• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.45-47
• /
• 2022

Mobile edge computing (MEC), which enables mobile terminals to offload computational tasks to a server located at the user's edge, is considered an effective way to reduce the heavy computational burden and achieve efficient computational offloading. In this paper, we study a multi-user MEC system in which multiple user devices (UEs) can offload computation to the MEC server via a wireless channel. To solve the resource allocation and task offloading problem, we take the total cost of latency and energy consumption of all UEs as our optimization objective. To minimize the total cost of the considered MEC system, we propose an DRL-based method to solve the resource allocation problem in wireless MEC. Specifically, we propose a Asynchronous Advantage Actor-Critic (A3C)-based scheme. Asynchronous Advantage Actor-Critic (A3C) is applied to this framework and compared with DQN, and Double Q-Learning simulation results show that this scheme significantly reduces the total cost compared to other resource allocation schemes

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.537-542
• /
• 2021

Smart TVs provide a variety of services and information compared to existing TVs based on the Internet. In order to provide more personalized services or information, it is necessary to analyze users' viewing patterns and provide customized services or information based on them. The proposed system receives the user's TV viewing pattern, analyzes it, and recommends a TV program or movie as customized information to the user. For this, the system was constructed with a preprocessor and a deep learning model. The preprocessor refines the name of the TV program watched by the user, the date the TV program was watched, and the watched time. Then, the multi-attribute LSTM model trains the refined data and performs prediction.The proposed system is a system that provides customized information to users, and is believed to be a leading technology in digital convergence that combines existing IoT technology and deep learning technology.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• International conference on construction engineering and project management
• /
• 2009.05a
• /
• pp.338-344
• /
• 2009

Organizational learning of construction team has been long addressed in the literatures, but the mechanism of learning and the influence of leader in the team still remain vague. This paper presents a computational model (OLT) depicting the mechanism and the influence of leader in a systemic way. The OLT model is a multi-agent system based on some eloquent propositions proposed in previous researches. The proposed model is preliminarily validated by some toy-problem simulations. In the OLT model, the leader is assigned as a project manager. The results show that a proper leader can effectively improve the learning process and the result-in performance, in which the team learning is mainly affected by both the leader and the majority in a team. Based on our findings, two propositions are concluded accordingly: (1) Learning of a team would be enhanced if a proper leader is assigned; (2) The effectiveness of learning would increase in a team, in which the members retain explorative attitudes.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.585-594
• /
• 2007

The back propagation algorithm took a long time to learn the input patterns and was difficult to train the additional or repeated learning patterns. So Aleksander proposed the binary neural network which could overcome the disadvantages of BP Network. But it had the limitation of repeated learning and was impossible to extract a generalized pattern. In this paper, we proposed a dynamic 3 dimensional Neuro System which was consisted of a learning network which was based on weightless neural network and a feedback module which could accumulate the characteristic. The proposed system was enable to train additional and repeated patterns. Also it could be produced a generalized pattern by putting a proper threshold into each learning-net's discriminator which was resulted from learning procedures. And then we reused the generalized pattern to elevate the recognition rate. In the last processing step to decide right category, we used maximum response detector. We experimented using the MNIST database of NIST and got 99.3% of right recognition rate for training data.

• Journal of Korean Medical Science
• /
• v.33 no.43
• /
• pp.239.1-239.12
• /
• 2018

Background: We described a novel multi-step retinal fundus image reading system for providing high-quality large data for machine learning algorithms, and assessed the grader variability in the large-scale dataset generated with this system. Methods: A 5-step retinal fundus image reading tool was developed that rates image quality, presence of abnormality, findings with location information, diagnoses, and clinical significance. Each image was evaluated by 3 different graders. Agreements among graders for each decision were evaluated. Results: The 234,242 readings of 79,458 images were collected from 55 licensed ophthalmologists during 6 months. The 34,364 images were graded as abnormal by at-least one rater. Of these, all three raters agreed in 46.6% in abnormality, while 69.9% of the images were rated as abnormal by two or more raters. Agreement rate of at-least two raters on a certain finding was 26.7%-65.2%, and complete agreement rate of all-three raters was 5.7%-43.3%. As for diagnoses, agreement of at-least two raters was 35.6%-65.6%, and complete agreement rate was 11.0%-40.0%. Agreement of findings and diagnoses were higher when restricted to images with prior complete agreement on abnormality. Retinal/glaucoma specialists showed higher agreements on findings and diagnoses of their corresponding subspecialties. Conclusion: This novel reading tool for retinal fundus images generated a large-scale dataset with high level of information, which can be utilized in future development of machine learning-based algorithms for automated identification of abnormal conditions and clinical decision supporting system. These results emphasize the importance of addressing grader variability in algorithm developments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.

• Journal of Multimedia Information System
• /
• v.8 no.2
• /
• pp.101-110
• /
• 2021

In computer vision, single-image super resolution has been an area of research for a significant period. Traditional techniques involve interpolation-based methods such as Nearest-neighbor, Bilinear, and Bicubic for image restoration. Although implementations of convolutional neural networks have provided outstanding results in recent years, efficiency and single model multi-scalability have been its challenges. Furthermore, previous works haven't placed enough emphasis on real-number scalability. Interpolation-based techniques, however, have no limit in terms of scalability as they are able to upscale images to any desired size. In this paper, we propose a convolutional neural network possessing the advantages of the interpolation-based techniques, which is also efficient, deeming it suitable in practical implementations. It consists of convolutional layers applied on the low-resolution space, post-up-sampling along the end hidden layers, and additional layers on high-resolution space. Up-sampling is applied on a multiple channeled feature map via bicubic interpolation using a single model. Experiments on architectural structure, layer reduction, and real-number scale training are executed with results proving efficient amongst multi-scale learning (including scale multi-path-learning) based models.

• Journal of Satellite, Information and Communications
• /
• v.12 no.3
• /
• pp.74-79
• /
• 2017

In this paper, we propose a system model that predicts the original signal transmitted from the transmitter using the received signal in the power line communication system based on the multi - layer perceptron which is one of the machine learning algorithms. Power line communication system using communication system using power network has more noise than communication system using general communication line. It causes a problem that the performance of the power line communication system is degraded. In order to solve this problem, the communication system model proposed in this paper minimizes the influence of noise through original signal prediction and mitigates the performance degradation of the power line communication system. In this paper, we prove that the original signal is predicted by applying the proposed communication system model to the white noise environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.6 no.6
• /
• pp.502-505
• /
• 2005

According to use of a multimedia content being increased in an e-learning, a size deviation of a content to provide in an e-teaming system is increased. It is becoming a factor to drop efficiency of education because this makes a deviation of response time on an e-learning user. Therefore, studies about a deviation improvement of user response speed is necessary in the e-learning system that used a multimedia content. In this study, we designe the hybrid e-teaming system that used multi-layed structire. A proposed system is based on a characteristics of media and size of a content that a multimedia data had. Also, it proved superiority of performance through experimentation.