• Wind and Structures
• /
• 제36권6호
• /
• pp.367-377
• /
• 2023

This study proposes a few-shot learning model for extrapolating the wind pressure of scaled experiments to full-scale measurements. The proposed ML model can use scaled experimental data and a few full-scale tests to accurately predict the remaining full-scale data points (for new specimens). This model focuses on extrapolating the prediction to different scales while existing approaches are not capable of accurately extrapolating from scaled data to full-scale data in the wind engineering domain. Also, the scaling issue observed in wind tunnel tests can be partially resolved via the proposed approach. The proposed model obtained a low mean-squared error and a high coefficient of determination for the mean and standard deviation wind pressure coefficients of the full-scale dataset. A parametric study is carried out to investigate the influence of the number of selected shots. This technique is the first of its kind as it is the first time an ML model has been used in the wind engineering field to deal with extrapolation in wind performance prediction. With the advantages of the few-shot learning model, physical wind tunnel experiments can be reduced to a great extent. The few-shot learning model yields a robust, efficient, and accurate alternative to extrapolating the prediction performance of structures from various model scales to full-scale.

• 품질경영학회지
• /
• 제34권2호
• /
• pp.129-135
• /
• 2006

In the advance of computer technology, it is possible to keep all the related informations for monitoring equipments in control and huge amount of real time manufacturing data in a data base. Thus, the statistical analysis of large data sets with hundreds of thousands observations and hundred of independent variables whose some of values are missing at many observations is needed even though it is a formidable computational task. A tree structured approach to classification is capable of screening important independent variables and their interactions. In a Six Sigma project handling large amount of manufacturing data, one of the goals is to screen vital few variables among trivial many variables. In this paper we have reviewed and summarized CART, C4.5 and CHAID algorithms and proposed a simple method of screening vital few variables by selecting common variables screened by all the three algorithms. Also how to develop a logistics regression model on a large data set is discussed and illustrated through a large finance data set collected by a credit bureau for th purpose of predicting the bankruptcy of the company.

• 전기전자학회논문지
• /
• 제27권4호
• /
• pp.537-547
• /
• 2023

퓨삿학습(few-shot learning)은 사전에 확보한 관련 지식과 소규모의 학습데이터를 이용하여 학습데이터의 부족으로 인한 어려움을 해결할 수 있는 가능성을 제시해주어 최근 많은 주목을 받고 있다. 본 논문에서는 퓨삿학습의 개념과 주요 접근방법을 빠르게 파악할 수 있도록 데이터 증강, 임베딩과 측도학습, 메타학습의 세 관점에서 최신연구동향을 설명한다. 또한 퓨샷학습을 적용하려는 연구자들에게 도움을 제공할 수 있도록 주요 벤치마크 데이터셋에 대하여 간략하게 소개하였다. 퓨삿학습은 이미지 분석과 자연어 처리 등 다양한 분야에서 활용되고 있으나, 본 논문은 이미지 처리를 위한 퓨삿학습의 접근법에 집중하였다.

• 한국멀티미디어학회논문지
• /
• 제25권1호
• /
• pp.52-60
• /
• 2022

Few-shot learning is a sub-area of machine learning problems, which aims to classify target images that only contain a few labeled samples for training. As a representative few-shot learning method, the Prototypical network has been received much attention due to its simplicity and promising results. However, the Prototypical network uses the sample mean of samples from the same class as the prototypes of that class, which easily results in learning uncharacteristic features in the low-data scenery. In this study, we propose to use local descriptors (i.e., patches along the channel within feature maps) from the same class to explicitly obtain more representative prototypes for Prototypical Network so that significant intra-class feature information can be maintained and thus improving the classification performance on few-shot learning tasks. Experimental results on various benchmark datasets including mini-ImageNet, CUB-200-2011, and tiered-ImageNet show that the proposed method can learn more discriminative intra-class features by the local descriptors and obtain more generic prototype representations under the few-shot setting.

• 한국전자파학회논문지
• /
• 제13권2호
• /
• pp.130-135
• /
• 2002

이 논문에서 는 부호 알고리듬(Sign Algorithm)의 수렴성능을 향상시킨 새로운 Equalizer 알고리듬을 소개하였다. 이것은 입력 데이터를 재활용하여 필터계수를 다중 갱신하는 Data-Recycling 방식을 곱셈 계산이 적은 Sign 알고리듬에 적용하였다. Sign 알고리듬은 계산량이 적고 구현이 간단한 장점을 가지나 느린 수렴속도의 한계를 가지고 있다. 제안한 알고리듬은 Sign 알고리듬의 계산량이 적은 장점과 Data-Recycling LMS 알고리듬의 단순성과 빠른 수렴속도를 가지는 장점을 결합한 구조의 알고리듬이다. 컴퓨터 시뮬레이션에서 제안된 적응 등화 알고리듬은 LMS 알고리듬보다 2배 빠른 수렴 속도를 나타내었으며, 근사한 수렴성능에 조건에서 Data-Recycling LMS와 비교할 때 반으로 줄어든 곱셈 계산량을 보였다.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• 스마트미디어저널
• /
• 제12권1호
• /
• pp.24-31
• /
• 2023

