• Current Optics and Photonics
• /
• v.8 no.2
• /
• pp.127-137
• /
• 2024

The distribution of tags is an important factor that affects the performance of radio-frequency identification (RFID). To study RFID performance, it is necessary to obtain RFID tags' coordinates. However, the positioning method of RFID technology has large errors, and is easily affected by the environment. Therefore, a new method using optical measurement is proposed to achieve RFID performance analysis. First, due to the possibility of blurring during image acquisition, the paper derives a new image prior to removing blurring. A nonlocal means-based method for image deconvolution is proposed. Experimental results show that the PSNR and SSIM indicators of our algorithm are better than those of a learning deep convolutional neural network and fast total variation. Second, an RFID dynamic testing system based on photoelectric sensing technology is designed. The reading distance of RFID and the three-dimensional coordinates of the tags are obtained. Finally, deep learning is used to model the RFID reading distance and tag distribution. The error is 3.02%, which is better than other algorithms such as a particle-swarm optimization back-propagation neural network, an extreme learning machine, and a deep neural network. The paper proposes the use of optical methods to measure and collect RFID data, and to analyze and predict RFID performance. This provides a new method for testing RFID performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.256-264
• /
• 2024

In the last 10 years, AI has made rapid progress, and image classification, in particular, are showing excellent performance based on deep learning. Nevertheless, due to the nature of deep learning represented by a black box, it is difficult to actually use it in critical decision-making situations such as national defense, autonomous driving, medical care, and finance due to the lack of explainability of judgement results. In order to overcome these limitations, in this study, a model description algorithm capable of local interpretation was applied to the inception network-derived AI to analyze what grounds they made when classifying national defense data. Specifically, we conduct a comparative analysis of explainability based on confidence values by performing LIME analysis from the Inception v2_resnet model and verify the similarity between human interpretations and LIME explanations. Furthermore, by comparing the LIME explanation results through the Top1 output results for Inception v3, Inception v2_resnet, and Xception models, we confirm the feasibility of comparing the efficiency and availability of deep learning networks using XAI.

• Journal of the Korean School Mathematics Society
• /
• v.3 no.2
• /
• pp.69-82
• /
• 2000

Mathematics is the subject that requires high mental function such as the ability of logically thinking and investigating. Because of the reason there exists much greater difference in students' individual scholastic abilities in mathematics class than in other classes. Recently many schools organize students into two or three level-based mathematics classes according to each student's level to solve the problem. But in spite of its many merits the new system of class organization has some problems. The problem which is pointed out as the most serious thing frequently is that many teachers still use the same textbook and the same teaching method for all students, not considering student's level. Obviously it causes the reduction of students' interest and motivation. In this point of view, I tried to solve such a problem by development and application of level learning materials reconstructed text book according to students' abilities and levels through this research. As the result of the research to examine the changes of students' emotional factors such as the recognition, interest, and attitude which influence on improving self-educability in learning mathematics has occurred, the following conclusion comes out. 1. Through the mathematics class utilizing level learning materials reconstructed textbook, students come to recognize that level learning materials are more effective than uniformed contents of the same textbook and get more active learning attitude. 2 The application of level learning materials in a level-based class has contributed to increasing students' interest in mathematics. Furthermore it was also effective in the positive changes of students' emotional factors such as the recognition, interest, and attitude which influence on improving self-educability in learning mathematics.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.5
• /
• pp.987-999
• /
• 2021

Recently, Federated learning has become an issue due to privacy invasion caused by data. Federated learning is safe from privacy violations because it does not need to be collected into a server and does not require learning data. As a result, studies on application methods for utilizing distributed devices and data are underway. However, Federated learning is no longer safe as research on the reconstruction attack to restore learning data from gradients transmitted in the Federated learning process progresses. This paper is to verify numerically and visually how well data reconstruction attacks work in various data situations. Considering that the attacker does not know how the data is constructed, divide the data with the class from when only one data exists to when multiple data are distributed within the class, and use MNIST data as an evaluation index that is MSE, LOSS, PSNR, and SSIM. The fact is that the more classes and data, the higher MSE, LOSS, and PSNR and SSIM are, the lower the reconstruction performance, but sufficient privacy invasion is possible with several reconstructed images.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.1256-1263
• /
• 2024

