• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.324-327
• /
• 2022

Crack inspection of aged structures is mostly conducted by inspectors using surveying tools on site and visually inspecting them. This method greatly depends on professional worker, and consumes a lot of time and money. An artificial intelligence image classification algorithm is used to make reliable and objective judgments. Since 2018, image augmentation techniques have been used in the image pre-processing stage as they lead to high performance improvement. In this study, an analysis algorithm for cracks in concrete structures was developed using image augmentation techniques, in which the accuracy and speed according to the augmentation ratio were compared and measured for optimization. As a result, it was found that 8 times of image augmentation was appropriate when the accuracy was improved and economic feasibility was taken into account.

• Communications for Statistical Applications and Methods
• /
• v.30 no.2
• /
• pp.119-133
• /
• 2023

With the rapid growth of the economy and fossil fuel consumption, the concentration of air pollutants has increased significantly and the air pollution problem is no longer limited to small areas. We conduct statistical analysis with the actual data related to air quality that covers the entire of South Korea using R and Python. Some factors such as SO₂, CO, O₃, NO₂, PM₁₀, precipitation, wind speed, wind direction, vapor pressure, local pressure, sea level pressure, temperature, humidity, and others are used as covariates. The main goal of this paper is to predict air quality index (AQI) spatio-temporal data. The observations of spatio-temporal big datasets like AQI data are correlated both spatially and temporally, and computation of the prediction or forecasting with dependence structure is often infeasible. As such, the likelihood function based on the spatio-temporal model may be complicated and some special modelings are useful for statistically reliable predictions. In this paper, we propose several methods for this big spatio-temporal AQI data. First, random effects with spatio-temporal basis functions model, a classical statistical analysis, is proposed. Next, neural networks model, a deep learning method based on artificial neural networks, is applied. Finally, random forest model, a machine learning method that is closer to computational science, will be introduced. Then we compare the forecasting performance of each other in terms of predictive diagnostics. As a result of the analysis, all three methods predicted the normal level of PM_2.5 well, but the performance seems to be poor at the extreme value.

• Journal of Fashion Business
• /
• v.26 no.1
• /
• pp.1-15
• /
• 2022

Digital transformation has induced changes in human life patterns; consumption patterns are also changing to digitalization. Entering the era of industry 4.0 with the 4th industrial revolution, it is important to pay attention to a new paradigm in the fashion industry, the shift from developer-centered to user-centered in the era of the 3rd industrial revolution. The meaning of storing users' changing life and consumption patterns and analyzing stored big data are linked to consumer sentiment. It is more valuable to read emotions, then develop and distribute products based on them, rather than developer-centered processes that previously started in the fashion market. An AI(Artificial Intelligence) deep learning algorithm that analyzes user emotion big data from user experience(UX) to emotion and uses the analyzed data as a source has become possible. By combining AI technology, the fashion industry can develop various new products and technologies that meet the functional and emotional aspects required by consumers and expect a sustainable user experience structure. This study analyzes clear and useful user experience in the fashion industry to derive the characteristics of AI algorithms that combine emotions and technologies reflecting users' needs and proposes methods that can be used in the fashion industry. The purpose of the study is to utilize information analysis using big data and AI algorithms so that structures that can interact with users and developers can lead to a sustainable ecosystem. Ultimately, it is meaningful to identify the direction of the optimized fashion industry through user experienced emotional fashion technology algorithms.

• The Bulletin of The Korean Astronomical Society
• /
• v.46 no.2
• /
• pp.47.3-48
• /
• 2021

We studied the large scale dynamo process in a system forced by helical magnetic field. The dynamo process is basically nonlinear, but can be linearized with 𝛼&𝛽 coefficients and large scale magnetic field $\bar{B}$. This is very useful to the investigation of solar (stellar) dynamo. A coupled semi-analytic equations based on statistical mechanics are used to investigate the exact evolution of 𝛼&𝛽. This equation set needs only magnetic helicity ${\bar{H}}_M({\equiv}{\langle}{\bar{A}}{\cdot}{\bar{B}}{\rangle},\;{\bar{B}}={\nabla}{\times}{\bar{A}})$ and magnetic energy ${\bar{E}}_M({\equiv}{\langle}{\bar{B}}^2{\rangle}/2)$. They are fundamental physics quantities that can be obtained from the dynamo simulation or observation without any artificial modification or assumption. 𝛼 effect is thought to be related to magnetic field amplification. However, in reality the averaged 𝛼 effect decreases very quickly without a significant contribution to ${\bar{B}}$ field amplification. Conversely, 𝛽 effect contributing to the magnetic diffusion maintains a negative value, which plays a key role in the amplification with Laplacian ∇²(= - k²) for the large scale regime. In addition, negative magnetic diffusion accounts for the attenuation of plasma kinetic energy E_V(= 〈 U² 〉/2) (U: plasma velocity) when the system is saturated. The negative magnetic diffusion is from the interaction of advective term - U • ∇ B from magnetic induction equation and the helical velocity field. In more detail, when 'U' is divided into the poloidal component U_pol and toroidal one U_tor in the absence of reflection symmetry, they interact with - B • ∇ U and - U • ∇ B from ∇ × 〈 U × B 〉 leading to 𝛼 effect and (negative) 𝛽 effect, respectively. We discussed this process using the theoretical method and intuitive field structure model supported by the simulation result.

