• Journal of Engineering Education Research
• /
• v.22 no.6
• /
• pp.12-20
• /
• 2019

The purpose of this study is to development of a teaching-learning model for active learning in engineering education. For this, the adequacy between educational objectives and active learning activities is verified and furthermore an "active learning teaching-learning model" is suggested. This suggested teaching-learning model is expected to supplement weakness of traditional lecture-type teaching-learning activity. Based on the literature review, first, the representative activities of active learning were derived. there are twenty active learning activities, which compose of five of individual learning activity, five of pair-learning activity and five of group-learning activity, and five of alternative- learning activity. In addition, a survey on adequacy between designed active learning activities and learning outcomes were conducted to ten educational experts. Lawshe's content validity calculation method was applied to analyze the validity of this study. Second, five teaching-learning principles, such as thinking, interaction, expression, reflection, and evaluation were derived to develop an "active learning teaching-learning model" which supplements lecture-type classes and then the "TIERA teaching-learning model" which consists of five stages was designed. Finally, based on the survey on educational experts, adequate active learning activities were proposed to apply in each stage of the "TIERA teaching-learning model" and as a result the TIERA model's active learning activities were developed. The result of this study shows that some activities of active learning are appropriate to induce high cognitive learning skills from the learners even in traditional lecture-type classrooms and therefore this study suggests meaningful direction to new paradigm of teaching-learning for engineering education. This study also suggests that instructors of engineering education can turn their traditional teaching-learning activities into dynamic learning activities by utilizing "active learning teaching-learning model".

• Structural Engineering and Mechanics
• /
• v.83 no.2
• /
• pp.167-178
• /
• 2022

Surrogate models aim to approximate the performance function with an active-learning design of experiments (DoE) to obtain a sufficiently accurate prediction of the performance function's sign for an inexpensive computational demand in reliability analysis. Nevertheless, many existing active-learning methods are limited to the Kriging model, while the uncertainties of the Kriging itself affect the reliability analysis results. Moreover, the existing general active-learning methods may not achieve a fully satisfactory balance between accuracy and efficiency. Therefore, a novel active-learning method GLM-CM is constructed to yield the issues, which conciliates several merits of existing methods. To demonstrate the performance of the proposed method, four examples, concerning both mathematical and engineering problems, were selected. By benchmarking obtained results with literature findings, various surrogate models combined with the proposed method not only provide an accurate reliability evaluation while highly alleviating the computational burden, but also provides a satisfactory balance between accuracy and efficiency compared to the other reliability methods.

• MALSORI
• /
• no.66
• /
• pp.87-103
• /
• 2008

We describe a new active learning method in conditional random fields (CRFs) framework for keyphrase extraction. To save elaboration in annotation, we use diversity and representative measure. We select high diversity training candidates by sentence confidence value. We also select high representative candidates by clustering the part-of-speech patterns of contexts. In the experiments using dialog corpus, our method achieves 86.80% and saves 88% training corpus compared with those of supervised method. From the results of experiment, we can see that the proposed method shows improved performance over the previous methods. Additionally, the proposed method can be applied to other applications easily since its implementation is independent on applications.

• ETRI Journal
• /
• v.32 no.5
• /
• pp.766-773
• /
• 2010

Support vector machine (SVM) active learning plays a key role in the interactive content-based image retrieval (CBIR) community. However, the regular SVM active learning is challenged by what we call "the small example problem" and "the asymmetric distribution problem." This paper attempts to integrate the merits of semi-supervised learning, ensemble learning, and active learning into the interactive CBIR. Concretely, unlabeled images are exploited to facilitate boosting by helping augment the diversity among base SVM classifiers, and then the learned ensemble model is used to identify the most informative images for active learning. In particular, a bias-weighting mechanism is developed to guide the ensemble model to pay more attention on positive images than negative images. Experiments on 5000 Corel images show that the proposed method yields better retrieval performance by an amount of 0.16 in mean average precision compared to regular SVM active learning, which is more effective than some existing improved variants of SVM active learning.

• Research in Mathematical Education
• /
• v.19 no.4
• /
• pp.211-227
• /
• 2015

Information Technology influenced on classroom to change the teaching and learning method. Recently, flipped learning method became a hot issue in education by using Information Technology. Learning management system that is introduced in our university in the spring semester 2015, made it possible to apply flipped learning method. So, we used the flipped learning method in a calculus course. In this paper, we found that flipped learning in Calculus we was a little bit affirmative in the aspect of motivation and active learning from students' response on flipped learning method. We analyzed the reason that students were not so positive in continuing flipped learning even though they liked flipped learning a little bit better than traditional learning. We suggest what we pay attention to for applying the flipped learning method effectively.

• International journal of advanced smart convergence
• /
• v.4 no.2
• /
• pp.34-37
• /
• 2015

An ideal teaching-learning method, such as the blended learning method, is to motivate interests in education and to allow active class participation of students. Students exposed to this method are hypothesized to be dedicated in learning and their school life. A research was conducted on $11^{th}$ graders in Daejeon city high school specialized in industry; the blended learning method was applied to a course, digital logic circuit and the effects on the students' learning were monitored. The result shows that compared with a common leaning method, the blended learning method is very effective in terms of increasing educational interest, class participation, the level of concentration in class and academic achievement of students. Also, it shows positive feedbacks from the students on the educational videos and the usage of the contents. Conclusively, the blended learning method effectively increases academic achievements through improved educational motivation and active class participation which positively affect the overall satisfaction of participants.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.6 no.10
• /
• pp.2650-2662
• /
• 2012

Due to the semantic gap issue, the performance of automatic image annotation is still far from satisfactory. Active learning approaches provide a possible solution to cope with this problem by selecting most effective samples to ask users to label for training. One of the key research points in active learning is how to select the most effective samples. In this paper, we propose a novel active learning approach based on sparse graph. Comparing with the existing active learning approaches, the proposed method selects the samples based on two criteria: uncertainty and representativeness. The representativeness indicates the contribution of a sample's label propagating to the other samples, while the existing approaches did not take the representativeness into consideration. Extensive experiments show that bringing the representativeness criterion into the sample selection process can significantly improve the active learning effectiveness.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Journal of Fisheries and Marine Sciences Education
• /
• v.17 no.2
• /
• pp.252-259
• /
• 2005

In this research, as an educational tool in the Refrigeration instruction, a project learning method was applied which enables active hand on practice and encourages a more active participation of students with an increased level of interest in learning. The purpose of this study is to present project learning method as an educational tool that can arouse interest and motivation of students by an active hands-on learning process. This will aid in the enhancement of understanding of educators and students in the project learning method, and assist in development of project learning method that can increase intuitiveness and originality of students. For the purpose of the study, the following questions were asked. First, what is the level of existing knowledge pertaining to Refrigeration Training Program of students? Second, what effect does Refrigeration Training Program conducted via the project approach have on the level of motivation and interest of students? Third, what effect does Refrigeration Training Program conducted via the project approach have on the study habits of students?

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.10
• /
• pp.705-712
• /
• 2013

Active learning aims to improve the performance of a classification model by repeating the process to select the most helpful unlabeled data and include it to the training set through labelling by expert. In this paper, we propose a method for active learning based on hierarchical agglomerative clustering using Ward's linkage. The proposed method is able to construct a training set actively so as to include at least one sample from each cluster and also to reflect the total data distribution by expanding the existing training set. While most of existing active learning methods assume that an initial training set is given, the proposed method is applicable in both cases when an initial training data is given or not given. Experimental results show the superiority of the proposed method.