메타 학습(meta learning)이란 즉각적으로 아는 것과 모르는 것을 구별하는 메타 인지로 적은 양의 데이터로 스스로 학습하고, 학습한 정보와 알고리즘으로 새로운 문제에 적응하며 해결하는 학습 방식이다. 그 중, few-shot 학습 방법은 메타 학습 방법의 한 종류로 매우 적은 학습 데이터 (support set)으로도 질의 데이터(query set)를 올바르게 예측하도록 하는 학습 방법이다. 본 연구에서는 각 클래스의 mean-point vector로 생성한 프로토타입의 한계점인 높은 밀도값을 낮추면서 이상치(outlier)값을 극복하는 방법을 제안한다. 제안한 방법은 기존의 방법을 해결하기 위해, 딥러닝 모델에서 feature를 추출하고, 획득한 feature사이의 요소별로 중앙값 계산하여 프로토타입을 생성하는 방법을 사용한다. 그 후, 앞서 생성한 중앙값 프로토타입을 기반으로 few-shot 학습 방법에 사용한다. 제안한 방법의 정량적인 평가를 위해 필체 인식 데이터셋을 사용하여 기존의 방법과 비교하였다. 실험 결과를 통해 기존의 방법보다 향상된 성능을 내는 것을 확인할 수 있었다.

• 한국인터넷방송통신학회논문지
• /
• 제20권4호
• /
• pp.107-113
• /
• 2020

매우 많은 소프트웨어 결함 예측에 관한 연구들이 수행되어왔지만 대부분은 라벨 데이터를 훈련 데이터로 사용하는 감독형 모델들이었다. 언라벨 데이터만을 사용하는 비감독형 모델이나 언라벨 데이터와 매우 적은 라벨 데이터 정보를 함께 사용하는 세미감독형 모델에 관한 연구는 극소수에 불과하다. 본 논문은 Self-training 기법에 트리 알고리즘들을 사용하여 새로운 세미감독형 모델들을 제작하였다. 세미감독형 기법인 Self-training 모델에 트리 기법들을 사용하는 새로운 세미감독형 모델들을 제작하였다. 모델 평가 실험 결과 새롭게 제작한 트리 모델들이 기존 모델들보다 더 나은 성능을 보였으며, 특히 CollectiveWoods는 타 모델들에 비해 압도적으로 우월한 성능을 보였다. 또한 매우 적은 라벨 데이터 보유 상황에서도 매우 안정적인 성능을 보였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권12호
• /
• pp.5464-5484
• /
• 2016

Few samples face recognition has become a highly challenging task due to the limitation of available labeled samples. As two popular paradigms in face image representation, sparse component analysis is highly robust while parts-based paradigm is particularly flexible. In this paper, we propose a probabilistic generative model to incorporate the strengths of the two paradigms for face representation. This model finds a common spatial partition for given images and simultaneously learns a sparse component analysis model for each part of the partition. The two procedures are built into a probabilistic generative model. Then we derive the score function (i.e. feature mapping) from the generative score space. A similarity measure is defined over the derived score function for few samples face recognition. This model is driven by data and specifically good at representing face images. The derived generative score function and similarity measure encode information hidden in the data distribution. To validate the effectiveness of the proposed method, we perform few samples face recognition on two face datasets. The results show its advantages.

• 한국멀티미디어학회논문지
• /
• 제25권5호
• /
• pp.685-694
• /
• 2022

The goal of few-shot semantic segmentation is to build a network that quickly adapts to novel classes with extreme data shortage regimes. Most existing few-shot segmentation methods leverage single or multiple prototypes from extracted support features. Although there have been promising results for natural images, these methods are not directly applicable to the aerial image domain. A key factor in few-shot segmentation on aerial images is to effectively exploit information that is robust against extreme changes in background and object scales. In this paper, we propose a Mask-Guided Attention module to extract more comprehensive support features for few-shot segmentation in aerial images. Taking advantage of the support ground-truth masks, the area correlated to the foreground object is highlighted and enables the support encoder to extract comprehensive support features with contextual information. To facilitate reproducible studies of the task of few-shot semantic segmentation in aerial images, we further present the few-shot segmentation benchmark iSAID-, which is constructed from a large-scale iSAID dataset. Extensive experimental results including comparisons with the state-of-the-art methods and ablation studies demonstrate the effectiveness of the proposed method.