• 전자공학회논문지
• /
• 제50권4호
• /
• pp.182-188
• /
• 2013

본 논문에서는 정지하고 있는 배경에서 움직이는 목표물을 식별하기 위해 PDR(pulse doppler radar)을 이용하여 수집한 복소수 신호를 처리하는 복소수 SVM(support vector machine)을 제안한다. SVM은 패턴인식 분야에서 널리 이용되나 분류에 이용되는 특징이 대부분 실수 데이터이다. 제안된 복소수 SVM은 실수 데이터, 허수 데이터 정보와 실수부와 허수부 사이의 교차 정보를 모두 이용하여 이동하는 목표물의 분류를 수행한다. 복소수 SVM을 설계하기 위해 최적화 조건 적용 시 실수축과 허수축에 대한 슬랙변수를 고려하였고, 복소수 데이터에 대한 KKT(Karush-Kuhn-Tucker) 조건을 이용하였다. 또한 복소수 거리를 이용한 RBF(radial basis function)를 커널함수로 적용하였다. 제안된 복소수 SVM의 성능을 평가하기 위해 PDR 센서로 수집된 복소 데이터를 기존의 SVM과 복소수 SVM을 이용하여 분류한 결과 기존의 SVM에 비해 복소수 SVM의 식별결과가 개와 사람 각각 8%, 10% 향상되었다.

• 한국군사과학기술학회지
• /
• 제24권4호
• /
• pp.392-400
• /
• 2021

Unlike optical equipment, SAR(Synthetic Aperture Radar) has the advantage of obtaining images in all weather, and object detection in SAR images is an important issue. Generally, deep learning-based object detection was mainly performed in real-valued network using only amplitude of SAR image. Since the SAR image is complex data consist of amplitude and phase data, a complex-valued network is required. In this paper, a complex-valued ResNet network is proposed. SAR image object detection was performed by combining the ROI transformer detector specialized for aerial image detection and the proposed complex-valued ResNet. It was confirmed that higher accuracy was obtained in complex-valued network than in existing real-valued network.

• 대한임베디드공학회논문지
• /
• 제6권3호
• /
• pp.168-173
• /
• 2011

In this paper, an optical image hiding technique using real-valued decoding key is proposed. In the embedding process, a each zero-padded original image placed in a quadrants on an input plane is multiplied by a statistically independent random phase pattern and is Fourier transformed. An encoded image is obtained by taking the real-valued data from the Fourier transformed image. And then a phase-encoded pattern, used as a hidden image and a decoding key, is generated by the use of multiple phase wrapping from the encoded images. A transmitted image is made from the linear superposition of the weighted hidden images and a cover image. In reconstruction process, the mirror reconstructed images can be obtained at two quadrants by the inverse-Fourier transform of the product of the transmitted image and the decoding key. Computer simulation and optical experiment are demonstrated in order to confirm the proposed technique.

• Communications for Statistical Applications and Methods
• /
• 제21권6호
• /
• pp.471-486
• /
• 2014

This study introduces a new type of symbolic data, a candle chart-valued time series. We aggregate four stock indices (i.e., open, close, highest and lowest) as a one data point to summarize a huge amount of data. In other words, we consider a candle chart, which is constructed by open, close, highest and lowest stock indices, as a type of symbolic data for a long period. The proposed candle chart-valued time series effectively summarize and visualize a huge data set of stock indices to easily understand a change in stock indices. We also propose novel approaches for the candle chart-valued time series modeling based on a combination of two midpoints and two half ranges between the highest and the lowest indices, and between the open and the close indices. Furthermore, we propose three types of sum of square for estimation of the candle chart valued-time series model. The proposed methods take into account of information from not only ordinary data, but also from interval of object, and thus can effectively perform for time series modeling (e.g., forecasting future stock index). To evaluate the proposed methods, we describe real data analysis consisting of the stock market indices of five major Asian countries'. We can see thorough the results that the proposed approaches outperform for forecasting future stock indices compared with classical data analysis.

