• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.5
• /
• pp.323-330
• /
• 2020

This paper proposes the road roughness based Braking Pressure Calculation System(BPCS) for an Autonomous Vehicle Stability. The system consists of an image normalization module that processes the front image of a vehicle to fit the input of the random forest, a Random Forest based Road Roughness Classification Module that distinguish the roughness of the road on which the vehicle is travelling by using the weather information and the front image of a vehicle as an input, and a brake pressure control module that modifies a friction coefficient applied to the vehicle according to the road roughness and determines the braking strength to maintain optimal driving according to a vehicle ahead. To verify the efficiency of the BPCS experiment was conducted with a random forest model. The result of the experiment shows that the accuracy of the random forest model was about 2% higher than that of the SVM, and that 7 features should be bagged to make an accurate random forest model. Therefore, the BPCS satisfies both real-time and accuracy in situations where the vehicle needs to brake.

• The Journal of the Korea Contents Association
• /
• v.19 no.10
• /
• pp.341-352
• /
• 2019

Recently, as cultural projects are being carried out in various ways, the interest in the space where culture and arts can be provided is also increasing. Therefore, this study selected and analyzed F1963 in Busan. The purpose of this study is to examine the effects of brand asset factors of brand image, brand awareness, brand asset awareness, and loyalty on customer satisfaction and community development of brand asset in complex cultural space and to examine whether customer satisfaction has a mediating effect on the relationship between brand asset in complex cultural space and community development. As a result of the analysis, brand asset of complex cultural space had a positive effect on the satisfaction of users. Also, brand asset of complex cultural space has a positive effect on community development. The satisfaction that users get from the complex cultural space has a mediating effect on the influence of brand asset of the complex cultural space itself on the community development. The implications of this study suggest that complex cultural space plays an important role in the region, and it is necessary for local communities and local governments to brand complex cultural space through diversity of cultural and artistic activities.

• Journal of the Korean Society of Radiology
• /
• v.16 no.2
• /
• pp.103-113
• /
• 2022

In this paper, a combined ¹⁸F-FDG(fluorodeoxyglucose) and MNP(magnetic nanoparticles) contrast agent was synthesized using N-(p-maleimidophenyl) isocyanate as the crosslinker for use in simultaneous PET-MRI scans. PET-MRI images were acquired and evaluated before and after injection of the combined contrast imaging agent (¹⁸F-FDG labeled MNP) from a glioma stem cell mouse model. After setting the region of interest (ROI) on each acquired image, the area of the lesion was calculated by segmentation. As a result, the PET image was larger than the MRI. In particular, the simultaneous PET-MRI images showed accurate lesions along with the surrounding soft tissue. The mean and standard deviation values were higher in the MRI images alone than in the PET images or the simultaneous PET-MRI images, regardless of whether the contrast agent was injected. In addition, the simultaneous PET-MRI image values were higher than for the PET images. For PSNR experiments, the original image was PET Image using 18F-FDG, MRI using MNPs, and MRI without contrast medium, and the target image was simultaneous PET-MRI image using 18F-FDG labeled MNPs contrast medium. As a result, all of them appeared significantly, suggesting that the 18F-FDG labeled MNPs contrast medium is useful. Future research is needed to develop an agent that can simultaneously diagnose and treat through SPECT-MRI imaging research that can use various nuclides.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.85-92
• /
• 2023

In this paper, we propose a method for automatically generating story-based abbreviated summaries from long-form dramas and movies. From the shooting stage, the basic premise was to compose a frame with illusion of depth considering the golden division as well as focus on the object of interest to focus the viewer's attention in terms of content delivery. To consider how to extract the appropriate frames for this purpose, we utilized elemental techniques that have been utilized in previous work on scene and shot detection, as well as work on identifying focus-related blur. After converting the videos shared on YouTube to frame-by-frame, we divided them into a entire frame and three partial regions for feature extraction, and calculated the results of applying Laplacian operator and FFT to each region to choose the FFT with relative consistency and robustness. By comparing the calculated values for the entire frame with the calculated values for the three regions, the target frames were selected based on the condition that relatively sharp regions could be identified. Based on the selected results, the final frames were extracted by combining the results of an offline change point detection method to ensure the continuity of the frames within the shot, and an edit decision list was constructed to produce an abbreviated summary of 62.77% of the footage with F1-Score of 75.9%

