• Korean Journal of Culture and Social Issue
• /
• v.21 no.3
• /
• pp.551-573
• /
• 2015

The rise of single living has been one of the most important demographic shifts of recent decades. The solo household is a little less than 40% in Europe areas and that of Tokyo is over 45%. Being impacted this figure, the formation of single economy is the key word in World Economic Forum(WEF) 2008. Seoul' single household is increasing rapidly. Between 2000 and 2005, the growth of single person is around 34%, the population of single person reached 700,000 people. Now 20% of total household in Seoul is Single household. Living alone or solo living is not exceptional or special in Seoul Metropolitan City. The rise in single living will create pressures towards poverty and inequality and so on. Seoul should develop and prepare the urban policy for single household. We figured out the four key trends which composed of single household in Seoul. Four types of single person are like below : Gold Mr and Miss, Reserved labor forces, depressed single and silver generation. Gold group is amonst people aged 30 and 40 who is working in the area of white collar and professional. They are usually elective single person household who have chosen solo living. Reserved labor forces group is usually among 20s people who have not get the regular hob. For this group, job acquiring is the most important issue. Depressed single person household group is among people aged late 30s and 40s. Its group is the result from the broken family. The silver group is among aged over 65 that is the main issue of the aged society. In this research, we stressed that people living alone can be split into two types - elective single person households who have chosen single living, and forced single person household who have been constrained to this lifestyle by circumstances. Except gold group, the rest of the group is the forced single household who are faced to poverty. The monthly income of single person household is almost under 2 million won. Single person household is usually working in the blue collar job and service area. So, except gold group that is the smallest part of single person household, almost single person is not the target of private market, but the object of public policy.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.67-67
• /
• 2023

수문관측의 핵심은 강우-유출 관계다. 하천유량 생산을 위해 수많은 지점에서 유량측정을 수행한다. 그러나 유량자료의 신뢰도는 높지 않다. 그리고 댐 유입량 산정에 아무 도움이 되지 않고 있다. 더구나 저수지의 경우는 유입량 자료도 없이 운영되고 있다. 저수지, 댐에 물이 고여 있는데 이를 활용하면 유입량을 계산할 수 있고, 그 지점에서 유량이 얼마인지 고품질로 생산할 수 있다. 여기서는 총저수량 260만m³, 유역면적 3.7km²인 감포댐에 적용하여 저수량 자료를 활용하여 유입량의 신뢰도를 얼마나 개선시킬 수 있는지 분석한 결과는 다음과 같다. 여기서 적용 기간은2020.9.1.~9.14., 2022.9.5.~9.6 등 2개 사상이고, ONE 모형에 의해 10분 단위로 유출량을 모의했다. 모의 방법은 총유량을 같게 하는 방법과 저수위 오차를 최소로 하는 방법 등 두 가지로 했다. 첫째, 2020.9.1.~9.14. 사상은 강우량은 10분 최대 19.0mm, 총 127.0mm였다. 총유량을 같게 하는 경우 유입량은 10분 최대 5.4m³/s, 총 40만m³로 모의돼, 유출률 85.5%로 나타났고, 관측은 10분최대 4.7m³/s, 총 40만m³, 유출률 85.3%로 나타났다. 유량 신뢰도는 RMSE 0.491mm, NSE 0.237, R²는 0.455로 나타났다. 이 경우 저수위 모의 신뢰도는 RMSE 0.600m, NSE 0.158, R²는 0.893로나타났다. 저수량 오차를 최소로 한 경우 유입량은 10분 최대 4.0m³/s, 총 28만m³로 모의돼, 유출률 59.4%로 나타났고, 관측은 10분 최대 4.0m³/s, 총 28만m³, 유출률 85.3%로 나타났다. 유량 신뢰도는 RMSE 0.425mm, NSE 0.430, R²는 0.507로 나타났다. 이 경우 저수위 모의 신뢰도는 RMSE 0.110m, NSE 0.972, R²는 0.995로 높았다. 둘째, 2022.9.5.~9.6. 사상은 강우량은 10분 최대 32.3mm, 총 196.0mm였다. 총유량을 같게 하는 경우 유입량은 10분 최대 64.5m³/s, 총 59만m³로 모의돼, 유출률 81.6%로 나타났고, 관측은 10분 최대 80.1m³/s, 총 59만m³, 유출률 81.6%로 나타났다. 유량 신뢰도는 RMSE 1.832mm, NSE 0.960, R²는 0.984로 나타났다. 이 경우 저수위 모의 신뢰도는 RMSE 0.323m, NSE 0.968, R²는 0.999로나타났다. 저수량 오차를 최소로 한 경우 유입량은 10분 최대 80.1m³/s, 총 66만m³로 모의돼, 유출률 91.6%로 나타났고, 관측은 10분 최대 80.1m³/s, 총 59만m³, 유출률 81.8%로 나타났다. 유량 신뢰도는 RMSE 2.120mm, NSE 0.947, R2는 0.949로 나타났다. 이 경우 저수위 모의 신뢰도는 RMSE 0.153m, NSE 0.993, R²는 0.997로 높았다. 종합하면 저수량 오차가 최소가 되도록 하천 유출량을 모의하면 결과적으로 하천유량의 신뢰도를 향상시키는 것이라 말할 수 있다.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.57-78
• /
• 2023

