• Ecology and Resilient Infrastructure
• /
• v.9 no.4
• /
• pp.207-217
• /
• 2022

The purpose of this study was to understand and develop various environmental designs to play a key roles in urban design, so that public green spaces remain vital with future changes. Variability in space, ecology, and society were analyzed based on research of variable environmental spaces in 11 selected studies conducted locally and abroad since the 2010s. Moreover, landscape characteristics, design methods, and design strategies were analyzed accordingly for each case. The results of the study showed that variability in landscapes provided various possibilities for spatial change and satisfied people's functional needs for spatial use. In addition, variable environmental design greatly compensated for the defects by solving the issues associated with fixed landscapes by increasing the flexibility of use and adaptability to the environment. This study showed that variable design is applicable to public green spaces; environmental stress; and variability in architecture, the environment, and landscaping, and it contributes to enhancing the sustainability and resilience of the environment.

• Journal of Korea Multimedia Society
• /
• v.25 no.5
• /
• pp.748-756
• /
• 2022

Thanks to the competition of AlphaGo and Sedol Lee, machine learning has received world-wide attention and huge investments. The performance improvement of computing devices greatly contributed to big data processing and the development of neural networks. Artificial intelligence not only imitates human beings in many fields, but also seems to be better than human capabilities. Although humans' creation is still considered to be better and higher, several artificial intelligences continue to challenge human creativity. The quality of some creative outcomes by AI is as good as the real ones produced by human beings. Sometimes they are not distinguishable, because the neural network has the competence to learn the common features contained in big data and copy them. In order to confirm whether artificial intelligence can express the inherent characteristics of different arts, this paper proposes a new neural network model called Humming. It is an experimental model that combines vgg16, which extracts image features, and DeepJ's architecture, which excels in creating various genres of music. A dataset produced by our experiment shows meaningful and valid results. Different results, however, are produced when the amount of data is increased. The neural network produced a similar pattern of music even though it was a different classification of images, which was not what we were aiming for. However, these new attempts may have explicit significance as a starting point for feature transfer that will be further studied.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.199-206
• /
• 2022

A malfunction or breakdown of a manufacturing facility leads to product defects and the suspension of production lines, resulting in huge financial losses for manufacturers. Due to the spread of smart factory services, a large amount of data is being collected in factories, and AI-based research is being conducted to predict and diagnose manufacturing facility breakdowns or manufacturing site efficiency. However, because of the characteristics of manufacturing data, such as a severe class imbalance about abnormalities and ambiguous label information that distinguishes abnormalities, developing classification or anomaly detection models is highly difficult. In this paper, we present an deep learning algorithm for anomaly detection of a manufacturing facility using reconstruction loss of CNN-based model and ananlyze its performance. The algorithm detects anomalies by relying solely on normal data from the facility's manufacturing data in the exclusion of abnormal data.

• Korean Journal of Agricultural Science
• /
• v.49 no.1
• /
• pp.61-75
• /
• 2022

The first purpose of this study is to evaluate the usefulness of pork traceability data, which is monthly time-series data, and to draw implications with regard to its usefulness. The second purpose is to construct a dynamic ecological equation model (DEEM) that reflects the biological characteristics at each growth stage, such as pregnancy, birth and growth, and the slaughter of pigs, using traceability data. With the monthly pig model devised in this study, it is expected that the number of slaughtered animals (supply) that can be shipped in the future is predictable and that policy simulations are possible. However, this study was limited to traceability data and focused only on building a supply-side model. As a result of verifying the traceability data, it was found that approximately 6% of farms produce by mixing great grand parent (GGP), grand parent (GP), parent stock (PS), and artificial insemination (AI), meaning that it is necessary to separate them by business type. However, the analysis also showed that the coefficient values estimated by constructing an equation for each growth stage were consistent with the pig growth outcomes. Also, the model predictive power test was excellent. For this reason, it is judged that the model design and traceability data constructed with the cohort and the dynamic ecological equation model system considering biological growth and shipment times are excellent. Finally, the model constructed in this study is expected to be used as basic data to inform producers in their decision-making activities and to help with governmental policy directions with regard to supply and demand. Research on the demand side is left for future researchers.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.9
• /
• pp.105-111
• /
• 2023

Currently, most of content restoration using artificial intelligence learning is 2D learning. However, 3D form of artificial intelligence learning is in an incomplete state due to the disadvantage of requiring a lot of computation and learning speed from the existing 2 axes (X, Y) to 3 axes (X, Y, Z). The purpose of this paper is to secure a data-set for artificial intelligence learning by analyzing and 3D modeling the stone pagodas of ourinari by era based on the two-dimensional information (image) of cultural assets. In addition, we analyzed the differences and characteristics of towers in each era in Korea, and proposed a feature modeling method suitable for artificial intelligence learning. Restoration of cultural properties relies on a variety of materials, expert techniques and historical archives. By recording and managing the information necessary for the restoration of cultural properties through this study, it is expected that it will be used as an important documentary heritage for restoring and maintaining Korean traditional pagodas in the future.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.2
• /
• pp.135-145
• /
• 2023

