• The Journal of the Korea Contents Association
• /
• v.4 no.3
• /
• pp.99-105
• /
• 2004

This paper proposes optimal learning rates in the gradient descent training of multilayer perceptrons, which are a separate learning rate for weights associated with each neuron and a separate one for assigning virtual hidden targets associated with each training pattern Effectiveness of the proposed error function was demonstrated for a handwritten digit recognition and an isolated-word recognition tasks and very fast learning convergence was obtained.

• Journal of KIISE:Software and Applications
• /
• v.33 no.12
• /
• pp.999-1007
• /
• 2006

The Backpropagation learning algorithm is known to have slow and false convergence aroused from plateau and local minima. Many substitutes for backpropagation announced so far appear to pay some trade-off for convergence speed and stability of convergence according to parameters. Here, a new algorithm is proposed, which avoids some of those problems associated with the conventional backpropagation problems, especially with local minima, and gives relatively stable and fast convergence with low storage requirement. This is the separate learning algorithm in which the upper connections, hidden-to-output, and the lower connections, input-to-hidden, separately trained. This algorithm requires less computational work than the conventional backpropagation and other improved algorithms. It is shown in various classification problems to be relatively reliable on the overall performance.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.136-145
• /
• 2019

The crowded environment of a domestic pig farm is highly vulnerable to the spread of infectious diseases such as foot-and-mouth disease, and studies have been conducted to automatically analyze behavior of pigs in a crowded pig farm through a video surveillance system using a camera. Although it is required to correctly separate occluding pigs for tracking each individual pigs, extracting the boundaries of the occluding pigs fast and accurately is a challenging issue due to the complicated occlusion patterns such as X shape and T shape. In this study, we propose a fast and accurate method to separate occluding pigs not only by exploiting the characteristics (i.e., one of the fast deep learning-based object detectors) of You Only Look Once, YOLO, but also by overcoming the limitation (i.e., the bounding box-based object detector) of YOLO with the test-time data augmentation of rotation. Experimental results with two-pigs occlusion patterns show that the proposed method can provide better accuracy and processing speed than one of the state-of-the-art widely used deep learning-based segmentation techniques such as Mask R-CNN (i.e., the performance improvement over Mask R-CNN was about 11 times, in terms of the accuracy/processing speed performance metrics).

• Journal of the HCI Society of Korea
• /
• v.13 no.4
• /
• pp.25-34
• /
• 2018

This study is a literature study that analyzes empirical case study of Flipped learning application which has emerged as a method of future university education in Korea. The purpose of the study is to explore the use of digital media by learners in the Flipped learning applied courses in domestic universities considering current digital-based media environment. For this purpose, we analyzed the measurement variables and statistical significance of the preceding studies and analyzed the media utilization. The most important measurement variables were 'learning achievement' and 'class satisfaction', which were measures of effectiveness on the Flipped learning classes. All studies analyzed used media, but most studies focused on verifying the effectiveness of classroom classes, resulting in separate media utilization measurements in one study and statistically meaningful results for the 'video learning recognition' variable. The qualitative measurement related to the use of media for each study was presented as a separate analysis result. In the future, in order for effective follow-up studies on application of Flipped learning and digital media utilization, there are five main issues that need to be studied, which are securing the necessary treatment period for accurate effect measurement, etc.

• English Language & Literature Teaching
• /
• v.12 no.3
• /
• pp.123-145
• /
• 2006

The purpose of this study is to propose an efficient vocabulary assessment model in task-based language learning and to verify the viability of this assessment model. Bachman and Palmer (1996) pointed out the fact that many language tests focus on just one of the areas of language knowledge. However, researchers suggested that it is necessary to acknowledge the needs of several analytic scales, which can provide separate ratings for different components of the language ability to be tested. Although there were many studies which tried to evaluate the various aspects of vocabulary ability, most of them measured only one or two factors. Based on previous research, this study proposed an assessment model of general construct of vocabulary ability and tried to measure vocabulary ability in four separate areas. The subjects were two classes of university level Korean EFL students. They participated in small group discussion via synchronous CMC. One class used a lexically focused task, which was proposed by Kim and Jeong (2006) and the other class used a non-lexically focused task. The results showed that the students with a lexically focused task significantly outperformed those with a non-lexically focused task in overall vocabulary ability as well as four subdivisions of vocabulary ability. In conclusion, the assessment model of separate ratings is a viable measure of vocabulary ability and this can provide elaborate interpretation of vocabulary ability.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2006.05a
• /
• pp.209-212
• /
• 2006

In this study, Support Vector Machine(SVM) and Artificial Neural Network(ANN) are used for developing the defect diagnostic algorithm of the aircraft turbo-shaft engine. Effect of altitude variation on the Defect Diagnostics algorithm has been included and evaluated. Separate learning Algorithm(SLA) suggested with ANN to loam the performance data selectively after classifying the position of defects by SVM improves the classification speed and accuracy.

