• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.5
• /
• pp.273-280
• /
• 2022

Along with the advancement of deep learning technology, securing high-quality dataset for verification of developed technology is emerging as an important issue, and developing robust deep learning models to the domestic road environment is focused by many research groups. Especially, unlike expressways and automobile-only roads, in the complex city driving environment, various dynamic objects such as motorbikes, electric kickboards, large buses/truck, freight cars, pedestrians, and traffic lights are mixed in city road. In this paper, we built our dataset through multi camera-based processing (collection, refinement, and annotation) including the various objects in the city road and estimated quality and validity of our dataset by using YOLO-based model in object detection. Then, quantitative evaluation of our dataset is performed by comparing with the public dataset and qualitative evaluation of it is performed by comparing with experiment results using open platform. We generated our 2D dataset based on annotation rules of KITTI/COCO dataset, and compared the performance with the public dataset using the evaluation rules of KITTI/COCO dataset. As a result of comparison with public dataset, our dataset shows about 3 to 53% higher performance and thus the effectiveness of our dataset was validated.

• Journal of Korean Society on Water Environment
• /
• v.26 no.1
• /
• pp.160-167
• /
• 2010

In this research, the performance evaluation between an alternating type process and a recirculating type process was investigated by using mathematical models. The Advanced Phase Isolation Ditch (APID) process and the $A^2/O$ process were selected the target processes of the alternating type and recirculating type, respectively. For more quantitative evaluation, 5 performance indexes which included economy and energy efficiency as well as effluent quality were used, and various disturbance conditions of influent were given to the process models. As simulation results, the APID process which had the specific operation modes to use the organic matter in influent effectively showed higher efficiency of denitrification than the $A^2/O$ process. In the case of effluent TSS, the $A^2/O$ process that the retention time in reactors could be maintained stably was more effective than the APID process. In the cases of various disturbance condition, although it was identified that both two processes had similar effluent quality, the sludge production of the $A^2/O$ process showed lower than that of the APID process while the APID process showed higher energy efficiency.

• Journal of Power Electronics
• /
• v.16 no.2
• /
• pp.717-730
• /
• 2016

The harmonic components of grid voltage result in oscillations of the calculated phase obtained via phase synchronization. This affects the security and stability of grid-connected converters. Moving average filter, delayed signal cancellation and their related harmonic elimination algorithms are major methods for such issues. However, all of the existing methods have their limitations in dealing with multiple harmonics issues. Furthermore, few studies have focused on a comparison and evaluation of these algorithms to achieve optimal algorithm selections in specific applications. In this paper, these algorithms are quantitatively analyzed based on the derived mathematical models. Moreover, an enhanced moving average filter and enhanced delayed signal cancellation algorithms, which are applicable for eliminating a group of selective harmonics with only one calculation block, are proposed. On this basis, both a comprehensive comparison and a quantitative evaluation of all of the aforementioned algorithms are made from several aspects, including response speed, required data storage size, sensitivity to sampling frequency, and elimination of random noise and harmonics. With the conclusions derived in this paper, better overall performance in terms of harmonic elimination can be achieved. In addition, experimental results under different conditions demonstrate the validity of this study.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.1
• /
• pp.119-130
• /
• 2018

The VE/LCC study on the existing multi-utility tunnel examined the economical feasibility of the collective area through the cost-benefit analysis of the ten major routes of Seoul for the benefit (7 items) and the cost (5 items) through quantitative methods. In this paper, we analyzed the economic efficiency of 61 sectors by adding 3 items (reduced traffic accident, reduced vehicle noise, social-economic loss). The reduced traffic accident item is an improvement of the traffic accident cost that can be saved by the implementation of the project, and the reduced vehicle noise item is an indicator of the amount of noise change caused by the implement of the business. Finally, the social-economic loss items represent the impact on the local economy due to the construction of the multi-utility tunnel. The amounts of the additional items were compared and items added in the open type and tunnel type multi-utility tunnel were analyzed for each analysis. Result on the analysis, it analyzed the items applied to the basic and detail models in the economic evaluation of the multi-utility tunnel design, and makes it possible to evaluate the economic efficiency more efficiently. The economic evaluation of the basic and detailed models including the items presented in this study will be often used in the design of the multi-utility tunnel design.

