• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.2
• /
• pp.52-56
• /
• 1996

In trainir~ga back-propagation neural network, the learning speed of the network is greatly affected by its learning rate. Most of off-line fashioned learning-rate selection methods, however, are empirical except for some deterministic methods. It is very tedious and difficult to find a good learning rate using the empirical methods. The deterministic methods cannot guarantee the quality of the quality of the learning rate. This paper proposes a new learning-rate selection method. Our off-line fashioned method selects a good learning rate through stochastically searching process using evolutionary programming. The simulation results show that the learning speed achieved by our method is superior to that of deterministic and empirical methods.

• IE interfaces
• /
• v.25 no.4
• /
• pp.441-449
• /
• 2012

Solar PV(photovoltaic) is paid great attention to as a possible renewable energy source to overcome recent global energy crisis. However to be a viable alternative energy source compared with fossil fuel, its market competitiveness should be attained. Grid parity is one of effective measure of market competitiveness of renewable energy. In this paper, we forecast the grid parity timing of solar PV energy in Korea using two factor learning curve model. Two factors considered in the present model are production capacity and technological improvement. As a result, it is forecasted that the grid parity will be achieved in 2019 in Korea.

• The Journal of Korea Robotics Society
• /
• v.15 no.4
• /
• pp.398-403
• /
• 2020

Robot's throwing control is difficult to accurately calculate because of air resistance and rotational inertia, etc. This complexity can be solved by using machine learning. Reinforcement learning using reward function puts limit on adapting to new environment for robots. Therefore, this paper applied deep reinforcement learning using neural network without reward function. Throwing is evaluated as a success or failure. AI network learns by taking the target position and control policy as input and yielding the evaluation as output. Then, the task is carried out by predicting the success probability according to the target location and control policy and searching the policy with the highest probability. Repeating this task can result in performance improvements as data accumulates. And this model can even predict tasks that were not previously attempted which means it is an universally applicable learning model for any new environment. According to the data results from 520 experiments, this learning model guarantees 75% success rate.

• The Journal of Korean Association of Computer Education
• /
• v.14 no.1
• /
• pp.159-168
• /
• 2011

This study analyzed whether the ontology-based information-searching model affected the ability of students to effectively search for meaningful information to carry out their projects. The experiment results illustrated that the amount of relevant information sought by the ontology-based information retrieval (OIR) method was significantly greater than that of the existing information retrieval (EIR) method. In addition, the relevance rate of the bookmarked documents sought by the OIR method was significantly greater than that of the EIR method. Interviews showed that the OIR model was helpful for students to effectively find information and thus, it helped them to complete the project more easily. Furthermore, the OIR model was beneficial for them to understand the subordinate concepts and their relationships for an important learning concept. The results of this study indicate that the OIR model could be used as a supplementary learning tool for project-based learning.

• Journal of the Korea Convergence Society
• /
• v.5 no.4
• /
• pp.163-169
• /
• 2014

A stable neural network control scheme for unknown non-linear systems is developed in this paper. While the control variable is optimised to minimize the performance index, convergence of the index is guaranteed asymptotically stable by a Lyapnov control law. The optimization is achieved using a gradient descent searching algorithm and is consequently slow. A fast convergence algorithm using an adaptive learning rate is employed to speed up the convergence. Application of the stable control to a single input single output (SISO) non-linear system is simulated. The satisfactory control performance is obtained.

• International journal of advanced smart convergence
• /
• v.8 no.3
• /
• pp.95-101
• /
• 2019

Recently, there have been many issues related to text recognition using Tesseract. One of these issues is that the text recognition accuracy is significantly lower for smaller fonts. Tesseract extracts text by creating an outline with direction in the image. By searching the Tesseract database, template matching with characters with similar feature points is used to select the character with the lowest error. Because of the poor text extraction, the recognition accuracy is lowerd. In this paper, we compared text recognition accuracy after applying various super-resolution methods to smaller text images and experimented with how the recognition accuracy varies for various image size. In order to recognize small Korean text images, we have used super-resolution algorithms based on deep learning models such as SRCNN, ESRCNN, DSRCNN, and DCSCN. The dataset for training and testing consisted of Korean-based scanned images. The images was resized from 0.5 times to 0.8 times with 12pt font size. The experiment was performed on x0.5 resized images, and the experimental result showed that DCSCN super-resolution is the most efficient method to reduce precision error rate by 7.8%, and reduce the recall error rate by 8.4%. The experimental results have demonstrated that the accuracy of text recognition for smaller Korean fonts can be improved by adding super-resolution methods to the OCR preprocessing module.

