• Korean Journal of Applied Biomechanics
• /
• v.23 no.2
• /
• pp.179-187
• /
• 2013

This case study was conducted to determine the effects of water exercise on the foot pressure distribution (FPD) of persons who have a hemiplegia. A 43-year old female with hemiplegia acquired at the age of 3 years was selected from a local disability program. A 12-week water exercise program (60 min. per session and twice a week) focusing on gait training was developed and implemented as the intervention of this study. A recent product of the Pedar-X (Novel, Germany) was used to measure the FPD of hemiplegic gait before and after the intervention. Variables considered in this study included the average pressure (AP), contact area (CA), maximum pressure (MP), ground reaction force (GRF), and center of pressure (COP). The data collected were analyzed via the descriptive statistics and qualitative analyses on the graphical presentations of the FPD. Results revealed that the AP and CA of the hemiplegic foot was considerably increased before and after the intervention. Similar results were also found in the MP and GRF. Additionally, the graphical route of the COP related to hemiplegic foot was changed in a positive way after the intervention. It can be concluded that water exercise may be beneficial to restore hemiplegic gait. Limitations related to measurement and generalizability are further discussed.

• Korean Journal of Applied Biomechanics
• /
• v.26 no.4
• /
• pp.433-441
• /
• 2016

Objective: The purpose of this study was to understand the injury mechanism and to provide quantitative data to use in prevention or posture correction training by conducting kinematic and kinetic analyses of risk factors of lower extremity joint injury depending on the change of direction at different angles after a landing motion. Method: This study included 11 men in their twenties (age: $24.6{\pm}1.7years$, height: $176.6{\pm}4.4cm$, weight: $71.3{\pm}8.0kg$) who were right-leg dominant. By using seven infrared cameras (Oqus 300, Qualisys, Sweden), one force platform (AMTI, USA), and an accelerometer (Noraxon, USA), single-leg drop landing was performed at a height of 30 cm. The joint range of motion (ROM) of the lower extremity, peak joint moment, peak joint power, peak vertical ground reaction force (GRF), and peak vertical acceleration were measured. For statistical analysis, one-way repeated-measures analysis of variance was conducted at a significance level of ${\alpha}$ <.05. Results: Ankle and knee joint ROM in the sagittal plane significantly differed, respectively (F = 3.145, p = .024; F = 14.183, p = .000), depending on the change of direction. However, no significant differences were observed in the ROM of ankle and knee joint in the transverse plane. Significant differences in peak joint moment were also observed but no statistically significant differences were found in negative joint power between the conditions. Peak vertical GRF was high in landing (LAD) and after landing, left $45^{\circ}$ cutting (LLC), with a significant difference (F = 9.363, p = .000). The peak vertical acceleration was relatively high in LAD and LLC compared with other conditions, but the difference was not significant. Conclusion: We conclude that moving in the left direction may expose athletes to greater injury risk in terms of joint kinetics than moving in the right direction. However, further investigation of joint injury mechanisms in sports would be required to confirm these findings.

• Journal of the Korean Society for Library and Information Science
• /
• v.52 no.1
• /
• pp.425-446
• /
• 2018

As makerspaces continue to be introduced in academic libraries in Korea, this study explores potential operating strategies of, and long-term justifications for, makerspaces as digital literacy eduational spaces and services at academic libraries. By examining related literature reviews and case studies of makerspaces, this study analyzes various programs and their respective creation, funding, development, and outcomes, including educational value and library-specific goals such as digital literacy and lifelong learning. This study also considers the perspectives of librarians at academic libraries in Korea who were asked about the purpose, impact, and limitations of makerspaces. Certain common themes appear: for example, it is necessary for makerspaces to resolve challenges related to stable funding, as well as staffing and training of professional librarians assisting with the on-the-ground operation of makerspaces. This study proposes that designing makerspaces for an academic library setting goes deeper than providing a collaborative environment with access to new technologies like 3D printers and laser cutters, and it may be uniquely appropriate to draw connections to libraries' objectives to provide digital literacy education and universities' mission to foster innovation and creativity among students.

• Journal of Advanced Navigation Technology
• /
• v.8 no.2
• /
• pp.105-111
• /
• 2004

This paper describes the design of navigation system for an unmanned target drone which is operated by Korean army as for anti-air gun shooting training. Current target drone is operated by pilot control of on-board servo motor via remote control system. Automatic flight control system for the target drone greatly reduces work load of ground pilot and can increase application area of the drone. Most UAVs being operated nowdays use high-priced sensors as AHRS and IMU to measure the attitude, but those are costly. This paper introduces the development of low-cost automatic flight control system with low-cost sensors. The integrated automatic flight control system has been developed by integrating combining power module, switching module, monitoring module and RC receiver as an one module. The performance of navigation for low cost unmanned aerial vehicle, unmanned target drone as our test bed in this paper is verified by both Hardware in the loop simulation(HILS) to test performance of GPS as GPS output frequency high and results of flight test.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.451-454
• /
• 2019

In this paper, we propose a verifiable image transformation networks to transform face sketch to photo and vice versa. Face sketch-photo is very popular in computer vision applications. It has been used in some specific official departments such as law enforcement and digital entertainment. There are several existing face sketch-photo synthesizing methods that use feed-forward convolution neural networks; however, it is hard to assure whether the results of the methods are well mapped by depending only on loss values or accuracy results alone. In our approach, we use two Resnet encoder-decoder networks as image transformation networks. One is for sketch-photo and another is for photo-sketch. They depend on each other to verify their output results during training. For example, using photo-sketch transformation networks to verify the photo result of sketch-photo by inputting the result to the photo-sketch transformation networks and find loss between the reversed transformed result with ground-truth sketch. Likely, we can verify the sketch result as well in a reverse way. Our networks contain two loss functions such as sketch-photo loss and photo-sketch loss for the basic transformation stages and the other two-loss functions such as sketch-photo verification loss and photo-sketch verification loss for the verification stages. Our experiment results on CUFS dataset achieve reasonable results compared with the state-of-the-art approaches.

