• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.491-500
• /
• 2021

In this study, we propose a method for detecting fall behavior using MS Kinect v2 RGBD Camera-based Human-Skeleton Keypoints and a 2-Stacked Bi-LSTM model. In previous studies, skeletal information was extracted from RGB images using a deep learning model such as OpenPose, and then recognition was performed using a recurrent neural network model such as LSTM and GRU. The proposed method receives skeletal information directly from the camera, extracts 2 time-series features of acceleration and distance, and then recognizes the fall behavior using the 2-Stacked Bi-LSTM model. The central joint was obtained for the major skeletons such as the shoulder, spine, and pelvis, and the movement acceleration and distance from the floor were proposed as features of the central joint. The extracted features were compared with models such as Stacked LSTM and Bi-LSTM, and improved detection performance compared to existing studies such as GRU and LSTM was demonstrated through experiments.

• Journal of Internet of Things and Convergence
• /
• v.8 no.2
• /
• pp.25-33
• /
• 2022

The purpose of this study is to provide the basic data for establishing a unique admissions promotion strategy for each university and to innovate the paradigm of university admissions promotion through the examples of central universities in the practice of PR promotion based on big data analysis. To this end, prior literature related to university publicity (marketing), and recognition of prospective college students who visited the university, and database data were defined and analyzed as big data. As a result, first, the preliminary studies related to college entrance exam promotion (marketing) increased dramatically in the 2000s and 2010s as part of preparing for countermeasures against population decline in school age. Responding to the need for an admissions promotion strategy to accelerate visits to prospective college students, the database data analysis result suggested the selection and concentration of entrance exam strategies based on the university's regional and academic characteristics.

• Journal of Korean Clinical Nursing Research
• /
• v.27 no.3
• /
• pp.233-244
• /
• 2021

Purpose: The purpose of this study was to investigate the actual utilization of clinical practice guidelines developed by Hospital Nurses Association. Methods: The subjects were 70 nurses who were in charge of guideline distributions in 70 advanced general hospital and general hospitals with 500 beds or more nationwide. Data were collected between June and August, 2020 by mail (return rate: 88.6%). Data were analyzed using descriptive statistics, t-test, and ANOVA with SPSS/WIN 24.0. Results: Among the clinical practice guidelines developed by Hospital Nurses Association, 72.9~90.1% were placed with book and electronic file in nursing department and 24.3~35.8% were placed with book and electronic file in each nursing unit at hospital. The average number of utilized clinical practice guidelines were 3.96±3.88, and average score of guideline utilization was score 2.85±0.79 which means 'use sometimes'. Conclusion: To improve the distribution and utilization of the clinical practice guidelines, it is necessary to enhance the recognition of values of evidence based nursing practice targeting head of nursing department and to stimulate the distribution and utilization of the clinical practice guidelines using diverse education programs for staff nurses.

• Journal of the Korean Society for information Management
• /
• v.38 no.4
• /
• pp.129-152
• /
• 2021

This study proposed a plan to develop wearable devices suitable for female college students by analyzing female college students' perceptions and preferences for wearable devices and their needs for health care using topic modeling and network analysis techniques. To this end, 2,457 posts related to health care and wearable devices were collected from the community used by S Women's University students. After preprocessing the collected posts and comment data, LDA-based topic modeling was performed. Through topic modeling techniques, major issues of female college students related to health care and wearable devices are derived, and bi-gram analysis and network analysis are performed on posts containing related keywords to understand female college students' views on wearable devices.

• Journal of Platform Technology
• /
• v.9 no.4
• /
• pp.3-9
• /
• 2021

In this paper, a graph data model is introduced to effectively recognize the situation between each object on the road detected by vehicles or road infrastructure sensors. The proposed method builds a graph database by modeling each object on the road as a node of the graph and the relationship between objects as an edge of the graph, and updates object properties and edge properties in real time. In this case, the relationship between objects represented as edges is set when there is a possibility of approach between objects in consideration of the position, direction, and speed of each object. Finally, we propose a spatial indexing technique for graph nodes and edges to update the road object graph database represented through the proposed graph modeling method continuously in real time. To show the superiority of the proposed indexing technique, we compare the proposed indexing based database update method to the non-indexing update method through simulation. The results of the simulation show the proposed method outperforms more than 10 times to the non-indexing method.

• Journal of Information Technology Services
• /
• v.20 no.5
• /
• pp.89-104
• /
• 2021

Food delivery service combined with IT technology and HMR (Home Meal Replacement) are rapidly growing due to the COVID-19. Recently, the demand for salads along with HMR has increased among office workers in their 20s and 30s who are interested in health and beauty. Freshcode is a food startup with 6 years of experience that started selling salad products through O2O service. Freshcode applied for a patent for a service that collects orders from nearby areas and delivers them on the same day to a designated delivery address 'FCOSPOT' to save shipping costs. In March 2021, in recognition of the growth potential of the regular delivery service, Freshcode received an investment of 6 billion won in Series A. This study may have practical implications to early-stage startups and scale-up stage startups through a longitudinal case study on the growth of a single company. As for the research method, the lean startup methodology and lean canvas were used in the early stage of startup. In particular, the process of the build-measure and learn feedback-loop, which is the core of lean startup methodology, was applied to each major decision-making step. In the scale-up stage after 5 years, the business model canvas was used to schematize the growth as a food online O2O platform to verify continuous innovation. This case study has three main findings. First, the idea of 'FCOSPOT' was successfully implemented through the Lean Startup methodology. Second, Freshcode demonstrated the scalability of the differentiated business model of shared base delivery O2O. Third, a key factor of success was the digital integrated communication operation strategy that maximizes the experience for the created customers.

