• 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.

• Health Policy and Management
• /
• v.31 no.2
• /
• pp.173-179
• /
• 2021

Background: In Korea, the length of stay and medical expenses incurred by medical aid patients are increasing at a rate faster than the national health insurance. Therefore, there is a need to create a management strategy for each type of hospitalization to manage the length of stay of medical aid patients. Methods: The study used data from the 2019 National Health Insurance Claims. We analyzed the factors that affect the length of stay for 186,576 medical aid patients who were hospitalized for more than 31 days, with a focus on the type of hospitalization in long-term care hospitals. Results: The study found a significant correlation between gender, age, medical aid type, chronic disease ratio, long-term care hospital patient classification, and hospitalization type variables as factors that affect the length of hospital stay. The analysis of the differences in the length of stay for each type of hospitalization showed that the average length of stay is 291.4 days for type 1, 192.9 days for type 2, and 157.0 days for type 3, and that the difference is significant (p<0.0001). When type 3 was 0, type 1 significantly increased by 99.4 days, and type 2 by 36.6 days (p<0.0001). Conclusion: A model that can comprehensively view factors, such as provider factors and institutional factors, needs to be designed. In addition, to reduce long stays for medical aid patients, a mechanism to establish an early discharge plan should be prepared and concerns about underutilization should be simultaneously addressed.

• 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.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.215-229
• /
• 2020

The interest in machine learning is growing in all industries, but it is difficult to apply it to real-world tasks because of inexplicability. This paper introduces a case of developing a financial customer churn prediction model for a securities company, and introduces the research results on an attempt to develop a machine learning model that can be explained using the SHAP Value methodology and derivation of interpretability. In this study, a total of six customer churn models are compared and analyzed, and the cause of customer churn is inferred through the classification and data analysis of SHAP Value and the type of customer asset change. Based on the results of this study, it would be possible to use it as a basis for comprehensive judgment, such as using the Value of the deviation prediction result that can infer the cause of the marketing manager's actual customer marketing in the future and establishing a target marketing strategy for each customer.

• The Journal of Information Systems
• /
• v.31 no.1
• /
• pp.59-90
• /
• 2022

Purpose This paper presents a new method of classifying online platforms. It also explains how to apply the framework using case studies and generate new insight about platform strategies and policy development. Design/methodology/approach This paper focuses on the relationship between platforms, especially the hierarchy and power relations, and broadly classifies platforms as follows: content/services, meta information, app stores, operating systems, and cloud. Both the content/service platform and the meta information platform have matching as their main function. However, most content/services tend to collect and access information through meta-information platforms, so meta-information platforms are closer to infrastructure than content/service platforms. App store, operating system, and cloud can be said to be platforms of platforms. A small number of companies in the US and China dominate platforms of platforms, and become the recent development and regulatory targets of their respective governments. Findings We should be wary of the attempts to regulate domestic platforms by importing foreign regulations that ignore the hierarchical structure that our framework highlights. We believe that Korea's strategy to become a true platform powerhouse is clear. As one of the few countries with significant companies in the area of meta information platforms, it will be necessary to fully utilize the position and advance into the strategically important area of platforms of platforms. Furthermore, it is necessary to encourage world-class companies to appear in Korea in the app store, operating system, and cloud. To do so, the government needs to introduce promotion policies to strategically nurture such platforms rather than to regulate them.

• Journal of Industrial Convergence
• /
• v.20 no.7
• /
• pp.1-11
• /
• 2022

In this paper, numerical values are derived using topic modeling among data-based evaluation methodologies discussed by various research institutes. In addition, we will focus on the ICT field to see if there is a difference in policy perception between the national R&D project and standing committee. First, we create model for classifying ICT documents by learning R&D project data using HAN model. And we perform LDA topic modeling analysis on ICT documents classified by applying the model, compare the distribution with the topics derived from the R&D project data and proceedings of standing committees. Specifically, a total of 26 topics were derived. Also, R&D project data had professionally topics, and the standing committee-discuss relatively social and popular issues. As the difference in perception can be numerically confirmed, it can be used as a basic study on indicators that can be used for future policy or project evaluation.

• Journal of Preventive Medicine and Public Health
• /
• v.55 no.1
• /
• pp.10-18
• /
• 2022

Disability-adjusted life-year (DALY) estimates may vary according to factors such as the standard life expectancy, age weighting, time preference and discount rate, calculation of disability weights, and selection of the estimation method. DALY estimation methods are divided into the following 3 approaches: the incidence-based approach, the pure prevalence-based approach, and the hybrid approach. These 3 DALY estimation approaches each reflect different perspectives on the burden of disease using unique characteristics, based on which the selection of a suitable approach may vary by the purpose of the study. The Global Burden of Disease studies, which previously estimated DALYs using the incidence-based approach, switched to using the hybrid approach in 2010, while the National Burden of Disease studies in Korea still mainly apply the incidence-based approach. In order to increase comparability with other international burden of disease studies, more DALY studies using the prevalence-based approach need to be conducted in Korea. However, with the limitations of the hybrid approach in mind, it is necessary to conduct more research using a disease classification system suitable for Korea. Furthermore, more detailed and valid data sources should be established before conducting studies using a broader variety of DALY estimation approaches. This review study will help researchers on burden of disease use an appropriate DALY estimation approach and will contribute to enhancing researchers' ability to critically interpret burden of disease studies.

