• 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 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.

• The Sea:JOURNAL OF THE KOREAN SOCIETY OF OCEANOGRAPHY
• /
• v.26 no.3
• /
• pp.220-237
• /
• 2021

Since the functional importance of marine phytoplankton was firstly advocated from early 1880s massive data on the species composition and abundance were produced by classical microscopic observation and the advanced auto-imaging technologies. Recently, pigment composition resulted from direct chemical analysis of phytoplankton samples or indirect remote sensing could be used for the group-specific quantification, which leads us to more diversified data production methods and for more improved spatiotemporal accessibilities to the target data-gathering points. In quite a few cases of many long-term marine ecosystem monitoring programs the phytoplankton species composition and abundance was included as a basic monitoring item. The phytoplankton data could be utilized as a crucial evidence for the long-term change in phytoplankton community structure and ecological functioning at the monitoring stations. Usability of the phytoplankton data sometimes is restricted by the differences in data producers throughout the whole monitoring period. Methods for sample treatments, analyses, and species identification of the phytoplankton species could be inconsistent among the different data producers and the monitoring years. In-depth study to determine the precise quantitative values of the phytoplankton species composition and abundance might be begun by Victor Hensen in late 1880s. International discussion on the quality assurance of the marine phytoplankton data began in 1969 by the SCOR Working Group 33 of ICSU. Final report of the Working group in 1974 (UNESCO Technical Papers in Marine Science 18) was later revised and published as the UNESCO Monographs on oceanographic methodology 6. The BEQUALM project, the former body of IPI (International Phytoplankton Intercomparison) for marine phytoplankton data QA/QC under ISO standard, was initiated in late 1990. The IPI is promoting international collaboration for all the participating countries to apply the QA/QC standard established from the 20 years long experience and practices. In Korea, however, such a QA/QC standard for marine phytoplankton species composition and abundance data is not well established by law, whereas that for marine chemical data from measurements and analysis has been already set up and managed. The first priority might be to establish a QA/QC standard system for species composition and abundance data of marine phytoplankton, then to be extended to other functional groups at the higher consumer level of marine food webs.

• Science of Emotion and Sensibility
• /
• v.24 no.4
• /
• pp.139-148
• /
• 2021

This study aimed to verify how a multisensory storytelling-based activity-based intervention affects social interaction in children with cerebral palsy. As a quasi-experimental investigation, this study used a single-blind, two-group pre-post test design. This study comprised 24 children aged 7 to 8 y who had been diagnosed with spastic cerebral palsy and were classified as having GMFCS stages I to III. Twelve children were randomly assigned to experimental and control groups, with neither the children nor their guardians knowing which group they were placed in. The group program comprised 16 sessions of 60 min each, twice a week for eight weeks. The experimental group engaged in an activity-centered intervention centered on multisensory storytelling, whereas the control group engaged in structured physical activity. The activities were assessed using the peer relations skills scale to determine the extent to which social interaction had changed prior to and during the child's intervention. The SPSS 25.0 for Windows (IBM Corp, USA) application was used to analyze the data, and the significance level (α) for statistical verification was set to 0.05. Furthermore, the Wilcoxon Signed-Rank and Mann-Whitney U tests were used to assess the differences in social interaction between the experimental and control groups. Significant differences were observed in the total of the peer relationship skill scale and cooperation and empathy areas of the subtest in the intragroup change of the peer relationship skill scale between the experimental and control groups. However, the experimental group demonstrated a significant difference in the initiative area, whereas the control group demonstrated no significant difference. A significant difference was observed in the amount of change between the two groups in the initiative area and total of the subtest of peer relationship skills but no significant difference in the collaboration and empathy areas. We gave a multisensory storytelling-based activity-based intervention based on multisensory storytelling to children with cerebral palsy and saw a significant improvement in peer relationship skills. It may be proposed as an effective intervention strategy for children with cerebral palsy who struggle with social contact.

