• 한국멀티미디어학회논문지
• /
• 제21권2호
• /
• pp.98-107
• /
• 2018

In this paper, we propose a method to classify the skeletal maturity with a small amount of hand wrist X-ray image using deep learning-based meta-learning. General deep-learning techniques require large amounts of data, but in many cases, these data sets are not available for practical application. Lack of learning data is usually solved through transfer learning using pre-trained models with large data sets. However, transfer learning performance may be degraded due to over fitting for unknown new task with small data, which results in poor generalization capability. In addition, medical images require high cost resources such as a professional manpower and mcuh time to obtain labeled data. Therefore, in this paper, we use meta-learning that can classify using only a small amount of new data by pre-trained models trained with various learning tasks. First, we train the meta-model by using a separate data set composed of various learning tasks. The network learns to classify the bone maturity using the bone maturity data composed of the radiographs of the wrist. Then, we compare the results of the classification using the conventional learning algorithm with the results of the meta learning by the same number of learning data sets.

• Communications for Statistical Applications and Methods
• /
• 제30권2호
• /
• pp.215-226
• /
• 2023

Deep learning has made great strides in the field of unstructured data such as text, images, and audio. However, in the case of tabular data analysis, machine learning algorithms such as ensemble methods are still better than deep learning. To keep up with the performance of machine learning algorithms with good predictive power, several deep learning methods for tabular data have been proposed recently. In this paper, we review the latest deep learning models for tabular data and compare the performances of these models using several datasets. In addition, we also compare the latest boosting methods to these deep learning methods and suggest the guidelines to the users, who analyze tabular datasets. In regression, machine learning methods are better than deep learning methods. But for the classification problems, deep learning methods perform better than the machine learning methods in some cases.

• 디지털융복합연구
• /
• 제16권10호
• /
• pp.205-212
• /
• 2018

고성능 CPU/GPU의 개발과 심층신경망 등의 인공지능 알고리즘, 그리고 다량의 데이터 확보를 통해 기계학습이 다양한 응용 분야로 확대 적용되고 있다. 특히, 사물인터넷, 사회관계망서비스, 웹페이지, 공공데이터로부터 수집된 다량의 데이터들이 기계학습의 활용에 가속화를 가하고 있다. 기계학습을 위한 학습 데이터세트는 응용 분야와 데이터 종류에 따라 다양한 형식으로 존재하고 있어 효과적으로 데이터를 처리하고 기계학습에 적용하기에 어려움이 따른다. 이에 본 논문은 표준화된 절차에 따라 기계학습을 위한 학습 데이터세트를 구축하기 위한 방안을 연구하였다. 먼저 학습 데이터세트가 갖추어야할 요구사항을 문제 유형과 데이터 유형별로 분석하였다. 이를 토대로 기계학습 활용을 위한 학습 데이터세트 구축에 관한 참조모델을 제안하였다. 또한 학습 데이터세트 구축 참조모델을 국제 표준으로 개발하기 위해 대상 표준화 기구의 선정 및 표준화 전략을 제시하였다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제5권9호
• /
• pp.411-418
• /
• 2016

교수-학습 지원 시스템에서 교수자와 학습자의 참여 활동 데이터를 활용하여 성공적으로 과정을 이수할 수 있도록 지원하기 위해 학습 분석이 활용되고 있다. 즉, 학습 분석은 학습자의 학습활동을 이해하기 위한 방법이다. 교수-학습 활동 데이터를 보다 유용하게 활용하기 위해서는 데이터 모델이 필요하다. 이에 본 연구에서는 사용자 중심의 학습양식과 학습객체 데이터모델(LSLODM)을 제안한다. 이는 사용자, 학습양식, 학습객체, 학습활동을 결합하여 표현한 것이다. LSLODM은 이를 기반으로 교수-학습 데이터를 수집하고, 교수-학습 활동 요소의 속성들을 최근성, 빈도성, 지속성을 정량적으로 파악할 수 있도록 한 것이다. 즉, 단위 과목에서 학습자의 교수-학습 활동을 분석할 수 있는 토대를 마련한 것이다.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.233-244
• /
• 2023

Although artificial intelligence and machine learning technologies have been used in various fields, problems with personal information protection have arisen based on centralized data collection and processing. Federated learning has been proposed to solve this problem. Federated learning is a process in which clients who own data in a distributed data environment learn a model using their own data and collectively create an artificial intelligence model by centrally collecting learning results. Unlike the centralized method, Federated learning has the advantage of not having to send the client's data to the central server. In this paper, we quantitatively present the performance improvement when federated learning is applied using the building change detection learning data. As a result, it has been confirmed that the performance when federated learning was applied was about 29% higher on average than the performance when it was not applied. As a future work, we plan to propose a method that can effectively reduce the number of federated learning rounds to improve the convergence time of federated learning.

