• Journal of Information Technology Applications and Management
• /
• 제13권4호
• /
• pp.197-214
• /
• 2006

This study explores factors to facilitate web-based collaborative learning and the effect of learning, based on the PBL(Problem Based Learning) from the constructivist approach in e-learning. A research model, using the key variables such as situations, interactions, and systems, was developed. In order to test this proposed model, experimental design and post-survey was conducted to the learners who took on-line and off-line course with team project. In the research model, situation category was divided into instructor's support, unstructured problem, and self-directed learning. Interaction category was divided into three factors; 'interaction between learners', 'interaction between learner and instructor', and 'interaction between learner and technology'. System category was divided into.monitoring and incentives. As a result, it was found that collaborative learning can be improved by situations, interactions, and systems, and the effectiveness of learning can be improved by situations and interactions in PBL.

• 한국측량학회지
• /
• 제38권5호
• /
• pp.443-453
• /
• 2020

The automatic land category extraction method was proposed, and the accuracy was evaluated by learning the aerial photo characteristics by land category in the border area with various restrictions on the acquisition of geospatial data. As experimental data, this study used four years' worth of published aerial photos as well as serial cadastral maps from the same time period. In evaluating the results of land category extraction by learning features from different temporal and spatial ranges of aerial photos, it was found that land category extraction accuracy improved as the temporal and spatial ranges increased. Moreover, the greater the diversity and quantity of provided learning images, the less the results were affected by the quality of images at a specific time to be extracted, thus generally demonstrating accurate and practical land category feature extraction.

• 한국전자거래학회:학술대회논문집
• /
• 한국전자거래학회 2004년도 e-Biz World Conference
• /
• pp.294-301
• /
• 2004

·Text-mining approach to e-documents organization based on topic hierarchy - Machine-Learning ＆ information Theory-based ㆍ 'Category(topic) discovery' problem → document bundle-based user-constraint document clustering ㆍ 'Automatic categorization' problem → Accelerated EM with CU-based active learning → 'Hierarchy Construction' problem → Unsupervised learning of category subsumption relation

• 한국통신학회논문지
• /
• 제42권2호
• /
• pp.366-373
• /
• 2017

본 논문은 그로스버그(Grossberg)에 의해 개발된 퍼지 ART 신경 회로망의 성능을 향상시키기 위하여 가변가중 평균(VWA) 학습 방법을 제안한다. 기존의 방법인 고속수용저속부호화(FCSR)는 입력패턴이 임의의 카테고리 내에 포함될 때 카테고리를 대표하는 대표패턴의 갱신이 입력패턴과의 거리(유사성)와 관계없이 고정 학습률로 갱신되고, 또한 이를 개선한 가변학습(VL)은 대표패턴과 입력패턴 사이의 거리를 대표패턴의 갱신에 반영하여 카테고리 증식 문제와 패턴 인식률을 개선한다. 그러나 두 방법 모두 학습 시 퍼지 AND에 의한 과도한 학습이 필수적으로 발생하여 카테고리 증식 문제와 패턴 인식 향상에 한계를 갖는다. 제안된 방법은 카테고리를 대표하는 대표패턴의 갱신 시 대표패턴과 입력패턴 사이의 거리를 반영한 가중평균 학습을 적용하여 대표패턴의 과도한 학습을 억제한다. 시뮬레이션 결과 기존의 학습 방법인 고속수용저속부호화(FCSR)와 가변학습(VL) 보다 제안된 가변가중평균(VWA) 학습 방법이 잡음 환경에서 대표패턴의 과도한 학습을 억제하여 퍼지 ART 신경 회로망의 카테고리 증식문제를 완화하고 패턴 인식률을 향상시키는 것을 보여준다.

