• 응용통계연구
• /
• 제37권2호
• /
• pp.239-253
• /
• 2024

본 연구는 learning-to-rank (LTR) 기법 중 point-wise와 pair-wise learning을 적용하여 서울 경마경기 순위 예측을 수행하였다. Point-wise learning으로는 선형 회귀와 랜덤 포레스트를 pair-wise learning으로는 RankNet, LambdaMART (XGBoost Ranker, LightGBM Ranker, CatBoost Ranker)을 활용하였다. 또한 데이터 불균형 문제를 해결하기 위해 전처리 과정에서 경주기록을 경주거리에 따라 표준화하는 방식을 채택하였으며, 모형의 예측 능력 향상을 위해 경기 정보, 기수 정보, 마필 정보, 조교사 정보 등의 다양한 데이터를 사용하였다. 그 결과 아이템 간의 순위관계를 학습할 수 있는 pair-wise learning이 point-wise learning보다 전반적으로 더 뛰어난 예측력을 보이는 것을 확인하였다. 특히 CatBoost Ranker는 제시된 모형들 중 가장 뛰어난 예측 성능을 보였다. 마지막으로 섀플리 값을 통해 CatBoost Ranker에서 경주마의 성적, 직전 경주기록, 경주마의 출발훈련 횟수, 누적 출발훈련 횟수, 질병 진단횟수 등이 상위 10개 중요 변수에 포함된 것을 확인하였다.

• 천문학논총
• /
• 제27권4호
• /
• pp.367-373
• /
• 2012

The first all-sky mid-/far-infrared survey by IRAS in the 1980s, has been followed by only two more, by AKARI, from 2006, and WISE in 2010. I discuss some features of the WISE survey, and highlight some key results from early extragalactic observations that have been made by the science team during the operation of the telescope, and the post-operation proprietary period during which the public release data products were being generated. The efficient survey strategy and very high-data rate from WISE produced a catalogue of 530 million objects that was released to the public in March 2012. The WISE survey strategy naturally provided the deepest coverage at the ecliptic poles, where matched comparison fields were obtained using Spitzer, and where AKARI also observed deep fields. I describe some of the follow-up work that has been carried out based on the WISE survey, and the prospects for enhancing the WISE data by combining the AKARI survey results are also discussed. While the all-sky AKARI survey is less deep than the WISE catalogue, and is still being worked on by the AKARI science team, it includes a larger number of bands, extends to longer wavelengths, and in particular has very complementary band passes to WISE in the mid-infrared waveband, which will provide enhanced spectral information for relatively bright targets.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제40권2호
• /
• pp.179-194
• /
• 2001

The seventh curriculum put into operation gradually from first-year student in 2000 academic years of elementary school is subject to form and apply a step-wise level curriculum. Mathematics(correspond to junior high school course from 7th school year to 9th school year) should apply a step-wise level curriculum from 7th school year in 2001 academic years. Accordingly, mathematics teachers must diagnose actual conditions of educations, distribution tables of test results, step-wise teaching-studying programs etc. They also make proper plans suitable for actual situations of each school, prepare appropriate teaching materials and aids. I investigated preceding studies planned for preparation of putting into operation of a step-wise level curriculum. It showed that most of the studies were conducted at schools of medium or large scale and studies conducted at schools of small scale was rare. There were 113 small scale middle schools out of total 297 middle schools in Kyongsangbuk-do area in 2000. In this situation, I felt necessities of modeling of a step-wise level curriculum suitable for small scale schools. In this study, I modeled a step-wise level curriculum suitable for small scale middle schools, applied this model to 44 students in M middle school. I modeled two types of curriculum. One is a step-wise level curriculum that execute special supplementation process to students who do not complete 7-가 step successfully. The other is a step-wise level curriculum which is a regular model for a step-wise level of 7-나 step. I carried out an academic achievement test and intimacy test about mathematics before and after the application of the model. In this study, I found out that this model was very effective in academic achievement of students and helpful to declined students in scholarship. In the intimacy test, It was found out that most of the students gained confidence in mathematics, felt less anxiety, formed positive self consciousness. Therefore, I think that this model will be helpful to the application of the seventh step-wise level curriculum.

