• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.243-248
• /
• 2019

Multi-Task Learning(MTL) is a training method that trains a single neural network with multiple tasks influences each other. In this paper, we compare performance of MTL Named entity recognition(NER) model trained with Korean traditional culture corpus and other NER model. In training process, each Bi-LSTM layer of Part of speech tagging(POS-tagging) and NER are propagated from a Bi-LSTM layer to obtain the joint loss. As a result, the MTL based Bi-LSTM model shows 1.1%~4.6% performance improvement compared to single Bi-LSTM models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3917-3941
• /
• 2019

The recent interest in artificial intelligence and machine learning has partly contributed to an interest in the use of such approaches for hyperspectral remote sensing (HRS) imagery classification, as evidenced by the increasing number of deep framework with deep convolutional neural networks (CNN) structures proposed in the literature. In these approaches, the assumption of obtaining high quality deep features by using CNN is not always easy and efficient because of the complex data distribution and the limited sample size. In this paper, conventional handcrafted learning-based multi features based on expert knowledge are introduced as the input of a special designed CNN to improve the pixel description and classification performance of HRS imagery. The introduction of these handcrafted features can reduce the complexity of the original HRS data and reduce the sample requirements by eliminating redundant information and improving the starting point of deep feature training. It also provides some concise and effective features that are not readily available from direct training with CNN. Evaluations using three public HRS datasets demonstrate the utility of our proposed method in HRS classification.

• Journal of Digital Convergence
• /
• v.18 no.5
• /
• pp.347-356
• /
• 2020

The purpose of this study was to identify the intention to use of virtual reality-based cognitive training system for the elderly residing in community based on extended technology acceptance model. The data were collected 100 elderly residing in community from January 2 to January 31, 2020. As a result, the influence the intent to use a virtual reality-based cognitive training system for the elderly is social influence, perceived usefulness, perceived enjoyment, age. The explaining 54.4% of the variance, it is considered that technology development these factors will be necessary for elderly in the community to promote the intent to use of virtual reality-based cognitive training systems. This study is meaningful in that it has identified the degree of intent to use and influencing factors of virtual reality devices for the elderly in the community. This study could be used as basic data for the development of technologies for virtual reality-based cognitive training systems in the future.

• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.111-118
• /
• 2024

In general network-based intrusion detection system is designed to detect malicious behavior directed at a network or its resources. The key goal of this paper is to look at network data and identify whether it is normal traffic data or anomaly traffic data specifically for accounting information systems. In today's world, there are a variety of principles for detecting various forms of network-based intrusion. In this paper, we are using supervised machine learning techniques. Classification models are used to train and validate data. Using these algorithms we are training the system using a training dataset then we use this trained system to detect intrusion from the testing dataset. In our proposed method, we will detect whether the network data is normal or an anomaly. Using this method we can avoid unauthorized activity on the network and systems under that network. The Decision Tree and K-Nearest Neighbor are applied to the proposed model to classify abnormal to normal behaviors of network traffic data. In addition to that, Logistic Regression Classifier and Support Vector Classification algorithms are used in our model to support proposed concepts. Furthermore, a feature selection method is used to collect valuable information from the dataset to enhance the efficiency of the proposed approach. Random Forest machine learning algorithm is used, which assists the system to identify crucial aspects and focus on them rather than all the features them. The experimental findings revealed that the suggested method for network intrusion detection has a neglected false alarm rate, with the accuracy of the result expected to be between 95% and 100%. As a result of the high precision rate, this concept can be used to detect network data intrusion and prevent vulnerabilities on the network.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.33 no.3
• /
• pp.176-183
• /
• 2010

The benefits of information technology cannot be obtained unless potential users utilize it for their work. This led to a lot of research works on computer system acceptance. But most of the works address the early stage of system introduction, leaving the learning effect on system acceptance unexplored. In this longitudinal study, two groups of novice and experienced users have been empirically investigated and compared for their acceptance of computer system and for the learning effect of actual usage. A research model based on the technology acceptance theory has been proposed and applied to the two groups. The result shows that the factor job relevance gets more important and the effect of user training on system acceptance diminishes as time passes. This finding may help introducing computer systems which can be easily accepted by users over the whole life cycle period of computer systems.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.4
• /
• pp.545-554
• /
• 2019

