• Journal of the Korean Geotechnical Society
• /
• v.37 no.5
• /
• pp.47-63
• /
• 2021

Recently, the demand for three-dimensional (3D) underground maps from the perspective of digital twins and the demand for linkage utilization are increasing. However, the vastness of national geotechnical survey data and the uncertainty in applying geostatistical techniques pose challenges in modeling underground regional geotechnical characteristics. In this study, an optimal learning model based on multi-layer perceptron (MLP) was constructed for 3D subsurface lithological and geotechnical classification in Seoul, South Korea. First, the geotechnical layer and 3D spatial coordinates of each borehole dataset in the Seoul area were constructed as a geotechnical database according to a standardized format, and data pre-processing such as correction and normalization of missing values for machine learning was performed. An optimal fitting model was designed through hyperparameter optimization of the MLP model and model performance evaluation, such as precision and accuracy tests. Then, a 3D grid network locally assigning geotechnical layer classification was constructed by applying an MLP-based bet-fitting model for each unit lattice. The constructed 3D geotechnical layer map was evaluated by comparing the results of a geostatistical interpolation technique and the topsoil properties of the geological map.

• Journal of the Korean Geotechnical Society
• /
• v.37 no.8
• /
• pp.51-58
• /
• 2021

South Korea, as the 10th country to join the Artemis program led by NASA, is actively supporting various researches related to the lunar exploration. In particular, the utilization of water as a resource in the Moon has been focused since it was discovered that ice exists at the lunar pole as a form of frozen soil. Information on the thermal conductivity of lunar regolith can be used to estimate the existence for ice water extraction by thermal mining. In this study, the vacuum pressure effect on thermal conductivity of KLS-1 was investigated with a DTVC (Dusty Thermal Vacuum Chamber). The reliability of KLS-1 was reconfirmed through comparison with thermal conductivity of known standard lunar regolith simulants such as JSC-1A. An empirical equation to assess thermal conductivity considering dry unit weight and vacuum pressure was proposed. The results from this study can be implemented to simulate lunar cryogenic environment using the DTVC.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.141-148
• /
• 2022

Recently, reinforcement learning combined with deep neural network technology has achieved remarkable success in various fields such as board games such as Go and chess, computer games such as Atari and StartCraft, and robot object manipulation tasks. However, such deep reinforcement learning describes states, actions, and policies in vector representation. Therefore, the existing deep reinforcement learning has some limitations in generality and interpretability of the learned policy, and it is difficult to effectively incorporate domain knowledge into policy learning. On the other hand, dNL-RRL, a new relational reinforcement learning framework proposed to solve these problems, uses a kind of vector representation for sensor input data and lower-level motion control as in the existing deep reinforcement learning. However, for states, actions, and learned policies, It uses a relational representation with logic predicates and rules. In this paper, we present dNL-RRL-based policy learning for transportation mobile robots in a manufacturing environment. In particular, this study proposes a effective method to utilize the prior domain knowledge of human experts to improve the efficiency of relational reinforcement learning. Through various experiments, we demonstrate the performance improvement of the relational reinforcement learning by using domain knowledge as proposed in this paper.

• Knowledge Management Research
• /
• v.22 no.4
• /
• pp.27-40
• /
• 2021

Click-Through Rate (CTR) prediction is a key function that determines the ranking of candidate items in the recommendation system and recommends high-ranking items to reduce customer information overload and achieve profit maximization through sales promotion. The fields of natural language processing and image classification are achieving remarkable growth through the use of deep neural networks. Recently, a transformer model based on an attention mechanism, differentiated from the mainstream models in the fields of natural language processing and image classification, has been proposed to achieve state-of-the-art in this field. In this study, we present a method for improving the performance of a transformer model for CTR prediction. In order to analyze the effect of discrete and categorical CTR data characteristics different from natural language and image data on performance, experiments on embedding regularization and transformer normalization are performed. According to the experimental results, it was confirmed that the prediction performance of the transformer was significantly improved when the L2 generalization was applied in the embedding process for CTR data input processing and when batch normalization was applied instead of layer normalization, which is the default regularization method, to the transformer model.

• Land and Housing Review
• /
• v.13 no.1
• /
• pp.67-84
• /
• 2022

This study aims to investigate the value of greenbelts exploring how they can be linked with green infrastructure networks. This research interprets the results of geographical information system (GIS) analysis differently from a conventional approach. The findings of the research are four-fold based on the analysis of the Daejeon Metropolitan Area. First, the most controversial greenbelts are laid on Yuseong-gu because the relaxation of the greenbelts for new housing development has caused outstanding issues since the early 2000s. Decisions on further relaxation or restoration of the greenbelts, which will provide a new direction for the establishment of green infrastructure networks, should be made through accurate environmental assessments. Second, the connected north-south corridors of large cities will affect the greenbelts not only in Daejeon, but also in the entire Chungcheong Provinces, and surrounding local municipalities, which should be considered for the revision of the greenbelt policy. Third, it is expected to experience growing development pressures towards neighboring municipalities due to the ongoing strict greenbelt policy. Among them, the most likely areas are Sejong City to the north and Nonsan to the south, requiring policy measures. Fourth, the value of green infrastructure should be added to current evaluation criteria rather than a binary approach - relaxing or preserving the greenbelts - to be holistically integrated with a metropolitan plan.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.47-67
• /
• 2022

