• 전기전자학회논문지
• /
• 제26권4호
• /
• pp.742-745
• /
• 2022

본 논문에서 우리는 열화상에서 전력선 유무를 검출하는 영상처리 기법과 딥러닝 기반의 하이브리드 방법을 제안한다. 딥러닝은 다수의 데이터로부터 목적에 부합하는 특징 벡터를 학습할 수 있는 장점 덕분에 영상 인식, 객체 검출 등 다양한 분야에서 기존의 직접 설계한 특징 벡터를 사용하는 방법들보다 높은 성능을 달성할 수 있는 장점이 있고, 영상처리 기법은 사람의 직관을 그대로 적용할 수 있다는 장점이 있다. 두 장점을 모두 이용하여 열화상에서 전력선 유무를 검출하는 방법을 제안한다. 전력선 유무 검출에 가장 적합한 영상처리 기법을 찾기 위해 총 5가지 방법을 적용 및 비교하였고, 그 결과로 제안하는 방법은 기존의 영상처리 기반 방법과 딥러닝 기반의 방법 두 가지 모두에 비해 더 높은 99.48%의 정확도로 전력선 유무를 검출할 수 있다.

• 융합신호처리학회논문지
• /
• 제24권3호
• /
• pp.147-152
• /
• 2023

본 논문은 고등학교 주문형 강좌에서 진행된 선형대수학 교과목 수업사례에 대한 연구이다. 일반적인 수업과 비교하여 플립러닝 수업이 추가되었고, 학생들의 진로 희망 분야를 고려하여 신호처리 관련 응용문제에 대한 적용도 다루었다. 전체적으로 보면, 전통적 방식의 강의 수업과 플립러닝이 혼합된 형태로 수업이 진행되었다. 플립러닝은 2차례 실시되었다. 플립러닝 수업은 사전학습, 조별 협력학습, 사후학습으로 구성되었다. 수업의 효과성을 검증하기 위하여 설문조사를 실시하였고 대부분의 평가 항목이 4점 이상이었다. 플립러닝의 주제는 신호처리 분야에서도 매우 비중 있게 다루어지는 마르코프 체인과 최소제곱법을 대상으로 진행되었다.

• Smart Structures and Systems
• /
• 제24권5호
• /
• pp.567-585
• /
• 2019

In the past two decades, structural health monitoring (SHM) systems have been widely installed on various civil infrastructures for the tracking of the state of their structural health and the detection of structural damage or abnormality, through long-term monitoring of environmental conditions as well as structural loadings and responses. In an SHM system, there are plenty of sensors to acquire a huge number of monitoring data, which can factually reflect the in-service condition of the target structure. In order to bridge the gap between SHM and structural maintenance and management (SMM), it is necessary to employ advanced data processing methods to convert the original multi-source heterogeneous field monitoring data into different types of specific physical indicators in order to make effective decisions regarding inspection, maintenance and management. Conventional approaches to data analysis are confronted with challenges from environmental noise, the volume of measurement data, the complexity of computation, etc., and they severely constrain the pervasive application of SHM technology. In recent years, with the rapid progress of computing hardware and image acquisition equipment, the deep learning-based data processing approach offers a new channel for excavating the massive data from an SHM system, towards autonomous, accurate and robust processing of the monitoring data. Many researchers from the SHM community have made efforts to explore the applications of deep learning-based approaches for structural damage detection and structural condition assessment. This paper gives a review on the deep learning-based SHM of civil infrastructures with the main content, including a brief summary of the history of the development of deep learning, the applications of deep learning-based data processing approaches in the SHM of many kinds of civil infrastructures, and the key challenges and future trends of the strategy of deep learning-based SHM.

• 한국과학교육학회지
• /
• 제24권5호
• /
• pp.843-850
• /
• 2004

이 연구에서는 과제 지향 보상 협동학습에서 소집단 활동 점검 과정이 학업 성취도, 학습 동기, 과학 수업에 대한 태도에 미치는 영향에 대하여 조사하였다. 서울에 있는 중학교 2학년 58명을 처치 집단과 비교 집단으로 무선 할당한 후, "혼합물의 분리" 단원에 대하여 8차시 동안 수업하였다. 처치 집단에는 소집단 활동 점검 과정이 있는 과제 지향 보상 협동학습(GCL)을 실시하였고, 비교 집단에는 소집단 활동 점검 과정이 없는 과제 지향 보상 협동 학습(CL)을 실시하였다. 연구 결과 학업 성취도와 과학 수업에 대한 태도에서 수업 처치와 사전 성취 수준 사이에 상호작용 효과가 있었다. 상위 수준 학생들은 GCL 집단에서 학업 성취도와 태도에서 더 높은 점수를 받았으며, 하위 수준 학생들은 CL 집단에서 성취도와 태도에서 더 높은 점수를 나타냈다.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.521-538
• /
• 2012

As the knowledge society matures, not only distant, but also off-line universities are trying to provide learners with on-line educational contents. Particularly, high effectiveness of mobile devices for e-Learning has been demonstrated by the university sector, which uses distant learning that is based on blended learning. In this paper, we analyzed previous m-Learning scenarios and future technology prospects. Based on the proposed m-Learning scenario, we designed cellular phone-based educational contents and service structure, implemented m-Learning system, and analyzed m-Learning service satisfaction. The design principles of the m-Learning service are 1) to provide learners with m-Learning environment with both cellular phones and desktop computers; 2) to serve announcements, discussion boards, Q&A boards, course materials, and exercises on cellular phones and desktop computers; and 3) to serve learning activities like the reviewing of full lectures, discussions, and writing term papers using desktop computers and cellular phones. The m-Learning service was developed on a cellular phone that supports H.264 codex in 3G communication technology. Some of the functions of the m-Learning design principles are implemented in a 3G cellular phone. The contents of lectures are provided in the forms of video, text, audio, and video with text. One-way educational contents are complemented by exercises (quizzes).

