• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1347-1349
• /
• 2013

현시대 온라인 사용자들에게 각광받고 있는 형태의 웹기반 서비스의 한 형태인 소셜 네트워크 서비스는 동창모임, 지역모임 등의 다양한 현실 인간관계를 기반으로 한 사용자간의 매칭 기능을 제공하고 있다. 이러한 매칭 기능을 바탕으로 소셜 네트워크 서비스는 개인의 일상을 공유하는 용도로 사용되고 있다. 이와는 별도로 학습관리시스템은 대학이상의 고등교육 현장에서 사용되어 학습자의 학습 내용 및 그에 대한 교수자의 피드백을 주기 위한 용도로 이용되고 있다. 본 논문에서는 이러한 소셜 네트워크 서비스의 특성과 학습관리 시스템을 융합하여 학교현장 및 평생교육 관점에서 활용 가능한 소셜 네트워크 서비스기반의 사용자 협업형 학습관리시스템의 구조를 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.1035-1036
• /
• 2017

재난관리 및 대응 분야에서는 무인기의 낮은 운영비용과 자유로운 이동능력의 장점을 토대로, 무인기를 활용한 다양한 재난대응 방안이 연구되고 있다. 본 논문은 무인기를 통해 획득한 항공영상에 대하여, 기계학습 기반의 영상분석을 통한 사람 검출 및 사람 위험 감지 기술을 제안한다. 제안하는 기법은 사람 검출을 위한 딥러닝 네트워크와 범람지역 검출을 위한 딥러닝 네트워크로 구성된다. 제안하는 기법에서 사용하는 두 개의 딥러닝 네트워크를 통해, 사람의 단순 검출뿐만 아니라, 범람지역과 같은 위험지역 검출을 통해, 사람의 위험도를 판단할 수 있다.

• 한국지형공간정보학회:학술대회논문집
• /
• 2001.04a
• /
• pp.1-15
• /
• 2001

본 연구는 도시토지이용의 적합성분석을 실시하는 데 있어 GSIS와 인공신경망의 유기적인 결합을 시도해 보았다. 인공신경망은 학습이라는 과정을 통해 신경망 노드(node)간의 연결강도를 합리적으로 결정할 수 있는 이점이 있다. 이러한 점에서 공간분석에서 요구되는 인자간의 경중률과 신경망의 연결강도는 대체가 가능하리라 판단된다. 본 연구를 수행하기 위해 두 종류의 신경망을 구성하였다. 1차 신경망은 토지이용별 적합성 분석에 적용했으며, 2차 신경망은 최적의 토지이용패턴을 분석하기 위해 구성하였다. 이들 신경망은 C++로 작성된 프로그램에 의해 구현된 최급강하법에 의한 역전파 알고리즘에 의해 학습을 실시하였으며, 활성화 함수는 시그모이드 함수를 사용하였다. 분석결과는 현행 용도지역제에서 주거, 상업, 공업, 녹지에 대한 토지이용 적합도면과 4가지 유형의 토지이용에 대한 대상지역의 최적토지이용패턴을 제시한 도면으로서 Arc/Info의 Grid 형식으로 작성하였다. 또한 토지이용별 적합도면상에 나타난 적합지역과 최적토지이용패턴은 위치적인 면과 공간 구성에 있어 실제의 도시토지이용계획의 이론적인 개념에 매우 합치되는 분포형태를 보였다.

• Journal of Engineering Education Research
• /
• v.3 no.2
• /
• pp.44-50
• /
• 2000

Possible directions of chemical engineering education have been proposed in many studies. However, new curriculum is demanded to accommodate the special needs of our students' level and community industrial characteristics. We can think of two reasons. One is that various kinds of chemical engineering industry are found in every community. The other is that students' educational standards are different in every university. We have surveyed and analyzed jobs of our university graduates who are working in chemical company of our community Pusan and Kyoung-Nam. This study aims to develop the new curriculum with an emphasis on practical education and to propose the new direction for our major characteristic based on the survey.

