• 수산해양교육연구
• /
• 제26권1호
• /
• pp.156-165
• /
• 2014

The purpose of this study was to find research trends of smart learning. For this, we identified the research's characteristics such as the subject or keyword of research, method, data collection, and statistical analysis method. The 2,865 articles published from 1995 to 2013 were gathered from five Korean academic journals related to smart learning. Among them, research keyword, areas, research method, data collection method, and statistical analysis method were analyzed on 596 papers. The findings of this study were as follows: (a) Smart learning papers such keyword likes u-learning, m-learning, and smart-learning were emerging after 2006. Smart learning papers with ICT related topics were highly increased after 2000, but they were decreased after 2006. Smart learning papers with e-learning related keywords were steadily increased after 2000 through 2013. (b) The research field of deign had the highest portion in smart learning research, but managing had the lowest portion. (c) Development was mainly used as a research method. Both questionnaire and experiment were mainly used for collecting data methods. T-test and frequency analysis were mainly used as statistical analysis methods.

• 대한원격탐사학회지
• /
• 제37권5_1호
• /
• pp.871-884
• /
• 2021

본 연구의 목적은 항공 및 위성영상을 활용한 토지피복 관련 인공지능 학습 데이터를 구축, 검증 및 알고리즘 적용의 효율화 방안을 연구하였다. 이를 위하여 토지피복 8개 항목에 대하여 고해상도의 항공영상 및 Sentinel-2 인공위성에서 얻은 이미지를 사용하여 0.51 m 및 10 m Multi-resolution 데이터셋을 구축하였다. 또한, 학습 데이터의 구성은 Fine data (총 17,000개) 와 Coarse data (총 33,000개)를 동시 구축 및 정밀한 변화 탐지 및 대규모 학습 데이터셋 구축이라는 2가지 목적을 달성하였다. 학습 데이터의 정확도를 위한 검수는 정제 데이터, 어노테이션 및 샘플링으로 3단계로 진행하였다. 최종적으로 검수가 완료된 학습데이터를 Semantic Segmentation 알고리즘 중 U-Net, DeeplabV3+에 적용하여, 결과를 분석하였다. 분석결과 항공영상 기반의 토지피복 평균 정확도는 U- Net 77.8%, Deeplab V3+ 76.3% 및 위성영상 기반의 토지피복에 대한 평균 정확도는 U-Net 91.4%, Deeplab V3+ 85.8%이다. 본 연구를 통하여 구축된 고해상도 항공영상 및 위성영상을 이용한 토지피복 인공지능 학습 데이터셋은 토지피복 변화 및 분류에 도움이 되는 참조자료로 활용이 가능하다. 향후 우리나라 전체를 대상으로 인공지능 학습 데이터셋 구축 시, 토지피복을 연구하는 다양한 인공지능 분야에 활용될 것으로 기대된다.

• 대한원격탐사학회지
• /
• 제38권6_1호
• /
• pp.1407-1422
• /
• 2022

본 연구는 분류(classification)기반 딥러닝 모델(deep learning model)인 Inception과 SENet을 결합한 SE-Inception을 활용하여 수종분류를 수행하고 분류정확도를 평가하였다. 데이터세트의 입력 이미지는 Worldview-3와 GeoEye-1 영상을 활용하였으며, 입력 이미지의 크기는 10 × 10 m, 30 × 30 m, 50 × 50 m로 분할하여 수종 분류정확도를 비교·평가하였다. 라벨(label)자료는 분할된 영상을 시각적으로 해석하여 5개의 수종(소나무, 잣나무, 낙엽송, 전나무, 참나무류)으로 구분한 후, 수동으로 라벨링 작업을 수행하였다. 데이터세트는 총 2,429개의 이미지를 구축하였으며, 그중약 85%는 학습자료로, 약 15%는 검증자료로 활용하였다. 딥러닝 모델을 활용한 수종분류 결과, Worldview-3 영상을 활용하였을 때 최대 약 78%의 전체 정확도를 달성하였으며, GeoEye-1영상을 활용할 때 최대 약 84%의 정확도를 보여 수종분류에 우수한 성능을 보였다. 특히, 참나무류는 입력 이미지크기에 관계없이 F₁은 약 85% 이상의 높은 정확도를 보였으나, 소나무, 잣나무와 같이 분광특성이 유사한 수종은 오분류가 다수 발생하였다. 특정 수종에서 위성영상의 분광정보 만으로는 특징량 추출에 한계가 있을 수 있으며, 식생지수, Gray-Level Co-occurrence Matrix (GLCM) 등 다양한 패턴정보가 포함된 이미지를 활용한다면 분류 정확도를 개선할 수 있을 것으로 판단된다.

• 한국정보전자통신기술학회논문지
• /
• 제17권4호
• /
• pp.205-212
• /
• 2024

본 연구는 건조부각을 유탕기에 투입하기 전 로봇에 장착된 진공 그리퍼를 활용하여 건조 반제품(건조부각)을 이송하기 위한 선별 작업에서 그리핑 성공률을 향상시기키 위한 수단으로 건조부각의 앞면(고명이 있는)과 뒷면(고명이 없는) 표면을 판별하는 딥러닝 모델을 제안한다. 획득한 건조부각 440개의 RGB 영상을 기반으로 데이터 증강 기법을 적용한 후 건조부각 영역 및 표면 정보 라벨링을 진행하였다. 데이터 전처리 과정을 거친 건조부각 데이터를 기반으로 영역 검출을 위해 딥러닝 모델은 YOLO-v5을 적용하였다. 그 결과 건조부각 앞면 영역 검출의 mAP와 mIoU 값은 각각 0.98와 0.96으로 나타났으며, 뒷면의 경우 각각 1.00과 0.95로 나타났다. 앞면과 뒷면 2개의 클래스에 대하여 이진분류한 결과는 average 98.5%, recall 98.3%, precision 98.6%, F1-score 98.4%로 나타났다. 본 연구 결과를 통하여 RGB 영상을 활용한 건조부각의 표면 정보에 대한 분류가 가능하며, 추후 유탕 전 건조부각 표면 선별공정의 로봇-자동화 시스템 개발에 활용될 가능성을 확인하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권1호
• /
• pp.49-53
• /
• 2010

