• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.383-386
• /
• 2019

4 차산업혁명의 발달은 전 세계가 건강한 삶에 관련된 스마트시티 및 맞춤형 치료에 큰 관심을 갖게 하였고, 특히 기계학습 기술은 암을 극복하기 위한 유전체 기반의 정밀 의학 연구에 널리 활용되고 있어 암환자의 예후 예측 및 예후에 따른 맞춤형 치료 전략 수립 등을 가능케하였다. 하지만 암 예후 예측 연구에 주로 사용되는 유전자 발현량 데이터는 약 17,000 개의 유전자를 갖는 반면에 샘플의 수가 200 여개 밖에 없는 문제를 안고 있어, 예후 예측을 위한 신경망 모델의 일반화를 어렵게 한다. 이러한 문제를 해결하기 위해 본 연구에서는 고차원의 유전자 발현량 데이터를 신경망 모델이 효과적으로 학습할 수 있도록 2D 이미지로 표현하는 기법을 제안한다. 길이 17,000 인 1 차원 유전자 벡터를 64×64 크기의 2 차원 이미지로 사상하여 입력크기를 압축하였다. 2 차원 평면 상의 유전자 좌표를 구하기 위해 유전자 네트워크 데이터와 Node2Vec 이 활용되었고, 이미지 기반의 암 예후 예측을 수행하기 위해 합성곱 신경망 모델을 사용하였다. 제안하는 기법을 정확하게 평가하기 위해 이중 교차 검증 및 무작위 탐색 기법으로 모델 선택 및 평가 작업을 수행하였고, 그 결과로 베이스라인 모델인 고차원의 유전자 벡터를 입력 받는 다층 퍼셉트론 모델보다 더 높은 예측 정확도를 보여주는 것을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.6
• /
• pp.100-110
• /
• 2007

When compressed video data is transmitted over error-prone network such as wireless channel, data is likely to be lost, so the quality of reconstructed picture is severely decreased. It is specially so in case that important information such as motion vector or macroblock mode is lost. H.264/AVC standard includes DP as error resilient technique for protecting important information from error in which data is labeled according to its relative importance. But DP technique requires a network that supports different reliabilities of transmitted data. In general, the benefits of UEP is sought by sending multiple times of same packets corresponding to important information. In this paper, we propose MDC technique based on data partitioning technique. The proposed method encodes motion vector of H.264/AVC standard into multiple parts using MDC and transmits each part as independent packet. Even if partial packet is lost, the proposed scheme can decode the compressed bitstream by using estimated motion vector with partial packets correctly transmitted, so that achieving improved performance of error concealment with minimal effect of channel error. Also in decoding process, the proposed multiple description matching increases the accuracy of estimated lost motion vector and quality of reconstructed video.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.12
• /
• pp.1122-1132
• /
• 2012

Compressed sensing has been applied to many fields such as images, speech signals, radars, etc. It has been mainly applied to stationary signals, and reconstruction error could grow as compression ratios are increased by decreasing measurements. To resolve the problem, speech signals are divided into frames and processed in parallel. The frames are made sparse by dictionary learning, and adaptive compressed sensing is applied which designs the compressed sensing reconstruction matrix adaptively by using the difference between the sparse coefficient vector and its reconstruction. Through the proposed method, we could see that fast and accurate reconstruction of non-stationary signals is possible with compressed sensing.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2013.11a
• /
• pp.178-181
• /
• 2013

본 논문에서는 SVC와 MVC의 부호화 구조를 결합하여 구현된 스케일러블 다시점 비디오 부호화의 움직임 추정 기법과 DPB를 위한 GPB 기반의 RPL (reference picture list) 설계를 제안한다. 제안된 움직임 추정 기법에서는 부호화 과정에서 필요한 예측 부호화의 성능 향상을 위해서 서로 다른 시점 (view)의 픽처 정보를 참조픽처의 후보로서 사용한다. 또한, B픽처 예측의 경우 HEVC에서 사용하는 HEVC GPB 기술을 통해 참조화면에서 두 개의 움직임 벡터를 활용한다. 제안된 움직임 예측 구조에 의해서 압축된 비디오 데이터의 크기를 감소시켜 압축 효율을 증대시킬 수 있다. 다양한 실험을 통해서 제안된 예측 구조를 적용함으로써 스케일러블 다시점 비디오 부호화에서의 압축 효율의 향상을 얻어낼 수 있음을 확인하였다.