COVID-19, which started in Wuhan, China in November 2019, spread beyond China in 2020 and spread worldwide in March 2020. It is important to prevent a highly contagious virus like COVID-19 in advance and to actively treat it when confirmed, but it is more important to identify the confirmed fact quickly and prevent its spread since it is a virus that spreads quickly. However, PCR test to check for infection is costly and time consuming, and self-kit test is also easy to access, but the cost of the kit is not easy to receive every time. Therefore, if it is possible to determine whether or not a person is positive for COVID-19 based on the sound of a cough so that anyone can use it easily, anyone can easily check whether or not they are confirmed at anytime, anywhere, and it can have great economic advantages. In this study, an experiment was conducted on a method to identify whether or not COVID-19 was confirmed based on a cough sound. Cough sound features were extracted through MFCC, Mel-Spectrogram, and spectral contrast. For the quality of cough sound, noisy data was deleted through SNR, and only the cough sound was extracted from the voice file through chunk. Since the objective is COVID-19 positive and negative classification, learning was performed through XGBoost, LightGBM, and FCNN algorithms, which are often used for classification, and the results were compared. Additionally, we conducted a comparative experiment on the performance of the model using multidimensional vectors obtained by converting cough sounds into both images and vectors. The experimental results showed that the LightGBM model utilizing features obtained by converting basic information about health status and cough sounds into multidimensional vectors through MFCC, Mel-Spectogram, Spectral contrast, and Spectrogram achieved the highest accuracy of 0.74.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.145-165
• /
• 2023

Recommendation system plays a significant role on relieving difficulties of selecting information among rapidly increasing amount of information caused by the development of the Internet and on efficiently displaying information that fits individual personal interest. In particular, without the help of recommendation system, E-commerce and OTT companies cannot overcome the long-tail phenomenon, a phenomenon in which only popular products are consumed, as the number of products and contents are rapidly increasing. Therefore, the research on recommendation systems is being actively conducted to overcome the phenomenon and to provide information or contents that are aligned with users' individual interests, in order to induce customers to consume various products or contents. Usually, collaborative filtering which utilizes users' historical behavioral data shows better performance than contents-based filtering which utilizes users' preferred contents. However, collaborative filtering can suffer from cold-start problem which occurs when there is lack of users' historical behavioral data. In this paper, hybrid music recommendation system, which can solve cold-start problem, is proposed based on the playlist data of Melon music streaming service that is given by Kakao Arena for music playlist continuation competition. The goal of this research is to use music tracks, that are included in the playlists, and metadata of music tracks and playlists in order to predict other music tracks when the half or whole of the tracks are masked. Therefore, two different recommendation procedures were conducted depending on the two different situations. When music tracks are included in the playlist, LightFM is used in order to utilize the music track list of the playlists and metadata of each music tracks. Then, the result of Item2Vec model, which uses vector embeddings of music tracks, tags and titles for recommendation, is combined with the result of LightFM model to create final recommendation list. When there are no music tracks available in the playlists but only playlists' tags and titles are available, recommendation was made by finding similar playlists based on playlists vectors which was made by the aggregation of FastText pre-trained embedding vectors of tags and titles of each playlists. As a result, not only cold-start problem can be resolved, but also achieved better performance than ALS, BPR and Item2Vec by using the metadata of both music tracks and playlists. In addition, it was found that the LightFM model, which uses only artist information as an item feature, shows the best performance compared to other LightFM models which use other item features of music tracks.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.185-209
• /
• 2023

