• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.43-50
• /
• 2022

For high-quality education of the modern generation of students, forms of organizing the educational process and the latest methods of obtaining knowledge that differ from traditional ones are necessary. The importance of multimedia teaching tools is shown, which are promising and highly effective tools that allow the teacher not only to present an array of information in a larger volume than traditional sources of information, but also to include text, graphs, diagrams, sound, animation, video, etc. in a visually integrated form. Approaches to the classification of multimedia learning tools are revealed. Special features, advantages of multimedia, expediency of use and their disadvantages are highlighted. A comprehensive analysis of the capabilities of multimedia teaching tools gave grounds for identifying the didactic functions that they perform. Several areas of multimedia application are described. Multimedia technologies make it possible to implement several basic methods of pedagogical activity, which are traditionally divided into active and passive principles of student interaction with the computer, which are revealed in the article. Important conditions for the implementation of multimedia technologies in the educational process are indicated. The feasibility of using multimedia in education is illustrated by examples. Of particular importance in education are game forms of learning, in the implementation of which educational elements based on media material play an important role. The influence of the game on the development of attention by means of works of media culture, which are very diverse in form and character, is shown. The importance of the role of multimedia in student education is indicated. In the educational process of multimedia students, a number of educational functions are implemented, which are presented in the article. Recommendations for using multimedia are given.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.674-684
• /
• 2023

In this paper, a real-time prediction technique for gravity disturbances is proposed using a multi-layer perceptron (MLP) model. To select a suitable MLP model, 4 models with different network sizes were designed to compare the training accuracy and execution time. The MLP models were trained using the data of vehicle moving along the surface of the sea or land, including their positions and gravity disturbance. The gravity disturbances were calculated using the 2160^th degree and order EGM2008 with SHM. Among the models, MLP4 demonstrated the highest training accuracy. After training, the weights and biases of the 4 models were stored in the embedded computer of the INS to implement the MLP network. MLP4 was found to have the shortest execution time among the 4 models. These research results are expected to contribute to improving the navigation accuracy of INS through gravity disturbance compensation in the future.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.1
• /
• pp.27-32
• /
• 1998

This paper is written to introduce a multimedia tutoring system for nondestructive testing using personal computer. Nondestructive testing, one of the chief methods for inspecting welds and many other components, is very difficult for the NDT inspectors to understand its technical basis without a wide experience. And it is necessary for considerable repeated education and training for keeping their knowledge. The tutoring system that can simulate NDT works is suggested to solve the above problem based on reasonable condition. The tutoring system shows basic theories of nondestructive testing in a book-style with video images and hyper-links, and it offers practices, in which users can simulate the testing equipment. The book-style and simulation practices provide effective and individual environments for learning nondestructive testing.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.1157-1160
• /
• 2005

The denoising and reconstruction of color images are increasingly studied in the field of computer vision and image processing. Especially, the denoising and reconstruction of color face images are more difficult than those of natural images because of the structural characteristics of human faces as well as the subtleties of color interactions. In this paper, we propose a denoising method based on PCA reconstruction for removing complex color noises on human faces, which is not easy to remove by using vectorial color filters. The proposed method is composed of the following five steps; training of canonical eigenface space using PCA, automatic extracting of face features using active appearance model, relighing of reconstructed color image using bilateral filter, extraction of noise regions using the variance of training data, and reconstruction using partial information of input images (except the noise regions) and blending of the reconstructed image with the original image. Experimental results show that the proposed denosing method efficiently removes complex color noises on input face images.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-58
• /
• 2005

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.90-104
• /
• 2020

It is difficult for non-experts to build machine learning (ML) models at the level that satisfies their needs. Deep learning models are even more challenging because it is unclear how to improve the model, and a trial-and-error approach is not feasible since training these models are time-consuming. To assist these novice users, we examined how interactive and explainable feedback while training a deep learning network can contribute to model performance and users' satisfaction, focusing on the data preparation process. We conducted a user study with 31 participants without expertise, where they were asked to improve the accuracy of a deep learning model, varying feedback conditions. While no significant performance gain was observed, we identified potential barriers during the process and found that interactive and explainable feedback provide complementary benefits for improving users' understanding of ML. We conclude with implications for designing an interface for building ML models for novice users.