• Journal of radiological science and technology
• /
• v.46 no.4
• /
• pp.277-285
• /
• 2023

In this study, pneumonia identification networks with the small number of layers were constructed by using chest X-ray images. The networks had similar trainable-parameters, and the performance of the trained models was quantitatively evaluated with the modification of the network architectures. A total of 6 networks were constructed: convolutional neural network (CNN), VGGNet, GoogleNet, residual network with identity blocks, ResNet with bottleneck blocks and ResNet with identity and bottleneck blocks. Trainable parameters for the 6 networks were set in a range of 273,921-294,817 by adjusting the output channels of convolution layers. The network training was implemented with binary cross entropy (BCE) loss function, sigmoid activation function, adaptive moment estimation (Adam) optimizer and 100 epochs. The performance of the trained models was evaluated in terms of training time, accuracy, precision, recall, specificity and F1-score. The results showed that the trained models with the small number of layers precisely detect pneumonia from chest X-ray images. In particular, the overall quantitative performance of the trained models based on the ResNets was above 0.9, and the performance levels were similar or superior to those based on the CNN, VGGNet and GoogleNet. Also, the residual blocks affected the performance of the trained models based on the ResNets. Therefore, in this study, we demonstrated that the object detection networks with the small number of layers are suitable for detecting pneumonia using chest X-ray images. And, the trained models based on the ResNets can be optimized by applying appropriate residual-blocks.

• The korean journal of orthodontics
• /
• v.46 no.1
• /
• pp.27-35
• /
• 2016

Objective: The aims of our study were to verify the validity of the T-Scan III system (Tekscan) as an objective occlusal evaluation tool, and to assess the differences between two occlusal indexes - the peer assessment rating (PAR) index and the American Board of Orthodontics objective grading system (OGS) - by comparing the scores derived from the T-Scan III system with the two occlusal indexes and analyzing the correlations between them. Methods: The final study sample included 48 adult volunteers (39 men and 9 women, mean age $24.14{\pm}3.16years$), after excluding 29 volunteers whose occlusion could not be evaluated by the T-Scan III system due to severe skeletal or occlusal problems. PAR index and OGS scores were assessed using dental study models, and measurements of centric occlusion, protrusive movement, and lateral excursion movement were obtained via the T-Scan III system. The results were analyzed to determine correlations. Results: Occlusal analysis by the T-Scan III system was clinically reliable (p < 0.05), and the PAR index and OGS scores were significantly correlated with several measurements obtained with the T-Scan III system (p < 0.05). Conclusions: The T-Scan III system is a quantitative and reliable method for occlusal evaluation, and represents a potential substitute for occlusal indexes. Compared to the PAR index, the OGS scores of more variables were significantly correlated with the T-Scan measurements.

• Journal of Technologic Dentistry
• /
• v.42 no.1
• /
• pp.27-33
• /
• 2020

Purpose: This study is to compare and analyze the precision of glass fiber resin dentures. Methods: A lower edentulous model was prepared. Ten study models were produced using Type IV stone. Ten wax lower resin dentures containing artificial teeth were prepared. The lower wax denture was buried with plaster and deflasking was performed to remove the wax. Five conventional lower resin dentures and five glass fiber lower resin dentures were produced. The scanning spray was coated on the impression surface and then scanned. Independent sample t-test were performed using statistical software. Results: In the color different map, which is a qualitative evaluation, the green area of the precision of the conventional lower resin denture occupied the whole. The glass fiber conventional resin dentures had many negative and positive area. In quantitative evaluation, the RMS of conventional lower resin was 89.83 ㎛ and that of fiberglass resin was 224.92 ㎛. The two groups showed statistically significant differences (p<0.05). Conclusion: Conventional lower resin dentures were superior in precision, and glass fiber resin dentures would have to improve the process.