• Journal of Korea Multimedia Society
• /
• v.24 no.6
• /
• pp.796-804
• /
• 2021

In computer vision, visual tracking method addresses the problem of localizing an specific object in video sequence according to the bounding box. In this paper, we propose a tracking method by introducing the feature correlation comparison into the siamese network to increase its matching identification. We propose a way to compute location of object to improve matching performance by a correlation operation, which locates parts for solving the searching problem. The higher layer in the network can extract a lot of object information. The lower layer has many location information. To reduce error rate of the object center point, we built a siamese network that extracts the distribution and location information of target objects. As a result of the experiment, the average center error rate was less than 25%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2086-2097
• /
• 2021

The current cultural assets are being restored depending on the opinions of experts (craftsmen). We intend to introduce digitalized artificial intelligence techniques, excluding the personal opinions of experts on reconstruction of such cultural properties. The first step toward restoring digitized cultural properties is separation. The restoration of cultural properties should be reorganized based on recorded documents, period historical backgrounds and regional characteristics. The cultural properties in the form of photographs or images should be collected by separating the background. In addition, when restoring cultural properties most of them depend a lot on the tendency of the restoring person workers. As a result, it often occurs when there is a problem in the accuracy and reliability of restoration of cultural properties. In this study, we propose a search method for learning stored digital cultural assets using AI technology. Pagoda was selected for restoration of Cultural Properties. Pagoda data collection was collected through the Internet and various historical records. The pagoda data was classified by period and region, and grouped into similar buildings. The collected data was learned by applying the well-known CNN algorithm for artificial intelligence learning. The pagoda search used Yolo Marker to mark the tower shape. The tower was used a total of about 100-10,000 pagoda data. In conclusion, it was confirmed that the probability of searching for a tower differs according to the number of pagoda pictures and the number of learning iterations. Finally, it was confirmed that the number of 500 towers and the epochs in training of 8000 times were good. If the test result exceeds 8,000 times, it becomes overfitting. All so, I found a phenomenon that the recognition rate drops when the enemy repeatedly learns more than 8,000 times. As a result of this study, it is believed that it will be helpful in data gathering to increase the accuracy of tower restoration.

• Journal of Digital Convergence
• /
• v.15 no.7
• /
• pp.27-39
• /
• 2017

To grasp the current status of smart campus and look for future directions, this study investigated the usage rate and perceived usefulness of digital devices and services by conducting online survey of 580 university students. The main results are as follows. First, smartphones have the highest ownership rate, followed by laptops, desktops, and digital cameras. Purchase intention of virtual reality devices is highest followed by smart watches/bands, and tablets. Second, mobilization in campus life is almost realized, however the usage of desktops is still high in education and administration context. Digital devices have been perceived particularly useful when searching and sharing information. Third, students use digital services such as search engines, messengers, and online libraries in their learning, and they use messengers, music and video services in their lives. Service usage rate and perceived usefulness are not proportional.

• Journal of Broadcast Engineering
• /
• v.19 no.3
• /
• pp.396-404
• /
• 2014

The field of searching clothing, which is very difficult due to the nature of the informal sector, has been in an effort to reduce the recognition error and computational complexity. However, there is no concrete examples of the whole progress of learning and recognizing for cloth, and the related technologies are still showing many limitations. In this paper, the whole process including identifying both the person and cloth in an image and analyzing both its color and texture pattern is specifically shown for classification. Especially, deformable search descriptor, LBPROT_35 is proposed for identifying the pattern of clothing. The proposed method is scale and rotation invariant, so we can obtain even higher detection rate even though the scale and angle of the image changes. In addition, the color classifier with the color space quantization is proposed not to loose color similarity. In simulation, we build database by training a total of 810 images from the clothing images on the internet, and test some of them. As a result, the proposed method shows a good performance as it has 94.4% matching rate while the former Dense-SIFT method has 63.9%.