• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.301-310
• /
• 2021

The TATI model is a Traffic Accident Text to RGB Image model, which is a methodology proposed in this paper for predicting the severity of traffic accidents. Traffic fatalities are decreasing every year, but they are among the low in the OECD members. Many studies have been conducted to reduce the death rate of traffic accidents, and among them, studies have been steadily conducted to reduce the incidence and mortality rate by predicting the severity of traffic accidents. In this regard, research has recently been active to predict the severity of traffic accidents by utilizing statistical models and deep learning models. In this paper, traffic accident dataset is converted to color images to predict the severity of traffic accidents, and this is done via CNN models. For performance comparison, we experiment that train the same data and compare the prediction results with the proposed model and other models. Through 10 experiments, we compare the accuracy and error range of four deep learning models. Experimental results show that the accuracy of the proposed model was the highest at 0.85, and the second lowest error range at 0.03 was shown to confirm the superiority of the performance.

• Journal of the Korean Society of Safety
• /
• v.36 no.3
• /
• pp.31-39
• /
• 2021

In Korea, more than half of work-related fatalities have occurred on construction sites. To reduce such occupational accidents, safety inspection by government agencies is essential in construction sites that present a high risk of serious accidents. To address this issue, this study developed risk prediction models of serious accidents in construction sites using five machine learning methods: support vector machine, random forest, XGBoost, LightGBM, and AutoML. To this end, 15 proactive information (e.g., number of stories and period of construction) that are usually available prior to construction were considered and two over-sampling techniques (SMOTE and ADASYN) were used to address the problem of class-imbalanced data. The results showed that all machine learning methods achieved 0.876~0.941 in the F1-score with the adoption of over-sampling techniques. LightGBM with ADASYN yielded the best prediction performance in both the F1-score (0.941) and the area under the ROC curve (0.941). The prediction models revealed four major features: number of stories, period of construction, excavation depth, and height. The prediction models developed in this study can be useful both for government agencies in prioritizing construction sites for safety inspection and for construction companies in establishing pre-construction preventive measures.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.7-14
• /
• 2022

COVID-19 has caused a global disturbance, increased anxiety, and panic, eliciting diverse reactions. While its cure has not been discovered, new infection cases and fatalities are being recorded daily. The focus of the present study was to analyze the reaction of gifted undergraduate students on social media during the quarantine period of the COVID-19. A special group of gifted students, who joined the program of attracting and nurturing talents at the University of Jeddah, University students as were the target sample of this study. To analyze online reactions during the pandemic; the choice of university students was arrived at as they are perceived to be gifted academically. Hence, the analysis of the impacts on their behavior on social media use is imperative. This study presented accurate and consistent data on the effects of social media using Twitter platforms on gifted students during the quarantine occasioned by the COVID-19 pandemic. The behavior of learners due to during the use of social media was extensively explored and results analyzed. The study was carried out between April and May 2020 (quarantine period in Saudi Arabia) to establish whether the online behavior of gifted students reflects positive or negative feelings. The methods used in conducting this study the research were online interviews and scraping participants' Twitter accounts (where most of the online activities and studies take place). The study employed the Activity theory to analyze the behavior of gifted students on social media. The sample size used was 60 students, and the analysis of their behavior was based on Activity theory Overall, the results showed proactive, positive behavior for coping with a challenging situation, educating society, and entertaining. Finally, this study recommends investing in gifted students due to their valuable problem-solving skills that can help handle global pandemics efficiently.

• The Korean Journal of Physiology and Pharmacology
• /
• v.25 no.4
• /
• pp.273-280
• /
• 2021

Lung cancer despite advancement in the medical field continues to be a major threat to human lives and accounts for a high proportion of fatalities caused by cancers globally. The current study investigated vanillin oxime, a derivative of vanillin, against lung cancer cells for development of treatment and explored the mechanism. Cell viability changes by vanillin oxime were measured using MTT assay. Vanillin oxime-mediated apoptosis was detected in A549 and NCI-H2170 cells at 48 h of exposure by flow cytometry. The CEBP homologous protein (CHOP) and death receptor 5 (DR5) levels were analysed by RT-PCR and protein levels by Western blotting. Vanillin oxime in concentration-dependent way suppressed A549 and NCI-H2170 cell viabilities. On exposure to 12.5 and 15 μM concentrations of vanillin oxime elevated Bax, caspase-3, and -9 levels in A549 and NCI-H2170 cells were observed. Vanillin oxime exposure suppressed levels of Bcl-2, survivin, Bcl-xL, cFLIP, and IAPs proteins in A549 and NCI-H2170 cells. It stimulated significant elevation in DR4 and DR5 levels in A549 and NCI-H2170 cells. In A549 and NCI-H2170 cells vanillin oxime exposure caused significant (p < 0.05) enhancement in CHOP and DR5 mRNA expression. Vanillin oxime exposure of A549 and NCI-H2170 cells led to significant (p < 0.05) enhancement in levels of phosphorylated extracellular-signal-regulated kinase and c-Jun N-terminal kinase. Thus, vanillin oxime inhibits pulmonary cell proliferation via induction of apoptosis through tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) mediated pathway. Therefore, vanillin oxime may be studied further to develop a treatment for lung cancer.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.116-124
• /
• 2022

After the death of Min-sik Kim in Asan, South Chungcheong Province in September 2019, awareness of the school zone has been increasing, and the traffic law is being revised continuously. However, despite these efforts, the number of traffic accidents among children has not decreased significantly. This indicates the need for a new direction considering the behavioral characteristics of children and the traffic environment. Therefore, this study identified the current status and problems of school zones through case analysis of school zones in Korea. In addition, we analyzed the Vision Zero policy, the concept of Home Zone, and engineering-oriented road design cases and operation methods in Sweden, an advanced country in traffic safety. In addition, the cases of the two countries were compared and organized focusing on the basic principles of disaster prevention design. The purpose of this study is to suggest the direction of design and policy to improve school zone problems in Korea. Through this, it is expected that the results of this study will be used as data for future research development for the reduction of school zone fatalities in Korea.