• Communications for Statistical Applications and Methods
• /
• 제27권1호
• /
• pp.149-161
• /
• 2020

In this paper we extend the functional principal component analysis for real-valued random functions to the case of Hilbert-space-valued functional random objects. For this, we introduce an autocovariance operator acting on the space of real-valued functions. We establish an eigendecomposition of the autocovariance operator and a Karuhnen-Loève expansion. We propose the estimators of the eigenfunctions and the functional principal component scores, and investigate the rates of convergence of the estimators to their targets. We detail the implementation of the methodology for the cases of compositional vectors and density functions, and illustrate the method by analyzing time-varying population composition data. We also discuss an extension of the methodology to multivariate cases and develop the corresponding theory.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제37권2호
• /
• pp.120-128
• /
• 2010

하이퍼네트워크는 하이퍼그래프의 일반화된 모델로 학습과정에 있어 진화적 개념을 도입한 확률 그래프 기반의 기계학습 알고리즘으로서 최근 들어 여러 다양한 분야에 응용되고 있다. 그러나 하이퍼네트워크 모델은 데이터와 모델을 구성하는 하이퍼에지 간의 동등비교를 기반으로 하는 학습과정의 특성상 데이터를 구성하는 인자들이 범주형인 경우에만 학습 및 모델링이 가능하고 실수 값으로 표현된 데이터를 학습하기 위해서는 이산화 등의 전처리가 선행되어야 한다는 한계점이 있다. 하지만 데이터 전처리에 있어 이산화 하는 과정은 필연적으로 정보손실이 발생할 수밖에 없기 때문에 이는 분류 예측 모델의 성능 저하를 유발하는 원인이 될 수 있다. 이러한 기존 하이퍼네트워크 모델의 한계점을 극복하기 위해 본 연구에서는 별도의 데이터 전처리 과정을 거치지 않고 실수 인자로 구성된 데이터의 패턴 학습이 가능한 개선된 하이퍼네트워크 모델을 제안한다. 여러 실험 결과를 통해 제안한 하이퍼네트워크 모델은 기존 하이퍼네트워크 모델에 비해 실수형 데이터에 대한 학습 및 분류 결과 성능이 향상되었을 뿐 아니라, 다른 여러기계학습 방법들에 비해서도 경쟁력 있는 성능이 나타남을 확인하였다.

• Communications for Statistical Applications and Methods
• /
• 제26권3호
• /
• pp.295-304
• /
• 2019

This article deals with threshold-asymmetric volatility models for over-dispersed and zero-inflated time series of count data. We introduce various threshold integer-valued autoregressive conditional heteroscedasticity (ARCH) models as incorporating over-dispersion and zero-inflation via conditional Poisson and negative binomial distributions. EM-algorithm is used to estimate parameters. The cholera data from Kolkata in India from 2006 to 2011 is analyzed as a real application. In order to construct the threshold-variable, both local constant mean which is time-varying and grand mean are adopted. It is noted via a data application that threshold model as an asymmetric version is useful in modelling count time series volatility.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제49권12호
• /
• pp.667-674
• /
• 2000

In this paper, a modified real-valued genetic algorithm is developed by using the meiosis for human's chromosome. Unlike common crossover methods adapted in the conventional genetic algorithms, our suggested modified real-valued genetic algorithm makes gametes by conducting the meiosis for individuals composed of chromosomes, and then generates a new individual through crossovers among those. Ultimately, when appling it for the gas data of Box-Jenkin, model and parameter identifications can be concurrently done to construct the optimal model of a neural network in terms of minimizing with the structure and the error.

• 응용통계연구
• /
• 제32권6호
• /
• pp.879-887
• /
• 2019

본 연구에서는 이표본 구간 자료의 확률적 순서 검정 절차를 제안한다. 제안하는 검정 통계량은 U-통계량에 해당하며 본 연구에서는 이에 대한 점근적 분포를 귀무 가설 하에서 유도하였다. 실제 자료와 모의 실험을 통해 새로 제안한 방법의 성능을 단측 이변량 Kolmogorov-Smirnov 검정법과 비교한다.

• 대한산업공학회지
• /
• 제27권4호
• /
• pp.394-405
• /
• 2001

Since most real-world application data involve continuous-valued attributes, properly addressing the discretization process for constructing a decision tree is an important problem. A continuous-valued attribute is typically discretized during decision tree generation by partitioning its range into two intervals recursively. In this paper, by removing the restriction to the binary discretization, we present a hybrid multi-interval discretization algorithm for discretizing the range of continuous-valued attribute into multiple intervals. On the basis of experiment using semiconductor etching machine, it has been verified that our discretization algorithm constructs a more efficient incremental decision tree compared to previously proposed discretization algorithms.