• Journal of the Korean Data and Information Science Society
• /
• 제19권1호
• /
• pp.25-36
• /
• 2008

Error Correcting Output Codes (ECOC) can improve generalization performance when applied to multicategory classification problem. In this study we propose a new criterion to select hyperparameters included in ECOC scheme. Instead of margins of a data we propose to use the probability of misclassification error since it makes the criterion simple. Using this we obtain an upper bound of leave-one-out error of OVA(one vs all) method. Our experiments from real and synthetic data indicate that the bound leads to good estimates of parameters.

• 한국통신학회논문지
• /
• 제33권6C호
• /
• pp.438-443
• /
• 2008

The efficient method to implement the Max-Log-MAP algorithm is proposed by modifying the conventional algorithm. It is called a parallel soft output Viterbi algorithm (SOVA) and the rigorous proof is given for the equivalence between the Max-Log-MAP algorithm and the parallel SOVA. The parallel SOVA is compared with the conventional algorithms and we show that it is an efficient algorithm implementing the modified SOVA in parallel.

• Journal of the Korean Data and Information Science Society
• /
• 제19권4호
• /
• pp.1219-1231
• /
• 2008

The main object of this paper is to develop a leave-one-out(LOO) bound of all pairwise comparison error correcting output codes (APC-ECOC). To avoid using classifiers whose corresponding target values are 0 in APC-ECOC and requiring pilot estimates we developed a bound based on mean misclassification probability(MMP). It can be used to tune kernel hyperparameters. Our empirical experiment using kernel mean squared estimate(KMSE) as the binary classifier indicates that the bound leads to good estimates of kernel hyperparameters.

• 대한전자공학회논문지TC
• /
• 제43권8호
• /
• pp.59-68
• /
• 2006

채널 부호의 균일 오율에 대한 연구는 부가성백색가우시안 채널에 대해 국한되어 연구되어 왔으며, 기하학적 균일성으로 불려왔다. 본 논문에서는 전송 채널과 수신기를 완전히 묘사해주는 확률밀도함수를 직접 다루어 균일 오율 특성을 다중 송수신안테나가 사용되는 시공간 부호로 확장한다. 또한 빠른 페이딩 채널에서 곱거리 스펙트럼를 고려한 기하학적 균일 시공간 부호 설계 과정을 보여준다. 균일 오율 특성으로 부호 검색의 복잡도가 현격히 감소하고, 이런 복잡도 감소는 높은 상태 수를 갖는 시공간 격사상 부호에 대해서도 최적의 부호 검색을 가능하게 한다. 모의 실험을 통해 새로 설계된 부호가 다른 알려진 부호들에 비해 빠른 페이딩 채널에서 더 좋은 성능을 가지는 것을 확인한다.

• 한국인터넷방송통신학회논문지
• /
• 제13권6호
• /
• pp.161-166
• /
• 2013

최근 정보기술 발달로 산업 전 분야에서 IT 융합이 보편적으로 이루어지고 있다. 특히 의료IT 융합분야는 사용자 서비스 측면에서 많은 변화를 보이고 있다. 본 논문에서는 사용자 서비스 측면에 하나의 사례로 기존 종이처방전을 모바일을 이용한 QR코드로 전송할 수 있는 환경을 제안하고자 한다. QR코드는 종이처방전의 출력에서 전달, 보관하는 과정상의 부담을 최소화할 수 있다. 또한 정보 표현을 다양하고 폭넓게 활용할 수 있으며, 정보 복원과 암호화가 가능하므로 개인 정보 노출 및 변조의 위험을 최소화할 수 있는 미디어로 간주된다. 따라서 QR코드의 기능을 의료분야에 유합함으로서 사용자의 편의는 물론 정보의 기밀성, 저장능력을 발휘할 것으로 기대한다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권4호
• /
• pp.1807-1823
• /
• 2016

Local Binary Pattern (LBP) and its variants have powerful discriminative capabilities but most of them just consider each LBP code independently. In this paper, we propose sub oriented histograms of LBP for smoke detection and image classification. We first extract LBP codes from an image, compute the gradient of LBP codes, and then calculate sub oriented histograms to capture spatial relations of LBP codes. Since an LBP code is just a label without any numerical meaning, we use Hamming distance to estimate the gradient of LBP codes instead of Euclidean distance. We propose to use two coordinates systems to compute two orientations, which are quantized into discrete bins. For each pair of the two discrete orientations, we generate a sub LBP code map from the original LBP code map, and compute sub oriented histograms for all sub LBP code maps. Finally, all the sub oriented histograms are concatenated together to form a robust feature vector, which is input into SVM for training and classifying. Experiments show that our approach not only has better performance than existing methods in smoke detection, but also has good performance in texture classification.

