• Journal of the Korean Statistical Society
• /
• 제36권1호
• /
• pp.149-156
• /
• 2007

This study suggests a new method for testing seasonal unit roots in a momentum threshold autoregressive (MTAR) process. This sign test is robust against heteroscedastic or heavy tailed errors and is invariant to monotone data transformation. The proposed test is a seasonal extension of the sign test of Park and Shin (2006). In the case of partial seasonal unit root in an MTAR model, a Monte-Carlo study shows that the proposed test has better power than the seasonal sign test developed for AR model.

• Journal of the Korean Statistical Society
• /
• 제33권2호
• /
• pp.149-157
• /
• 2004

The stationarity is one of the most important properties of a time series. We propose robust sign tests for seasonal autoregressive processes to determine whether or not a time series is stationary. The proposed tests are robust to the outliers and the heteroscedastic errors, and they have an exact binomial null distribution regardless of the period of seasonality and types of median adjustments. A Monte-Carlo simulation shows that the sign test is locally more powerful than the tests based on ordinary least squares estimator (OLSE) for heavy-tailed and/or heteroscedastic error distributions.

• 한국통계학회:학술대회논문집
• /
• 한국통계학회 2003년도 춘계 학술발표회 논문집
• /
• pp.281-286
• /
• 2003

The stationarity is one of the most important properties of a time series. We propose robust sign tests for seasonal autoregressive process to determine whether or not a time series is stationary. The tests have an exact binomial null distribution and are robust to the outliers and the heteroscedastic errors. Monte-Carlo simulation shows that the sign test is locally more powerful than the OLSE-based tests for heavy-tailed and/or heteroscedastic error distributions.

• Communications for Statistical Applications and Methods
• /
• 제19권1호
• /
• pp.177-182
• /
• 2012

A structural break in the level as well as in the innovation variance has often been exhibited in economic time series. In this paper we propose robust unit root tests based on a sign-type test statistic when a time series has a shift in its level and the corresponding volatility. The proposed tests are robust to a wide class of partially stationary processes with heavy-tailed errors, and have an exact binomial null distribution. Our tests are not affected by the size or location of the break. We set the structural break under the null and the alternative hypotheses to relieve a possible vagueness in interpreting test results in empirical work. The null hypothesis implies a unit root process with level shifts and the alternative connotes a stationary process with level shifts. The Monte Carlo simulation shows that our tests have stable size than the OLSE based tests.

• 방송공학회논문지
• /
• 제21권4호
• /
• pp.562-568
• /
• 2016

본 논문에서는 다양한 교통 표지판 중에서 운전자의 안전운행에 밀접하게 관계가 있는 속도 표지판을 인식하는 연구에 초점을 맞추고 있다. HOG (histogram of gradient)와 LBP (local binary patterns) 가 객체 인식을 위한 대표적 특징이지만, 이러한 특징들은 패턴을 생성할 때 목표 객체의 회전을 고려하지 않음으로써 객체의 회전에 약한 특성을 가지고 있다. 따라서 본 논문에서는 회전에 강인한 이진 패턴을 생성하기 위해 FRIBP (fast rotation-invariant binary patterns)를 제안하고 있다. 본 논문에서 제안하는 FRIBP 알고리즘은 히스토그램에서 불필요한 레이어를 삭제하고 비교연산과 시프트 연산을 제거하여 빠르게 원하는 특징을 추출할 수 있도록 설계되었다. 제안된 FRIBP 알고리즘은 GTSRB (German Traffic Sign Recognition Benchmark) 데이터에 적용되어, 다른 비교 알고리즘과 유사한 성능을 보여주었다. 또한, 12,630개의 테스트 데이터에 대해 기존의 방법들보다 약 0.47초가 향상된 인식 속도를 보여주었다.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2010년도 춘계학술발표대회
• /
• pp.377-380
• /
• 2010

This paper proposes texture descriptor for texture classification called Local Neighbor Differences (LND). LND is a high discriminating texture descriptor and also robust to illumination changes. The proposed descriptor utilizes the sign of differences between surrounding pixels in a local neighborhood. The differences of those pixels are thresholded to form an 8-bit binary codeword. The decimal values of these 8-bit code words are computed and they are called LND values. A histogram of the resulting LND values is created and used as feature to describe the texture information of an image. Experimental results, with respect to texture classification accuracies using OUTEX_TC_00001 test suite has been performed. The results show that LND outperforms LBP method, with average classification accuracies of 92.3% whereas that of local binary patterns (LBP) is 90.7%.