• Journal of Intelligence and Information Systems
• /
• v.27 no.2
• /
• pp.1-15
• /
• 2021

If it is difficult for us to make decisions, we ask for advice from friends or people around us. When we decide to buy products online, we read anonymous reviews and buy them. With the advent of the Data-driven era, IT technology's development is spilling out many data from individuals to objects. Companies or individuals have accumulated, processed, and analyzed such a large amount of data that they can now make decisions or execute directly using data that used to depend on experts. Nowadays, the recommender system plays a vital role in determining the user's preferences to purchase goods and uses a recommender system to induce clicks on web services (Facebook, Amazon, Netflix, Youtube). For example, Youtube's recommender system, which is used by 1 billion people worldwide every month, includes videos that users like, "like" and videos they watched. Recommended system research is deeply linked to practical business. Therefore, many researchers are interested in building better solutions. Recommender systems use the information obtained from their users to generate recommendations because the development of the provided recommender systems requires information on items that are likely to be preferred by the user. We began to trust patterns and rules derived from data rather than empirical intuition through the recommender systems. The capacity and development of data have led machine learning to develop deep learning. However, such recommender systems are not all solutions. Proceeding with the recommender systems, there should be no scarcity in all data and a sufficient amount. Also, it requires detailed information about the individual. The recommender systems work correctly when these conditions operate. The recommender systems become a complex problem for both consumers and sellers when the interaction log is insufficient. Because the seller's perspective needs to make recommendations at a personal level to the consumer and receive appropriate recommendations with reliable data from the consumer's perspective. In this paper, to improve the accuracy problem for "appropriate recommendation" to consumers, the recommender systems are proposed in combination with context-based deep learning. This research is to combine user-based data to create hybrid Recommender Systems. The hybrid approach developed is not a collaborative type of Recommender Systems, but a collaborative extension that integrates user data with deep learning. Customer review data were used for the data set. Consumers buy products in online shopping malls and then evaluate product reviews. Rating reviews are based on reviews from buyers who have already purchased, giving users confidence before purchasing the product. However, the recommendation system mainly uses scores or ratings rather than reviews to suggest items purchased by many users. In fact, consumer reviews include product opinions and user sentiment that will be spent on evaluation. By incorporating these parts into the study, this paper aims to improve the recommendation system. This study is an algorithm used when individuals have difficulty in selecting an item. Consumer reviews and record patterns made it possible to rely on recommendations appropriately. The algorithm implements a recommendation system through collaborative filtering. This study's predictive accuracy is measured by Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). Netflix is strategically using the referral system in its programs through competitions that reduce RMSE every year, making fair use of predictive accuracy. Research on hybrid recommender systems combining the NLP approach for personalization recommender systems, deep learning base, etc. has been increasing. Among NLP studies, sentiment analysis began to take shape in the mid-2000s as user review data increased. Sentiment analysis is a text classification task based on machine learning. The machine learning-based sentiment analysis has a disadvantage in that it is difficult to identify the review's information expression because it is challenging to consider the text's characteristics. In this study, we propose a deep learning recommender system that utilizes BERT's sentiment analysis by minimizing the disadvantages of machine learning. This study offers a deep learning recommender system that uses BERT's sentiment analysis by reducing the disadvantages of machine learning. The comparison model was performed through a recommender system based on Naive-CF(collaborative filtering), SVD(singular value decomposition)-CF, MF(matrix factorization)-CF, BPR-MF(Bayesian personalized ranking matrix factorization)-CF, LSTM, CNN-LSTM, GRU(Gated Recurrent Units). As a result of the experiment, the recommender system based on BERT was the best.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.49 no.1
• /
• pp.1-18
• /
• 2021

This study was intended to present measures for the improvement of the apartment house landscaping supervision system by examining the adequacy of landscaping supervision, which is aimed at improving the quality of landscape plants and facilities in apartment house landscaping sites. Additionally, this study aims to identify the problems occurring in the process of the performance of landscaping supervision and to provide the evidence for legislative activities and revision of the laws currently being pushed forward for the mandatory deployment of apartment house landscaping supervision personnel. The results of the analysis showed that no landscaping supervision personnel was deployed to apartment complexes with less than 1,500 households and that the landscaping comprised 19% to 46% of the entire construction process. The civil engineering firm performed the landscaping supervision, which made it impracticable to fully focus on the construction quality in the field of landscaping. The quality control in terms of landscape plants revealed differences in quality control, depending on the competence and experience of the civil engineer supervising the personnel, where the landscaping supervision personnel was not deployed. The apartment houses landscaping supervision activity index was analyzed, and the results showed that the supervision activity index for apartment house A was 72.0, B was 70.4, and apartment houses C to G ranged from 38.7 to 46.9, which suggested that the difference in quality control, process control, and technical support affected the construction quality and occurrence of defects.The improvement of landscaping process quality control and process management will be carried out more smoothly and the rate of defects will be drastically reduced if the landscaping supervision personnel placement threshold is lowered from 1,500 households to 300 households in complexes. The results of this study are expected to be useful in promoting and re-establishing the landscaping industry based on the improvement of construction quality in the field of landscaping in connection with the construction of apartment houses.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.264-271
• /
• 2021