Computer and Internet information technologies(ICTs) have changed the modern service industry and people's life style. In particular, the global spread of COVID-19 has attracted more attention to contact service types such as self-service technology. With the increase in labor costs and the enhancement of consumer self-awareness, more and more companies transfer part of their work to customers through their own service technology. This study seeks to answer the following questions. (1) Do technology difficulty and safety perception affect customer value recognition in the self-service technologies? (2) Does customer value recognition influence the intention to use such technologies continuously? This study conducted an empirical analysis with 327 samples to validate the influence of self-service characteristics(technology difficulty and safety perception) on customer value recognition and continuous utilization intentions. Also, it analyzes the moderating effects of age and frequency of use on the relationship between self-service characteristics and customer value recognition. The study results show that the technology difficulty does not affect the customer's perceived value recognition; and the higher the customer's value recognition, the higher the intention of continuous use.

• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.4
• /
• pp.1-18
• /
• 2021

Today, record management has become more important in management as records generated from administrative work and data production have increased significantly, and the development of information and communication technology, the working environment, and the size and various functions of the government have expanded. It is explained as an example in connection with the concept of public records with the characteristics of big data and big data characteristics. Social, Technological, Economical, Environmental and Political (STEEP) analysis was conducted to examine such areas according to the big data generation environment. The appropriateness and necessity of applying big data technology in the field of public record management were identified, and the top priority applicable framework for public record management work was schematized, and business implications were presented. First, a new organization, additional research, and attempts are needed to apply big data analysis technology to public record management procedures and standards and to record management experts. Second, it is necessary to train record management specialists with "big data analysis qualifications" related to integrated thinking so that unstructured and hidden patterns can be found in a large amount of data. Third, after self-learning by combining big data technology and artificial intelligence in the field of public records, the context should be analyzed, and the social phenomena and environment of public institutions should be analyzed and predicted.

• The Journal of the Korea Contents Association
• /
• v.22 no.4
• /
• pp.742-753
• /
• 2022

Recently, the globalization of culture and the global trend of K-culture have become a good background for further developing and promoting Korean traditional culture. However, although Korean traditional music has an excellent notation method called Jeongganbo developed by King Sejong, it is gradually not being used as the universality of Western notation. However, since the 7th curriculum, the proportion of introduction and utilization of Jeongganbo in elementary music education has been increasing. And this is a good opportunity to re-generalize our unique traditional notation. On the other hand, in addition to practicing the interpretation of the notation method, more diverse tools will be needed to activate the practice of Jeongganbo. Therefore, this study studied the design of a web program that can make Jeongganbo on the web without installation or download. In addition, in order to increase the user's convenience in the process of publishing Jeongganbo, it designs and proposes a method of inputting using a computer keyboard like a piano keyboard and method of listening to input music information through MIDI function and save it as a file. Through this study, it is possible to develop a web program that anyone can easily and simply approach, practice, and publish, and it is expected to be a useful tool for practicing Korean traditional music or publishing traditional music in the future.

• Korean Journal of Remote Sensing
• /
• v.38 no.2
• /
• pp.153-166
• /
• 2022

Waterstorage is one of the factorsthat most directly represent the amount of available water resources. Since the effects of drought can be more intuitively expressed, it is also used in variousstudies for drought evaluation. In a recent study, hydrological drought was evaluated through information on observing reservoirs with optical images. The short observation cycle and diversity of optical satellites provide a lot of data. However, there are some limitations because it is vulnerable to the influence of weather or the atmospheric environment. Therefore, thisstudy attempted to conduct a study on estimating the drought index using Synthetic Aperture Radar (SAR) image with relatively little influence from the observation environment. We produced the waterbody of Baekgok and Chopyeong reservoirs using SAR images of Sentinel-1 satellites and calculated the Reservoir Area Drought Index (RADI), a hydrological drought index. In order to validate the applicability of RADI to drought monitoring, it was compared with Reservoir Storage Drought Index (RSDI) based on measured storage. The two indices showed a very high correlation with the correlation coefficient, r=0.87, Area Under curve, AUC=0.97. These results show the possibility of regional-scale hydrological drought monitoring of SAR-based RADI. As the number of available SAR images increases in the future, it is expected that the utilization of drought monitoring will also increase.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.193-202
• /
• 2022

The purpose of this study is to propose an effective informatization policy by categorizing consumer groups according to the level of digital divide and identifying the characteristics of each type. For this end, a total of 402 data were collected through an online and on-site surveys targeting consumers with internet experience, and the data were analyzed using the SPSS 26.0 program. As a result of conducting a K-means cluster analysis based on access to, capability, and utilization of digital devices, four consumer groups were categorized: 'device lover', 'proficient user', 'general user', and 'digital alienated'. By consumer type, significant differences were found in demographic characteristics, social capital, perception of the future information society, attitude toward technology as innovativeness, discomfort and familiarity, which are the antecedent variables of the digital divide. Significant differences in digital device satisfaction and intention to use, which are outcome variables of the digital divide, were also confirmed by consumer type. This study is academically and practically valuable in that it proposes customized informatization policies for each consumer group according to the level of digitization.