• The Korean Society of Law and Medicine
• /
• v.22 no.4
• /
• pp.117-157
• /
• 2021

This research reviewed the HIPAA/HITECH, 21st Century Cures Act, Common Law, and private Guidances from the perspectives in protecting and utilitizing the medical data, while implications were followed. First, the standards for protection and utilization are relatively clearly regulated through single law on personal medical information in the United States. The HIPAA has been introduced in 1996 as fundamental act on protection of medical data. Medical data was divided into personally identifiable information, non-identifying information, and limited dataset under HIPAA. Regulations on de-identification measures for medical information, objects for deletion of limited data sets, and agreement on prohibition of data re-identification were stipulated. Moreover, in the 21st Century Cures Act regulated mutual compatibility for data sharing, prohibition of data blocking, and strengthening of accessibility of data subjects. Common Law introduced comprehensive consent system and clearly stipulates procedures. Second, the regulatory system is relatively simplified and clearly stipulated in the United States. To be specific, the expert consensus and the safe harbor system were introduced as an anonymity measure for identifiable medical information, which clearly defines the process while increasing trust. Third, the protection of the rights of the data subject is specified, the duty of explanation is specified in detail, while the information right of the consumer (opt-out procedure) for identification information is specified. For instance, the HHS rule and FDA regulations recognize the comprehensive consent system for human research, but the consent procedure, method, and requirements are stipulated through the common rule. Fourth, in the case of the United States, a trust-based system is being used throughout the health and medical data legislation. To be specific, Limited Data Sets are allowed to use in condition to the researcher's agreement to prohibit re-identification, and de-identification or consent process is simplified under the system.

• The Journal of Korean Society for Radiation Therapy
• /
• v.33
• /
• pp.89-97
• /
• 2021

Purpose: The purpose of this study is to compare and evaluate the dose change according to the gas volume variations in the rectum, which was not included in the treatment plan during radiation therapy for cervical cancer. Materials and methods: Static Intensity Modulated Radiation Therapy (S-IMRT) using a 9-field and Volumetric Modulated Arc Therapy (VMAT) using 2 full-arcs were established with treatment planning system on Computed Tomography images of a human phantom. Random gas parameters were included in the Planning Target Volume(PTV) with a maximum change of 2.0 cm in increments of 0.5 cm. Then, the Conformity Index (CI), Homogeneity Index (HI) and PTV D_max for the target volume were calculated, and the minimum dose (D_min), mean dose (D_mean) and Maximum Dose (D_max) were calculated and compared for OAR(organs at risk). For statistical analysis, T-test was performed to obtain a p-value, where the significance level was set to 0.05. Result: The HI coefficients of determination(R²) of S-IMRT and VMAT were 0.9423 and 0.8223, respectively, indicating a relatively clear correlation, and PTV D_max was found to increase up to 2.8% as the volume of a given gas parameter increased. In case of OAR evaluation, the dose in the bladder did not change with gas volume while a significant dose difference of more than D_mean 700 cGy was confirmed in rectum using both treatment plans at gas volumes of 1.0 cm or more. In all values except for D_mean of bladder, p-value was less than 0.05, confirming a statistically significant difference. Conclusion: In the case of gas generation not considered in the reference treatment plan, as the amount of gas increased, the dose difference at PTV and the dose delivered to the rectum increased. Therefore, during radiation therapy, it is necessary to make efforts to minimize the dose transmission error caused by a large amount of gas volumes in the rectum. Further studies will be necessary to evaluate dose transmission by not only varying the gas volume but also where the gas was located in the treatment field.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1723-1735
• /
• 2022

Landslides are one of the most prevalent natural disasters, threating both humans and property. Also landslides can cause damage at the national level, so effective prediction and prevention are essential. Research to produce a landslide susceptibility map with high accuracy is steadily being conducted, and various models have been applied to landslide susceptibility analysis. Pixel-based machine learning models such as frequency ratio models, logistic regression models, ensembles models, and Artificial Neural Networks have been mainly applied. Recent studies have shown that the kernel-based convolutional neural network (CNN) technique is effective and that the spatial characteristics of input data have a significant effect on the accuracy of landslide susceptibility mapping. For this reason, the purpose of this study is to analyze landslide vulnerability using a pixel-based deep neural network model and a patch-based convolutional neural network model. The research area was set up in Gangwon-do, including Inje, Gangneung, and Pyeongchang, where landslides occurred frequently and damaged. Landslide-related factors include slope, curvature, stream power index (SPI), topographic wetness index (TWI), topographic position index (TPI), timber diameter, timber age, lithology, land use, soil depth, soil parent material, lineament density, fault density, normalized difference vegetation index (NDVI) and normalized difference water index (NDWI) were used. Landslide-related factors were built into a spatial database through data preprocessing, and landslide susceptibility map was predicted using deep neural network (DNN) and CNN models. The model and landslide susceptibility map were verified through average precision (AP) and root mean square errors (RMSE), and as a result of the verification, the patch-based CNN model showed 3.4% improved performance compared to the pixel-based DNN model. The results of this study can be used to predict landslides and are expected to serve as a scientific basis for establishing land use policies and landslide management policies.

