• 한국게임학회 논문지
• /
• 제17권4호
• /
• pp.109-116
• /
• 2017

보드게임은 많은 수의 말들과 상태공간을 갖고 있다. 그러므로 게임은 학습을 오래하여야 한다. 그러나 강화학습은 학습초기에 학습속도가 느려지는 단점이 있다. 그러므로 학습 도중에 동일한 최선 값이 있을 때, 영향력분포도를 고려한 문제 영역 지식을 활용한 휴리스틱을 사용해 학습의 속도 향상을 시도하였다. 기존 구현된 말과 개선 구현된 말을 비교하기 위해 보드게임을 제작하였다. 그래서 일방공격형 말과 승부를 하게 하였다. 실험 결과 개선 구현된 말의 성능이 학습속도 측면에서 향상됨을 알 수 있었다.

• 대한간호학회지
• /
• 제36권6호
• /
• pp.942-949
• /
• 2006

Purpose: This study was to investigate the knowledge and learning needs of chemotherapy in gynecological cancer patients. Method: The subjects consisted of 103 gynecological cancer patients receiving chemotherapy from April 2005 to August 2005. Data was collected using a questionnaire about knowledge and learning needs of chemotherapy. The data was analyzed by t-test, ANOVA, Scheffe test, and Pearson's correlation coefficient using SAS. Result: Average scores of knowledge and learning needs of general treatment and care were 2.74, and 3.30 respectively. Average score of knowledge and learning needs of chemotherapy were 2.54 and 3.23 respectively. Learning needs of general treatment and care and of chemotherapy were significantly different in relation to marital status, educational level, family support, the operation, and the amount of chemotherapy received. Items with the highest level of learning needs were the symptoms of recurring illness of general treatment, and minimizing side effects of chemotherapy. There were a negative correlation between knowledge and learning needs on general treatment and a positive correlation between knowledge and learning needs on chemothearpy but there were not significant statistically. Conclusion: The level of learning needs related to cancer treatment was high, whereas, that of knowledge was low. Therefore, when designing an educational program for gynecological cancer patients, understanding of learning needs is necessary. Also, consideration of a patient's characteristics, and a systematic and detailed educational program should be provided.

• 제어로봇시스템학회논문지
• /
• 제21권6호
• /
• pp.565-570
• /
• 2015

Supervised machine learning has become popular in discovering context descriptions from sensor data. However, collecting a large amount of labeled training data in order to guarantee good performance requires a great deal of expense and time. For this reason, semi-supervised learning has recently been developed due to its superior performance despite using only a small number of labeled data. In the existing semi-supervised learning algorithms, unlabeled data are used to build a graph Laplacian in order to represent an intrinsic data geometry. In this paper, we represent the unlabeled data as the spatial-temporal dataset by considering smoothly moving objects over time and space. The developed algorithm is evaluated for position estimation of a smartphone-based robot. In comparison with other state-of-art semi-supervised learning, our algorithm performs more accurate location estimates.

• 한국멀티미디어학회논문지
• /
• 제24권11호
• /
• pp.1508-1517
• /
• 2021

In CCTV environments, a lot of learning image data is required to monitor illegal dumping of garbage with a typical image-based object detection using deep learning method. In this paper, we propose a system to monitor unauthorized dumping of garbage by learning the articular points of the person using only a small number of images without immediate use of the image for deep learning. In experiment, the proposed system showed 74.97% of garbage dumping detection performance with only a relatively small amount of image data in CCTV environments.

• International journal of advanced smart convergence
• /
• 제10권3호
• /
• pp.51-58
• /
• 2021

In this paper, we propose a deep learning classifier for estimating the number of layers in the Earth's structure. When installing a grounding system, knowledge of the subsurface in the area is absolutely necessary. The subsurface structure can be modeled by the earth parameters. Knowing the exact number of layers can significantly reduce the amount of computation to estimate these parameters. The classifier consists of a feedforward neural network. Apparent resistivity curves were used to train the deep learning classifier. The apparent resistivity at 20 equally spaced log points in each curve are used as the features for the input of the deep learning classifier. Apparent resistivity curve data sets are collected either by theoretical calculations or by Wenner's measurement method. Deep learning classifiers are coded by Keras, an open source neural network library written in Python. This model has been shown to converge with close to 100% accuracy.