• International Journal of Oral Biology
• /
• v.46 no.4
• /
• pp.168-175
• /
• 2021

To investigate the perceptions and attitudes of dental hygienists toward radiation safety management in Korea. A total of 800 dental hygienists were randomly selected for an anonymous survey, and 203 of them participated. The questionnaire items included the following: sex, career period, type of installed radiographic equipment, recognition of the diagnostic reference level (DRL), participation in radiation safety education, and attitudes toward radiation protection for both patients and dental hygienists. The participants were divided into two groups according to their years of experience (< 10 years versus ≥ 10 years). The difference between the groups was investigated according to frequency distribution. Fisher's exact test or Pearson's chi-square (𝛘²) test was used as appropriate. A regression analysis was performed to investigate the impact of wearing a thyroid collar for personnel protection during patient radiation exposure. The types of installed radiographic equipment included panoramic radiography (96.1%), cephalometric radiography (76.9%), intraoral radiography (72.9%), and cone-beam computed tomography (69.5%). Significant differences were observed in the learning pathway for the DRL (Fisher's exact test, p < 0.05), satisfaction with radiation safety education (Pearson's 𝛘² test = 5.3975, Pr = 0.02), and use of personnel radiation monitoring systems (Pearson's 𝛘² test = 18.1233, Pr = 0.000) between the groups. Significant differences were also observed in personnel protection using a thyroid collar and patient protection during panoramic radiography (odds ratio = 14.2). Dental hygienists with more than 10 years of experience were more satisfied with radiation safety education and more interested in radiation monitoring. Considering career experience, customized, continuous, and effective radiation safety management education should be provided.

• Anayses & Alternatives
• /
• v.4 no.2
• /
• pp.103-132
• /
• 2020

The purpose of this study is to observe whether intergenerational differences exist in support among major Korean political parties and, if so, how they exist, based on the results of the survey conducted nationwide. To achieve the purpose of the study, a questionnaire was prepared based on conjoint analysis, and the collected data was analyzed by applying a random parameter logit model. The main results of model analysis are summarized as follows. First, among the policy variables, statistically significant results were observed in the generation of 20s and 30s for the education variable. It was found that both 20s and 30s aimed for equal education at a higher level than other generations. Especially, the highest intensity aim for equal education culture was observed in the 20s. Second, the coefficients of major political parties were observed with a high level of statistical significance. This appears to be a result suggesting that voters decide on their voting behavior through thorough policy comparisons in addition to comprehensive consideration on various current issues. Third, a clear support for conservative parties was observed in the generation of 20s. A clear and intense distribution of preference for political parties classified as conservatives was observed in the 20s generation, which can be said to be mainly college students. This seems to be a profound founding related to the issue of "conservatization of the 20s," which has recently become a hot topic in Korean society. Fourth, a high level of support for progressive parties was observed in the 30s and 40s. The Justice Party can be classified as a minority party in the National Assembly House as of January 2019. Nevertheless, it was maintained at a relatively high level in national recognition, and it is presumed that the background was high level of support from the 30s and 40s. Fifth, a large level of standard deviation was observed in the preference for conservative parties in the 50s. This means that some respondents who are in their 50s or older strongly support the Liberty Korea Party, and some respondents in the same generation strongly disapprove it. Due to this countervailing power, it seems that the average support level for the Liberal Korean Party is low in the generations of 50s and older.?

• Journal of the Society of Disaster Information
• /
• v.18 no.1
• /
• pp.154-162
• /
• 2022

Purpose: The government intends to come up with measures to revitalize safety management at construction sites to shift safety management at construction sites from human capabilities to system-oriented management systems using advanced technologies AIoT and Mobile technologies. Method: The construction site safety management monitoring system using AIoT and Mobile technology conducted an experiment on the effectiveness of the construction site by applying three algorithms: virtual fence, fire monitoring, and recognition of not wearing a safety helmet. Result: The number of workers in the experiment was 215 and 7.61 virtual fence intrusion was 3.5% compared to the number of subjects and 0.16 fire detection were 0.07% compared to the subjects, and the average monthly rate of not wearing a safety helmet was 8.79, 4.05% compared to the subjects. Conclusion: It was found that the construction site safety management monitoring system using AIoT and Mobile technology has a valid effect on the construction site.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.214-227
• /
• 2021

The purpose of this study is to find the driving difficulty of automated vehicles in terms of road infrastructure operation. It was judged out of this study that the level of automated driving would be enhanced if the road situation recognition ability was advanced through the presentation of infrastructure information during the difficult driving situations. The difficulty evaluation index was divided into three stages, and a survey of experts and an AHP were conducted. The result of the AHP showed that the driving difficulty of the interrupted flow was much higher than that of the uninterrupted flow. The AHP results also showed that and the driving difficulty of unsignalized intersections and roundabouts under an interrupted flow was evaluated as the highest. The top six driving situations with high difficulty were also evaluated to occur under unsignalized intersections and roundabouts.