The purpose of this study is to develop a method of applying AR(Augmented Reality)/VR(Virtual Reality) to educational and training systems from a comprehensive perspective, rather than applying AR/VR technology to specific education and training systems. We suggested whether to apply AR or VR technology to education and training system, the level of application of technology when constructing using AR/VR technology, and the criteria of priority among many education and training systems. To do this, we presented the framework of application of AR/VR technology, the evaluation criteria for selecting priority of education and training system applying AR/VR, and the systematic procedure for utilization of developed method. This study is significant in that it has developed a method to determine the direction of systematic AR/VR technology application for all education and training systems operated by the military or organization. This is expected to contribute to the overall efficiency of the organization in terms of economical utilization of the limited budget as well as the various benefits of utilizing basic AR/VR technology.

• The Journal of Korean Association of Computer Education
• /
• v.11 no.2
• /
• pp.23-33
• /
• 2008

The computer education has not to remain literacy education but to change with object of training a member of real society which is logic in thinking, initiativeness in suit with the knowledge information-oriented society by teaching the theory of computer science. This study examined effects and applied by means of developing project- based programming teaching model for elementary students in a classroom when teachers instruct programming education This study is expected to contribute to make computer teaching methods better, by providing teachers with teaching models of computer programming education for elementary students.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.2044-2059
• /
• 2022

Recent works have shown that the geometric constraint can be harnessed to boost the performance of CNN-based camera localization. However, the existing strategies are limited to imposing image-level constraint between pose pairs, which is weak and coarse-gained. In this paper, we introduce a pixel-level epipolar geometry constraint to vanilla localization framework without the ground-truth 3D information. Dubbed EpiLoc, our method establishes the geometric relationship between pixels in different images by utilizing the epipolar geometry thus forcing the network to regress more accurate poses. We also propose a variant called EpiSingle to cope with non-sequential training images, which can construct the epipolar geometry constraint based on a single image in a self-supervised manner. Extensive experiments on the public indoor 7Scenes and outdoor RobotCar datasets show that the proposed pixel-level constraint is valuable, and helps our EpiLoc achieve state-of-the-art results in the end-to-end camera localization task.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.1-10
• /
• 2022

This study aims to build a model is capable of classifying the categories of hadith, according to the reliability of hadith' narrators (sahih, hassan, da'if, maudu) and according to what was attributed to the Prophet Muhammad (saying, doing, describing, reporting ) using the supervised learning algorithms, with a view to discover a relationship between these classifications, based on the outputs of this model, which might be useful to avoid the controversy and useless debate on automatic classifications of hadith, using some of the statistical methods such as chi-square, information gain and association rules. The experimental results showed that there is a relation between these classifications, most of Sahih hadiths are belong to saying class, and most of maudu hadiths are belong to reporting class. Also the best classifier had given high accuracy was MultinomialNB, it achieved higher accuracy reached up to 0.9708 %, for his ability to process high dimensional problems and identifying the most important features that are relevant to target data in training stage. Followed by LinearSVC classifier, reached up to 0.9655, and finally, KNeighborsClassifier reached up to 0.9644.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.19 no.1
• /
• pp.122-133
• /
• 2012

Purpose: The purpose of this study was to develop a web-based education program on control vancomycin-resistant enterococci (VRE) infections and to identify the effects of the program on knowledge and performance of nursing students. Methods: The web-based VRE infection control education program was developed by using the network-based instructional systems design model. The nursing students in the experimental group could access this web-based education program at any time, and as many times as they wanted, during the clinical training period. Effects were evaluated by assessing knowledge and performance of VRE infection control measures during the clinical training period. Results: The contents of the education program included diagnosis, transmission, and treatment of VRE, contact precautions, hand washing, personal protective equipment, environment management, and quizzes. The lecture portion was filmed in a virtual screen studio using flash animation, video, and sound effects, and it was uploaded on an internet site. The knowledge and performance scores of the experimental group after using the education program were significantly higher than those of the control group. Conclusion: The results suggest that the web-based VRE infection control education program is an effective educational method to enhance knowledge and performance of VRE infection control measures.