• Journal of Digital Convergence
• /
• v.20 no.5
• /
• pp.39-46
• /
• 2022

As the link between traffic accidents and social and economic losses has been confirmed, there is a growing interest in developing safety policies based on crash data and a need for countermeasures to reduce severe crash outcomes such as severe injuries and fatalities. In this study, we select Daejeon city where the relative proportion of fatal crashes is high, as a case study region and focus on the severity of pedestrian crashes. After a series of data manipulation process, we run machine learning algorithms for the optimal model selection and variable identification. Of nine algorithms applied, AdaBoost and Random Forest (ensemble based ones) outperform others in terms of performance metrics. Based on the results, we identify major influential factors (i.e., the age of pedestrian as 70s or 20s, pedestrian crossing) on pedestrian crashes in Daejeon, and suggest them as measures for reducing severe outcomes.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.4
• /
• pp.210-219
• /
• 2023

The decline in the rural populace and an aging workforce have led to fatalities due to worsening environments and hazards within vinyl greenhouses. Therefore, it is necessary to automate crop cultivation and disease detection system in greenhouses to prevent labor loss. In this paper, an object detection-based model is used to detect diseased crop in greenhouses. In addition, the system proposed configures the environment of the artificial intelligence model in the cloud to ensure stability. The system captures images taken inside the vinyl greenhouse and stores them in a database, and then downloads the images to the cloud to perform inference based on Yolo-v4 for detection, generating JSON files for the results. Analyze this file and send it to the database for storage. From the experimental results, it was confirmed that disease detection through object detection showed high performance in real environments like vinyl greenhouses. It was also verified that efficient monitoring is possible through the database

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.5
• /
• pp.17-28
• /
• 2023

Potholes that occur on paved roads can have fatal consequences for vehicles traveling at high speeds and may even lead to fatalities. While manual detection of potholes using human labor is commonly used to prevent pothole-related accidents, it is economically and temporally inefficient due to the exposure of workers on the road and the difficulty in predicting potholes in certain categories. Therefore, completely preventing potholes is nearly impossible, and even preventing their formation is limited due to the influence of ground conditions closely related to road environments. Additionally, labeling work guided by experts is required for dataset construction. Thus, in this paper, we utilized the Mean Teacher technique, one of the semi-supervised learning-based knowledge distillation methods, to achieve robust performance in pothole image classification even with limited labeled data. We demonstrated this using performance metrics and GradCAM, showing that when using semi-supervised learning, 15 pre-trained CNN models achieved an average accuracy of 90.41%, with a minimum of 2% and a maximum of 9% performance difference compared to supervised learning.

• Journal of Preventive Medicine and Public Health
• /
• v.56 no.3
• /
• pp.231-237
• /
• 2023

Objectives: This study aimed to identify risk factors associated with coronavirus disease 2019 (COVID-19) mortality in pre-elderly and elderly individuals in Jakarta, Indonesia. Methods: We employed a case-control study design, utilizing secondary data from the Epidemiology Surveillance, Immunization Prevention, and Disease Control Sections of the DKI Jakarta Provincial Health Office, collected from December 2020 to January 2021. The study included 188 cases and an equal number of controls. Cases were COVID-19 patients confirmed to have died, as reported by hospitals and communities and subsequently verified by healthcare workers. Control subjects were patients who completed a 14-day isolation period and had been officially declared recovered by healthcare professionals. The dependent variable was the mortality of COVID-19 patients in the January 2021 period. The independent variables consisted of demographic data (age and sex), clinical symptoms (cough, runny nose, anosmia, diarrhea, headaches, abdominal pain, muscle pain, and nausea/vomiting), and comorbidities (hypertension, heart disease, and diabetes). Multivariate analysis was conducted using multiple logistic regression. Results: The multiple logistic regression analysis revealed several factors associated with COVID-19 fatalities in Jakarta: age of 60 years or older (odds ratio [OR], 4.84; 95% CI, 3.00 to 7.80), male (OR, 2.38; 95% CI, 2.41 to 3.68), dyspnea (OR, 3.93; 95% CI, 2.04 to 7.55), anosmia (OR, 0.13; 95% CI, 0.04 to 0.46), and heart disease (OR, 4.38; 95% CI, 1.04 to 18.46). Conclusions: The control and prevention of COVID-19 among elderly individuals require particular vigilance. When a COVID-19 case is detected within this demographic, prompt treatment and medication administration are crucial to mitigate the presenting symptoms.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.43 no.4
• /
• pp.477-484
• /
• 2023

The number and age of elderly drivers are continuously increasing according to the extension of the human lifespan. Therefore, in transportation, efforts are being made to differentiate and manage elderly drivers by age group. This study aims to identify the factors affecting the crash severity of early and late elderly drivers, compared to middle-aged drivers, and to identify the characteristics between these groups. Crash data that occurred on nationwide roads for the past 5 years (2017-2021) was applied. Unlike previous studies, this study only targeted drivers in their 40s and older, when presbyopia begins: middle-aged driver (40-64), early elderly driver (65-74), and late elderly driver (75+). As a result of logistic regression analysis, a total of 18 variables were found to affect serious injuries including fatalities in early and late elderly drivers. Most of these variables appeared to lead to severity more sensitively in the late elderly group. The results of this study are expected to be useful as basic information for establishing traffic safety policies for elderly drivers in the future.