary mean pattern base on method.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.2
• /
• pp.130-135
• /
• 2004

This paper presents a new design methods of the short-term load forecasting system (STLFS) using the data mining. The structure of the proposed STLFS is divided into two parts: the Takagi-Sugeno (T-S) fuzzy model-based classifier and predictor The proposed classifier is composed of the Gaussian fuzzy sets in the premise part and the linearized Bayesian classifier in the consequent part. The related parameters of the classifier are easily obtained from the statistic information of the training set. The proposed predictor takes form of the convex combination of the linear time series predictors for each inputs. The problem of estimating the consequent parameters is formulated by the convex optimization problem, which is to minimize the norm distance between the real load and the output of the linear time series estimator. The problem of estimating the premise parameters is to find the parameter value minimizing the error between the real load and the overall output. Finally, to show the feasibility of the proposed method, this paper provides the short-term load forecasting example.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.494-500
• /
• 2020

This paper proposes a new distance estimation technique for indoor localization in ultra wideband (UWB) systems. The proposed technique is based on recurrent neural network (RNN), one of the deep learning methods. The RNN is known to be useful to deal with time series data, and since UWB signals can be seen as a time series data, RNN is employed in this paper. Specifically, the transmitted UWB signal passes through IEEE802.15.4a indoor channel model, and from the received signal, the RNN regressor is trained to estimate the distance from the transmitter to the receiver. To verify the performance of the trained RNN regressor, new received UWB signals are used and the conventional threshold based technique is also compared. For the performance measure, root mean square error (RMSE) is assessed. According to the computer simulation results, the proposed distance estimator is always much better than the conventional technique in all signal-to-noise ratios and distances between the transmitter and the receiver.

• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1586-1593
• /
• 2010

Vocabulary recognition error correction method has probabilistic pattern matting and dynamic pattern matting. In it's a sentences to based on key-word by semantic analysis. Therefore it has problem with key-word not semantic analysis for morphological changes shape. Recognition rate improve of vocabulary unrecognized reduced this paper is propose. In syllable restoration algorithm find out semantic of a phoneme recognized by a phoneme semantic analysis process. Using to sentences restoration that morphological analysis and morphological analysis. Find out error correction rate using phoneme likelihood and confidence for system parse. When vocabulary recognition perform error correction for error proved vocabulary. system performance comparison as a result of recognition improve represent 2.0% by method using error pattern learning and error pattern matting, vocabulary mean pattern base on method.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.856-860
• /
• 2008

Wire-suspensions in the conventional actuators mechanically support the moving part and guarantee the accuracy of the actuator without tangential tilt actuation. However, such a suspension configuration has considerable stiffness in the tangential tilt direction with two additional wire beams for the tangential tilt. Thus, we performed a design sensitivity analysis for the wire-suspension stiffness of 4-axis actuator and controlled the main parameters such as distance among wire-suspensions and wire-suspension length to allow tangential tilt flexibility. The elasticity of frame PCB that supports the moving part by wire-suspensions was also exploited to improve the flexibility of wire-suspension in the tangential tilt direction. A novel suspension structure was devised by establishing eight wire-suspensions at both sides of the moving part for electrical connection to coils. The magnetic circuit according to the proposed 4-axis actuator using multi-polar magnet and coils was also suggested for the generation of electromagnetic forces in the focusing, tracking, radial and tangential tilt directions.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.61-64
• /
• 1999

기존의 CELP 보코더에서, 무성음에 대한 별도의 처리 없이 유성음과 동일하게 처리하였다. 유성음과 무성음은 발성모델측면에서 임펄스열과 랜덤 잡음으로 각각 다름에 도 불구하고 동일하게 처리함으로써 합성음에서 음질의 저하 및 계산량과 전송률 측면에서 손실을 가져왔다. 또, U/V(Unvoiced /voiced) 분류기를 사용하는 경우에는 U/V 분류기의 성능에 따라 합성음의 음질저하의 정도의 차이가 심하다. 본 논문에서는 에러율과 전처리 계산량을 쳐소로 할 수 있는 U/V 분류기를 사용하여 CELP 보코더에서 전송률을 감소시키는 방법을 제안한다. CELP 보코더에서는 스펙트럼 정보를 LPC 파라미터로 추출한 후 다시 전송형 파라미터인 LSP(Line Spectrum Frequency)로 변환한다 새로운 린/V 분류기는 이 LSP 파라미터를 이용한다. LSP 파라미터의 주파수영역 분포도와 간격정보를 이용하여 U/V를 결정하게 된다 제안한 방법을 5.3kbps ACELP에 적용하여 성능 평가를 실시하였다 실험결과 음질의 저하 없이 $5.6\%$ (280bps)의 전송률을 감소할 수 있었다.

• Ecology and Resilient Infrastructure
• /
• v.5 no.3
• /
• pp.125-133
• /
• 2018

Artificial neural network (ANN) is a powerful model to predict time series data and have been frequently adopted to predict groundwater level (GWL). Many researchers have also tried to improve the performance of ANN prediction for GWL in many ways. Dummies are usually used in ANN as input to reflect the seasonal effect on predicted results, which is necessary for improving the predicting performance of ANN. In this study, the effect of Dummy on the prediction performance was analyzed qualitatively and quantitatively using several graphical methods, correlation coefficient and performance index. It was observed that results predicted using dummies for ANN model indicated worse performance than those without dummies.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.12
• /
• pp.97-106
• /
• 1999

We propose a new watermarking method to embed a label in a video which is robust against the change of the group of picture. The proposed method embeds labels in the pixel domain, but detects the label in the DCT frequency domain. For embedding a label, the size of watermark based on the human visual system is calculated to keep a quality of videos. A lookup table haying the pixel patterns and the sequences of a sign of DCT coefficients is used for detecting a label in the DCT frequency domain. In this paper, we analyze bit error rates for labels of videos compressed by MPEG2 using the central limit theorem and compare the simulation results with previous methods.

• The Journal of the Korea Contents Association
• /
• v.6 no.2
• /
• pp.34-43
• /
• 2006

This paper shows modeling methods for VBR video trace. It is well known that VBR video trace is characterized as longterm correlated and highly intermittent burst data. To analyze this, we attempt to model it using neural network with auxiliary linear structures derived from residual threshold. For testing purpose, we generate VBR video trace from chaotic nonlinear function combined with the geometric random noise. The modeling result of the generated data shows that the attempted method represents more accurately than the traditional neural network. However, we also found that combining hRU to the attempted modeling method can yield a closer agreement to statistical features of the generated data than the attempted modeling method alone.