With the advent of the 4th industrial revolution, various technologies have received much attention. Technologies related to the 4th industry include the Internet of Things (IoT), big data, artificial intelligence, virtual reality (VR), 3D printers, and robotics, and these technologies are often converged. In particular, the robotics field is combined with technologies such as big data, artificial intelligence, VR, and digital twins. Accordingly, much research using robotics is being conducted, which is applied to distribution, airports, hotels, restaurants, and transportation fields. In the given situation, research on human-robot interaction is attracting attention, but it has not yet reached the level of user satisfaction. However, research on robots capable of perfect communication is steadily being conducted, and it is expected that it will be able to replace human emotional labor. Therefore, it is necessary to discuss whether the current human-robot interaction technology can be applied to business. To this end, this study first examines the trend of human-robot interaction technology. Second, we compare LDA (Latent Dirichlet Allocation) topic modeling and BERTopic topic modeling methods. As a result, we found that the concept of human-robot interaction and basic interaction was discussed in the studies from 1992 to 2002. From 2003 to 2012, many studies on social expression were conducted, and studies related to judgment such as face detection and recognition were conducted. In the studies from 2013 to 2022, service topics such as elderly nursing, education, and autism treatment appeared, and research on social expression continued. However, it seems that it has not yet reached the level that can be applied to business. As a result of comparing LDA (Latent Dirichlet Allocation) topic modeling and the BERTopic topic modeling method, it was confirmed that BERTopic is a superior method to LDA.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.361-381
• /
• 2023

Research on corporate bankruptcy prediction has been focused on financial information. Since the company's financial information is updated quarterly, there is a problem that timeliness is insufficient in predicting the possibility of a company's business closure in real time. Evaluated companies that want to improve this need a method of judging the soundness of a company that uses information other than financial information to judge the soundness of a target company. To this end, as information technology has made it easier to collect non-financial information about companies, research has been conducted to apply additional variables and various methodologies other than financial information to predict corporate bankruptcy. It has become an important research task to determine whether it has an effect. In this study, we examined the impact of electronic payment-related information, which constitutes non-financial information, when predicting the closure of business operators using electronic payment service and examined the difference in closure prediction accuracy according to the combination of financial and non-financial information. Specifically, three research models consisting of a financial information model, a non-financial information model, and a combined model were designed, and the closure prediction accuracy was confirmed with six algorithms including the Multi Layer Perceptron (MLP) algorithm. The model combining financial and non-financial information showed the highest prediction accuracy, followed by the non-financial information model and the financial information model in order. As for the prediction accuracy of business closure by algorithm, XGBoost showed the highest prediction accuracy among the six algorithms. As a result of examining the relative importance of a total of 87 variables used to predict business closure, it was confirmed that more than 70% of the top 20 variables that had a significant impact on the prediction of business closure were non-financial information. Through this, it was confirmed that electronic payment-related information of non-financial information is an important variable in predicting business closure, and the possibility of using non-financial information as an alternative to financial information was also examined. Based on this study, the importance of collecting and utilizing non-financial information as information that can predict business closure is recognized, and a plan to utilize it for corporate decision-making is also proposed.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.1-17
• /
• 2023

With the recent rapid development of ICT(Information and Communication Technology) and the popularization of digital devices, the size of the online market continues to grow. As a result, we live in a flood of information. Thus, customers are facing information overload problems that require a lot of time and money to select products. Therefore, a personalized recommender system has become an essential methodology to address such issues. Collaborative Filtering(CF) is the most widely used recommender system. Traditional recommender systems mainly utilize quantitative data such as rating values, resulting in poor recommendation accuracy. Quantitative data cannot fully reflect the user's preference. To solve such a problem, studies that reflect qualitative data, such as review contents, are being actively conducted these days. To quantify user review contents, text mining was used in this study. The general CF consists of the following three steps: user-item matrix generation, Top-N neighborhood group search, and Top-K recommendation list generation. In this study, we propose a recommendation algorithm that applies an extended similarity measure, which utilize quantified review contents in addition to user rating values. After calculating review similarity by applying TF-IDF, Word2Vec, and Doc2Vec techniques to review content, extended similarity is created by combining user rating similarity and quantified review contents. To verify this, we used user ratings and review data from the e-commerce site Amazon's "Health and Personal Care". The proposed recommendation model using extended similarity measure showed superior performance to the traditional recommendation model using only user rating value-based similarity measure. In addition, among the various text mining techniques, the similarity obtained using the TF-IDF technique showed the best performance when used in the neighbor group search and recommendation list generation step.

