• Journal of Digital Convergence
• /
• v.19 no.4
• /
• pp.25-31
• /
• 2021

Moving toward an aged society, traffic accidents involving elderly drivers have also attracted broader public attention. A rapid increase of senior involvement in crashes calls for developing appropriate crash-severity prediction models specific to senior drivers. In that regard, this study leverages machine learning (ML) algorithms so as to predict the severity of vehicle-pedestrian collisions induced by elderly drivers. Specifically, four ML algorithms (i.e., Logistic model, K-nearest Neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM)) have been developed and compared. Our results show that Logistic model and SVM have outperformed their rivals in terms of the overall prediction accuracy, while precision measure exhibits in favor of RF. We also clarify that driver education and technology development would be effective countermeasures against severity risks of senior driver-induced collisions. These allow us to support informed decision making for policymakers to enhance public safety.

• Journal of Trauma and Injury
• /
• v.34 no.2
• /
• pp.87-97
• /
• 2021

Purpose: This study examined emergency medical service (EMS) transportation patterns for adult trauma patients before and after establishing a level 1 regional trauma center (RTC) and to evaluate the transportation approach after prehospital severity screening. Methods: This was a retrospective observational study of trauma patients aged ≥18 years admitted via EMS to the emergency department or a level 1 RTC, 1 year before to 3 years after RTC establishment. Patients with an Injury Severity Score (ISS) in the patient registration system were selected. Analyses were performed to determine transportation pattern changes by comparing patients pre- and post-RTC establishment and by yearly comparisons over the 4-year study period using the Mann-Whitney U test and chi-square test. Results: Overall, 3,587 patients were included. The mean ISS was higher in the post-RTC group (n=2,693; 10.63±8.90, median 9.00) than in the pre-RTC group (n=894; 9.44±8.20, median 8.00; p<0.001). The mean transportation distance (9.84±13.71, median 5.80 vs. 13.12±16.15 km, median 6.00; p<0.001) was longer in the post-RTC group than in the pre-RTC group. Furthermore, proportionally fewer patients were transported from an area in the same city as the RTC after establishment (86.1% vs. 78.3%; p<0.001). Yearly comparisons revealed a gradually increasing trend in the hospital death rate (ptrend=0.031). Conclusions: After establishing a level 1 RTC, the EMS transportation of severe trauma patients increased gradually along with the long-distance transportation of minor trauma patients. Therefore, improved prehospital EMS trauma severity assessments and level 1 RTC involvement in patient classification in the prehospital phase are necessary.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.1123-1130
• /
• 2020

This study aims to classify the severity in car crashes using five classification learning models. The dataset used in this study contains 21,013 vehicle crashes, obtained from Korea Expressway Corporation, between the year of 2015-2017 and the LightGBM(Light Gradient Boosting Model) performed well with the highest accuracy. LightGBM, the number of involved vehicles, type of accident, incident location, incident lane type, types of accidents, types of vehicles involved in accidents were shown as priority factors. Based on the results of this model, the establishment of a management strategy for response of highway traffic accident should be presented through a consistent prediction process of accident severity level. This study identifies applicability of Machine Learning Models for Predicting of the Severity of Car Traffic Accidents on a Highway and suggests that various machine learning techniques based on big data that can be used in the future.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.4
• /
• pp.1-10
• /
• 2022

Attempts to interpret human perspectives using computer vision have been developed in various fields. In this paper, we propose a method for evaluating the walking environment through semantic segmentation results of images from road images. First, the Kakao Map API was used to collect road images, and four-way images were collected from about 50,000 points in JeonJu. 20% of the collected images build datasets through crowdsourcing-based paired comparisons, and train various regression models using paired comparison data. In order to derive the walkability score of the image data, the ranking score is calculated using the Trueskill algorithm, which is a ranking algorithm, and the walkability and analysis using various regression models are performed using the constructed data. Through this study, it is shown that the walkability of Jeonju can be evaluated and scores can be derived through the correlation between pixel distribution classification information rather than human vision.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.1
• /
• pp.85-94
• /
• 2022

Recently, consumers who prefer contactless consumption are increasing due to pandemic trends such as Corona 19. This is the driving force for developing the last mile-based logistics ecosystem centered on the online e-commerce market. Lastmile led to the continued development of the logistics industry, but increased the amount of cargo in urban area, and caused social problems such as overcrowding of logistics. The courier service in the logistics base area utilizes the process of visiting the delivery site directly because the courier must precede the loading work of the cargo in the truck for the delivery of the ordered product. Currently, it's carried out as automated logistics equipment such as conveyor belt in unloading or classification stage, but the automation system isn't applied, so the work efficiency is decreasing and the intensity of the courier worker's labor is increased. In particular, small-scale courier workers belonging to the sub-terminal unload at night at underdeveloped facilities outside the city center. Therefore, the productivity of the work is lowered and the risk of safety accidents is exposed, so robot-based loading technology is needed. In this paper, we have derived the top-level concept and requirements of robot-based loading system to increase the flexibility of logistics processing and to ensure the safety of courier drivers. We defined algorithms and motion concepts to increase the cargo loading efficiency of logistics sub-terminals through the requirements of end effector technology, which is important among concepts. Finally, the control technique was proposed to determine and position the load for design input development of the automatic conveyor system.