• 한국통신학회논문지
• /
• 제34권6C호
• /
• pp.571-577
• /
• 2009

본 논문에서는, LDPC 부호를 위한 node-wise VCRBP의 개선된 기법인, 강제수렴 node-wise VCRBP와 부호기반 node-wise VCRBP를 제안한다. 두 가지 기법 모두 node-wise VCRBP에 비하여 매우 적은 오류 정정 성능 열화만으로 복호 복잡도와 대기시간을 현저하게 줄인다.

• 대한수학회보
• /
• 제54권4호
• /
• pp.1095-1110
• /
• 2017

The t-wise intersection is a useful property of a linear code due to its many applications. Recently, the second author determined the t-wise intersection of a relative two-weight code. By using this result and generalizing the finite projective geometry method, we will present the t-wise intersection of a relative three-weight code and its applications in this paper.

• 대한수학회지
• /
• 제60권5호
• /
• pp.987-998
• /
• 2023

It is shown that every continuum-wise expansive C¹ generic vector field X on a compact connected smooth manifold M satisfies Axiom A and has no cycles, and every continuum-wise expansive homoclinic class of a C¹ generic vector field X on a compact connected smooth manifold M is hyperbolic. Moreover, every continuum-wise expansive C¹ generic divergence-free vector field X on a compact connected smooth manifold M is Anosov.

• 대한수학회논문집
• /
• 제12권3호
• /
• pp.769-778
• /
• 1997

In this paper, we obtain a strong law of large number for sums of level-wise independent and level-wise identically distributed fuzzy random variables.

• 제어로봇시스템학회논문지
• /
• 제12권7호
• /
• pp.706-712
• /
• 2006

Recursive Partial Least Squares(RPLS) method has been used for processing the on-line available multivariate chemical process data and modeling adaptive prediction model for process changes. However, RPLS method is unstable in PLS model updating because RPLS method updates PLS model by merging past PLS model and new data. In this study, Adaptive Predictive Partial Least Squres(APPLS) method is suggested for more sensitive adaptation to process changes. By expanding APPLS method, block-wise Adaptive Predictive Partial Least Squares(block-wise APPLS) method is suggested for a lager scale data of chemical processes. APPLS method has been applied to predict the reactor properties and the product quality of a direct esterification reactor for polyethylene terephthalate(PTT), and block-wise APPLS method has been applied to predict the cetane number using NIR Diesel Spectra data. APPLS and block-wise APPLS methods show better prediction and updating performance than RPLS method.

• 대한임베디드공학회논문지
• /
• 제15권2호
• /
• pp.43-49
• /
• 2020

In this paper, we propose a stage-wise knowledge transfer method that uses block-wise retraining to transfer the useful knowledge of a pre-trained residual network (ResNet) in a teacher-student framework (TSF). First, multiple hint information transfer and block-wise supervised retraining of the information was alternatively performed between teacher and student ResNet models. Next, Softened output information-based knowledge transfer was additionally considered in the TSF. The results experimentally showed that the proposed method using multiple hint-based bottom-up knowledge transfer coupled with incremental block-wise retraining provided the improved student ResNet with higher accuracy than existing KD and hint-based knowledge transfer methods considered in this study.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2021년도 추계학술대회
• /
• pp.154-156
• /
• 2021

Depth-wise separable convolution 은 컴퓨터 자원이 제한된 환경에서 기존의 standard convolution을 대체하는데 강력하고, 효과적인 대안으로 잘 알려져 있다.[1] MobileNetV2 에서는 Inverted residual block을 소개한다. 이는 depth-wise separable convolution으로 인해 생기는 손실, 즉 channel 간의 데이터를 조합해 새로운 feature를 만들어낼 기회를 잃어버릴 때, 이를 depth-wise separable convolution 양단에 point-wise convolution(1×1 convolution)을 사용함으로써 극복해낸 block이다.[1] 하지만 1×1 convolution은 채널 수에 의존적(dependent)인 특징을 갖고 있고, 따라서 결국 네트워크가 깊어지면 깊어질수록 효율적이고(efficient) 가벼운(light weight) 네트워크를 만드는데 병목 현상(bottleneck)을 일으키고 만다. 이 논문에서는 channel-wise squeeze and excitation block(CSE)을 통해 1×1 convolution을 부분적으로 대체하는 방법을 통해 이 병목 현상을 해결한다.