• Journal of the Korea Society of Computer and Information
• /
• v.25 no.4
• /
• pp.165-172
• /
• 2020

In this paper we propose an uses on-device-based edge computing technology and big data analysis methods through the use of on-device-based edge computing technology and analysis of big data, which are distributed computing paradigms that introduce computations and storage devices where necessary to solve problems such as transmission delays that occur when data is transmitted to central centers and processed in current general smart factories. However, even if edge computing-based technology is applied in practice, the increase in devices on the network edge will result in large amounts of data being transferred to the data center, resulting in the network band reaching its limits, which, despite the improvement of network technology, does not guarantee acceptable transfer speeds and response times, which are critical requirements for many applications. It provides the basis for developing into an AI-based facility prediction conservation analysis tool that can apply deep learning suitable for big data in the future by supporting intelligent facility management that can support productivity growth through research that can be applied to the field of facility preservation and smart factory industry with integrated hardware technology that can accommodate these requirements and factory management and control technology.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.30-37
• /
• 2018

The social media data and the broadcasting data related to onion as well as agri-food consumer panel data were collected and investigated if the amount of money spent to purchase onion in year 2014 when onion price plunged latest were correlated with the frequencies of onion-related keywords in the social media data and the broadcasting programs because onion price in year 2018 is expected to plunge due to overproduction and there has been needs to analyze impacts of social media and broadcasting program on onion purchase in the previous similar events, and identify potential factors that can promote onion consumption in advance. What we identified from our study include a) broadcasting news programs mentioning words "onion," were correlated with onion purchase with 3 - 6 weeks in advance; b) broadcasting entertainment programs mentioning words "onion and health," were correlated with onion purchase with 11 weeks in advance; c) blog mentioning words "onion and efficacy," were correlated with onion purchase with 5 weeks in advance. Our study provided a case on how social media and broadcasting programs could be analyzed for their effects on consumer purchase behavior using big data collection and analysis in the field of agriculture. We propose to use the findings from the study may be applied to promote onion consumption.

• Korean Journal of Food Science and Technology
• /
• v.51 no.2
• /
• pp.176-181
• /
• 2019

The aim of this study was to analyze dieting practices and tendencies in 2016 using big data. The keywords related to diet were collected from the portal site Naver and analyzed through simple frequency, N-gram, keyword network, and analysis of seasonality. The results showed that exercise had the highest frequency in simple frequency analysis. However, diet menu appeared most frequently in N-gram analysis. In addition, analysis of seasonality showed that the interest of subjects in diet increased steadily from February to July and peaked in October 2016. The monthly frequency of the keyword highfat diet was highest in October, because that showed the 'Low Carbohydrate High Fat' TV program. Although diet showed a certain pattern on a yearly basis, the emergence of new trendy diets in mass media also affects the pattern of diet. Therefore, it is considered that continuous monitoring and analysis of diet is needed rather than periodic monitoring.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.34-48
• /
• 2019

The purpose of this study was two-fold; first, to develop safety performance functions (SPF) using transportation-related big data for all types of roads in Korea were developed, Second, to provide basic information to develop measures for relatively dangerous roads by evaluating the safety grade for various roads based on it. The coordinates of traffic accident data are used to match roads across the country based on the national standard node and link system. As independent variables, this study effort uses link length, the number of traffic volume data from ViewT established by the Korea Transport Research Institute, and the number of dangerous driving behaviors based on the digital tachograph system installed on commercial vehicles. Based on the methodology and result of analysis used in this study, it is expected that the transportation safety improvement projects can be properly selected, and the effects can be clearly monitored and quantified.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.432-438
• /
• 2021

This dissertation's object is to confirm the drastic popularity of La Peste of Albert Camus in Korea post-corona society using big data as the mean of inductive research. Analyzing news articles concerning Camus and investigating word frequency of the book La Peste will affirm the implications La Peste has on current Korea society as the outbreak spreads. As an analysis tool, Bigkinds of Korea Press Foundation and Nuagedemots, the French version of Word Cloud were used. For the past 30 years, Albert Camus has been known in Korea as the writer of L'étranger, but after the epidemic, he earned more reputation with La Peste. Compared to L'étranger that rebelled against the world's absurdity with ennui, La peste emphasizes the importance of resistance accompanied by solidarity. La peste conveys hope by depicting disastrous situations of citizens who confront the plague by organizing a health college. The novel delivers a lot of ethical inspiration to humanity in this exceptional circumstance of COVID-19.

• Journal of Korea Foundry Society
• /
• v.41 no.6
• /
• pp.550-557
• /
• 2021

With the advent of the fourth industrial revolution, the interest in the internet of things (IoT) in manufacturing is growing, even at foundries. There are several types of process data that can be automatically collected at a foundry, but considerable amounts of process data are still managed based on handwriting for reasons such as the limited functions of outdated production facilities and process design based on operator know-how. In particular, despite recognizing the importance of converting process data into big data, many companies have difficulty adopting these steps willingly due to the burden of system construction costs. In this study, the field applicability of IoT-based devices was examined by manufacturing devices and applying them directly to the site of a centrifugal foundry. For the centrifugal casting process, the temperature and humidity of the working site, the molten metal temperature, and mold rotation speed were selected as process parameters to be collected. The sensors were selected in consideration of the detailed product specifications and cost required for each process parameter, and the circuit was configured using a NodeMCU board capable of wireless communication for IoT-based devices. After designing the circuit, PCB boards were prepared for each parameter, and each device was installed on site considering the working environment. After the on-site installation process, it was confirmed that the level of satisfaction with the safety of the workers and the efficiency of process management increased. Also, it is expected that it will be possible to link process data and quality data in the future, if process parameters are continuously collected. The IoT-based device designed in this study has adequate reliability at a low cast, meaning that the application of this technique can be considered as a cornerstone of data collecting at foundries.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.3
• /
• pp.268-278
• /
• 2022