• 반도체디스플레이기술학회지
• /
• 제19권2호
• /
• pp.60-67
• /
• 2020

Recently, artificial intelligence related technologies including machine learning are being applied to various fields, and the demand is also increasing. In particular, with the development of AR, VR, and MR technologies related to image processing, the utilization of computer vision based on deep learning has increased. The algorithms for object recognition and detection based on deep learning required for image processing are diversified and advanced. Accordingly, problems that were difficult to solve with the existing methodology were solved more simply and easily by using deep learning. This paper introduces various deep learning-based object recognition and extraction algorithms used to detect and recognize various objects in an image and analyzes the technologies that attract attention.

• Journal of Information Processing Systems
• /
• 제10권4호
• /
• pp.543-554
• /
• 2014

It is difficult for mobile learners to maintain a high level of concentration when learning content for more than an hour while they are on the move. Despite the attention span issue, many m-learning systems still provide their mobile learners with the same content once used in e-learning systems. This has called for an investigation to identify the suitable characteristics of the m-learning environment. With this in mind, we have conducted a survey in hopes of determining the requirements for developing more suitable m-learning content. Based on the results of the survey, we have developed a content model comprised of two types: a segment type and a supplement type. In addition, we have implemented a prototype system of the content model for Apple iPhones and Android smartphones in order to investigate a feasibility study of the model application.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.441-452
• /
• 2021

Federated learning provides an efficient integrated model for distributed data, allowing the local training of different data. Meanwhile, the goal of multi-task learning is to simultaneously establish models for multiple related tasks, and to obtain the underlying main structure. However, traditional federated multi-task learning models not only have strict requirements for the data distribution, but also demand large amounts of calculation and have slow convergence, which hindered their promotion in many fields. In our work, we apply the rank constraint on weight vectors of the multi-task learning model to adaptively adjust the task's similarity learning, according to the distribution of federal node data. The proposed model has a general framework for solving optimal solutions, which can be used to deal with various data types. Experiments show that our model has achieved the best results in different dataset. Notably, our model can still obtain stable results in datasets with large distribution differences. In addition, compared with traditional federated multi-task learning models, our algorithm is able to converge on a local optimal solution within limited training iterations.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1223-1230
• /
• 2020

Recently, extensive studies have been conducted to apply deep learning to reinforcement learning to solve the state-space problem. If the state-space problem was solved, reinforcement learning would become applicable in various fields. For example, users can utilize dance-tutorial systems to learn how to dance by watching and imitating a virtual instructor. The instructor can perform the optimal dance to the music, to which reinforcement learning is applied. In this study, we propose a method of reinforcement learning in which the action space is dynamically adjusted. Because actions that are not performed or are unlikely to be optimal are not learned, and the state space is not allocated, the learning time can be shortened, and the state space can be reduced. In an experiment, the proposed method shows results similar to those of traditional Q-learning even when the state space of the proposed method is reduced to approximately 0.33% of that of Q-learning. Consequently, the proposed method reduces the cost and time required for learning. Traditional Q-learning requires 6 million state spaces for learning 100,000 times. In contrast, the proposed method requires only 20,000 state spaces. A higher winning rate can be achieved in a shorter period of time by retrieving 20,000 state spaces instead of 6 million.

• 영어어문교육
• /
• 제12권3호
• /
• pp.267-286
• /
• 2006

The purpose of the study was to investigate what kinds of learning strategies EFL learners use to learn English grammar and what is benefit from structured grammar input processing. Students of the study consisted of 48 college students who took Practical English Grammar at a university in Kyung-Gi area and were divided into two groups based on grammar scores. The students were asked to take two grammar tasks and grammar tests and complete a survey including questions on grammar strategy and input processing. The results of the study are as follows. First, learners' grammar level has an effect on use of grammar attack strategy including asking teachers, using grammar books and given contexts whereas there was no significant difference between groups in the planning strategies, Among memory strategies, using grammar exercise and linking with already known structure demonstrated a significant difference between groups. Second, with regard to input processing, high level students got higher score on how much they understood the structured grammar input compared with low level students. Third, explicit implicit instruction added to input processing seems more comprehensible and more available than structured input only, Finally, it showed that there is positive relationship between perception and score of input processing tasks and grammar tests. Especially, learners' perception of input processing correlated more with final tests and tasks. Therefore, it suggests that the more input processing task need to develop and utilize in order to facilitate learners' intake.