• Journal of Communications and Networks
• /
• 제5권3호
• /
• pp.187-196
• /
• 2003

We consider the use of error control coding in direct sequence-code-division multiple access (OS-COMA) systems that employ multiuser detection (MUO) and space diversity. The relative performance gain between Reed-Solomon (RS) code and convolutional code (CC) is well known in [1] for the single user, additive white Gaussian noise (AWGN) channel. In this case, RS codes outperform CC's at high signal-to-noise ratios. We find that this is not the case for the multiuser interference channel mentioned above. For useful error rates, we find that soft-decision CC's to be uniformly better than RS codes when used with DS-COMA modulation in multiuser space-time channels. In our development, we use the Gaussian approximation on the interference to determine performance error bounds for systems with low number of users. Then, we check their accuracy in error rate estimation via system's simulation. These performance bounds will in turn allow us to consider a large number of users where we can estimate the gain in user-capacity due to channel coding. Lastly, the use of turbo codes is considered where it is shown that they offer a coding gain of 2.5 dB relative to soft-decision CC.

• 한국산학기술학회논문지
• /
• 제5권1호
• /
• pp.69-72
• /
• 2004

상품 정보를 저장하기 위해 현재 널리 사용되고 있는 바코드에 비해, 칼라코드는 미관상 수려하고 더 많은 조합을 수용할 수 있기 때문에, 용도가 더 다양하다. 그러나, 실제 사용에 있어서 수집된 이미지에서의 칼라코드는 환경 또는 장비에 의해 색깔이 심하게 왜곡될 수 있다. 이 논문에서는 이러한 왜곡에 의한 영향을 줄이고, 미로 찾기에 사용되는 우선법(Right hand on wall) 알고리즘을 이용하여 효율적으로 칼라코드를 검출하는 방법을 제시한다. 이 논문에서 사용하는 칼라코드는 Hue 값과 Saturation값이 높은 색들을 사용하는 동심원형이며, 프리프로세싱에 의해 전체 이미지에서 칼라코드의 후보 영역을 검출한 견과 이미지에 우선법 알고리즘을 적용하여 각 후보 영역을 포함하는 최적 직각사각형의 좌표를 도출한다. 실험결과, 우선법을 적용하여 칼라코드 영역의 정확한 좌표를 도출할 수 있었다.

• Journal of Communications and Networks
• /
• 제9권3호
• /
• pp.265-273
• /
• 2007

This paper expands an analytical performance model of 802.11 to accurately estimate throughput and energy demand of 802.11-based wireless sensor network (WSN) when sensor nodes employ Reed-Solomon (RS) codes, one of block forward error correction (FEC) techniques. This model evaluates these two metrics as a function of the channel bit error rate (BER) and the RS symbol size. Since the basic recovery unit of RS codes is a symbol not a bit, the symbol size affects the WSN performance even if each packet carries the same amount of FEC check bits. The larger size is more effective to recover long-lasting error bursts although it increases the computational complexity of encoding and decoding RS codes. For applying the extended model to WSNs, this paper collects traffic traces from a WSN consisting of two TIP50CM sensor nodes and measures its energy consumption for processing RS codes. Based on traces, it approximates WSN channels with Gilbert models. The computational analyses confirm that the adoption of RS codes in 802.11 significantly improves its throughput and energy efficiency of WSNs with a high BER. They also predict that the choice of an appropriate RS symbol size causes a lot of difference in throughput and power waste over short-term durations while the symbol size rarely affects the long-term average of these metrics.

• Journal of Information Science Theory and Practice
• /
• 제11권3호
• /
• pp.43-57
• /
• 2023

Government codes are created and utilized to streamline and standardize government administrative procedures. They are generally employed in government information systems. Because they are included in open datasets of public data, users must be able to understand them. However, information that can be used to comprehend administrative code is lost during the process of releasing data in the government system, making it difficult for data consumers to grasp the code and limiting the connection or convergence of different datasets that use the same code.This study proposes a way to employ the administrative code produced by the Korean government as a standard in a public data environment on a regular basis. Because consumers of public data are barred from accessing government systems, a means of universal access to administrative code is required. An ontology model is used to represent the administrative code's data structure and meaning, and the full administrative code is built as a knowledge graph. The knowledge graph thus created is used to assess the accuracy and connection of administrative codes in public data. The method proposed in this study has the potential to increase the quality of coded information in public data as well as data connectivity.