• The Journal of Engineering Geology
• /
• v.33 no.2
• /
• pp.293-305
• /
• 2023

Three ground models are analyzed using a 1g shaking table and laminar shear box (LSB) to investigate the impact of the ground structure on seismic wave amplification during earthquakes. Multi-layer horizontal, embankment, and basin ground models are selected for this investigation, with each model being divided into dense and loose ground layers, Accelerometers are installed during the construction of each ground model to capture any seismic wave amplification owing th the propagation of an artificial seismic wave, sine wave sweep, and 10-Hz sine wave through a given ground model. The amplification of the tested seismic waves is analyzed using the observed peak ground acceleration and spectrum acceleration. The observed acceleration amplification in the multi-layer horizontal ground model is significantly higher the seismic waves that propagated across the dense ground-loose ground boundary compared with those that only propagated through the dense ground. Furthermore, the observed acceleration amplification gradually increases in the central part of the multi-layer embankment and basin models for the seismic waves that propagated across the dense ground-loose ground boundary.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.295-301
• /
• 2021

This study tried to examine the necessity of AI literacy education to increase the effectiveness of artificial intelligence education ahead of the revision of the next revised curriculum. To this end, AI modeling classes were conducted for high school students and the necessity, content, and training period of AI literacy perceived by students in AI education were investigated through a questionnaire. The results showed that they generally agreed on the need for data utilization and data preprocessing in the AI class, and in the course of the AI class, there were many cases of difficulties due to lack of basic competencies for database use. In particular, it was observed that the understanding of the file structure for data analysis was insufficient and the understanding of the data storage format for data analysis was low. In order to overcome this part, the necessity of prior education for data processing was recognized, and there were many opinions that it is generally appropriate to go to high school at that time. As for the content elements of AI literacy, it was found that there were high demands on the content of data visualization along with data transformation, including data creation and deletion.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.309-314
• /
• 2023

This study examines the development and limitations of current artificial intelligence (AI) music composition programs. AI music composition programs have progressed significantly owing to deep learning technology. However, they possess limitations pertaining to the creative aspects of music. In this study, we collect, compare, and analyze information on existing AI-based music composition programs and explore their technical orientation, musical concept, and drawbacks to delineate future directions for AI music composition programs. Furthermore, this study emphasizes the importance of developing AI music composition programs that create "personalized" music, aligning with the era of personalization. Ultimately, for AI-based composition programs, it is critical to extensively research how music, as an output, can touch the listeners and implement appropriate changes. By doing so, AI-based music composition programs are expected to form a new structure in and advance the music industry.

• Journal of Veterinary Clinics
• /
• v.40 no.3
• /
• pp.238-241
• /
• 2023

This study determined the effect of ovarian status at the beginning of the modified Double-Ovsynch program on reproductive performance in dairy cows. In the study, 1,302 cows were treated with a modified Double-Ovsynch program at 56 days after calving. This program comprises administering gonadotropin-releasing hormones (GnRH), prostaglandin F_2α (PGF_2α) 10 days later, GnRH 3 days later, GnRH 7 days later, and GnRH 56 h later, followed by timed artificial insemination (TAI) 16 h later. At the beginning of the program, cows were categorized according to the size of the largest follicle and the presence of a corpus luteum (CL) in the ovaries as follows: 1) small follicle (<5 mm, SF group, n = 100), 2) medium follicle (8-20 mm, MF group, n = 538), and 3) large follicle (≥25 mm, LF group, n = 354) without a CL, or 4) the presence of a CL (CL group, n = 310). The pregnancies per AI after the first TAI were analyzed by logistic regression using the LOGISTIC procedure, and the logistic model included the fixed effects of the herd size, parity, body condition score (BCS) at the first TAI, TAI period, and ovarian status. A larger herd size, higher BCS at the first TAI, and TAI period with no heat stress increased (p < 0.05) the probability of pregnancy per AI after the first TAI. However, ovarian status at the beginning of the program did not affect (p > 0.05) the pregnancies per AI (ranges of 37.9% to 42.9%). These results show that the modified Double-Ovsynch program can be used effectively while maintaining good fertility regardless of the ovarian status in dairy herds.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.272-275
• /
• 2022

Large-scale online platforms such as MOOCs-Massive Open Online Courses, which provide a variety of educational contents, have provided a learning environment that allows students to freely access and learn anytime and anywhere. Currently, the proportion of online lectures and home-based learning is increasing, and portfolio or experience-based learning such as bootcamp, field activities, and team project-based group learning are also being actively carried out for educational outcomes. At present, interest in nano or microdegree focused on core technology in units of hours or credits is increasing significantly because such strategic intensive education enables effective learning in terms of continuity and efficiency of education. In an era of large changes in job market due to the reorganization of the industrial structure by new technologies, intensive education in specialized new technology fields such as smart mobility, big data, and artificial intelligence is much more conducive to finding a job. With this reason it is attracting attention as an alternative to lifelong learning are receiving In this paper we propose an educational platform that can efficiently and effectively support the purpose learning for the personalized microdegree education in the online learning era.

• (The) Research of the performance art and culture
• /
• no.19
• /
• pp.61-86
• /
• 2009

Jainpalkwangdae(慈仁八廣大) of Kyungsan area in Kyungbuk province was restored through over 50 years gap. This play basically has the structure of conflict - reconcillation, which is differentiated from a masque and a tightrope walking. The characters of this play are a nobleman, Malttuki (a servant), a legal wife and a second wife. Their personality is deviant from a existing Korean masque. This weird and artificial appearance may be a problem in the process of restoration. Otherwise, it might be a very different transmission type of masque. Therefore, we need to investigate why Jainpalkwangdae is different from a traditional masque.