• The Journal of Korean Physical Therapy
• /
• v.33 no.1
• /
• pp.7-15
• /
• 2021

Purpose: This study was examined to improve the standing posture of a scoliosis client using the ICF Tool. Methods: For examination, the study subject was a 16-year-old female student diagnosed with 3curve-pelvic (3CP) type scoliosis. Information about her were collected through a client interview and based on international Classification of Functioning, Disability and Health (ICF). The ICF core set was for post-acute musculoskeletal conditions, and the ICF level 2 items suggested by National Rehabilitation Information Center (NARIC) were added to the recommendations for scoliosis. For evaluation, the ICF assessment sheet was used to identify the interaction among the problems. For the diagnosis, the client's functional problems were described in ICF terms. For the prognosis, the global goals for reaching the client's functional activity and participation level were presented as the long-and short-term goals. For the intervention, a coordinative locomotor training program composed of warm-up, main exercise, and cool-down was applied 3 times a week, 50 minutes a day, for 5 weeks. For the outcome, the differences between before and after the intervention were compared with the ICF qualifier and are shown with the ICF evaluation display. Results: Clinical advantages were observed in body function and structure (7° decrease of thoracic angle, 7 score increase of trunk muscle power, 6.47s improve of one leg standing, 4 score decrease of neck pain). The activity for maintaining the standing posture, in which the client had a primary limitation, was improved. Conclusion: Applying the coordinative locomotor training program is expected to improve scoliosis client's standing posture.

• Journal of Animal Science and Technology
• /
• v.63 no.6
• /
• pp.1453-1463
• /
• 2021

Feeding is the most important behavior that represents the health and welfare of weanling pigs. The early detection of feed refusal is crucial for the control of disease in the initial stages and the detection of empty feeders for adding feed in a timely manner. This paper proposes a real-time technique for the detection and recognition of small pigs using a deep-leaning-based method. The proposed model focuses on detecting pigs on a feeder in a feeding position. Conventional methods detect pigs and then classify them into different behavior gestures. In contrast, in the proposed method, these two tasks are combined into a single process to detect only feeding behavior to increase the speed of detection. Considering the significant differences between pig behaviors at different sizes, adaptive adjustments are introduced into a you-only-look-once (YOLO) model, including an angle optimization strategy between the head and body for detecting a head in a feeder. According to experimental results, this method can detect the feeding behavior of pigs and screen non-feeding positions with 95.66%, 94.22%, and 96.56% average precision (AP) at an intersection over union (IoU) threshold of 0.5 for YOLOv3, YOLOv4, and an additional layer and with the proposed activation function, respectively. Drinking behavior was detected with 86.86%, 89.16%, and 86.41% AP at a 0.5 IoU threshold for YOLOv3, YOLOv4, and the proposed activation function, respectively. In terms of detection and classification, the results of our study demonstrate that the proposed method yields higher precision and recall compared to conventional methods.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.20 no.4
• /
• pp.489-500
• /
• 2022

The decommissioning of nuclear facilities produces various types of radiologically contaminated waste. In addition, dismantlement activities, including cutting, packing, and clean-up at the facility site, result in secondary radioactive waste such as filters, resin, plastic, and clothing. Determining of the radionuclide content of this waste is an important step for the determination of a suitable management strategy including classification and disposal. In this work, we radiochemically characterized the radionuclide activities of filters used during the decommissioning of Korea Research Reactors (KRRs) 1 and 2. The results indicate that the filter samples contained mainly ³H (500-3,600 Bq·g^-1), ¹⁴C (7.5-29 Bq·g^-1), ⁵⁵Fe (1.1- 7.1 Bq·g^-1), ⁵⁹Ni (0.60-1.0 Bq·g^-1), ⁶⁰Co (0.74-70 Bq·g^-1), ⁶³Ni (0.60-94 Bq·g^-1), ⁹⁰Sr (0.25-5.0 Bq·g^-1), ¹³⁷Cs (0.64-8.7 Bq·g^-1), and ¹⁵²Eu (0.19-2.9) Bq·g^-1. In addition, the gross alpha radioactivity of the samples was measured to be between 0.32-1.1 Bq·g^-1. The radionuclide concentrations were below the concentration limit stated in the low- and intermediatelevel waste acceptance criteria of the Nuclear Safety and Security Commission, and used for the disposal of the KRRs waste drums to a repository site.