• International Journal of Advanced Culture Technology
• /
• 제6권2호
• /
• pp.123-128
• /
• 2018

Learning data is composed of 100 characters with 10 different fonts, and test data is composed of 10 characters with a new font that is not used for the learning data. In order to consider the variety of learning data with several different fonts, 10 learning masks are constructed by accumulating pixel values of same characters with 10 different fonts. This process eliminates minute difference of characters with different fonts. After finding maximum values of learning masks, test data is expanded by multiplying these maximum values to the test data. The algorithm calculates sum of differences of two corresponding pixel values of the expanded test data and the learning masks. The learning mask with the smallest value among these 10 calculated sums is selected as the result of the recognition process for the test data. The proposed algorithm can recognize various types of fonts, and the learning data can be modified easily by adding a new font. Also, the recognition process is easy to understand, and the algorithm makes satisfactory results for character recognition.

• Investigative Magnetic Resonance Imaging
• /
• 제25권1호
• /
• pp.10-22
• /
• 2021

Purpose: To overcome the difficulty in building a large data set with a high-quality in medical imaging, a concept of 'blended-transfer learning' (BTL) using a combination of both source data and target data is proposed for the target task. Materials and Methods: Source and target tasks were defined as training of the source and target networks to reconstruct cardiac CINE images from undersampled data, respectively. In transfer learning (TL), the entire neural network (NN) or some parts of the NN after conducting a source task using an open data set was adopted in the target network as the initial network to improve the learning speed and the performance of the target task. Using BTL, an NN effectively learned the target data while preserving knowledge from the source data to the maximum extent possible. The ratio of the source data to the target data was reduced stepwise from 1 in the initial stage to 0 in the final stage. Results: NN that performed BTL showed an improved performance compared to those that performed TL or standalone learning (SL). Generalization of NN was also better achieved. The learning curve was evaluated using normalized mean square error (NMSE) of reconstructed images for both target data and source data. BTL reduced the learning time by 1.25 to 100 times and provided better image quality. Its NMSE was 3% to 8% lower than with SL. Conclusion: The NN that performed the proposed BTL showed the best performance in terms of learning speed and learning curve. It also showed the highest reconstructed-image quality with the lowest NMSE for the test data set. Thus, BTL is an effective way of learning for NNs in the medical-imaging domain where both quality and quantity of data are always limited.

• 반도체디스플레이기술학회지
• /
• 제19권4호
• /
• pp.121-125
• /
• 2020

With miniaturization of semiconductor, the manufacturing process become more complex, and undetected small changes in the state of the equipment have unexpectedly changed the process results. Fault detection classification (FDC) system that conducts more active data analysis is feasible to achieve more precise manufacturing process control with advanced machine learning method. However, applying machine learning, especially in supervised learning criteria, requires an arduous data labeling process for the construction of machine learning data. In this paper, we propose a semi-supervised learning to minimize the data labeling work for the data preprocessing. We employed equipment status variable identification (SVID) data and optical emission spectroscopy data (OES) in silicon etch with SF6/O2/Ar gas mixture, and the result shows as high as 95.2% of labeling accuracy with the suggested semi-supervised learning algorithm.

• 정보교육학회논문지
• /
• 제21권4호
• /
• pp.393-401
• /
• 2017

본 연구의 목적은 학습자의 데이터 분석적 사고력 향상을 위한 딥러닝 기반 학습 시스템 개발 연구이다. 연구의 내용은 다음과 같다. 첫째, 데이터 분석적 사고력 향상을 위해 발견학습 모형에 딥러닝 기법을 적용하였다. 이는 데이터의 관계를 나타내주는 모델을 딥러닝 기법을 사용하여 생성하고, 새로운 데이터를 이 모델에 적용하여 데이터를 분석하는 과정을 경험할 수 있는 학습 방법이다. 둘째, 이 학습 방법에 따른 수업을 위한 딥러닝 기반 학습 시스템을 개발하였다. 딥러닝 기법을 사용하여 학습자가 입력한 데이터의 모델을 생성하고 적용할 수 있는 시스템을 개발하였다. 딥러닝을 적용한 발견학습 및 시스템 설계 연구는 데이터의 중요성이 더욱 커지는 미래 사회에서 학습자의 데이터 분석적 사고력을 향상시킬 수 있는 새로운 접근이 될 것으로 기대한다.

• Educational Technology International
• /
• 제17권2호
• /
• pp.175-202
• /
• 2016

Most of the learning analytics research has investigated how quantitative data can affect learning. The information that is provided to learners has been determined by teachers and researchers based on reviews of the previous literature. However, there have been few studies on standard learning activities that are performed in e-learning environments independent of the teaching methods or on learning behavior data that are obtained through learning analytics. This study aims to explore the general learning activities and learning behaviors that can be used in the analysis of learning data. Learning activities and learning behavior are defined in conjunction with the concept of learning analytics to identify the differences between teachers' and learners' learning activities. Learning activities and learning behavior were verified by an expert panel review in an e-learning environment. The differences between instructors and learners in their usage were analyzed using a survey method. As results, 8 learning activities and 29 learning behaviors were validated. The Research has shown that instructors' degree of utilization is higher than that of the learners.