• Tunnel and Underground Space
• /
• v.33 no.4
• /
• pp.281-298
• /
• 2023

Continuous research efforts are being devoted to unmanned mobile platforms for lunar exploration. There is an ongoing demand for real-time information processing to accurately determine the positioning and mapping of areas of interest on the lunar surface. To apply deep learning processing and analysis techniques to practical rovers, research on software integration and optimization is imperative. In this study, a foundational investigation has been conducted on real-time analysis of virtual lunar base construction site images, aimed at automatically quantifying spatial information of key objects. This study involved transitioning from an existing region-based object recognition algorithm to a boundary box-based algorithm, thus enhancing object recognition accuracy and inference speed. To facilitate extensive data-based object matching training, the Batch Hard Triplet Mining technique was introduced, and research was conducted to optimize both training and inference processes. Furthermore, an improved software system for object recognition and identical object matching was integrated, accompanied by the development of visualization software for the automatic matching of identical objects within input images. Leveraging satellite simulative captured video data for training objects and moving object-captured video data for inference, training and inference for identical object matching were successfully executed. The outcomes of this research suggest the feasibility of implementing 3D spatial information based on continuous-capture video data of mobile platforms and utilizing it for positioning objects within regions of interest. As a result, these findings are expected to contribute to the integration of an automated on-site system for video-based construction monitoring and control of significant target objects within future lunar base construction sites.

• Journal of dental hygiene science
• /
• v.13 no.2
• /
• pp.125-134
• /
• 2013

The purpose of this study was to compare between early childhood teachers and mothers in oral health knowledge, oral health care behavior, and perception of oral health education. The subjects in this study were 90 early childhood teachers who worked in all of kindergartens and child-care centers and 235 mothers who have young children (aged from 1 to 5) in 2 kindergartens and 2 childcare centers Y region. They completed questionnaires about oral health knowledges, oral health care behaviors, and perception of oral health education. The collected data was analyzed by descriptive statistics, $x^2$-test, and Fisher's exact test of SPSS WIN. The results were as follows: 1. There was not statistically significant difference between early childhood teacher's knowledge about oral health and mothers'. 2. There was statistically significant difference between early childhood teachers' oral health care behaviors for children and mothers' in prevention of cavity, keeping toothbrushes, guiding oral health behaviors, and check up at dentist's. 3. There was statistically significant difference between early childhood teachers' perception of interest and experience in oral health education and mothers'. Therefore, There was not difference between early childhood teacher's knowledge about oral health and mothers. But early childhood teachers more frequently carry out preventing of cavity, keeping toothbrushes, guiding oral health behavior to their children than mothers. Mothers were more interested in oral health than early childhood teachers. And Mothers wanted to be educated about children' oral care and early childhood teachers wanted to be educated about guidebook and media of oral health education.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.37 no.6
• /
• pp.535-543
• /
• 2019

Recently, growing social interest in alley markets, which have shown rapid growth like Gyeonglidan-gil street in Seoul, has led to the need for an analysis of growth factors. This paper aims at exploring growing alley markets through time-series clustering using DTW (Dynamic Time Warping) and examining the growth factors through logistic regression. According to cluster analysis, the number of growing markets of the Northeast, the Southwest, and the Southeast were much more than the Northwest but the proportion in region of the Northwest, the Northeast, and the Southwest were much more than the Southeast. Logistic regression results show that people in 20s and 30s have a lower impact on sales than those in 50s, but have a greater impact on growth of alley market. Alley markets located in high-income areas often reached their growth limits, indicating a tendency to stagnate or decline. The proximity of a subway station effected positive on sales but negative on growth. This research is an advanced study in that the causes of sales growth of alley markets is examined, which has not been examined in the preceding study.