In the realm of Architecture, Engineering, and Construction (AEC) education, various factors play a crucial role in shaping students' acceptance of the learning environments facilitated by visualization technologies, such as virtual reality (VR). Works on leveraging the heterogeneous educational information (i.e., pedagogical data, student performance data, and student survey data) to identify essential factors influencing students' learning experience and performance in virtual environments are still insufficient. This research proposed KnowLearn, an interactive learning assistant system, to integrate an educational knowledge graph (KG) and a locally deployed large language model (LLM) to generate real-time personalized learning recommendations. As the knowledge base of KnowLearn, the educational KG accommodated multi-faceted educational information from twelve perspectives, such as the teaching content, students' academic performance, and their perceived confidence in a specific course from the AEC discipline. A heterogeneous graph attention network (HAN) was utilized to infer the latent information in the KG and, thus, identified the perceived confidence, intention to use, and performance in a relevant quiz as the top three indicators that significantly influenced students' learning outcomes. Based on the information preserved in the KG and learned from the HAN model, the LLM enhanced the personalization of recommendations concerning adopting virtual learning environments while protecting students' privacy. The proposed KnowLearn system is expected to feasibly provide enhanced recommendations on the teaching module design for educators from the AEC domain.

• Research in Mathematical Education
• /
• v.9 no.1 s.21
• /
• pp.11-24
• /
• 2005

Problem solving is an important aspect of learning mathematics and has been extensively researched into by mathematics educators. In this paper we analyze the difficulties students encounter in various steps involved in solving problems involving physical and geometrical applications of mathematical concepts. Our research shows that, generally students, in spite of possessing adequate theoretical knowledge, have difficulties in identifying the hidden data present in the problems which are crucial links to their successful resolutions. Our research also shows that students have difficulties in solving problems involving constructions and use of symmetry.

• Korean Journal of Microbiology
• /
• v.49 no.1
• /
• pp.51-57
• /
• 2013

As facilities and equipments for learning activities in college campuses are handled by mass public, their contact surfaces may function as major routes of cross-infection of microbial pathogens. However, unlike items in cafeteria which is the typical target for campus hygiene, those surfaces are not under regular surveillance or sanitary maintenance. In this study, I made a quantitative comparison of the risk of being exposed to microbial pathogens from use of learning facilities such as classrooms and library to the risk from use of cafeteria, for about 1,500 students in a college. Regarding total coliforms as surrogate model of bacterial pathogens, exposure rates were estimated for each item in learning facilities and cafeterias by devising deterministic exposure algorithms based on bacterial abundance, contract rates and transfer rates. The exposure rate in cafeterias was 1.0 CFU/day while learning facilities imposed the rate of 0.5 CFU/day, which reaches a half of the exposure rate in cafeterias. However, 70% of students were exposed more in learning facilities than cafeteria because individuals had different frequencies in using cafeteria. Based on the results, some human-contact surfaces of learning facilities, including elevator buttons, may require regular sanitary maintenance. An efficient sanitary maintenance considering seasonality in diversity of pathogens involved with cross-infections is suggested besides improvement of personal hygiene among students.

• Smart Media Journal
• /
• v.11 no.11
• /
• pp.17-24
• /
• 2022

With the spread of smart speakers based on voice recognition technology and deep learning technology, not only non-disabled people, but also the blind or physically handicapped can easily control home appliances such as lights and TVs through voice by linking home network services. This has greatly improved the quality of life. However, in the case of speech-impaired people, it is impossible to use the useful services of the smart speaker because they have inaccurate pronunciation due to articulation or speech disorders. In this paper, we propose a personalized voice classification technique for the speech-impaired to use for some of the functions provided by the smart speaker. The goal of this paper is to increase the recognition rate and accuracy of sentences spoken by speech-impaired people even with a small amount of data and a short learning time so that the service provided by the smart speaker can be actually used. In this paper, data augmentation and one cycle learning rate optimization technique were applied while fine-tuning ResNet18 model. Through an experiment, after recording 10 times for each 30 smart speaker commands, and learning within 3 minutes, the speech classification recognition rate was about 95.2%.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.7 no.4
• /
• pp.256-261
• /
• 2007

Electroencephalographic(EEG) is used to record activities of human brain in the area of psychology for many years. As technology developed, neural basis of functional areas of emotion processing is revealed gradually. So we measure fundamental areas of human brain that controls emotion of human by using EEG. Hands gestures such as shaking and head gesture such as nodding are often used as human body languages for communication with each other, and their recognition is important that it is a useful communication medium between human and computers. Research methods about gesture recognition are used of computer vision. Many researchers study Emotion Recognition method which uses one of EEG signals and Gestures in the existing research. In this paper, we use together EEG signals and Gestures for Emotion Recognition of human. And we select the driver emotion as a specific target. The experimental result shows that using of both EEG signals and gestures gets high recognition rates better than using EEG signals or gestures. Both EEG signals and gestures use Interactive Feature Selection(IFS) for the feature selection whose method is based on the reinforcement learning.