• Journal of the Korean Chemical Society
• /
• v.67 no.5
• /
• pp.378-392
• /
• 2023

The purpose of this study is to analyze the pre-service chemistry teachers' cognition of the nature of model in process of designing and developing models using technology. For this purpose, 19 pre-service chemistry teachers' in the 3rd grade of a education college located in the central region observe experimental phenomena related to Boyle's law presented in the 7th grade science textbook and researchers required the design and development of a model related to the observed experimental results using technology. Based on previous studies, the nature of model were classified into two aspect: 'Representational aspect' and 'Explanatory aspect'. The 'Representational aspect' was classified into 'Representation', 'Abstraction', and 'Simplification', and the 'Explanatory aspect' was classified into 'Analysis', 'Interpretation', 'Reasoning', 'Explanation', and 'Quantification'. The pre-service chemistry teachers' cognition were analyzed by the classification. As a result of the study, the 'Representation' of the 'expressive aspect' was uniformized in the form of space that changes in volume, and the pressure was expressed as the Brightness inside the cylinder or frequency of color change of particles for 'Abstraction'. In the case of 'Simplification', the particle collision was expressed as a perfectly elastic collision, but there was a group that could not simply indicate the type of particle. In the 'Explanatory aspect', in the case of 'Analysis', volume was classified as a manipulated variable, and in the case of 'Interpretation', most groups analyzed the change in pressure through the collision of gas particles. However, the cognition involved in 'Reasoning' was not observed much. In the case of 'Explanation', there were groups that did not succeed in explanation because the area where the particles collided was not set or incorrectly set, and in the case of 'Quantification', there was a group that formulated the number of collisions per unit time, and on the contrary, there was a group that could not quantify the number of collisions because they could not be expressed in numbers.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.41 no.2
• /
• pp.1-10
• /
• 2023

This study aims to explore the significance of historic changes and cultural characteristics of landscape architecture in Korean Seowon. Seowon refers to educational private institutes that also served as Confucian shrines and were prevalent during the mid-to-late Joseon dynasty. Seowon comprised three distinct functional spaces: a shrine, a school, and a garden. The concept of Seowon's garden extended beyond designed landscapes to include the surrounding natural environment. The importance of landscape architecture in Seowon is rooted in its connection to the educational philosophy of these institutes. During the Joseon dynasty, scholars revered nature as a manifestation of Confucian ideals, and they believed that close engagement with nature was integral to self-discipline and learning. This research investigated fifteen relatively well-preserved garden in South Korea and conducted a comprehensive analysis of their gardens. The analysis revealed two key findings. Firstly, gardens in Seowon were actively designed and constructed during the early phase of Seowon culture but gradually diminished after the 17th century. This can be attributed to the shift in Seowon's purpose, with a greater emphasis on its religious function over education. Consequently, the significance and presence of landscape architecture in Seowon, which was closely related with its Confucianist education, declined. Secondly, the study explored the historical backgrounds of each Seowon's landscape architecture and found that many of them were designed or influenced by individuals who were later memorialized and deified in the Seowon's shrines. The landscape architecture created by these predecessors was carefully preserved by the faculties and students as a form of respect. Therefore, landscape architecture in Korean Seowon not only conveys the institutional purpose as an educational hub for the local society but also reflects the institute's strong relationship with the figures they worship as shrines.

• Journal of Technology Innovation
• /
• v.31 no.2
• /
• pp.303-332
• /
• 2023

This study comprises critical questions of "What kinds of intangible resources are significant to create and reinforce competitive advantages for the small and medium-sized enterprises(SMEs) that significantly influence the national economy? What kinds of capacities do SMEs need in consideration with the large changes in market environment and during crisis? With large changes to market environment, would different capacities affect performance of platform and general SMEs?" To examine these questions, I have provided Entrepreneurial Orientation, Absorptive Capacity, and Organizational Resilience as key capacities that influence the competitive advantage and performance of SMEs. In particular, I have substantiated the control effect of Organizational Resilience (a rising key capacity for enterprises in recent times) on Corporate Performance. Moreover, I have analyzed the control effect of Organizational Resilience on Corporate Performance by comparing platform and general companies, and also substantiated how control effects may vary depending on sub-factors of Organizational Resilience. The results of this study indicate that Entrepreneurial Orientation and Absorptive Capacity significantly and positively influence Corporate Performance. Organizational Resilience also demonstrate a positive influence on Corporate Performance. Notably, sub-factors of Organizational Resilience (risk preparation capacity, risk response capacity, and change initiative capacity) significantly control correlation between Entrepreneurial Orientation and Corporate Performance. Risk preparation capacity and change initiative capacity significantly control correlation between Absorptive Capacity and Corporate Performance. Additionally, the control effect of risk preparation capacity significantly control correlation between Entrepreneurial Orientation and Corporate Performance. Also, the control effect of risk response capacity correlations between Entrepreneurial Orientation and Corporate Performance demonstrated themselves significantly only in platform enterprises. The study's results indicate that Organizational Resilience not only directly influence Corporate Performance, but also strengthens Corporate Performance via mutual interaction with Entrepreneurial Orientation and Absorptive Capacity, although the control effect of Organizational Resilience may vary between platform enterprises and general enterprises. I expect such results to provide practical value to the management of small and medium-sized enterprises (SMEs).