• Journal of Environmental Health Sciences
• /
• v.48 no.3
• /
• pp.159-166
• /
• 2022

Background: A quantitative structure-activity relationship (QSAR) model was adopted in the Registration, Evaluation, Authorization, and Restriction of Chemicals (REACH, EU) regulations as well as the Act on Registration, Evaluation, etc. of Chemicals (AREC, Republic of Korea). It has been previously used in the registration of chemicals. Objectives: In this study, we investigated the correlation between the predicted data provided by three prediction programs using a QSAR model and actual experimental results (acute fish, daphnia magna toxicity). Through this approach, we aimed to effectively conjecture on the performance and determine the most applicable programs when designating toxic substances through the AREC. Methods: Chemicals that had been registered and evaluated in the Toxic Chemicals Control Act (TCCA, Republic of Korea) were selected for this study. Two prediction programs developed and operated by the U.S. EPA - the Ecological Structure-Activity Relationship (ECOSAR) and Toxicity Estimation Software Tool (T.E.S.T.) models - were utilized along with the TOPKAT (Toxicity Prediction by Komputer Assisted Technology) commercial program. The applicability of these three programs was evaluated according to three parameters: accuracy, sensitivity, and specificity. Results: The prediction analysis on fish and daphnia magna in the three programs showed that the TOPKAT program had better sensitivity than the others. Conclusions: Although the predictive performance of the TOPKAT program when using a single predictive program was found to perform well in toxic substance designation, using a single program involves many restrictions. It is necessary to validate the reliability of predictions by utilizing multiple methods when applying the prediction program to the regulation of chemicals.

• The Korean Journal of Food & Health Convergence
• /
• v.8 no.4
• /
• pp.1-10
• /
• 2022

The term "Organic Food" is no longer strange to consumers around the world. Many people are concerned about their safety and health, so they have chosen this safe food. However, the decision to buy this product still faces some difficulties and challenges, such as the high price of organic products, short-time use, supply of products and so on. This study conducted an analysis to investigate the determinants of Danang City consumers' intention to purchase organic foods in Vietnam. The results show that, there are 6 influencing factors, including: subjective norm, food safety & health consciousness, consumer knowledge & environment consciousness, price of the product, availability product and trust in brands and certifications. The study uses a combination of 2 qualitative and quantitative methods. Qualitative methods are used through analysis, evaluation and synthesis of previous studies to build research models and scales for variables. Quantitative method with 250 samples applied SPSS 25.0 to test the scale by Cronbach's Alpha coefficients, to analyze the discovery factor EFA and regression analysis. The findings of the study provide useful information for consumers to buy organic foods and for marketers to increase sale of organic foods in Vietnam in general and Danang city in particular.

• Journal of the Korean Society of Industry Convergence
• /
• v.26 no.4_2
• /
• pp.669-678
• /
• 2023

Recently, spatial information has been applied to various fields and its usability is increasing day by day. In particular, in the field of civil engineering and construction, BIM based on spatial information is being applied to all construction industries and related research has been conducted. BIM is a technology that utilizes spatial information from the design phase and aids in the construction and maintenance of buildings, including the management of their attributes. However, to apply BIM technology to existing buildings, it takes a lot of time and money to produce models based on design drawings along with current surveying. In this study, quantitative and qualitative analysis was conducted to determine the applicability of the acquired data and the applicability of BIM by generating data and analyzing the accuracy using UAV images and ground lidar, which are representative spatial information acquisition methods. Quantitative analysis revealed that TLS (Terrestrial Laser Scanner) showed reliable accuracy in both planar and elevation measurements, whereas unmanned aerial images exhibited lower accuracy in elevation measurements, resulting in reduced reliability. Qualitative analysis indicated that neither TLS nor unmanned aerial images alone provided perfect completeness. However, the combination of both spatial information sources, tailored to specific needs, resulted in the most comprehensive completeness. Therefore, it is concluded that the appropriate utilization of spatial information acquired through unmanned aerial images and TLS holds the potential for application in the fields of BIM and reverse engineering.