• Journal of KIISE:Computer Systems and Theory
• /
• v.37 no.3
• /
• pp.184-193
• /
• 2010

This paper proposes a biological iridescence BRDF(Bidirectional Reflectance Distribution Function) compression and rendering method. In the graphics technology, iridescence sometimes is named structure colors. The main features of these symptoms are shown transform of color and brightness by varying viewpoint. Graphics technology to render this is the BRDF technology. The BRDF methods enable realistic representation of varying view direction, but it requires a lot of computing power because of large data. In this paper, we obtain reflection map from iridescence BRDF, analyze color of reflection map and propose representation method by several colorfully concentric circle. The one concentric circle represents beam width of reflection ray by one normal vector. In this paper, we synthesize rough concentric by using several virtually optical normal vectors. And we obtain spectrum information from concentric circles passing through the center point. The proposed method enables IBR(image based rendering) technique which results is realistic illuminance and spectrum distribution by one texture from reduced BRDF data within spectrum.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.38 no.6
• /
• pp.703-711
• /
• 2001

In this paper, we propose efficient multispectral image compression using variable block size vector quantization (VQ). In wavelet domain, we perform the variable block size VQ to remove intraband redundancy for a reference band image that has the lowest spatial variance and the best correlation with other band. And in wavelet domain, we perform the classified interband prediction to remove interband redundancy for the remaining bands. Then error wavelet coefficients between original image and predicted image are residual variable block size vector quantized to reduce prediction error. Experiments on remotely sensed satellite image show that coding efficiency of the proposed method is better than that of the conventional method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.7A
• /
• pp.1063-1075
• /
• 2000

This paper proposes an adaptive error concealment technique for compressed video. Since redundancy is extracted out during compression process, compressed video is vulnerable to errors which occur during transmission of video over error prone networks such as wireless channels and Internet. Error concealment is a process of reconstructing video out of damaged video bit stream. We proved that scalable encoding is very useful for error concealment. Analysis of experiments shows that some part of image is better concealed by using base layer information and other part of image is better concealed by using previous frame information. We developed a technique which enables to decide which methodology is more effective, adaptively, based on motion vectors and regional spatial activity. We used H.263v2 for scalable encoding, but, our approach could be applied to all DCT based video codec.

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.25 no.5
• /
• pp.550-558
• /
• 1988

This paper presents laplacian pyramid vector quantization (LPVQ) approach in which a vector quantizer is used to encode a series of quasi-bandpassed images generated by the laplacian pyramid processing. Performance of the LPVQ is compared to those of DCT domain methods at the same bit rate via computer simulations. Experimental results show that the PSNR's (peak signal-to-noise ratio) for the LPVQ are almost the same as those of the DCT based methods. However, subjective study indicates the LPVQ obtains slightly higher scores than the DCT based techniques.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.757-760
• /
• 2004

동영상은 포함하고 있는 정보량이 아주 많기 때문에, 영상처리기술 중에서도 데이터 압축기술은 대단히 중요하다. 본 논문에서는 DCT 이 외의 수법을 이용할 때의 동영상의 부호화에 대하여 검토하고, 특이값 전개에 주목한다. 이 방식이 DCT가 갖는 문제점을 모두 해결할 수 있는 것은 아니지만, 다른 방식에서의 영상부호화의 가능성을 보이고자 한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.06a
• /
• pp.123-124
• /
• 2018

본 논문에서는 HEVC 국제표준으로 압축된 비디오에서 움직임 물체를 추적하는 방법을 제안한다. 제안하는 방법은 HEVC 비트스트림의 대부분을 차지하는 인터 프레임의 움직임 벡터 정보를 입력 데이터로 사용하는 ST-MRF(Spatio-Temporal-Markov Random Field) 모델을 기반으로 하며, ST-MRF 모델에서 발생할 수 있는 오차전파로 점진적으로 객체를 부정확하게 추적하는 것을 HEVC GOP(Group of Picture)마다 삽입되는 인트라 프레임만을 복호화 하여 픽셀 정보를 입력으로 하는 YOLO 모델과 융합시켜 보정함으로써 추적하던 객체를 잃지 않고 강건하게 추적하는 방법을 제안한다.