• The Korean Journal of Pain
• /
• v.34 no.4
• /
• pp.454-462
• /
• 2021

Background: This study was performed to reveal the relationships between the cross-sectional areas (CSAs) of the paraspinal muscles and the severity of low back pain (LBP), including the level of disability. Methods: This single-center cross-sectional study was conducted on 164 patients with chronic LBP. The effects of demographic characteristics, posture, level of physical activity, disc herniation type, and sarcopenia risk on the CSAs of paraspinal muscles were evaluated along with the relationship between the CSAs and severity of pain and disability in all patients. The CSAs of paraspinal muscles were evaluated using the software program Image J 1.53. Results: A negative significant correlation was found between age and the paraspinal muscle's CSA (P < 0.05), whereas a positive correlation was present between the level of physical activity and the CSA of the paraspinal muscle at the L2-3 and L3-4 levels. The CSAs of paraspinal muscles in patients with sarcopenia risk was significantly lower than those in patients without sarcopenia risk (P < 0.05). The CSAs of paraspinal muscles at the L2-3 and L3-4 levels in obese patients were significantly higher than those in overweight patients (P = 0.028, P = 0.026, respectively). There was no relationship between the CSAs of paraspinal muscles and pain intensity or disability. Conclusions: Although this study did not find a relationship between paraspinal CSAs and pain or disability, treatment regimens for preventing paraspinal muscles from atrophy may aid pain physicians in relieving pain, restoring function, and preventing recurrence in patients with chronic LBP.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.5
• /
• pp.197-202
• /
• 2021

Biometric technology using finger veins is receiving a lot of attention due to its high security, convenience and accuracy. And the recent development of deep learning technology has improved the processing speed and accuracy for authentication. However, the training data is a subset of real data not in a certain order or method and the results are not constant. so the amount of data and the complexity of the artificial neural network must be considered. In this paper, the deep learning model of Inception-Resnet-v2 was used to improve the high accuracy of the finger vein recognizer and the performance of the authentication system, We compared and analyzed the performance of the deep learning model of DenseNet-201. The simulations used data from MMCBNU_6000 of Jeonbuk National University and finger vein images taken directly. There is no preprocessing for the image in the finger vein authentication system, and the results are checked through EER.

• Journal of radiological science and technology
• /
• v.44 no.5
• /
• pp.535-543
• /
• 2021

The purpose of this study is to investigate various opinions on changes and revisions in the Medical Technician Act, to compare the curriculum of radiological technologist and physicians or dentists, and to compare the definitions and scope of work of radiological technologist in Korea and abroad. From the information, The goal is to review whether the phrase 'guidance of a doctor or dentist' specified in the definition of the 'Act on Medical Technicians, etc.' is realistically appropriate. radiological technologist receive specialized college education on radioligical science & medical imaging. The training hours for radiolgical science student are greater than medical students. In addition, radiological technologists are continuously developing their competencies for new knowledge and skills through continuing education in clinical fields. In particular, radiological technologist are making steady research efforts to reduce patient exposure and improve medical image quality. As a result of this investigation, it is considered that the term "guided by a doctor or dentist" as currently defined in the 'Act on Medical Technicians, etc.' may need to be revised in consideration of the professionalism of the radiological technologist.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.9
• /
• pp.1158-1165
• /
• 2021

This paper proposes a CNN accelerator which is optimized Pooling layer operation incorporated in Multiplication And Accumulation(MAC) to reduce the memory size. For optimizing memory and data path circuit, the quantized 8bit integer weights are used instead of 32bit floating-point weights for pre-training of MNIST data set. To reduce chip area, the proposed CNN model is reduced by a convolutional layer, a 4*4 Max Pooling, and two fully connected layers. And all the operations use specific MAC with approximation adders and multipliers. 94% of internal memory size reduction is achieved by simultaneously performing the convolution and the pooling operation in the proposed architecture. The proposed accelerator chip is designed by using TSMC65nmGP CMOS process. That has about half size of our previous paper, 0.8*0.9 = 0.72mm². The presented CNN accelerator chip achieves 94% accuracy and 77us inference time per an MNIST image.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.173-182
• /
• 2021

In this paper, we analyzed driver's and passenger's motions that cause driver's distraction, and recognized 10 driver's behaviors related to mobile phones. First, distraction-inducing behaviors were classified into environments and factors, and related recent papers were analyzed. Based on the analyzed papers, 10 driver's behaviors related to cell phones, which are the main causes of distraction, were recognized. The experiment was conducted based on about 100,000 image data. Features were extracted through SURF and tested with three models (CNN, ResNet-101, and improved ResNet-101). The improved ResNet-101 model reduced training and validation errors by 8.2 times and 44.6 times compared to CNN, and the average precision and f1-score were maintained at a high level of 0.98. In addition, using CAM (class activation maps), it was reviewed whether the deep learning model used the cell phone object and location as the decisive cause when judging the driver's distraction behavior.