In this paper, we intended to find the labor situations and labor rights consciousness of local juveniles and also to identify how they are treated and respond to those treatments they encounter. At the same time, another purpose of this research is to collect basic data to give the youth proper education about labor rights when they are faced with unfair labor practice. The research results are as follows: First, 262 students (50.5%) have work experience. Second, 133 students(24.9%) took the education about labor rights, which means relatively small number of students were educated about labor rights. Third, it is reported that 54.2% of those students considered 'payment' top priority, and 67.7% of them got the work through their parents, friends, and acquaintances, and 60.2% had their jobs at restaurants. Average working hours are 7 hours a day and 20 hours a week, which shows that they worked quite long hours. Fourth, 28.9% of respondents reported they wrote employment contracts, and 82.1% said their main purpose of work was 'to make money'. Fifth, 24.7% of the students reported the experience of unfair treatment while working, and the most common case was 'jobs other than expected work'(17.9%). When they were asked how they coped with the unfair treatments, the largest percentage(30.3%) of them answered they 'quit the job'. Last, when the respondants were asked to list improvements for juvenile part-time jobs, the answers were minimum wage and payment with weekly vacation allowance(25.1%), enhancing social awareness(14.3%), increasing good job opportunity(12.8%), and etc.. This demonstrates that social awareness of juvenile labor jobs is to improve urgently in local community.

• Journal of the Korean Applied Science and Technology
• /
• v.37 no.6
• /
• pp.1556-1566
• /
• 2020

The purpose of this study was to investigate the effect of Nurida-Ball exercise on isokinetic muscle function, spinal alignment, and dynamic balance capacity in middle-aged men. All middle-aged men(n=16) were divided into 2 groups: Ball exercise(BE, n=8) and control(CON, n=8) group. BE group performed the Nurida-Ball exercise(30 min/day, 3 days/week, 8 weeks) and isokinetic knee and trunk muscle function, spinal alignment, and dynamic balance capacity were measured. All of the measured variables calculated the mean and standard deviation and verified normality using the Shapiro-Wilk test. The independent t-test method and the Paired t-test method were then analyzed to identify differences between groups. This study found that isokinetic knee and trunk muscle function was significantly strengthened in the BE compared with CON group by increasing peak torque(PT) of right and left knee extension(60°/sec, p<0.01, respectively), average power(AP) of right and left knee extension(60°/sec, p<0.05, p<0.01, respectively), and PT of right knee flexion(180°/sec, p<0.05) and AP of right knee extension(180°/sec, p<0.05). In the change of isokinetic trunk muscle function, only PT of trunk extension(180°/sec) was increased in the BE compared with the CON group(p<0.05). In addition, Nurida-ball exercise can improve the spinal alignment by reducing the trunk inclination(p<0.05) in the BE compared with the CON group. Finally, dynamic balance capacity was also enhanced in the BE compared with the CON group by decreasing the score of overall balance index(OBI, p<0.01) and Antero-posterior balance index(p<0.05) in the Stage-6, and OBI(p<0.05) in the Stage-1. This result demonstrated that Nurida-ball exercise may improve spinal alignment, dynamic balance capacity, and isokinetic muscle function, which might be an effective way for the improvement of health-related fitness in middle-aged men.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.23 no.1
• /
• pp.15-33
• /
• 2021

In this study, the possibility of discriminating Fire blight (FB) infection tested using the hyperspectral imagery. The reflectance of healthy and infected leaves and branches was acquired with 5 nm of full width at high maximum (FWHM) and then it was standardized to 10 nm, 25 nm, 50 nm, and 80 nm of FWHM. The standardized samples were divided into training and test sets at ratios of 7:3, 5:5 and 3:7 to find the optimal bands of FWHM by the decision tree analysis. Classification accuracy was evaluated using overall accuracy (OA) and kappa coefficient (KC). The hyperspectral reflectance of infected leaves and branches was significantly lower than those of healthy green, red-edge (RE) and near infrared (NIR) regions. The bands selected for the first node were generally 750 and 800 nm; these were used to identify the infection of leaves and branches, respectively. The accuracy of the classifier was higher in the 7:3 ratio. Four bands with 50 nm of FWHM (450, 650, 750, and 950 nm) might be reasonable because the difference in the recalculated accuracy between 8 bands with 10 nm of FWHM (440, 580, 640, 660, 680, 710, 730, and 740 nm) and 4 bands was only 1.8% for OA and 4.1% for KC, respectively. Finally, adding two bands (550 nm and 800 nm with 25 nm of FWHM) in four bands with 50 nm of FWHM have been proposed to improve the usability of multispectral image sensors with performing various roles in agriculture as well as detecting FB with other combinations of spectral bands.

