• The Journal of Korean Association of Computer Education
• /
• v.3 no.1
• /
• pp.23-30
• /
• 2000

The educational effect and practical use of collaborative learning produced in virtual learning communities are being discussed actively in these days. A higher-level interactive tool is essential for successful Internet-based collaborative learning through the network. In this paper, we designed and implemented an integrated browser which has the integrated learning environment to support collaborative learning, and thus the user interface of the network client(News, FTP, HTTP, SMTP, voice text chatting Clients) is improved. Therefore, the educational effect of Internet-based collaborative learning is get closer to that of face-to-face learning.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.751-770
• /
• 2019

Action recognition is an essential task in computer vision due to the variety of prospective applications, such as security surveillance, machine learning, and human-computer interaction. The availability of more video data than ever before and the lofty performance of deep convolutional neural networks also make it essential for action recognition in video. Unfortunately, limited crafted video features and the scarcity of benchmark datasets make it challenging to address the multi-person action recognition task in video data. In this work, we propose a deep convolutional neural network-based Effective Hybrid Learning (EHL) framework for two-person interaction classification in video data. Our approach exploits a pre-trained network model (the VGG16 from the University of Oxford Visual Geometry Group) and extends the Faster R-CNN (region-based convolutional neural network a state-of-the-art detector for image classification). We broaden a semi-supervised learning method combined with an active learning method to improve overall performance. Numerous types of two-person interactions exist in the real world, which makes this a challenging task. In our experiment, we consider a limited number of actions, such as hugging, fighting, linking arms, talking, and kidnapping in two environment such simple and complex. We show that our trained model with an active semi-supervised learning architecture gradually improves the performance. In a simple environment using an Intelligent Technology Laboratory (ITLab) dataset from Inha University, performance increased to 95.6% accuracy, and in a complex environment, performance reached 81% accuracy. Our method reduces data-labeling time, compared to supervised learning methods, for the ITLab dataset. We also conduct extensive experiment on Human Action Recognition benchmarks such as UT-Interaction dataset, HMDB51 dataset and obtain better performance than state-of-the-art approaches.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.1
• /
• pp.11-18
• /
• 2006

Many web-based learning systems have been developed and used widely. But it is known that web-based courses have higher drop out rate. Prior studies in classroom-based courses have shown there is a high correlation between student satisfaction and retention. This paper examines the developed web based self-regulated learning system and analyze self-regulated learning factors. We have derived key factors and their relationship that affect student satisfaction in web-based learning. The key factors are Self-evaluating, Goal setting & Planning, Seeking information, Seeking social assistance and Reviewing records. We found the key factors will help retention in web-based learning.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.4
• /
• pp.46-55
• /
• 1997

This paper presents the development of intelligent performance management of computer communication networks for larger-scale integrated systems and the demonstration of its efficacy using computer simula- tion. The innermost core of the performance management is based on fuzzy set theory. This fuzzy perfor- mance manager has learning ability by using principles of neuro-fuzzy model, neuralnetwork, genetic algo- rithm(GA). Two types of performance managers are described in this paper. One is the Neuro-Fuzzy Per- formance Manager(NFPM) of which learning ability is based on the conventional gradient method, and the other is GA-based Neuro-Fuzzy Performance Manager(GNFPM)with its learning ability based on a genetic algorithm. These performance managers have been evaluated via discrete event simulation of a computer network.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.247-253
• /
• 2021

The outbreak of the deadly virus COVID-19 is said to infect 17.3Cr people around the globe since 2019. This outbreak is continuously affecting a lot of new people till this day and, most of it is said to under control. However, vaccines introduced around the world can help mitigate the risk of the virus. Apart from medical professionals, prediction models are also said to combinedly help predict the risk of infection based on given datasets. This paper is based on publication of a machine learning approach using regression models to predict the output based on dataset which have indictors grouped based on active, tested, recovered and critical cases along with regions and cities covering most of it from Dubai. Hence, the active cases are tested based on the other indicators and other attributes. The coefficient of the determination (r²) is 0.96, which is considered promising. This model can be used as an frame work, among others, to predict the resources related to the dangerous outbreak.

