• International Journal of Computer Science & Network Security
• /
• v.24 no.5
• /
• pp.129-134
• /
• 2024

Object Detection is an emerging technology in the field of Computer Vision and Image Processing that deals with detecting objects of a particular class in digital images. It has considered being one of the complicated and challenging tasks in computer vision. Earlier several machine learning-based approaches like SIFT (Scale-invariant feature transform) and HOG (Histogram of oriented gradients) are widely used to classify objects in an image. These approaches use the Support vector machine for classification. The biggest challenges with these approaches are that they are computationally intensive for use in real-time applications, and these methods do not work well with massive datasets. To overcome these challenges, we implemented a Deep Learning based approach Convolutional Neural Network (CNN) in this paper. The Proposed approach provides accurate results in detecting objects in an image by the area of object highlighted in a Bounding Box along with its accuracy.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.5
• /
• pp.392-399
• /
• 2023

This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train deep neural networks for object detection tasks. Our approach involves the generation of a large dataset of synthetic images of military vehicles, which is then used to train a deep learning model. The resulting model is then evaluated on real-world images to measure its effectiveness. Our experimental results show that synthetic training data alone can achieve effective results in object detection. Our findings demonstrate the potential of CG-based synthetic data for deep learning and suggest its value as a tool for training models in a variety of applications, including military vehicle detection.

• Korean Journal of Clinical Pharmacy
• /
• v.33 no.3
• /
• pp.202-209
• /
• 2023

Background: With the emergent transition of online learning during the COVID-19 pandemic, the need for online/offline blended learning that can effectively be utilized in a team-based learning (TBL) course has emerged. Methods: We used the online metaverse platforms, Gather and Zoom, along with face-to-face teaching methods in a team-based Introductory Pharmacy Practice Experience (IPPE) course and examined students' learning satisfaction and achievement, as well as their preferences to the learning platforms. A survey questionnaire was distributed to the students after the IPPE course completion. All data were analyzed using Excel and SPSS. Results: Students had high levels of course satisfaction (4.61±0.57 out of 5) and achievement of course learning objectives (4.49±0.70 out of 5), and these were positively correlated with self-directed learning ability. While students believed that the face-to-face platform was the most effective method for many of the class activities, they responded that Gather was the most effective platform for team presentations. The majority of students (64.3%) indicated that blended learning was the most preferred method for a TBL course. Conclusion: Students in a blended TBL IPPE course had high satisfaction and achievements with the use of various online/offline platforms, and indicated that blended learning was the most preferred learning method. In the post-COVID-19 era, it is important to utilize the blended learning approach in a TBL setting that effectively applies online/offline platforms according to the learning contents and activities to maximize students' learning satisfaction and achievement.

• The Journal of the Korea Contents Association
• /
• v.11 no.12
• /
• pp.986-997
• /
• 2011

The purpose of this study is to verify the cognitive theory of Multimedia learning in a Smart Pad environment. Specifically, the viability of the multimedia principle and individual difference principle was tested for this study. To accomplish this, participants were divided into two groups based on their prior knowledge level (high/low), and members of each group were given one of two Smart Pad based programs, one text-based and the other text and image based. Results indicate that the use of images and the interaction between image use and prior knowledge did not have a significant effect on cognitive load levels. However, there were significant effects on learning achievement. This study implies that when developing Smart Pad based learning content, the small screen size compared to PC monitors, types and functions of images, and learning objectives should be considered.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.192-201
• /
• 2020

This study commercialization of 5G will enable transformation of university education. This study identifies five attributes (device type, learning place, learning content, learning field and expense payment) and corresponding levels to study the impact of 5G in the future of university education. The attributes and the levels are then combined into few 5G education service alternatives for respondents to rank. 102 students ranked the alternatives based on their preferences and intent to use. Results indicate that the intent to use 5G-based education service was high with 86% and the most important factor was expense payment (37%), followed by learning field (26%), learning content (24%), device type (8%) and learning place (5%). Specifically, students preferred smart device, practical and experiential content, ubiquitous (no limitation of space and time) learning, practical education and free rate when adopting 5G-based education service. These will provide implications to accelerate adoption of and exploitation of 5G for innovating university education.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.5
• /
• pp.181-189
• /
• 2006

The ubiquitous technology has requested many changes both to the way of learning and to the way of convergence learning content development. However, until now most of e-Learning contents can not meet the requirements of technology convergence and are not developed from the user's perspectives. In this paper, we focus a convergence learning model that is learner-oriented structure, active use of formal and informal learning. Furthermore, examine carefully importance about task analysis, storytelling, and feedback design strategy of learning management system for e-Learning content development. In this context, this paper suggests the effective e-Learning content development method in a convergence era.

• Convergence Security Journal
• /
• v.16 no.5
• /
• pp.17-22
• /
• 2016

This study examined the current state of ICT utilization in physical education and presented the available physical education ICT contents configuration model. Using ICT in physical education is expected to be an alternative of overcome the bad physical education facilities and environment, also highly utilized as a valuable material that can provide specific feedback in learning motor skill. The types of ICT use in physical education classes are being utilized divided by web-use learning and application program-use learning. In composing physical education ICT contents, the server presents a problem to be solved by each student and encourage cooperative learning. If one team determines the solving idea about learning problem through team discussion, they solve the problem by repeating the process of giving teacher and other team's feedback on determining opinion. On the other hand, the class begins after learning the principle of specific movement utilizing the VTR or computer S/W in the practical training lesson of physical education. If the good hardware and software environment combine with the transformation of the recognition on physical education which has been away from the ICT, it will be able expected a broad using of ICT in physical education.

• Journal of Science Education
• /
• v.47 no.2
• /
• pp.154-166
• /
• 2023

It has been known that the tool characteristics embedded in physical tools and virtual tools act with different underlying mechanisms in a user's knowledge acquisition and conceptual understanding. This overview study examines the learning process through the use of physical and virtual tools from the perspective of conceptual frameworks, affordability that tools present, and the depth of cognitive engagement that occurs in the process of learning concepts through various learning activities. Based on the conceptual frameworks, the results of previous comparative studies were reinterpreted. It was found that what mattered for learning is the amount of new information that a tool provides and the different level of cognitive engagement that students use through various learning activities. Finally, the implications to be considered when teachers use physical and virtual tools to help students better understand various concepts are discussed.

• International journal of advanced smart convergence
• /
• v.3 no.1
• /
• pp.11-14
• /
• 2014

We have been designing human interactions for some learning support system or education system. The design is based on a symbol grounding model. The model is applicable to many learning domains using virtual reality technology. The design policy is simple and compact. In order to realize the policy we use/reuse some devices from the viewpoint of virtual reality. This paper introduces basic ideas and explains several example cases based on the idea.