• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1749-1758
• /
• 1997

This paper suggests the development of dynamic forecasting model for short-term power demand based on Radial Basis Function Network and Pal's GLVQ algorithm. Radial Basis Function methods are often compared with the backpropagation training, feed-forward network, which is the most widely used neural network paradigm. The Radial Basis Function Network is a single hidden layer feed-forward neural network. Each node of the hidden layer has a parameter vector called center. This center is determined by clustering algorithm. Theatments of classical approached to clustering methods include theories by Hartigan(K-means algorithm), Kohonen(Self Organized Feature Maps %3A SOFM and Learning Vector Quantization %3A LVQ model), Carpenter and Grossberg(ART-2 model). In this model, the first approach organizes the load pattern into two clusters by Pal's GLVQ clustering algorithm. The reason of using GLVQ algorithm in this model is that GLVQ algorithm can classify the patterns better than other algorithms. And the second approach forecasts hourly load patterns by radial basis function network which has been constructed two hidden nodes. These nodes are determined from the cluster centers of the GLVQ in first step. This model was applied to forecast the hourly loads on Mar. $4^{th},\;Jun.\;4^{th},\;Jul.\;4^{th},\;Sep.\;4^{th},\;Nov.\;4^{th},$ 1995, after having trained the data for the days from Mar. $1^{th}\;to\;3^{th},\;from\;Jun.\;1^{th}\;to\;3^{th},\;from\;Jul.\;1^{th}\;to\;3^{th},\;from\;Sep.\;1^{th}\;to\;3^{th},\;and\;from\;Nov.\;1^{th}\;to\;3^{th},$ 1995, respectively. In the experiments, the average absolute errors of one-hour ahead forecasts on utility actual data are shown to be 1.3795%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.1080-1099
• /
• 2019

A better tradeoff between robustness and invisibility will be realized by using the just noticeable (JND) model into the quantization-based watermarking scheme. The JND model is usually used to describe the perception characteristics of human visual systems (HVS). According to the research of cognitive science, HVS can adaptively extract the structure features of an image. However, the existing JND models in the watermarking scheme do not consider the structure features. Therefore, a novel JND model is proposed, which includes three aspects: contrast sensitivity function, luminance adaptation, and contrast masking (CM). In this model, the CM effect is modeled by analyzing the direction features and texture complexity, which meets the human visual perception characteristics and matches well with the spread transform dither modulation (STDM) watermarking framework by employing a new method to measure edge intensity. Compared with the other existing JND models, the proposed JND model based on structural regularity is more efficient and applicable in the STDM watermarking scheme. In terms of the experimental results, the proposed scheme performs better than the other watermarking scheme based on the existing JND models.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.9A
• /
• pp.2289-2304
• /
• 1998

For the performance analysis and traffic control of ATM networks carrying video sequences, need an appropriate video traffic model. In this paper, we propose a new traffic model for MPEG compressed videos which are widely used for any type of video applications at th emoment. The proposed modeling scheme uses scene-based traffic characteristics and considers the correlation between frames of consecutiv GOPs. Using a simple scene detection algorithm, scene changes are modeled by state transitions and the number of GOPs of a scene state is modeled by a geometric distirbution. Frames of a scene stte are modeled by mean I, P, and B frame size. For more accurate traffic modeling, quantization errors (residual bits) that the state transition model using mean values has are compensated by autoregressive processes. We show that our model very well captures the traffic chracteristics of the original videos by performance analysis in terms of autocorrelation, histogram of frame bits genrated by the model, and cell loss rate in the ATM multiplexer with limited buffers. Our model is able to perrorm translations between levels (i.e., GOP, frame, and cell levels) and to estimate very accurately the stochastic characteristics of the original videos by each level.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.289-292
• /
• 2002

This paper provides a frame-layer method for controlling bit rate of compressed video data in real time. Our approach is easy to operate and can store encoded video data in real time without deteriorating the quality of an image. To provide ameliorated and consistent visual quality, a new concept named SOP (Set Of Pictures) and a new quantization parameter variation control algorithm based on a second-order rate-distortion model 〔2〕 are introduced. The total bit-budget is allocated efficiently to cope with unpredictable recording time by using the proposed algorithm and it is distributed to each frame. In the end, we show improved and consistent video quality with experimental results obtained from C-model of a MPEG-4 (simple-profile) encoder.