• English Language & Literature Teaching
• /
• v.13 no.2
• /
• pp.25-45
• /
• 2007

In this article, I discuss an International Collaborative Writing Course on the Internet (ICWCI) that focused on the learning effectiveness Korean EFL students (KEFLSs) perceived to be necessary to exchange with international EFL students (IEFLSs). The course development was based on an internet-based instructional module, applying widely accepted EFL theories for modern foreign language instruction: collaborative learning, process writing, project-based learning, and integrated approaches. Data from online discussion forum, mid-of-semester and end-of-semester surveys, and final oral interviews are conducted and discussed. KEFLSs and IEFLSs were questioned about (a) changes in attitude towards computers assisted language learning (CALL); (b) effect of computer background on motivation; (c) perception of their acquired writing skills; and (d) attitude towards collaborative learning. The result of this study demonstrated that the majority of ICWCI participants said they enjoyed the course, gained fruitful confidence in English communication and computer skills, and felt that they made significant progress in writing skills. In spite of positive benefits created by the ICWCI, it was found that there were some issues that are crucial to run appropriate networked collaborative courses. This study demonstrates that participants' computer skills, basic language proficiency, and local time differences are important factors to be considered when incorporating the ICWCI as these may affect the quality of online instructional courses and students' motivation toward network based collaboration interaction.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.415-416
• /
• 2018

최근 기존의 지식 전달 위주의 수업에서 활동 위주의 학습자 중심 수업이 각광받게 되면서 플립러닝과 프로젝트 기반 학습이 주목받고 있다. 플립러닝은 교실 수업 전에 온라인학습으로 학습자가 획득해야하는 개념들을 학습하고 교실 수업에서는 토의와 토론, 협력적 문제해결을 강조한다. 프로젝트 기반 학습은 학습자가 학습 과제를 해결하기 위해 다양한 분야의 지식을 유기적으로 통합시키고 실제적 경험과 지식을 연결함으로써 학습내용에 대한 심층적인 이해와 고차원적인 사고를 하게 한다. 본 논문에서는 플립러닝과 프로젝트 기반 학습을 통합한 플립러닝형 프로젝트 기반 학습에 대한 연구 동향 분석을 통해 향후 연구를 위한 시사점을 도출하고자 하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.9
• /
• pp.163-169
• /
• 2018

Problem solving by programming has a lot of influence on computational thinking improvement. Programming learning has been self-directed based on the individual's thoughts and principles. However, the revised informatics curriculum in 2015 puts importance on collaborative learning. Collaborative learning emphasizes results differently from cooperative learning, which emphasizes problem-solving processes. And cooperative learning leads to structured learning, such as role sharing and activity stages, within a small group, while collaborative learning leads to unstructured learning. Therefore, it is becoming more in collaborative learning that peer interaction can be affected by learners' cognitive style. In this paper, we propose the effect of cognitive style on problem solving ability in collaborative learning for problem solving by programming. As a result, collaborative learning was effective in improving problem solving ability and there was no significant difference in cognitive style.

• Proceedings of the KIEE Conference
• /
• 2008.10b
• /
• pp.292-293
• /
• 2008

In this paper, we propose a face hallucination method based on example-learning. The traditional approach based on example-learning requires alignment of face images. In the proposed method, facial images are segmented into patches and the weights are computed to represent input low resolution facial images into weighted sum of low resolution example images. High resolution facial images are hallucinated by combining the weight vectors with the corresponding high resolution patches in the training set. Experimental results show that the proposed method produces more reliable results of face hallucination than the ones by the traditional approach based on example-learning.

• International Journal of Computer Science & Network Security
• /
• v.23 no.8
• /
• pp.49-62
• /
• 2023

There has been a rapid increase in the creation and alteration of new malware samples which is a huge financial risk for many organizations. There is a huge demand for improvement in classification and detection mechanisms available today, as some of the old strategies like classification using mac learning algorithms were proved to be useful but cannot perform well in the scalable auto feature extraction scenario. To overcome this there must be a mechanism to automatically analyze malware based on the automatic feature extraction process. For this purpose, the dynamic analysis of real malware executable files has been done to extract useful features like API call sequence and opcode sequence. The use of different hashing techniques has been analyzed to further generate images and convert them into image representable form which will allow us to use more advanced classification approaches to classify huge amounts of images using deep learning approaches. The use of deep learning algorithms like convolutional neural networks enables the classification of malware by converting it into images. These images when fed into the CNN after being converted into the grayscale image will perform comparatively well in case of dynamic changes in malware code as image samples will be changed by few pixels when classified based on a greyscale image. In this work, we used VGG-16 architecture of CNN for experimentation.