• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.25-30
• /
• 2022

This study is a study on the filter bubble reinforcement phenomenon of SNS recommendation algorithm such as YouTube, which is a characteristic of the Russian-Ukraine war (2022), and the victory or defeat factors of the hybrid war. This war is identified as a hybrid war, and the use of New Media based on the SNS recommendation algorithm is emerging as a factor that determines the outcome of the war beyond political leverage. For this reason, the filter bubble phenomenon goes beyond the dictionary meaning of confirmation bias that limits information exposed to viewers. A YouTube video of Ukrainian President Zelensky encouraging protests in Kyiv garnered 7.02 million views, but Putin's speech only 800,000, which is a evidence that his speech was not exposed to the recommendation algorithm. The war of these SNS recommendation algorithms tends to develop into an algorithm war between the US (YouTube, Twitter, Facebook) and China (TikTok) big tech companies. Influenced by US companies, Ukraine is now able to receive international support, and in Russia, under the influence of Chinese companies, Putin's approval rating is over 80%, resulting in conflicting results. Since this algorithmic empowerment is based on the confirmation bias of public opinion by 'filter bubble', the justification that a new guideline setting for this distortion phenomenon should be presented shortly is drawing attention through this Russia-Ukraine war.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.43-51
• /
• 2023

As online transactions increase, the image of clothing has a great influence on consumer purchasing decisions. The importance of image information for clothing materials has been emphasized, and it is important for the fashion industry to analyze clothing images and grasp the materials used. Textile materials used for clothing are difficult to identify with the naked eye, and much time and cost are consumed in sorting. This study aims to classify the materials of textiles from clothing images based on deep learning algorithms. Classifying materials can help reduce clothing production costs, increase the efficiency of the manufacturing process, and contribute to the service of recommending products of specific materials to consumers. We used machine vision-based deep learning algorithms ResNet and Vision Transformer to classify clothing images. A total of 760,949 images were collected and preprocessed to detect abnormal images. Finally, a total of 167,299 clothing images, 19 textile labels and 20 fabric labels were used. We used ResNet and Vision Transformer to classify clothing materials and compared the performance of the algorithms with the Top-k Accuracy Score metric. As a result of comparing the performance, the Vision Transformer algorithm outperforms ResNet.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.51 no.4
• /
• pp.76-89
• /
• 2023

One of the technologies in urban agriculture, hydroponics cultivation, has primarily focused on technological development, resulting in a lack of research on urban agriculture's cultural utilization aspects, encompassing cultural values associated with urban residents' leisure activities. Therefore, this study aimed to identify the participation constraints perceived by school community members when implementing urban farming activities using hydroponics and understand the structural relationships between the variables that influence decision-making from the perspective of leisure activities in urban farming. As a result, participation constraints in urban farming activities utilizing hydroponics were first categorized into intrinsic, interpersonal, and structural factors. Second, the results of hypothesis model verification showed that interpersonal constraints significantly influenced the participants' willingness to participate and their expected behavior. This study found the multidimensional perceptions of school community members regarding hydroponic urban farming conducted in urban spaces, particularly rooftops, and revealed the influence of decision-making factors on participation when conducting urban farming activities using hydroponic cultivation.

• Journal of Korean Society of Forest Science
• /
• v.112 no.3
• /
• pp.363-373
• /
• 2023

Forest biomass surveys are regularly conducted to assess and manage forests as carbon sinks. LiDAR (Light Detection and Ranging), a remote sensing technology, has attracted considerable attention, as it allows for objective acquisition of forest structure information with minimal labor. In this study, we propose a method for estimating overstory and understory biomass in forest stands using backpack laser scanning (BPLS) and unmanned aerial vehicle laser scanning (UAV-LS), and assessed its accuracy. For overstory biomass, we analyzed the accuracy of BPLS and UAV-LS in estimating diameter at breast height (DBH) and tree height. For understory biomass, we developed a multiple regression model for estimating understory biomass using the best combination of vertical structure metrics extracted from the BPLS data. The results indicated that BPLS provided accurate estimations of DBH (R² =0.92), but underestimated tree height (R² =0.63, bias=-5.56 m), whereas UAV-LS showed strong performance in estimating tree height (R² =0.91). For understory biomass, metrics representing the mean height of the points and the point density of the fourth layer were selected to develop the model. The cross-validation result of the understory biomass estimation model showed a coefficient of determination of 0.68. The study findings suggest that the proposed overstory and understory biomass survey methods using BPLS and UAV-LS can effectively replace traditional biomass survey methods.

