• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.6
• /
• pp.714-721
• /
• 2020

DNN is expanding its use in embedded systems such as robots and autonomous vehicles. For high recognition accuracy, computational complexity is greatly increased, and multiple DNNs are running aperiodically. Therefore, the ability processing multiple DNNs in embedded environments is a crucial issue. Accordingly, multicore based platforms are being released. However, most DNN models are operated in a batch process, and when multiple DNNs are operated in multicore together, the execution time deviation between each DNN may be large and the end-to-end execution time of the whole DNNs could be long depending on how they are allocated to the cores. In this paper, we solve these problems by providing a framework that decompose each DNN into individual layers and then distribute to multicores through a global queue. As a result of the experiment, the total DNN execution time was reduced by 31%, and when operating multiple identical DNNs, the deviation in execution time was reduced by up to 95.1%.

• The Journal of Industrial Distribution & Business
• /
• v.12 no.2
• /
• pp.29-40
• /
• 2021

Purpose: In this study, with the transaction amount of foreign direct Purchase and foreign direct sales increasing, South Korea is in a situation where foreign direct sales are focused on China. We looked at the impact of consumer innovation and site characteristics on repurchase ability among the characteristics of overseas direct purchase consumers as a way to make direct overseas sales to various overseas countries. Research design, data and methodology: Consumer innovativeness consists of four variables: functional, hedonistic, social, and cognitive, and the site characteristics consisted of four variables: product price, product assortment, convenience, and service. The study was conducted on consumers with foreign direct purchase experience, and was finally used in 252 additional analyses. Results: The main findings of this study were first, that the impact on the degree of re-purchase among consumer innovativeness of foreign direct purchase consumers had a significant impact in the order of cognitive innovativeness, hedonistic innovativeness, and functional innovativeness. Social innovativeness did not affect the degree of re-purchase. Second, site characteristics have been found to have a significant impact on the degree of re-purchase in order of product assortment, commodity price, and service. Convenience did not affect the degree of re-purchase. Conclusions Taken together these results can be called the biggest characteristic of the cognitive innovativeness of the consumer's inclination to use the overseas direct purchase, the price or quick response of the goods sold on the site is a factor that affects the re-purchase, above all it is important to have a variety of products. We will present this element as a way to make direct sales abroad to various countries. In addition, foreign direct purchase is a lot of transactions in China, the United States, EU, but the share of China is high in foreign direct sales, and the U.S. and EU have a very low performance, it is important to consider the reasons why they prefer Korean products in China to study the social and cultural characteristics of U.S. and European consumers in the future, and to support and active marketing that companies and sellers can increase sales.

• Convergence Security Journal
• /
• v.20 no.5
• /
• pp.65-74
• /
• 2020

Recently, with the rapid development of eXtended Reality(XR) technology, the development and use of education and training systems using XR technology is increasing significantly. In particular, in areas that involve great risks and high costs such as military training and counter-terrorism training, the use of XR based simulators is preferred because they can improve training performance, reduce training costs, and minimize the risk of safety issues that may occur in actual training, by creating a training environment similar to actual training. In this paper, we propose a plan to build and evaluate an XR based hyper-realistic counter-terrorism education, training, and evaluation system to improve the ROK police's ability to respond to terrorist situations using the 5G and AR based Integrated Command and Control Platform previously developed by the Korea Military Academy. The proposed system is designed to improve counter-terrorism capabilities with virtual training for individual and team units based on hyper-realistic content and training scenarios. Futhermore, it can also be used as a on-site command and control post in connection with a simulation training site and an actual operation site.

• Imaging Science in Dentistry
• /
• v.51 no.1
• /
• pp.27-34
• /
• 2021

Purpose: This study was performed to compare the ability of limited- and large-volume cone-beam computed tomography (CBCT) to display isthmuses in the apical root canals of mandibular molars. Materials and Methods: Forty human mandibular first molars with isthmuses in the apical 3 mm of mesial roots were scanned by micro-computed tomography (micro-CT), and their thickness, area, and length were recorded. The samples were examined using 2 CBCT systems, using the smallest voxels and field of view available for each device. The Mann-Whitney, Friedman, and Dunn multiple comparison tests were performed (α=0.05). Results: The 3D Accuitomo 170 and i-Cat devices detected 77.5% and 75.0% of isthmuses, respectively (P>0.05). For length measurements, there were significant differences between micro-CT and both 3D Accuitomo 170 and i-Cat(P<0.05). Conclusion: Both CBCT systems performed similarly and did not detect isthmuses in the apical third in some cases. CBCT still does not equal the performance of micro-CT in isthmus detection, but it is nonetheless a valuable tool in endodontic practice.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.1-7
• /
• 2020

Early detection and classification of crop diseases play significant role to help farmers to reduce disease spread and to increase agricultural productivity. Recently, many researchers have used deep learning techniques like convolutional neural network (CNN) classifier for crop disease inspection with dataset of crop leaf images (e.g., PlantVillage dataset). These researches present over 90% of classification accuracy for crop diseases, but they have ability to detect only the pre-trained diseases. This paper proposes an efficient disease inspection CNN model for new crops not used in the pre-trained model. First, we present a benchmark crop disease classifier (CDC) for the crops in PlantVillage dataset using VGG16. Then we build a modified crop disease classifier (mCDC) to inspect diseases for untrained crops. The performance evaluation results show that the proposed model outperforms the benchmark classifier.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.3
• /
• pp.571-576
• /
• 2021

This study was carried out to overcome the problems of the existing fitness business and to build a fitness system that can meet the increased demand in the Corona situation. As a platform technology for non-face-to-face fitness edutainment service, it is a next-generation fitness exercise device that can use various body parts and synchronize network-type information. By synchronizing the exercise information of the fitness equipment, it was composed of learning contents through MR-based avatars. A quantified result was derived from examining the applicability of the customized evaluation system through momentum analysis with A.I analysis applying the LSTM-based algorithm according to the cumulative exercise effect of the user. It is a motion capture and 3D visualization fitness program for the application of systematic exercise techniques through academic experts, and it is judged that it will contribute to the improvement of the user's fitness knowledge and exercise ability.