• The Korean Journal of Archival Studies
• /
• no.58
• /
• pp.95-145
• /
• 2018

As a communication language, non-text records and archives such as photographs, images, and videos are becoming more important than text records. As a result, domestic institution, organizations, and specialists related to record management have been emphasizing the necessity of the archive management system appropriate for the distinctive characteristics of image records. This paper summarizes the points to be considered for the establishment of the Korean audiovisual archives management system, based on the writer's experience of participating in the International Audiovisual Archives Management Training for professionals in the world(INA Frame) of 2018. In particular, various types of contents including cinema, broadcasting, cultural should be managed at the national level. Furthermore, the necessity of a new concept establishment for "public audiovisual heritage" is accentuated. In addition, the tasks regarding the establishment of foundation, such as the modification of the related systems and infrastructures, and the layouts of the institution or governance, should be reviewed and revised. Moreover, the preliminary tasks revised, should be lead to the establishment of stable management system for public audiovisual archives of Korea.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.279-288
• /
• 2019

We evaluated the land cover classification performance of SegNet, which features semantic segmentation of aerial imagery. We selected four semantic classes, i.e., urban, farmland, forest, and water areas, and created 2,000 datasets using aerial images and land cover maps. The datasets were divided at a 8:2 ratio into training (1,600) and validation datasets (400); we evaluated validation accuracy after tuning the hyperparameters. SegNet performance was optimal at a batch size of five with 100,000 iterations. When 200 test datasets were subjected to semantic segmentation using the trained SegNet model, the accuracies were farmland 87.89%, forest 87.18%, water 83.66%, and urban regions 82.67%; the overall accuracy was 85.48%. Thus, deep learning-based semantic segmentation can be used to classify land cover.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.4
• /
• pp.381-387
• /
• 2019

The limitations of applying a variety of artificial intelligence to the medical community are, first, subjective views, extensive interpreters and physical fatigue in interpreting the image of an interpreter's illness. And there are questions about how long it takes to collect annotated data sets for each illness and whether to get sufficient training data without compromising the performance of the developed deep learning algorithm. In this paper, when collecting basic images based on acne data sets, the selection criteria and collection procedures are described, and a model is proposed to classify data into small loss rates (5.46%) and high accuracy (96.26%) in the sequential structure. The performance of the proposed model is compared and verified through a comparative experiment with the model provided by Keras. Similar phenomena are expected to be applied to the field of medical and skin care by applying them to the acne classification model proposed in this paper in the future.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.673-681
• /
• 2021

This study is a case study of artificial intelligence education subjects in the graduate school of education. The main educational contents consisted of understanding and practice of machine learning, data analysis, actual artificial intelligence using Entries, artificial intelligence and physical computing. As a result of the survey on the educational effect after the application of the curriculum, it was found that the students preferred the use of the Entry AI block and the use of the Blacksmith board as a physical computing tool as the priority applied to the elementary education field. In addition, the data analysis area is effective in linking math data and graph education. As a physical computing tool, Husky Lens is useful for scalability by using image processing functions for self-driving car maker education. Suggestions for desirable AI education include training courses by level and reinforcement of data collection and analysis education.

• Journal of Digital Convergence
• /
• v.17 no.11
• /
• pp.467-474
• /
• 2019

Key areas of digital contents, the games and animation industries are increasingly expanding. Therefore, training of a specialized workforce is required in accordance with these enterprises' growing demand. Education in the field of games and animation lies in cultivating talents with creative thinking, collaboration, and problem-solving skills. Thus, this paper aims to propose a PBSL teaching model for creative convergent talent through game and animation projects. The study will focus on the characteristics of creative convergence talents, project teaching, and related job competencies for game and animation education. Based on literature research, a 'Project Based Self Learning' instructional model is presented, in which creative thinking and collaboration competencies are explained in a way they can be performed by the learner. As a case study, D University's class was applied with PBSL. A survey showed that the autonomy aspects were higher than the creativity and convergence attitudes, indicating that the students improved their autonomy and motivation. However, the team composition needs further supplementation.