• Journal of Bio-Environment Control
• /
• v.31 no.2
• /
• pp.79-89
• /
• 2022

With the wide use of greenhouses, the working hours have been increasing inside the greenhouse for workers. In the closed ventilated greenhouse, the internal environment has less affected to external weather during making a suitable temperature for crop growth. Greenhouse workers are exposed to organic dust including soil dust, pollen, pesticide residues, microorganisms during tillage process, soil grading, fertilizing, and harvesting operations. Therefore, the health status and working environment exposed to workers should be considered inside the greenhouse. It is necessary to secure basic data on particulate matter (PM) concentrations in order to set up dust reduction and health safety plans. To understand the PM concentration of working environment in greenhouse, the PM concnentrations were monitored in the cut-rose and Hallabong greenhouses in terms of PM size, working type, and working period. Compare to no-work (move) period, a significant increase in PM concentration was found during tillage operation in Hallabong greenhouse by 4.94 times on TSP (total suspended particle), 2.71 times on PM-10 (particle size of 10 ㎛ or larger), and 1.53 times on PM-2.5, respectively. During pruning operation in cut-rose greenhouse, TSP concentration was 7.4 times higher and PM-10 concentration was 3.2 times higher than during no-work period. As a result of analysis of PM contribution ratio by particle sizes, it was shown that PM-10 constitute the largest percentage. There was a significant difference in the PM concentration between work and no-work periods, and the concentration of PM during work was significant higher (p < 0.001). It was found that workers were generally exposed to a high level of dust concentration from 2.5 ㎛ to 35.15 ㎛ during tillage operation.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.24 no.4
• /
• pp.99-112
• /
• 2021

This study was performed to predict spatial change of future forestland area in South Korea at regional level for supporting forest-related plans established by local governments. In the study, land use was classified to three types which are forestland, agricultural land, and urban and other lands. A logistic regression model was developed using transitional interaction between each land use type and topographical factors, land use restriction factors, socioeconomic indices, and development infrastructures. In this model, change probability from a target land use type to other land use types was estimated using raster dataset(30m×30m) for each variable. With priority order map based on the probability of land use change, the total annual amount of land use change was allocated to the cells in the order of the highest transition potential for the spatial analysis. In results, it was found that slope degree and slope standard value by the local government were the main factors affecting the probability of change from forestland to urban and other land. Also, forestland was more likely to change to urban and other land in the conditions of a more gentle slope, lower slope criterion allowed to developed, and higher land price and population density. Consequently, it was predicted that forestland area would decrease by 2027 due to the change from forestland to urban and others, especially in metropolitan and major cities, and that forestland area would increase between 2028 and 2050 in the most local provincial cities except Seoul, Gyeonggi-do, and Jeju Island due to locality extinction with decline in population. Thus, local government is required to set an adequate forestland use criterion for balanced development, reasonable use and conservation, and to establish the regional forest strategies and policies considering the future land use change trends.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.8
• /
• pp.131-143
• /
• 2021

In this study, the factors influencing the satisfaction of the online platform musical viewing method were investigated, and the effect of the satisfaction factors on the recommendation intention and rewatching intention of the online platform viewing method for musicals was investigated. In addition, the effect of the survey subjects' degree of involvement to musicals between the satisfaction of the online platform-based musical viewing method and recommendation intention, and rewatching intention was investigated. Satisfaction factors of online platform musicals, which are independent variables, were classified into image quality, convenience, economy, and interactivity, and dependent variables were classified into recommendation intention and rewatching intention of online platform musicals, and moderator variable was set to degree of involvement to musicals, and a total of 20 hypotheses were established. An online survey was conducted on 1,454 audiences who had experience watching musicals through the online platform from August 28 to September 7, 2021, and a total of 1,418 answers were used as valid samples. As a result of the analysis, the factors that make up the satisfaction of online platform musicals appeared in the order of convenience, video quality, economics, and interactivity. It was found that the satisfaction level of watching online platform musicals had a positive effect on the intention to recommend and rewatching online platform musicals in the path of all satisfaction factors. It was found that the moderating effect of the audience's involvement in musicals between online platform musical viewing satisfaction and recommendation intention and rewatching intention had a significant effect only between image quality and recommendation intention. It shows that audiences with high involvement in musicals have intention to recommend only when they are satisfied with the video quality of online platform musicals. Particularly important point is that the convenience factor was found to have the greatest influence on the satisfaction of online platform musical viewing method, but the image quality factor was found to have the greatest influence on the recommendation intention and rewatching intention of online platform musicals.