Objectives: This study aimed to establish a control group based on the big data from National Health Insurance Service. We also presented presented the number of incidences for each cancer, and analyzed the cancer incidence rate among Korean workers. Methods: The cohort definition was separated by 'baseline cohort', 'dynamic cohort', and 'fixed- industry cohort' according to the definition. Cancer incidence was calculated based on the Korean Standard Classification of Disease code. Incidence rate was calculated among the group of all workers and public officials. Based on the study subjects and each cohort definition, the number of observations, incidences, and the incidence rate according to sex and age groups was calculated. The incidence rate was estimated based on the incidence per 100,000 person-year, and 95% confidence intervals calculated according to the Poisson distribution. Results: The result shows that the number of cancer cases in the all-worker group decreases after the age of 55, but the incidence rate tends to increase, which is attributed to the retirement of workers over 55 years old. Despite the specific characteristics of the workers, the trend and figures of cancer incidence revealed in this study are similar to those reported in previous studies of the overall South Korean population. When comparing the incidence rates of all workers and the control group of public officials, the incidence rate of public officials is generally observed to be higher in the age group under the age of 55. On the other hand, for workers aged 60 or older, the incidence rates were 1,065.4 per 100,000 person-year for all workers and 1,023.7 per 100,000 person-year for civil servants. Conclusions: This study analyzed through health insurance data including all workers in Korea, and analyzed the incidence of cancer of workers by sex and age. In addition, further in-depth researches are needed to determine the incidence of cancer by industry.

• Journal of the Society of Disaster Information
• /
• v.18 no.4
• /
• pp.687-698
• /
• 2022

Purpose: This study was conducted to understand the public awareness of landslide and check dams in 2015-2020 using the big data platform 'Hyean' and to confirm the utilization of this platform in disaster prevention areas. Method: The total amount, number of detection by period by media, and affirmative and negative trends of a search for 'landslide' and 'check dam' in 2015-2020 were analyzed using a keyword search of 'Hyean.' Result: There is significant lack of public awareness of check dam compared to landslide, and the trend is more noticeable in the conspicuous gap of data amount between the news and SNS media. The number and the timing of the search for 'landslide' coincided with the actual occurrence of landslide, while the detection of 'check dam' was less related to it. Relatively affirmative preception for the check dam is inferred, but it was difficult to confirm accurate statistical affirmative and negative trends in the disaster prevention field using 'Hyean.' Conclusion: Unlike the experts who expect positive public awareness of check dam, the statistic results show that the public awareness of the check dam as an effective countermeasure against landslide was extremely low. Active promotion of erosion control projects should be carried out first, and a balanced sample survey should accompany online and periodic field surveys. Since there is a limit to grasping the effective perception in the field of disaster prevention area using 'Hyean', it should be very cautious to establish local/governmental policies using it.

• Journal of Korean Dental Hygiene Science
• /
• v.6 no.1
• /
• pp.13-25
• /
• 2023

Background: This study was conducted to confirm the service quality management of care workers, who are direct service personnel of long-term care insurance for the elderly, using unstructured big data. Methods: Using a textome, this study collected and analyzed unstructured social data related to care workers' service quality. Frequency, TF-IDF, centrality, semantic network, and CONCOR analyses were conducted on the top 50 keywords collected by crawling the data. Results: As a result of frequency analysis, the top-ranked keywords were 'Long-term care services,' 'Care workers,' 'Quality of care services,' 'Long term care,' 'Long term care facilities,' 'Enhancement,' 'Elderly,' 'Treatment,' 'Improvement,' and 'Necessity.' The results of degree centrality and eigenvector centrality were almost the same as those of the frequency analysis. As a result of the CONCOR analysis, it was found that the improvement in the quality of long-term care services, the operation of the long-term care services, the long-term care services system, and the perception of the psychological aspects of the care workers were of high concern. Conclusion: This study contributes to setting various directions for improving the service quality of care workers by presenting perceptions related to the service quality of care workers as a meaningful group.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.17-25
• /
• 2023

In this paper, we propose a model that can perform human pose estimation through a MobileViT-based model with fewer parameters and faster estimation. The based model demonstrates lightweight performance through a structure that combines features of convolutional neural networks with features of Vision Transformer. Transformer, which is a major mechanism in this study, has become more influential as its based models perform better than convolutional neural network-based models in the field of computer vision. Similarly, in the field of human pose estimation, Vision Transformer-based ViTPose maintains the best performance in all human pose estimation benchmarks such as COCO, OCHuman, and MPII. However, because Vision Transformer has a heavy model structure with a large number of parameters and requires a relatively large amount of computation, it costs users a lot to train the model. Accordingly, the based model overcame the insufficient Inductive Bias calculation problem, which requires a large amount of computation by Vision Transformer, with Local Representation through a convolutional neural network structure. Finally, the proposed model obtained a mean average precision of 0.694 on the MS COCO benchmark with 3.28 GFLOPs and 9.72 million parameters, which are 1/5 and 1/9 the number compared to ViTPose, respectively.