• Smart Media Journal
• /
• v.7 no.3
• /
• pp.43-50
• /
• 2018

Hanok (a traditional Korean-style house) has recently become a popular attraction for tourists all over the world. Jeonju Hanok Village, for example, attracted about 10 million visitors for 2 consecutive years. Observing Hanok's popularity, many local governments drew up plans to improve tourism dynamics by strengthening the advantages of Hanok. Emotionally rich experience is required to offer a greater satisfying experience that meets the demands of tourists. However, very few studies yet have addressed how to measure those emotions felt by users while experiencing Hanok. As an attempt to improve this situation, 182 emotional words were collected from earlier studies and classified into 33 groups with the Delphi method. Among the emotional words in each of the 33 groups, those of overlapping concepts on the characteristics of Hanok were re-grouped, and extracted the most appropriate 68 words. Additionally, a survey was conducted with 325 people who had experienced Hanok to gather 30-most representative emotions for measuring emotions felt from Hanok. The factor analysis of the 30 representative emotions resulted in classified 6 factors based on common features of emotional words: senses of aesthetics, happiness, novelty, ownership, balance and relaxation. The 30 representative emotions and six emotion categories found out by this study can help measure how much people feel certain emotions while experiencing hanoks. Further study will explore the degree of emotions hanok users feel about objects of hanok, such as roof materials and shapes, and body shapes.

• Convergence Security Journal
• /
• v.21 no.1
• /
• pp.191-200
• /
• 2021

Artificial intelligence technology is developing in an environment where a lot of data is produced due to the development of computing technology, a cloud environment that can store data, and the spread of personal mobile phones. Among these artificial intelligence technologies, the deep neural network provides excellent performance in image recognition and image classification. There have been many studies on image detection for forest fires and fire prevention using such a deep neural network, but studies on detection of cigarette smoking were insufficient. Meanwhile, military units are establishing surveillance systems for various facilities through CCTV, and it is necessary to detect smoking near ammunition stores or non-smoking areas to prevent fires and explosions. In this paper, by reflecting experimentally optimized numerical values such as activation function and learning rate, we did the detection of smoking pictures and non-smoking pictures in two cases. As experimental data, data was constructed by crawling using pictures of smoking and non-smoking published on the Internet, and a machine learning library was used. As a result of the experiment, when the learning rate is 0.004 and the optimization algorithm Adam is used, it can be seen that the accuracy of 93% and F1-score of 94% are obtained.

• Resources Recycling
• /
• v.32 no.1
• /
• pp.42-49
• /
• 2023

The glass ceramic secondary resource containing Li-Al-Si is used in inductor, fireproof glass, and transparent cookware and accounts for 14% of the total consumption of Li, which is the second most widely used after Li-ion batteries. Therefore, new Li resources should be explored when the demand for Li is exploding, and extensive research on Li recovery is needed. Herein, we recovered Li from fireproof Li-Al-Si glass ceramic, which is a new secondary resource containing Li. The fireproof glass among all Li-Al-Si glass ceramics was used as raw material that contained 1.5% Li, 9.4% Al, and 28.9% Si. The process for recovering Li from the fireproof glass was divided into two parts: (1) calcium salt roasting and (2) water leaching. In calcium salt roasting, a sample of fireproof glass was crushed and ground below 325 mesh. The leaching efficiency was compared based on the presence or absence of heat treatment of the fireproof glass. Moreover, the leaching rates based on the input ratios of calcium salt, Li-Al-Si glass, and ceramics and the leaching process based on calcium salt roasting temperatures were compared. In water leaching, the leaching and recovery rates of Li based on different temperatures, times, solid-liquid ratios, and number of continuous leaching stages were compared. The results revealed that fireproof glass ceramics containing Li-Al-Si should be heat treated to change phase to beta-type spodumene. CaCO₃ salt should be added at a ratio of 6:1 with glass ceramics containing Li-Al-Si, and then leached 4 times or more to achieve a recovery efficiency of Li over 98% from a solution containing 200 mg/L of Li.

• Journal of the Korea Concrete Institute
• /
• v.19 no.1
• /
• pp.121-130
• /
• 2007

To investigate the enhancement in strength and deformation capacities of concrete confined by FRP composites, tests under axial loads were carried out on three groups of thirty six short columns in circular section with diverse GFRP confining reinforcement. The major test variables considered include fiber content or orientation, wrap or tube type by varying the end loading condition, and continuous or discontinuous confinement depending on the presence of vortical spices between its two halves. The circumferential FRP strains at failure for different types of confinements were also investigated with emphasis. Various analytical models capable of predicting the ultimate strength and strain of the confined concrete were examined by comparing to observed results. Tests results showed that FRP wraps or tubes provide the substantial increase in strength and deformation, while partial wraps comprising the vertical discontinuities fail in an explosive manner with less increase in strength, particularly in deformation. A bilinear stress-strain response was observed throughout all tests with some variations of strain hardening. The failure hoop strains measured on the FRP surface were less than those obtained from the tensile coupons in all tests with a high degree of variation. In overall, existing predictive equations overestimated ultimate strengths and strains observed in present tests, with a much larger scatter related to the latter. For more accuracy, two simple design- oriented equations correlated with present tests are proposed. The strength equation was derived using the Mohr-Coulomb failure criterion, whereas the strain equation was based on entirely fitting of test data including the unconfined concrete strength as one of governing factors.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.307-325
• /
• 2023

Due to the prolonged COVID-19 pandemic, the frequency of people who are tired of living indoors visiting nearby mountains and national parks to relieve depression and lethargy has exploded. There is a place where thousands of people who came out of nature stop walking and breathe and rest, that is the mineral spring. Even in mountains or national parks, there are about 600 mineral springs that can be found occasionally in neighboring parks or trails in the metropolitan area. However, due to irregular and manual water quality tests, people drink mineral water without knowing the test results in real time. Therefore, in this study, we intend to develop a model that can predict the quality of the spring water in real time by exploring the factors affecting the quality of the spring water and collecting data scattered in various places. After limiting the regions to Seoul and Gyeonggi-do due to the limitations of data collection, we obtained data on water quality tests from 2015 to 2020 for about 300 mineral springs in 18 cities where data management is well performed. A total of 10 factors were finally selected after two rounds of review among various factors that are considered to affect the suitability of the mineral spring water quality. Using AutoML, an automated machine learning technology that has recently been attracting attention, we derived the top 5 models based on prediction performance among about 20 machine learning methods. Among them, the catboost model has the highest performance with a prediction classification accuracy of 75.26%. In addition, as a result of examining the absolute influence of the variables used in the analysis through the SHAP method on the prediction, the most important factor was whether or not a water quality test was judged nonconforming in the previous water quality test. It was confirmed that the temperature on the day of the inspection and the altitude of the mineral spring had an influence on whether the water quality was unsuitable.