e-learning and m-learning have some problems that data transmission frequently discontinuously, communication cost increases, the computation speed of mass data drops, battery limitation in the mobile learning environments. In this paper, we propose the PULIMS for u-learning systems. The proposed system intellectualize the education environment using intelligent mobile agent, supports the customized education service, and helps that learners feasible access to the education information through mobile phone. We can see the fact that the efficience of proposed method is outperformed that of the conventional methods. The PULIMS is new technology that can be used to learn whenever and wherever learners want in Ubiquitous education environment.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.177-188
• /
• 2013

Since the world entered the age called "Smart Revolution", there has also been a lot of changes in the field of education. In educational environment, there is a growing interest in smart learning based on mobile contents, with the development of Smart Devices and ubiquitous technology. This paper is about a research on what effects smart learning has on leaner side when learners make active use of mobile contents in this age of Smart Revolution. First, we embodied teaching plans for some practical classes in forms of mobile contents using M-bizmaker. After the learning process based on the embodied contents for students, we analyzed the survey results on 4 sections-their use of apps, screen composition, technical support, interactions. We also studied the results of a questionnaire on 4 sections-contents, information offering, feedback systems, learner assessment-to evaluate their satisfaction. The research suggests that learner satisfaction can be improved with smart learning based on mobile contents embodied for leaners.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.223-228
• /
• 2021

As a consequence of sudden outbreak of COVID-19 pandemic worldwide, educational institutes around the globe are forced to switch from traditional learning systems to e-learning systems. This has led to a variety of technology-driven pedagogies in e-teaching as well as e-learning. In order to take the best advantage, an appropriate understanding of the cognitive capability is of prime importance. This paper presents an intelligent cognitive maturity recognition system for confidence-based e-learning. We gather the data from actual test environment by involving a number of students and academicians to act as experts. Then a Genetic Programming based simulation and modeling is applied to generate a generalized classifier in the form of a mathematical expression. The simulation is derived towards an optimal space by carefully designed fitness function and assigning a range to each of the class labels. Experimental results validate that the proposed method yields comparative and superior results which makes it feasible to be used in real world scenarios.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1993년도 Fifth International Fuzzy Systems Association World Congress 93
• /
• pp.1082-1085
• /
• 1993

In this paper, we notice the fact that a human learning process is characterized by a process under a natural language environment, and discuss an approach of learning based on indirect linguistic instructions. An instruction is interpreted through some meaning elements and each trend. Fuzzy evaluation rule are constructed for the searched meaning elements of the given instruction, and the performance of a system to be learned is improved by the evaluation rules. In this paper, we propose a framework of learning based on indirect linguistic instruction based learning using fuzzy theory: FULLINS(FUzzy-Learning based on Linguistic IN-Struction). The validity of FULLINS is shown by applying it to helicopter flight control.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2024년도 춘계학술발표대회
• /
• pp.294-297
• /
• 2024

Malware detection has become increasingly critical with the proliferation of end devices. To improve detection rates and efficiency, the research focus in malware detection has shifted towards leveraging machine learning and deep learning approaches. This shift is particularly relevant in the context of the widespread adoption of end devices, including smartphones, Internet of Things devices, and personal computers. Machine learning techniques are employed to train models on extensive datasets and evaluate various features, while deep learning algorithms have been extensively utilized to achieve these objectives. In this research, we introduce TabNet, a novel architecture designed for deep learning with tabular data, specifically tailored for enhancing malware detection techniques. Furthermore, the Synthetic Minority Over-Sampling Technique is utilized in this work to counteract the challenges posed by imbalanced datasets in machine learning. SMOTE efficiently balances class distributions, thereby improving model performance and classification accuracy. Our study demonstrates that SMOTE can effectively neutralize class imbalance bias, resulting in more dependable and precise machine learning models.

• Animal cells and systems
• /
• 제13권3호
• /
• pp.275-281
• /
• 2009

The effects of pentylenetetrazol (PTZ), a GABA receptor antagonist, were studied on passive avoidance learning and expression of heat shock protein 70 (hsp70), neuroglobin, and fatty acid binding protein-7 (fabp-7) genes. Zebrafish were trained to stay in a dark compartment to avoid a weight dropping in an acryl shuttle box with a central sliding door. In two training sessions of 2 h interval, each consisting of 3 trials, the crossing time was significantly increased from $43.2{\pm}14.4s$ to $149.3{\pm}38.5s$ in the first training session and remained $116.1{\pm}36.0s$ s in the first trial of the second training session in the control. In zebrafish treated with PTZ before the first training session, the crossing time was significantly increased neither in the first nor in the second training session. However, the increased crossing time was maintained in the second training session when 10 mM PTZ was treated three times for 10 min at 30 min intervals between the first and second training session. Quantitative real-time PCR showed that expression level of hsp70 mRNA increased two to eight fold over that of control in the brain at 0-24 h after termination of PTZ treatment. No change in expression of neuroglobin and fabp-7 mRNA was shown in PTZ-treated zebrafish. Our studies suggest that PTZ impairs learning ability in avoidance response and also modifies expression of genes related to the neuroprotection.