• Journal of the Korean Society of Physical Medicine
• /
• v.10 no.1
• /
• pp.23-35
• /
• 2015

PURPOSE: People with physical disabilities such as cerebral palsy usually experience obstacles when interacting with computer through conventional keyboard because of their motor disabilities. The purpose of this study is empirically compare of text entry(alphabet and word) speed and accuracy using the three different keyboard type on four students(male 2 and female 2) with cerebral palsy. METHODS: This research design used a replicated single-case experimental approach to compare the individual performance. An alternating treatments design was used to examine the effectiveness of standard QWERTY keyboard and alternative keyboard(mini and big keyboard) on computer access for students with cerebral palsy. To avoid changes in posture that influence a keyboard character entry training and evaluation was carried out using his sitting in a wheelchair. Compass software program used in this study as an assessment tool to measure speed and accuracy when performance of text entry(alphabet and word). This was repeated until the stable status of reaction time. RESULTS: As a result, the alternative keyboard seems to be the most effective device for students with cerebral palsy to perform text entry. But various factors such as peculiarity of motor disabilities, experience and preferences of the user are heavily related. CONCLUSION: Thus, we must perform the objective and systematic assessment for computer access and if sustained training is accomplished, it could to improve speed and accuracy of text entry(alphabet and word).

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.2051-2054
• /
• 2002

In this research, we had two experiments. In the first experiment we focused on the comparison of loaming between two groups of hearing impaired students (multimedia training group and traditional print-based method group). The results from the first experiment indicated that there was no numerical difference in test scores between the two groups of students but the students enjoyed learning with computer. We then carried out the second experiment. This time, we focused more on measuring the qualitative nature of the learning using multimedia technology. The results of the second experiment indicated that the two methods of teaching and learning affected students similarly since the average scores of both groups showed no statistically significant difference. About 89% of the students in the second experiment enjoyed learning from the CD-ROM. This result was based not just on the CD-ROM Life in Saskatchewan, but included any kinds and subjects of CD-ROM used in the classroom. Although multimedia training is as good as, but no better than, the traditional print-based method, multimedia can be used as a valuable supplement in adaptive technology.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2007.11a
• /
• pp.439-443
• /
• 2007

Nowadays, activity recognition becomes a hot topic in context-aware computing. In activity recognition, machine learning techniques have been widely applied to learn the activity models from labeled activity samples. Most of the existing work uses only one learning method for activity learning and is focused on how to effectively utilize the labeled samples by refining the learning method. However, not much attention has been paid to the use of multiple classifiers for boosting the learning performance. In this paper, we use two methods to generate multiple classifiers. In the first method, the basic learning algorithms for each classifier are the same, while the training data is different (ASTD). In the second method, the basic learning algorithms for each classifier are different, while the training data is the same (ADTS). Experimental results indicate that ADTS can effectively improve activity recognition performance, while ASTD cannot achieve any improvement of the performance. We believe that the classifiers in ADTS are more diverse than those in ASTD.

• Journal of Information Processing Systems
• /
• v.16 no.6
• /
• pp.1293-1308
• /
• 2020

In fine-tuning-based transfer learning, the size of the dataset may affect learning accuracy. When a dataset scale is small, fine-tuning-based transfer-learning methods use high computing costs, similar to a large-scale dataset. We propose a mid-level feature extractor that retrains only the mid-level convolutional layers, resulting in increased efficiency and reduced computing costs. This mid-level feature extractor is likely to provide an effective alternative in training a small-scale medical image dataset. The performance of the mid-level feature extractor is compared with the performance of low- and high-level feature extractors, as well as the fine-tuning method. First, the mid-level feature extractor takes a shorter time to converge than other methods do. Second, it shows good accuracy in validation loss evaluation. Third, it obtains an area under the ROC curve (AUC) of 0.87 in an untrained test dataset that is very different from the training dataset. Fourth, it extracts more clear feature maps about shape and part of the chest in the X-ray than fine-tuning method.