• Phonetics and Speech Sciences
• /
• v.6 no.1
• /
• pp.77-83
• /
• 2014

This paper proposes a speaker and environment clustering method in order to overcome the degradation of the speech recognition performance caused by various noise and speaker characteristics. In this paper, instead of using the distance between Gaussian mixture model (GMM) weight vectors as in the Google's approach, the distance between the adapted mean vectors based on the modified maximum a posteriori (MAP) adaptation is used as a distance measure for vector quantization (VQ) clustering. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method yields error rate reduction of 10.6% compared with baseline speaker-independent (SI) model, which is slightly better performance than the Google's approach.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.287-290
• /
• 2002

본 논문에서는 디지털 컨텐츠 저작권 보호를 위해 강인성과 비가시성의 유지를 위한 보다 효과적인 방법으로 웨이브릿 변환에서 적응적 워터마크 삽입강도를 갖는 지각적 데이터 은닉 모델을 제안한다. 먼저 영상을 9/7 쌍직교 웨이브릿 필터를 사용해 4레벨로 다해상도 분해한다. 다음으로 연속부대역 양자화(successive subband quantization)를 통한 시각적 중요계수(perceptually significant coefficient: PSC)들을 선정하여 선택된 계수들에 대해서만 워터마크 정보를 삽입한다. 지각 모델은 정상상태의 일반화 가우시안 모델(generalized gaussian model)로 추정된 NVF(noise visibility function)로 에지와 텍스쳐영역 그리고 평탄영역에 따라 각각 적응적으로 삽입되게 한다. 이는 각 서브밴드 내의 분산과 형상계수(shape parameter)에 의해 결정된다. 적응적 워터마크의 삽입강도를 갖기 위해 에지와 텍스쳐영역의 삽입강도는 각 서브밴드의 주파수 감도(frequency sensitivity)로 결정되고, 평탄영역의 삽입강도는 영상의 국부적 특성에 근거한 통계적 가중치를 사용한다. 삽입되는 워터마크는 랜덤시퀀스로 N(0,1)이다. 여러 가지 공격에 대한 실험으로 제안한 방법의 비가시성과 강인성을 확인한다.

• Proceedings of the KIEE Conference
• /
• 1989.07a
• /
• pp.481-485
• /
• 1989

The object of this parer is on the design of an broad board classifier for connected. Korean digit. Many approaches have been applied in speech recognition systems: parametric vector quantization, dynamic programming and hiden Markov model. In the 80's the neural network method, which is expected to solve complex speech recognition problems, came bach. We have chosen the rule based system for our model. The phoneme-groups that we wish to classify are vowel_like, plosive_like fricative_like, and stop_like.The data used are 1380 connected digits spoken by three untrained male speakers. We have seen 91.5% classification rate.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.57-65
• /
• 1995

This paper presents a new classified vector quantization (VQ) technique using a neural network model in the transform domain. Prior to designing a codebook, the proposed approach extracts class features from a set of images using self-organizing feature map (SOFM) that has the pattern recognition characteristics and the same as VQ objective. Since we extract the class features from the training images unlike previous approaches, the reconstructed image quality is improved. Moreover, exploiting the adaptivity of the neural network model makes our approach be easily applied to designing a new vector quantizer when the processed image characteristics are changed. After the generalized BFOS algorithm allocates the given bits to each class, codebooks of each class are also generated using SOFM for the maximal reconstructed image quality. In experimental results using monochromatic images, we obtained a good visual quality in the reconstructed image. Also, PSNR is comparable to that of other classified VQ technique and is higher than that of JPEG baseline system.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.10
• /
• pp.50-62
• /
• 1996

A parallel looking stereo camera was mainly used as an input sensor for digital image processing, image understanding and the extraction of 3 dimensional information. Theoretical analysis and performance evaluation are dealt in this paper for a convergent looking stereo camera model having a fixation point with the result of crossing optical axes. The quantization error, depth resolution and equidepth map due to digital pixels, and the misalignments effects of pan, tilt and roll angles are analyzed by using rhe relationship between the reference and image coordinate systems. Also horopter, epipolar lines, probability density functions of the depth error, and stereo fusion areas for the two camera models are discussed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.23 no.8
• /
• pp.2025-2031
• /
• 1998

In moving picture coding standard MPEG2, a bit rate control system plays a key role for the compressing ratio and picture quality. We proposed a bit rate control scheme which assigns more bits to I, P frames and uses the average MQUANT of previous mackoblocks. The proposed scheme showed about 0.9dB improvement of image quality when compared to bit rate control method of MPEG2 Test-Model5.