• Journal of KIEE
• /
• v.10 no.1
• /
• pp.7-15
• /
• 2000

Source separation is a statistical method, the goal of which is to separate the linear instantaneous mixtures of statistically independent sources without resorting to any prior knowledge. This paper addresses a source separation algorithm which is able to separate the mixtures of sub- and super-Gaussian sources. The nonlinear function in the proposed algorithm is derived from the generalized Gaussian distribution that is a set of distributions parameterized by a real positive number (Gaussian exponent). Based on the relationship between the kurtosis and the Gaussian exponent, we present a simple and efficient way of selecting proper nonlinear functions for source separation. Useful behavior of the proposed method is demonstrated by computer simulations.

• International Journal of Internet, Broadcasting and Communication
• /
• v.4 no.2
• /
• pp.12-16
• /
• 2012

This paper presents a learning framework that fits the digital age - an e-Friendly PLE. The learning framework is based on the theory of connectivism which asserts that knowledge and the learning of knowledge is distributive and is not located in any given place but rather consists of the network of connections formed from experiences and interactions with a knowing community, thus, the newly empowered learner is thinking and interacting in new ways. The framework's approach to learning is based on conversation and interaction, on sharing, creation and participation, on learning not as a separate activity, but rather as embedded in meaningful activities such as games or workflows. It sees learning as an active, personal inquiry, interpretation, and construction of meaning from prior knowledge and experience with one's actual environment.

• Journal of Korean Elementary Science Education
• /
• v.36 no.3
• /
• pp.219-226
• /
• 2017

In this study, the reliability and validity of the retrospective pre-post test were analyzed in order to solve the problem of traditional pre-post test including response shift bias. Samples of the study were 162 elementary school students who are studying at the S university gifted education center in Seoul. Before completion of the field trip, we conducted pre test of science-related attitudes. After completion of the field trip, respondents were asked to compare their responses of pre and post science-related attitudes to quantitatively analyze the commonalities and differences of the two tests. To find out more characteristics, qualitative data such as daily records and interview were also gathered and analyzed. The major results of the study are as follows. First, for the paired t-test, there was no statistically significant difference between separate pre-test scores and retrospective pre-test. There was a very high correlation between the separate pre-test scores and the retrospective pre-test. Second, there were significant differences in all seven sub-factors of science-related attitudes between the retrospective pre-test and the post-test. Third, the separate pre-test scores showed a slightly higher tendency than the retrospective pre-test scores. This suggests that the response shift bias appears when it is performed the separate pre-test in affective domain. As a result of the interview, it was found that the evaluation standards of separate pre-test did not match with those of post-test. Forth, internal consistency reliability of the retrospective pre-test was higher than that of the separate pre-test. However, there were significant differences in six factors of science-related attitudes excluding the 'social implications of science' between the separate pre-test and the post-test. Based on these results, the retrospective pre-post test design provides simplicity and convenience to both respondents and investigators, as it is done with one test. The retrospective pre-post test design can be regarded as a valid design for the self-report measurement of affective domain on a single experimental group.

• Journal of Korea Multimedia Society
• /
• v.21 no.2
• /
• pp.98-107
• /
• 2018

In this paper, we propose a method to classify the skeletal maturity with a small amount of hand wrist X-ray image using deep learning-based meta-learning. General deep-learning techniques require large amounts of data, but in many cases, these data sets are not available for practical application. Lack of learning data is usually solved through transfer learning using pre-trained models with large data sets. However, transfer learning performance may be degraded due to over fitting for unknown new task with small data, which results in poor generalization capability. In addition, medical images require high cost resources such as a professional manpower and mcuh time to obtain labeled data. Therefore, in this paper, we use meta-learning that can classify using only a small amount of new data by pre-trained models trained with various learning tasks. First, we train the meta-model by using a separate data set composed of various learning tasks. The network learns to classify the bone maturity using the bone maturity data composed of the radiographs of the wrist. Then, we compare the results of the classification using the conventional learning algorithm with the results of the meta learning by the same number of learning data sets.