• Journal of Cadastre & Land InformatiX
• /
• v.52 no.1
• /
• pp.37-55
• /
• 2022

This study presents the plans to derive quality items for develop the data quality standard for ensuring the quality of 3D building geospatial data in NDT(National Digital Twin). This paper is organized as follows. The first section briefly examines various factors that impact the quality of 3D geospatial data, and proposes the role and necessity of the data quality standard as a means of addressing the data errors properly and also meeting the minimum requirements of stakeholders. The second section analyzes the relationship between the standards - building data model for NDT and ISO 19157: Geospatial data quality - in order to consider directly relevant standards. Finally, we suggest three plans on developing NDT data quality standard: (1) the scope for evaluating data quality, (2) additional quality elements(geometric integrity, geometric fidelity, positional accuracy and semantic classification accuracy), and (3) NDT data quality items model based on ISO 19157. The plans reveled through the study would contribute to establish a way for the national standard on NDT data quality as well as the other standards associated with NDT over the coming years.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.185-195
• /
• 2022

Deep learning is another field of artificial intelligence (AI) utilized for computer aided diagnosis (CAD) and image processing in scientific research. Considering numerous mechanical repetitive tasks, reading image slices need time and improper with geographical limits, so the counting of image information is hard due to its strong subjectivity that raise the error ratio in misdiagnosis. Regarding the highest mortality rate of Lung cancer, there is a need for biopsy for determining its class for additional treatment. Deep learning has recently given strong tools in diagnose of lung cancer and making therapeutic regimen. However, identifying the pathological lung cancer's class by CT images in beginning phase because of the absence of powerful AI models and public training data set is difficult. Convolutional Neural Network (CNN) was proposed with its essential function in recognizing the pathological CT images. 472 patients subjected to staging FDG-PET/CT were selected in 2 months prior to surgery or biopsy. CNN was developed and showed the accuracy of 87%, 69%, and 69% in training, validation, and test sets, respectively, for T1-T2 and T3-T4 lung cancer classification. Subsequently, CNN (or deep learning) could improve the CT images' data set, indicating that the application of classifiers is adequate to accomplish better exactness in distinguishing pathological CT images that performs better than few deep learning models, such as ResNet-34, Alex Net, and Dense Net with or without Soft max weights.

• Fashion & Textile Research Journal
• /
• v.25 no.4
• /
• pp.460-471
• /
• 2023

This study aimed to analyze the consumption value and clothing pursuit benefits of genderless fashion based on gender identity. The study questionnaire was distributed to and collected from men and women in their 20s and 30s living in Seoul City and the Gyeonggi province. The collected data were analyzed by using Cronbachs α, factor analysis, K-means group classification analysis, and ANOVA. The study results were as follows. First, gender identity was categorized into three groups: the genderless group, the traditional gender rejection group, and the traditional gender acceptance group. Therefore, it is necessary to subdivide gender identity rather than acceptance and rejection of traditional gender roles. Second, an analysis of consumption value based on gender identity showed significant differences in terms of fashion value and expressive value. Therefore, it is important to establish a differentiated strategy based on the relevant gender identity group when establishing genderless fashion design or marketing strategy. Finally, the study results showed that clothing pursuit benefits based on gender identity, there was a significant difference in terms of individuality pursuit, deviation from the norm, and fashion pursuit. In particular, since the genderless phenomenon agrees with the characteristics of the MZ generation, it will be necessary to share brand information or product information through digital media or to utilize a sharing culture-that is, 'meaning out' tendency and 'flex culture' (i.e., conspicuous consumption).

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.2C
• /
• pp.59-69
• /
• 2009

Based on the data obtained from field investigation and soil testing to slope hazards occurrence section and non-occurrence section in crystalline rocks like gneiss, granite, and so on, a prediction model was developed by the use of a decision tree model. The classification standard of the selected prediction model is composed of the slope angle, the coefficient of permeability and the void ratio in the order. The computer program, SHAPP ver. 1.0 for prediction of slope hazards around an important national facilities using GIS technique and the developed model. To prove the developed prediction model and the computer program, the field data surveyed from Jumunjin, Gangneung city were compared with the prediction result in the same site. As the result of comparison, the real occurrence location of slope hazards was similar to the predicted section. Through the continuous study, the accuracy about prediction result of slope hazards will be upgraded and the computer program will be commonly used in practical.

• Journal of radiological science and technology
• /
• v.46 no.6
• /
• pp.553-560
• /
• 2023

This study aimed to understand the correlations of prevalence and relevant variables of cholelithiasis with a group of cirrhosis patients and a control group targeting the subjects who received the abdomen ultrasonography from K university hospital in Daejeon Metropolitan City from January 1^st 2019 to December 31^st. And the results are as follows. First, the group of cirrhosis patients showed relatively higher prevalence of cholelithiasis than the control group as ordinary people, which showed statistically significant differences. Second, in the control group, there were statistically significant differences in the occurrence of cholelithiasis with respect to age. Conversely, in the cirrhosis patient, there was no statistically significant association observed with age; nonetheless, age itself exhibited statistical significance. Third, according to sex, the prevalence was not statistically significant in both group of cirrhosis patients and control group. Fourth, in each degree and cause of subdivided cirrhosis, the correlation was only shown in each degree. In the results of this study, the cirrhosis patients showed high correlation with the incidence of cholelithiasis, and the control group showed the high correlation with the incidence of cholelithiasis according to age.