• 로봇학회논문지
• /
• 제4권3호
• /
• pp.185-191
• /
• 2009

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship betweenfeatures, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

• 한국농공학회논문집
• /
• 제61권3호
• /
• pp.55-65
• /
• 2019

Although crack on concrete exists from its early formation, crack requires attention as it affects stiffness of structure and can lead demolition of structure as it grows. Detecting cracks on concrete is needed to take action prior to performance degradation of structure, and deep learning can be utilized for it. In this study, transfer learning, one of the deep learning techniques, was used to detect the crack, as the amount of crack's image data was limited. Pre-trained Inception-v3 was applied as a base model for the transfer learning. Web scrapping was utilized to fetch images of concrete wall with or without crack from web. In the recognition of crack, image post-process including changing size or removing color were applied. In the visualization of crack, source images divided into 30px, 50px or 100px size were used as input data, and different numbers of input data per category were applied for each case. With the results of visualized crack image, false positive and false negative errors were examined. Highest accuracy for the recognizing crack was achieved when the source images were adjusted into 224px size under gray-scale. In visualization, the result using 50 data per category under 100px interval size showed the smallest error. With regard to the false positive error, the best result was obtained using 400 data per category, and regarding to the false negative error, the case using 50 data per category showed the best result.

• 대한지구과학교육학회지
• /
• 제8권2호
• /
• pp.206-217
• /
• 2015

The purpose on this study is to identify how effectively experiential learning involving eco-activities make changes in environmental literacy and scientific attitude of elementary students by categorizing those activities into 5 fields of "marine", "rivers", "ecosystem", "climate" and "recycling" and applying those scheme specifically to 5th graders in a elementary school. The conclusion of this study is following. Firstly, after scientific attitude are applied to subjects, a significant disparity was found between experiment group and control group throughout all parts of environmental literacy. In the cognitive category, each specialist concerning his or her own topic was invited to educate the students, and subsequently a positive impact was detected in the category of environmental issue knowledge. In behavioral category, having eco-activities made a significant disparity in all sub-categories of environmental function, active participation, saving activities, recycling activities and so forth. Secondly, experiential learning involving eco-activities made a significant disparity between the two groups in terms of Scientific Attitude, showing effectiveness in all sub-categories except curiosity.

• 전자공학회논문지B
• /
• 제33B권5호
• /
• pp.102-108
• /
• 1996

Adaptive resonance theory (ART2) characterized by its built-in mechanism of handling the stability-plasticity switching and by the adaptive learning without forgetting informations learned in the past, is based on an unsupervised template matching. We propose an improved tow-stage learning algorithm for aRT2: the original unsupervised learning followed by a new supervised learning. Each of the output nodes, after the unsupervised learning, is labeled according to the category informations to reinforce the template pattern associated with the target output node belonging to the same category some dominant classes from exhausting a finite number of template patterns in ART2 inefficiently. Experimental results on a set of 2545 FLIR images show that the ART2 trained by the two-stage learning algorithm yields better accuracy than the original ART2, regardless of th esize of the network and the methods of evaluating the accuracy. This improvement shows the effectiveness of the two-stage learning process.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 하계종합학술대회 논문집
• /
• pp.1001-1004
• /
• 1999

We study on machine learning method for automatic document categorization using back propagation algorithm. Four categories are classified for the experiment and the system learns with 20 documents per a category by this method. As a result of the machine learning, we can find that a new document is automatically classified with a category according to the predefined ones.

• 한국통신학회논문지
• /
• 제38B권12호
• /
• pp.954-961
• /
• 2013

본 논문은 퍼지ART의 학습 방법의 하나인 FCSR(Fast Commit Slow Recode)에서 패턴 인식을 향상시키기 위해 가변 학습을 이용하는 새로운 학습방법을 제안하였다. 기존의 학습 방법은 연결 강도(대표패턴)의 갱신에 고정된 학습률이 사용된다. 이 방법은 같은 카테고리 내의 입력패턴과 대표패턴의 유사성의 정도와 관계없이 고정된 학습률로 연결 강도를 갱신한다. 이 경우 카테고리 경계에 있는 유사성이 낮은 입력패턴이 연결강도의 갱신에 크게 영향을 주게 된다. 따라서 잡음 환경에서 이것은 불필요한 카테고리 증식의 원인이 되고, 패턴 인식 능력을 낮추는 문제가 된다. 제안된 방법에서는 대표 패턴과 입력 패턴 사이에 유사성이 적을수록 연결강도의 갱신에 입력패턴의 기여를 낮추어간다. 그 결과 잡음환경에서 퍼지 ART의 불필요한 카테고리 증식을 억제하였고, 패턴 인식 능력을 향상시켰다.