• Korean Journal of Remote Sensing
• /
• v.16 no.1
• /
• pp.1-11
• /
• 2000

Multi-temporal data have been used frequently for analyzing dynamic characteristics of ecological environment. Little research, however, shows the characteristics and problems of the analysis of continental- or global-scale, multi-temporal satellite data. This research investigated the characteristics of large-area, multi-temporal data analysis and the problems of phenological difference of ground vegetation and scarcity of training data for a long term period. This research suggested a latitudinal image segmentation method and an invariant pixel method. As an application, the image segmentation and invariant pixel methods were applied to a set of AVHRR data covering most part of Asia from 1982 to 1993. Fuzzy classification results showed the decrease of forests and the increase of croplands at densely populated areas, however an opposite trend was detected at sparsely populated or depopulated areas.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.197-206
• /
• 2021

GPR data is used for underground exploration. The data gathered are interpreted by experts based on experience as the underground facilities often reflect GPR. In addition, GPR data are different in the noise and characteristics of the data depending on the equipment, environment, etc. This often results in insufficient data with accurate labels. Generally, a large amount of training data have to be obtained to apply CNN models that exhibit high performance in image classification problems. However, due to the characteristics of GPR data, it makes difficult to obtain sufficient data. Finally, this makes neural networks unable to learn based on general supervised learning methods. This paper proposes an image classification method considering data characteristics to ensure that the accuracy of each label is similar. The proposed method is based on semi-supervised learning, and the image is classified using clustering techniques after extracting the feature values of the image from the neural network. This method can be utilized not only when the amount of the labeled data is insufficient, but also when labels that depend on the data are not highly reliable.

• The korean journal of orthodontics
• /
• v.51 no.2
• /
• pp.77-85
• /
• 2021

Objective: To evaluate the accuracy of a multi-stage convolutional neural network (CNN) model-based automated identification system for posteroanterior (PA) cephalometric landmarks. Methods: The multi-stage CNN model was implemented with a personal computer. A total of 430 PA-cephalograms synthesized from cone-beam computed tomography scans (CBCT-PA) were selected as samples. Twenty-three landmarks used for Tweemac analysis were manually identified on all CBCT-PA images by a single examiner. Intra-examiner reproducibility was confirmed by repeating the identification on 85 randomly selected images, which were subsequently set as test data, with a two-week interval before training. For initial learning stage of the multi-stage CNN model, the data from 345 of 430 CBCT-PA images were used, after which the multi-stage CNN model was tested with previous 85 images. The first manual identification on these 85 images was set as a truth ground. The mean radial error (MRE) and successful detection rate (SDR) were calculated to evaluate the errors in manual identification and artificial intelligence (AI) prediction. Results: The AI showed an average MRE of 2.23 ± 2.02 mm with an SDR of 60.88% for errors of 2 mm or lower. However, in a comparison of the repetitive task, the AI predicted landmarks at the same position, while the MRE for the repeated manual identification was 1.31 ± 0.94 mm. Conclusions: Automated identification for CBCT-synthesized PA cephalometric landmarks did not sufficiently achieve the clinically favorable error range of less than 2 mm. However, AI landmark identification on PA cephalograms showed better consistency than manual identification.

• International Journal of Advanced Culture Technology
• /
• v.9 no.2
• /
• pp.100-105
• /
• 2021

Contactless service is rapidly emerging as a new growth strategy due to consumers who are reluctant to the face-to-face situation in the global pandemic of coronavirus disease 2019 (COVID-19), and various technologies are being developed to support the fast-growing contactless service market. In particular, the restaurant industry is one of the most desperate industrial fields requiring technologies for contactless service, and the representative technical case should be a kiosk, which has the advantage of reducing labor costs for the restaurant owners and provides psychological relaxation and satisfaction to the customer. In this paper, we propose a solution to the restaurant's store operation through the unmanned kiosk using a state-of-the-art artificial intelligence (AI) technology of image recognition. Especially, for the products that do not have barcodes in bakeries, fresh foods (fruits, vegetables, etc.), and autonomous restaurants on highways, which cause increased labor costs and many hassles, our proposed system should be very useful. The proposed system recognizes products without barcodes on the ground of image-based AI algorithm technology and makes automatic payments. To test the proposed system feasibility, we established an AI vision system using a commercial camera and conducted an image recognition test by training object detection AI models using donut images. The proposed system has a self-learning system with mismatched information in operation. The self-learning AI technology allows us to upgrade the recognition performance continuously. We proposed a fully automated payment system with AI vision technology and showed system feasibility by the performance test. The system realizes contactless service for self-checkout in the restaurant business area and improves the cost-saving in managing human resources.

• Journal of Broadcast Engineering
• /
• v.26 no.1
• /
• pp.70-78
• /
• 2021

Estimating 3D information from a single image is one of the essential problems in numerous applications. Since a 2D image inherently might originate from an infinite number of different 3D scenes, thus 3D reconstruction from a single image is notoriously challenging. This challenge has been overcame by the advent of recent deep convolutional neural networks (CNNs), by modeling the mapping function between 2D image and 3D information. However, to train such deep CNNs, a massive training data is demanded, but such data is difficult to achieve or even impossible to build. Recent trends thus aim to present deep learning techniques that can be trained in a weakly-supervised manner, with a meta-data without relying on the ground-truth depth data. In this article, we introduce recent developments of weakly-supervised deep learning technique, especially categorized as scene 3D reconstruction and object 3D reconstruction, and discuss limitations and further directions.