• Nutrition Research and Practice
• /
• v.15 no.2
• /
• pp.213-224
• /
• 2021

BACKGROUND/OBJECTIVES: To evaluate the nutritional status and prevalence of malnutrition in hospitalized children at admission and during hospitalization in South Korea. SUBJECTS/METHODS: This first cross-sectional nationwide "Pediatric Nutrition Day (pNday)" survey was conducted among 872 hospitalized children (504 boys, 368 girls; 686 medical, 186 surgical) from 23 hospitals in South Korea. Malnutrition risk was screened using the Pediatric Yorkhill Malnutrition Score (PYMS) and the Screening Tool Risk on Nutritional status and Growth. Nutritional status was assessed by z-scores of weight-for-age for underweight, weight-for-height for wasting, and height-for-age for stunting as well as laboratory tests. RESULTS: At admission, of the 872 hospitalized children, 17.2% were underweight, and the prevalence of wasting and stunting was 20.2% and 17.3%, respectively. During hospitalization till pNday, 10.8% and 19.6% experienced weight loss and decreased oral intake, respectively. During the aforementioned period, fasting was more prevalent in surgical patients (7.5%) than in medical patients (1.6%) (P < 0.001). According to the PYMS, 34.3% and 30% of the children at admission and on pNday, respectively, had a high-risk of malnutrition, requiring consultation with the nutritional support team (NST). However, only 4% were actually referred to the NST during hospitalization. CONCLUSIONS: Malnutrition was prevalent at admission and during hospitalization in pediatric patients, with many children experiencing weight loss and poor oral intake. To improve the nutritional status of hospitalized children, it is important to screen and identify all children at risk of malnutrition and refer malnourished patients to the multidisciplinary NST for proper nutritional interventions.

• Journal of Ginseng Culture
• /
• v.3
• /
• pp.11-37
• /
• 2021

Korean ginseng is the one of the most famous medicinal herbs globally and has long been a representative item of East Asian trade, including across China and Japan. Since Joseon (1392-1910) ginseng trade was entirely controlled by the state, The Veritable Records of the Joseon Dynasty are a valuable resource that can shed light on the history of the ginseng industry at that time. By studying the subsection "The Veritable Records of King Sejong" (世宗實錄), when ginseng was used even more widely, we assess the purpose and scale of its trade in the 15th century, identify its original listing in the geographical appendix, develop a distribution map, and explore similarities to current ginseng cultivation areas. During the reign of King Sejong (1418-1450), ginseng was sent to China as a tribute 101 times, with a combined weight of 7,060 kilograms, with less than one-third of that amount given to Japan and Okinawa. It was used to cover the travel expenses of foreign envoys and servants, but this can be seen to gradually decrease after the regnal mid-term, primarily due to a decrease in the amount of ginseng being collected. At the time, there were 113 areas of naturally growing ginseng as listed in the records' geographical appendix, including 12 recorded in the 'tributes' category: Yeongdeok-gun, Yeongju, and Cheongsong-gun in Gyeongsangbuk-do; Ulju-gun and Ulsan in Gyeongsangnam-do; Jeongeup, Wanju-gun, and Jangsu-gun in Jeollabuk-do; Hwasun-gun in Jeollanam-do; Goksan-gun and Sinpyeong-gun in Hwanghaebuk-do; Jeongju and Taecheon-gun in Pyeonganbuk-do; and Jaseong-gun and Junggang-gun in Jagang-do. A total of 101 places are recorded in the 'medicinal herbs' category, located throughout the mountains of the eight Joseon provinces, except the islands. In comparison with current ginseng cultivation sites, many of these historical areas are either consistent with or adjacent to contemporary locations. The geographical appendix to "The Veritable Records of King Sejong" was compiled in the early days of the king's reign (1432) when there was a lot of wild ginseng. The appendix is a valuable resource that indicates the possibility of growing ginseng on the Korean Peninsula in the future. The apparently natural habitats in the south, where ginseng is not currently cultivated, could be candidates for the future. Moreover, areas in the north where ginseng has not been grown, except Kaesǒng, could be a good alternative under sustainable inter-Korean exchange should cultivation sites move north due to climate warming.