• Journal of the Korea Computer Graphics Society
• /
• v.28 no.1
• /
• pp.1-9
• /
• 2022

Non-small cell lung cancer (NSCLC) accounts for a high proportion of 85% among all lung cancer and has a significantly higher mortality rate (22.7%) compared to other cancers. Therefore, it is very important to predict the prognosis after surgery in patients with non-small cell lung cancer. In this study, the types of preoperative chest CT image patches for non-small cell lung cancer patients with tumor as a region of interest are diversified into five types according to tumor-related information, and performance of single classifier model, ensemble classifier model with soft-voting method, and ensemble classifier model using 3 input channels for combination of three different patches using pre-trained ResNet and EfficientNet CNN networks are analyzed through misclassification cases and Grad-CAM visualization. As a result of the experiment, the ResNet152 single model and the EfficientNet-b7 single model trained on the peritumoral patch showed accuracy of 87.93% and 81.03%, respectively. In addition, ResNet152 ensemble model using the image, peritumoral, and shape-focused intratumoral patches which were placed in each input channels showed stable performance with an accuracy of 87.93%. Also, EfficientNet-b7 ensemble classifier model with soft-voting method using the image and peritumoral patches showed accuracy of 84.48%.

• Journal of the Korean Institute of Gas
• /
• v.27 no.1
• /
• pp.70-77
• /
• 2023

Air environment regulations have been strengthened due to increasing air pollutant emissions, the target of reducing emissions has increased and interest in gas measurement methods is also increasing. The sampling method is mainly used, but due to the spatial and temporal measurement limitations, the laser absorption spectroscopy which is a real-time and in-situ method is in the spotlight. In this study, we studied the wavelength modulation spectroscopy and described the calibration-free algorithm. The developed algorithm was modified to reflect 46 multi-absorption lines and was applied to light absorption signal analysis in visible and mid-infrared regions. In addition, the difference between the modulation parameters of laser was analyzed. As a result of reviewing the performance through O₂ and NO gas measurement experiments of various concentration conditions, the linearity was R²_O2=0.99999 and R²_NO=0.99967.

• The Korean Journal of Nuclear Medicine Technology
• /
• v.16 no.2
• /
• pp.120-125
• /
• 2012

Purpose : The purpose of this study was to compare count between Chang's method and CT-based attenuation correction (AC-CT) among the attenuation correction (AC) methods for non-attenuation correction (AC-non) images of Brain SPECT (Single Photon Emission Computed Tomography). Materials and Methods : We injected $^{99m}Tc$ 37Mbq in a Hoffman 3D phantom filled with distilled water in the phantom study, and injected intravenously $^{99m}Tc$-HMPAO 740Mbq in a normal volunteer in the patient study, and then obtained Brain SPECT images with Symbia T6 of Siemens and conducted quantitative brain analysis. Transverse images to which each method was applied were rebuilt at the same position, and 6 regions of interest (ROI) were drawn on each of Slice No. 10, 20 and 30 and then the counts of AC-non, AC-CT and Chang's method were compared. Results : The mean counts of AC-non, AC-CT and Chang's method were $4606.8{\pm}511.3$, $16794.6{\pm}2429.4$, and $8752.6{\pm}896.5$, respectively, in the phantom study and $5460.8{\pm}519.6$, $15320{\pm}1171.6$ and $12795{\pm}1422.1$, respectively, in the patient study. In the phantom study, the ratio of AC-CT to AC-non was 3.70 and the ratio of Chang's method to AC-non was 1.92, and in the patient study, they were 2.85 and 2.38, respectively. Conclusion : From this study, we found that AC-CT makes higher AC than Chang's method. In addition, when Chang's method was used, AC in the patient study was higher than that in the phantom study. These results need to be considered also in other examinations.