• Journal of the Korean association of regional geographers
• /
• v.18 no.2
• /
• pp.232-251
• /
• 2012

This paper is to examine new programme of study for geography by a revised geography(including historical, geographical and social understanding) National Curriculum in England. The new primary and secondary National Curriculum was respectively issued in 2007 for implementation from September 2008 and 2010 for implementation from September 2011. The revised National Curriculum was changed more than that of 1995 and 2000 in terms of its formation and content. Especially, Primary National Curriculum was rebuilded to the six areas of learning, in the end KS1-2 geography was integrated in 'historical, geographical and social understanding'. As a result of that, the subject named as geography only remains for KS3. Nevertheless, the new National Curriculum is consisted of programme of study(PoS) and attainment target(AT). But new programme of study was changed more than that of former curriculum in terms of its formation and content. Programme of study for primary school is organized with curriculum aims, the importance of areas of learning, essential knowledge, key skills, cross-curricular studies, breadth of learning and curriculum progression. On the other hand, that of geography for KS3 is organized with curriculum aims, the importance of geography, key concepts, key processes, range and content, curriculum opportunities. This paper examined on categorical features of new programme of study for KS3 geography and its implications for effective geography curriculum design and planning.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1685-1695
• /
• 2021

To generate a deep learning model with high performance, a large training dataset should be required. However, it requires a lot of time and cost to generate a large training dataset in remote sensing. Therefore, the importance of transfer learning of deep learning model using a small dataset have been increased. In this paper, we performed transfer learning of trained model based on open datasets by using orthoimages and digital maps to detect changes of building objects in multitemporal orthoimages. For this, an initial training was performed on open dataset for change detection through the HRNet-v2 model, and transfer learning was performed on dataset by orthoimages and digital maps. To analyze the effect of transfer learning, change detection results of various deep learning models including deep learning model by transfer learning were evaluated at two test sites. In the experiments, results by transfer learning represented best accuracy, compared to those by other deep learning models. Therefore, it was confirmed that the problem of insufficient training dataset could be solved by using transfer learning, and the change detection algorithm could be effectively applied to various remote sensed imagery.

• Journal of Convergence for Information Technology
• /
• v.8 no.6
• /
• pp.31-41
• /
• 2018

The purpose of this study was to investigate the applicability of project - based learning as a teaching method for 'Dental Hygiene Practice' in the community dental hygiene department at G city S university. The subjects were 30 students in the fourth grade in 2018. Data collection period was from March 12 to June 27, and mean and standard deviation were compared using SPSS 20.0 program. The results of the analysis showed that the score of the team with high team performance was high ($3.91{\pm}0.82$), the students were required to practice ($4.10{\pm}0.88$), and the feedback from the professor ($3.73{\pm}0.86$) Satisfaction was high. It was determined that the application of project - based learning classes in the 'Community Dental Hygienic Field Practice' course was appropriate for the class.

• Journal of the Society of Disaster Information
• /
• v.16 no.4
• /
• pp.682-690
• /
• 2020

Purpose: This study builds a database by collecting and refining disaster occurrence data and real-time weather and atmospheric data. In conjunction with the public data provided by the API, we propose a service model for the Big Data-based Urban Safety Index. Method: The plan is to provide a way to collect various information related to disaster occurrence by utilizing public data and SNS, and to identify and cope with disaster situations in areas of interest by real-time dashboards. Result: Compared with the prediction model by extracting the characteristics of the local safety index and weather and air relationship by area, the regional safety index in the area of traffic accidents confirmed that there is a significant correlation with weather and atmospheric data. Conclusion: It proposed a system that generates a prediction model for safety index based on machine learning algorithm and displays safety index by sector on a map in areas of interest to users.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.617-628
• /
• 2021

Drought is a major natural disaster that causes serious social and economic losses. Local drought forecasts can provide important information for drought preparedness. In this study, we propose a new machine learning model that predicts drought by using historical drought indices and meteorological data from 10 sites from 1981 to 2020 in the southeastern part of the Korean Peninsula, Busan-Ulsan-Gyeongnam. Using Bayesian optimization techniques, a hyper-parameter-tuned Random Forest, XGBoost, and Light GBM model were constructed to predict the evaporative demand drought index on a 6-month time scale after 1-month. The model performance was compared by constructing a single site model and a regional model, respectively. In addition, the possibility of improving the model performance was examined by constructing a fine-tuned model using data from a individual site based on the regional model.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.969-976
• /
• 2017

This paper proposes the learning method of an artificial neural network and a convolutional neural network using the WFSO algorithm developed as an optimization algorithm. Since the optimization algorithm searches based on a number of candidate solutions, it has a drawback in that it is generally slow, but it rarely falls into the local optimal solution and it is easy to parallelize. In addition, the artificial neural networks with non-differentiable activation functions can be trained and the structure and weights can be optimized at the same time. In this paper, we describe how to apply WFSO algorithm to artificial neural network learning and compare its performances with error back-propagation algorithm in multilayer artificial neural networks and convolutional neural networks.