• Journal of Radiation Protection and Research
• /
• v.47 no.1
• /
• pp.8-15
• /
• 2022

Background: We developed a machine vision technology program that tracks patients' real-time breathing and automatically analyzes their breathing patterns. Materials and Methods: To evaluate its potential for clinical application, the image tracking performance and accuracy of the program were analyzed using a respiratory motion phantom. Changes in the stability and regularity of breathing were observed in healthy adult volunteers according to whether the breathing pattern mirrored the breathing guidance. Results and Discussion: Displacement within a few millimeters was observed in real-time with a clear resolution, and the image tracking ability was excellent. This result was consistent even in the sections where breathing patterns changed rapidly. In addition, the respiratory gating method that reflected the individual breathing patterns improved breathing stability and regularity in all volunteers. Conclusion: The findings of this study suggest that this technology can be used to set the appropriate window and the range of internal target volume by reflecting the patient's breathing pattern during radiotherapy planning. However, further studies in clinical populations are required to validate this technology.

• Journal of Korean Society on Water Environment
• /
• v.38 no.2
• /
• pp.82-94
• /
• 2022

In this study, chemically modified biochar (NSBP500, KSBP500, OSBP500) derived from starfish was utilized to improve the adsorption ability of the SBP500 (Starfish Biochar Pyrolyzed at 500℃) in a solution contaminated with heavy metals. According to the biochar modification performance evaluation batch tests, the removal rate and adsorption amount of NSBP500 increased 1.4 times for Cu, 1.5 times for Cd, and 1.2 times for Zn as compared to the control sample SBP500. In addition, the removal rate and adsorption amount of KSBP500 increased 2 times for Cu, 1.8 times for Cd, and 1.2 times for Zn. The removal rate and adsorption amount of OSBP500 increased 5.8 times for Cu. The FT-IR analysis confirmed the changes in the generation and movement of new functional groups after adsorption. SEM analysis confirmed Cu in KSBP500 was in the form of Cu(OH)₂ and resembled the structure of nanowires. The Cd in KSBP500 was densely covered in cubic form of Cd(OH)₂. Lead(Pb) was in the form of Pb₃(OH)₂(CO₃)₂ in a hexagonal atomic layer structure in NSBP500. In addition, it was observed that Zn was randomly covered with Zn₅(CO₃)₂(OH)₆ pieces which resembled plates in KSBP500. Therefore, this study confirmed that biochar removal efficiency was improved through a chemical modification treatment. Accordingly, adsorption and precipitation were found to be the complex mechanisms behind the improved removal efficiency in the biochar. This was accomplished by electrostatic interactions between the biochar and heavy metals and ion exchange with Ca²⁺.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.529-534
• /
• 2021

Computing thinking is regarded as one of the important skills required in the 21st century, and many countries have introduced and implemented computing thinking training courses. Among computational thinking education methods, educational game-based methods increase student participation and motivation, and increase access to computational thinking. Autothinking is an educational game developed for the purpose of providing computational thinking education to learners. It is an adaptive system that dynamically provides feedback to learners and automatically adjusts the difficulty according to the learner's computational thinking ability. However, because the game was designed based on rules, it cannot intelligently consider the computational thinking of learners or give feedback. In this study, game data collected through Autothikning is introduced, and game score prediction that reflects computational thinking is performed in order to increase the adaptability of the game by using it. To solve this problem, a comparative study was conducted on linear regression, decision tree, random forest, and support vector machine algorithms, which are most commonly used in regression problems. As a result of the study, the linear regression method showed the best performance in predicting game scores.

• Geomechanics and Engineering
• /
• v.28 no.4
• /
• pp.385-396
• /
• 2022

The accurate determination of the subgrade reaction modulus (K_s) of soil is an important factor for geotechnical engineers. This study estimated the K_s of soft soil improved with floating deep cement mixing (DCM) columns. A novel prediction model was developed that emphasizes the accuracy of identifying the most significant parameters of K_s. Several multi-layer perceptron (MLP) models that were trained using the Levenberg Marquardt (LM) backpropagation method were developed to estimate K_s. The models were trained using a reliable database containing the results of 36 physical modelling tests. The input parameters were the undrained shear strength of the DCM columns, undrained shear strength of soft soil, area improvement ratio and length-to-diameter ratio of the DCM columns. Grey wolf optimization (GWO) was coupled with the MLPs to improve the performance indices of the MLPs. Sensitivity tests were carried out to determine the importance of the input parameters for prediction of K_s. The results showed that both the MLP-LM and MLP-GWO methods showed high ability to predict K_s. However, it was shown that MLP-GWO (R = 0.9917, MSE = 0.28 (MN/m²/m)) performed better than MLP-LM (R =0.9126, MSE =6.1916 (MN/m²/m)). This proves the greater reliability of the proposed hybrid model of MLP-GWO in approximating the subgrade reaction modulus of soft soil improved with floating DCM columns. The results revealed that the undrained shear strength of the soil was the most effective factor for estimation of K_s.