http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Large-Signal Robustness of the Chair-Varshney Fusion Rule Under Generalized-Gaussian Noises
Park, J,Eunchan Kim,Kiseon Kim IEEE 2010 IEEE SENSORS JOURNAL Vol.10 No.9
<P>The Chair-Varshney rule (CVR) has been used to provide a large signal-to-noise ratio (SNR) approximation of the optimal fusion rule under Gaussian noise. For more practical use in sensor networks, this paper extends CVR to Generalized-Gaussian noise channels, along with verification of the suboptimality and robustness of CVR under the Generalized-Gaussian channel noise through the use of Monte Carlo simulations.</P>
돌출영역 분할을 위한 대립과정이론 기반의 인공시각집중모델
정기선(Kiseon Jeong),홍창표(Changpyo Hong),박동선(Dong Sun Park) 대한전자공학회 2014 전자공학회논문지 Vol.51 No.7
본 논문에서는 자연영상에 대한 돌출영역을 자동으로 검출하고 이를 분할하기 위한 새로운 인공시각집중모델을 제안한다. 제안된 모델은 인간의 생물학적 시각인지 기반이며 주된 특징은 다음과 같다. 먼저 영상의 강도특징과 색상특징을 사용하는 대립과정이론 기반의 새로운 인공시각집중모델의 구조를 제안하고, 돌출영역을 인지하기 위해 영상의 강도 및 색상 특징채널의 정보량을 고려하는 엔트로피 필터를 설계하였다. 엔트로피 필터는 높은 정확도와 정밀도로 돌출영역에 대해 검출 및 분할이 가능하다. 마지막으로 최종 돌출지도를 효율적으로 구성하기 위한 적응 조합 방법 또한 제안되었다. 이 방법은 각 인지 모델로부터 검출된 강도 및 색상 가시성지도에 대하여 평가하며 평가된 점수로부터 얻어진 가중치를 이용해 가시성 지도들을 조합한다. 돌출지도에 대해 ROC분석을 이용한 AUC를 측정한 결과 기존 최신의 모델들은 평균 0.7824의 성능을 나타낸 반면 제안된 모델의 AUC는 0.9256으로서 약 15%의 성능 개선을 보였다. 또한 돌출영역 분할에 대해 F-beta를 측정한 결과 기존 최신의 모델은 0.5718이고 제안된 모델은 0.7325로서 분할 성능 또한 약 22%의 성능 개선을 보였다. We propose an novel artificial visual attention model that is capable of automatic detection and segmentation of saliency region on natural images in this paper. The proposed model is based on human visual perceptions in biological vision and contains there are main contributions. Firstly, we propose a novel framework of artificial visual attention model based on the opponent process theory using intensity and color features, and an entropy filter is designed to perceive salient regions considering the amount of information from intensity and color feature channels. The entropy filter is able to detect and segment salient regions in high segmentation accuracy and precision. Lastly, we also propose an adaptive combination method to generate a final saliency map. This method estimates scores about intensity and color conspicuous maps from each perception model and combines the conspicuous maps with weight derived from scores. In evaluation of saliency map by ROC analysis, the AUC of proposed model as 0.9256 approximately improved 15% whereas the AUC of previous state-of-the-art models as 0.7824. And in evaluation of salient region segmentation, the F-beta of proposed model as 0.7325 approximately improved 22% whereas the F-beta of previous state-of-the-art models.
Maximin Distributed Detection in the Presence of Impulsive Alpha-Stable Noise
Jintae Park,Shevlyakov, G.,Kiseon Kim IEEE 2011 IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS Vol.10 No.6
<P>The distributed detection problem in wireless sensor networks is studied under the impulsive α-stable noise assumption. Since symmetric α-stable density does not have a closed form, its approximation, the bi-parameter Cauchy Gaussian mixture model, is used to describe the impulsive behavior of α-stable noises. With this model, we propose a low-complexity robust fusion rule by taking the maximin setting with respect to the detection probability. An explicit formula for the detection probability is derived. Robustness of the proposed maximin fusion rule is justified by numerical and simulation results for α-stable noises.</P>
Robust Distributed Detection with Total Power Constraint in Large Wireless Sensor Networks
Jintae Park,Shevlyakov, G.,Kiseon Kim IEEE 2011 IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS Vol.10 No.7
<P>In practical problems of signal detection, it is quite common that the underlying noise distribution is not Gaussian and may vary in a wide range from light- to heavy-tailed forms. To design a robust fusion rule for distributed detection in wireless sensor networks, an asymptotic maximin approach is used by introducing weak signals in the canonical parallel fusion model. Explicit formulas for the detection and false alarm probabilities are derived. The analytic results are written out for the classes of nondegenerate, with a bounded variance and contaminated Gaussian noise distributions. Numerical and simulation results are obtained to justify robustness and asymptotic characteristics of the proposed fusion rule.</P>
Distributed Detection and Fusion of Weak Signals in Fading Channels with Non-Gaussian Noises
Jintae Park,Shevlyakov, G.,Kiseon Kim IEEE 2012 IEEE COMMUNICATIONS LETTERS Vol.16 No.2
<P>Distributed detection and information fusion have received recent research interest due to the success of emerging wireless sensor network (WSN) technologies. For the problem of distributed detection in WSNs under energy constraints, a weak signal model in the canonical parallel fusion scheme with additive non-Gaussian noises and fading channels is considered. To solve this problem in the Neyman-Pearson setting, a unified asymptotic fusion rule generalizing the maximum ratio combiner (MRC) fusion rule is proposed. Explicit formulas for the threshold and detection probability applicable for wide classes of fading channels and noise distributions are written out. Both asymptotic analysis and Monte Carlo modeling are used to examine the performance of the proposed detection fusion rule.</P>
자동차 응용분야를 위한 물리계층의 특성을 고려한 CAN 프로토콜 진단 장비의 구현에 관한 연구
이기선(Kiseon Lee),이태연(Taeyeon Lee),박재홍(Jaehong Park) 한국자동차공학회 2006 한국자동차공학회 Symposium Vol.- No.-
This paper introduces an implementation of a Controller Area Network (CAN) protocol analyzer including physical layer characteristics for an automotive application. CAN protocol analyzer is used to investigate plausibility of an internal network bus of an automobile. However, commercial CAN protocol analyzers tend to concentrate only on higher logical layer rather than physical layer which can not be neglected because many faults have been found to make troubles in physical aspects. This study analyzes requirements and designs an implementation of a CAN protocol analyzer for an automotive application. This analyzer can investigate not only messages and frames in logical layer but also signals in physical layer. It is implemented with a CAN controller and high speed ADC for logical and physical layers respectively. The experiment with an automotive CAN bus system with 100Kbps speed controlling 60 body electrical loads in a real passenger car is shown to validate feasibility of the implemented analyzer.