• Korean Journal of Radiology
• /
• 제24권7호
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• 대한의용생체공학회:의공학회지
• /
• 제41권1호
• /
• pp.48-54
• /
• 2020

In this paper, we deal with a liver fibrosis classification problem using ultrasound B-mode images. Commonly representative methods for classifying the stages of liver fibrosis include liver biopsy and diagnosis based on ultrasound images. The overall liver shape and the smoothness and roughness of speckle pattern represented in ultrasound images are used for determining the fibrosis stages. Although the ultrasound image based classification is used frequently as an alternative or complementary method of the invasive biopsy, it also has the limitations that liver fibrosis stage decision depends on the image quality and the doctor's experience. With the rapid development of deep learning algorithms, several studies using deep learning methods have been carried out for automated liver fibrosis classification and showed superior performance of high accuracy. The performance of those deep learning methods depends closely on the amount of datasets. We propose an enhanced U-net architecture to maximize the classification accuracy with limited small amount of image datasets. U-net is well known as a neural network for fast and precise segmentation of medical images. We design it newly for the purpose of classifying liver fibrosis stages. In order to assess the performance of the proposed architecture, numerical experiments are conducted on a total of 118 ultrasound B-mode images acquired from 78 patients with liver fibrosis symptoms of F0~F4 stages. The experimental results support that the performance of the proposed architecture is much better compared to the transfer learning using the pre-trained model of VGGNet.

• 공학교육연구
• /
• 제20권3호
• /
• pp.25-31
• /
• 2017

As the world enters the era of the Fourth Industrial Revolution, which is represented by advanced technology, it not only changes the industrial field but also the education field. In recent years, Smart Learning has enriched learning by using diverse forms and technologies that utilize vast amount of information about learners' individual knowledge through the emergence of realistic and intelligent contents that combine high technology such as artificial intelligence, big data and virtual reality and there is an increasing interest in intelligent adaptive learning, which can customize individual education. Therefore, the purpose of this study is to explore intelligent adaptive learning method through recent smart education environment, beyond traditional writing-based communication education which is highly dependent on the competency of instructors. In this study, we analyzed the various learner information collected in the communication course and constructed a concrete teaching and learning method of intelligent adaptive learning based on the instructor's intended smart contents. The result of this study is expected to be the basis of highly personalized teaching and learning method of digital method in communication education which is emphasized in the fourth industrial revolution era.

• 문화기술의 융합
• /
• 제6권4호
• /
• pp.797-802
• /
• 2020

지난 몇 년 동안 스마트 폰을 비롯한 다양한 스마트 기기들은 휴대성을 기반으로 사용자의 요구에 의해 지속적으로 성능이 향상 되고 있다. 유비쿼터스 컴퓨팅 (Ubiquitous Computing) 환경과 센서 네트워크 (Sensor network)등의 다양한 망 접속 기술로 인하여 휴대성을 기반으로 하는 단말기들이 다양하게 보급되어 사용되고 있다. 스마트 단말들은 사용 중에 보다 안정적인 동작을 위하여 에너지 모니터링을 세밀하게 할 수 있는 기술이 필요하게 되었다. 소형 경량화 된 스마트 단말기는 다양한 멀티미디어 작업으로 인하여 단말 운용 중에 전원 부족 문제가 발생하게 된다. 이와 같은 상황을 미리 방지하고 안정적인 단말 운용을 위해서 기존에 다양한 추정 하드웨어가 개발 되었다. 그러나 잔량 추정을 하는 방법이나 성능이 비교적 우수하지 못하였다. 본 논문에서는 스마트 단말의 운용 중에 발생 할 수 있는 잔여 잔량 문제를 미리 예측하여 보다 안정적인 운용을 위한 리튬이온 셀의 잔량 추정 방법을 머신러닝에 기초를 두고 연구 하였다. 기존의 하드웨어적인 추정 방법이 아니라 사용 중인 리튬이온 셀의 특성을 머신러닝 기법을 이용한 학습 알고리즘으로 학습 시키고 최적화된 결과를 추정하여 적용 하고자 한다.

• 의학교육논단
• /
• 제14권2호
• /
• pp.64-68
• /
• 2012

Learning in medical school is usually regarded as a very specialized type of learning compared to that of other academic disciplines. Medical students might have general beliefs about their own learning. Beliefs about learning have a critical effect on learning behavior. There are several factors that affect medical students' learning behavior: epistemological beliefs, learning styles, learning strategies, and learning beliefs. Several studies have addressed epistemological beliefs, learning styles, and learning strategies in medical education. There are, however, few studies that have reported on medical students' beliefs about learning. The purpose of this study was to determine what learning beliefs medical students have, what the causes of these beliefs are, and how medical educators teach students who have such beliefs. In this study, the five learning beliefs are assumed and we considered how these beliefs can affect students' learning behaviors. They include: 1) medical students are expected to learn a large amount of information in a short time. 2) memorization is more important than understanding to survive in medical schools. 3) learning is a competition and work is independent, rather than collaborative. 4) reading textbooks is a heavy burden in medical education. 5) the most effective teaching and learning method is the lecture. These learning beliefs might be the results of various hidden curricula, shared experiences of the former and the present students as a group, and personal experience. Some learning beliefs may negatively affect students' learning. In conclusion, the implications of medical students' learning beliefs are significant and indicate that students and educators can benefit from opportunities that make students' beliefs about learning more conscious.