ChatGPT is an artificial intelligence-based conversation agent developed by OpenAI using natural language processing technology. In this study, an empirical study was conducted on incumbent teachers on the intention to use the newly emerged Chat GPT. First, we studied how accuracy, entertainment, system accessibility, perceived usefulness, and perceived ease of use affect ChatGPT's acceptance intention. In addition, we analyzed whether perceived usefulness and perceived ease of use differ in the intention to accept depending on the digital technology of teachers. As a result of the study, the suitability of the structural equation model was generally good. Accuracy and entertainment were found to have a significant effect on perceived usefulness, and system accessibility was found to have a significant effect on perceived ease of use. In the analysis of teachers' digital technology control effects, it was found that perceived usefulness and perceived ease of use had a control effect between acceptance intentions. It was found that the group with high digital skills of teachers was strongly intended to accept the service regardless of perceived usefulness and ease of use. In the group with low digital skills of teachers, it is thought that ChatGPT's service shows the acceptance intention only when the perceived usefulness and ease of use are high. Therefore, in the group with low digital technology, it is necessary to seek teaching activities such as the development of instructional models using ChatGPT.

• Industry Promotion Research
• /
• v.8 no.1
• /
• pp.55-68
• /
• 2023

The purpose of this study is to investigate the factors that influence the intention to continuously use the RPA program used in the financial industry for those working in the financial industry. In particular, the purpose of this study is to understand the will to accept and the perception of acceptance conflict by considering the characteristics of individuals in the relationship between work and information technology. As a result of the study, it can be confirmed that the RPA system based on intelligent process automation including artificial intelligence should be further strengthened in the transformation of a digitalized enterprise rather than the RPA based on simple task automation that is currently most used. In general, the phenomenon of cognitive dissonance was prominent for the adoption of new technology, but the phenomenon of cognitive dissonance did not appear for the continued use of RPA in the financial industry. Able to know. In the future in the financial industry, it is thought that the change in the labor organization will be accelerated as the suitability of repetitive tasks and technologies is increased.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.56 no.3
• /
• pp.331-340
• /
• 2023

To estimate the biological reference points, suitable for fisheries management of sandfish Arctoscopus japonicas in the East Sea of Korea, we simulated the yield-per-recruit (Y/R) from age 0 to 6 (0-2,555 days). The stimulation was based on two instantaneous natural mortality conditions: size-dependent (M_t, d^-1) and constant (M_cons, d^-1); Subsequently, the biological reference points of the two mortality conditions was compared. M_t decreased from 0.0075 d^-1 to 0.0018 d^-1 depending on growth, and M_cons remained constant at 0.0011 d^-1 for all ages. Our Y/R model showed that the maximum yield of M_cons was 14 times higher than that of the M_t. The length at first capture to maximize the harvest at the F_0.1 points of the two natural mortality conditions was L_c,t=10.2 cm (TL) and L_c,cons=17 cm (TL). We concluded that M_t was more suitable for estimating M than M_cons; this is because L_c,t showed minimal difference from the current fishing regulations (11 cm, TL), and M_t reflected more biological characteristics than M_cons. We suggest that 10.2 cm and 0.8 as the suitable length at first capture and corresponding age, respectively for efficient fisheries management of sandfish.

• Communications of Mathematical Education
• /
• v.37 no.3
• /
• pp.497-516
• /
• 2023

The purpose of this study is to explore the possibility of enhancing teachers' pedagogical design capacity using ChatGPT. For this purpose, a survey was conducted to investigate preservice teachers' perceptions of ChatGPT, and lesson plans created using ChatGPT were analyzed from the perspectives of design elements, conversations with ChatGPT, and information transforming. The results showed that pre-service teachers have a rather passive attitude toward the use of ChatGPT, and that teacher moderation and ChatGPT characteristics affect pre-service teachers' perceptions of the use of ChatGPT. In addition, pre-service teachers mainly used ChatGPT for motivational activities and play activities, and there were significant differences in the level of utilization of ChatGPT among individuals, i.e., how they interacted with ChatGPT and how they transformed information. Based on these findings, we explored the possibility of using ChatGPT for teacher professional development and teacher education.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.629-634
• /
• 2023

In this paper, the design of a miniaturized wideband tapered slot antenna using slots combining various types of fan-shaped structures was studied. To miniaturize the tapered slot antenna and make it operate at low frequencies, slots combining fan-shaped structures were added to the ground plane of the tapered slot antenna. The miniaturization design process of the final proposed antenna was systematically explained by comparing the input reflection coefficient and gain variations when each fan-shaped structure was appended, compared to when there was no slot. The proposed miniaturized wideband tapered slot antenna using slots combining the fan-shaped structures was fabricated on an RF-35 substrate and its measured characteristics were compared with the simulation results. Experiment results show that the frequency band with a voltage standing wave ratio (VSWR) less than 2 was 2.59-11.39 GHz, and gain within the band was measured to be 3.3-7.0 dBi. The proposed miniaturized wideband tapered slot antenna can be reduced in size by 36.9%, compared to when there are no slots in the ground plane.