• Journal of the Korean Applied Science and Technology
• /
• v.38 no.1
• /
• pp.318-331
• /
• 2021

This study was conducted on the assumption that bone age would be more effective when it comes to physique and physical fitness assessment for adolescents, and the purpose of this study was to identify the differences in physique and physical fitness for students in their adolescence through bone age and chronological age in order to contribute to the well-balanced physique and physical fitness development in adolescents and the health improvement in students. Total 874 adolescents(483 males, 391 females) aged 11~16 were selected as subjects out of the total population of 1100 adolescents aged 6~16 based on the PAPS(Physical Activity Promotion System) and age standards of the TW3 method; and skeletal maturation, which symbolize the indicators of biological maturation, were evaluated by using the TW3(Tanner-Whitehouse 3) method after hand-wrist radiographs, and birth date was used for chronological age. A stadiometer and InBody 270 (Biospace, Korea) were used to measure 2 components in physique. A total of 7 components in physical fitness, which included muscular strength, muscular endurance, flexibility, power, cardiovascular endurance, balance, agility, were measured as well. A independent samples t-test was conducted for data processing using SPSS 25.0, and the significance level was set at p< .05. The study results are as follows. First, bone age and chronological age used for physique comparison in males aged 11 and 12, height and weight showed significant difference; in males aged 13, weight showed signicant difference. Weight and height in females aged 11, and height in females aged 12 showed significant difference. Second, bone age and chronological age used for physical fitness comparison in males aged 11, muscular strength, power, flexibility, cardiovascular endurance showed significant difference; in males aged 12, muscular strength. power, cardiovascular endurance; in males aged 13, flexibility showed significant difference. Muscular strength, power, flexibility, muscular endurance, cardiovascular endurance in females aged 11, and flexibility in females aged 14 showed significant difference. As a result, this study concluded that in a period of rapid skeletal growth, evaluating physique and physical fitness based on bone age is more accurate than evaluating based on chronological age.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.1
• /
• pp.35-57
• /
• 2021

This paper is to grasp the current trends of national bibliographies through analyzing representative national bibliographies using literature review, analysis of national bibliographies' web pages and survey. First, in order to conform to the definition of a national bibliography as a record of a national publication, it attempts to include a variety of materials from print to electronic resources, but in reality it cannot contain all the materials, so there are exceptions. It is impossible to create a general selection guide for national bibliography coverage, and a plan that reflects the national characteristics and prepares a valid and comprehensive coverage based on analysis is needed. Second, cooperation with publishers and libraries is being made to efficiently generate national bibliography. For the efficiency of national bibliography generation, changes should be sought such as the standardization and consistency, the collection level metadata description for digital resources, and the creation of national bibliography using linked data. Third, national bibliography is published through the national bibliographic online search system, linked data search, MARC download using PDF, OAI-PMH, SRU, Z39.50, and mass download in RDF/XML format, and is integrated with the online public access catalog or also built separately. Above all, national bibliographies and online public access catalogs need to be built in a way of data reuse through an integrated library system. Fourth, as a differentiated function for national bibliography, various services such as user tagging and national bibliographic statistics are provided along with various browsing functions. In addition, services of analysis of national bibliographic big data, links to electronic publications, and mass download of linked data should be provided, and it is necessary to identify users' needs and provide open services that reflect them in order to develop differentiated services. Through the current trends and considerations of the national bibliographies analyzed in this study, it will be possible to explore changes in national and international national bibliography.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.577-587
• /
• 2021

Drought is generally considered to be a natural disaster caused by accumulated water shortages over a long period of time, taking months or years and slowly occurring. However, climate change has led to rapid changes in weather and environmental factors that directly affect agriculture, and extreme weather conditions have led to an increase in the frequency of rapidly developing droughts within weeks to months. This phenomenon is defined as 'Flash Drought', which is caused by an increase in surface temperature over a relatively short period of time and abnormally low and rapidly decreasing soil moisture. The detection and analysis of flash drought is essential because it has a significant impact on agriculture and natural ecosystems, and its impacts are associated with agricultural drought impacts. In South Korea, there is no clear definition of flash drought, so the purpose of this study is to identify and analyze its characteristics. In this study, flash drought detection condition was presented based on the satellite-derived drought index Evaporative Stress Index (ESI) from 2014 to 2018. ESI is used as an early warning indicator for rapidly-occurring flash drought a short period of time due to its similar relationship with reduced soil moisture content, lack of precipitation, increased evaporative demand due to low humidity, high temperature, and strong winds. The flash droughts were analyzed using hydrometeorological characteristics by comparing Standardized Precipitation Index (SPI), soil moisture, maximum temperature, relative humidity, wind speed, and precipitation. The correlation was analyzed based on the 8 weeks prior to the occurrence of the flash drought, and in most cases, a high correlation of 0.8(-0.8) or higher(lower) was expressed for ESI and SPI, soil moisture, and maximum temperature.