• Journal of the Korean Geotechnical Society
• /
• v.39 no.8
• /
• pp.29-39
• /
• 2023

The degree of saturation determines the connectivity of void space and the particle surface. Thus, it greatly affects the electrical conductivity of soils. This study aimed to analyze the electrical conductivities of coarse grains with a high relevance of pore water conduction and fine grains with a high relevance of surface conduction based on the degree of saturation. It also aimed to express the electrical conductivity of unsaturated soils as a combination of surface and pore water conductions using the modified Archie's equation. Samples were prepared in a plastic cell equipped with four electrodes, and the electrical conductivity was measured based on the porosity at various degrees of saturation (40%~100%). The results demonstrate that Archie's equation can be used to express the electrical conductivity of coarse grains, with a saturation exponent of ~1.93 regardless of the pore water conductivity. However, the saturation exponent of fine grains varied considerably with pore water concentration. This variation can be attributed to the relative magnitude of surface conduction with respect to the electrical conductivity of soils at different pore water concentrations. Thus, the degree of saturation has varying effects on pore water conduction and surface conduction. Therefore, different saturation exponents must be used for pore water conduction and surface conduction to predict the electrical conductivity of unsaturated soils using the modified Archie's equation.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.478-478
• /
• 2022

섬진강은 하굿둑이 없는 열린 하구로서 하구로부터 약 21km까지 조석의 영향을 받아 강물의 염도가 시간에 따라 변하는 환경이다. 오랫동안 섬진강 하구는 다양한 원인으로부터 바다화로 대표되는 염하구 문제가 지역 현안 사항으로 제기되어 왔다. 상류에서의 용수사용 증가로 인한 하천 유하량 감소 또한 그 원인들 중 하나로 판단됨에 따라 실제 하구까지 내려오는 하천유량과 바다로부터 유입되는 해수를 구분하여 정량화하는 연구가 필요한 사안이다. 본 연구의 목적은 섬진강 수계 하구에서의 다양한 생태환경을 보전하기 위한 적정 염분유지가 요구됨에 따라 섬진강하구 염분계측기(섬진강대교)를 설치하여 염분농도를 관측하고 하천유량, 하천취수 및 해양조위에 따른 염분농도 변화를 모의하여 하천유량과 염분과의 관계를 제시하고자 하였다. 본 연구에서는 EFDC(Environmental Fluid Dynamics Code) 수치모델을 이용하여 상류로는 구례군(송정리) 수위관측소부터 하류로는 여수해만 및 문의리까지의 구역을 설정하고 광양조위, 하동수위 및 고정식 염분 계측기 관측염분농도 자료를 이용하여 수치모델링의 재현성을 검증하였다. 검증 결과, 결정계수(R²)는 0.87(하동수위), 0.93(광양조위), 0.56(섬진강대교 염도)를 나타냈다. 모델 검보정 후 하천유량에 따른 염분변화 실험을 실시하여 염분농도 거동을 분석하였다. 모델 결과, 섬진강하구에서의 염분거동은 소조기때 염분체류 현상으로 인해 대조기 거동과는 큰 차이를 나타냈다. 따라서, 모델링 결과를 이용한 유량-염분 조견표는 각각 대조기와 소조기로 구분하여 산정하였다. 대조기때는 송정유량이 10톤/초의 평균갈수량이 흐를 경우 다압에서의 취수량이 2.52톤/초 ~ 4.63/초로 증가할수록 18.8psu ~ 19.9psu로 증가하였다. 소조기의 경우는 25.5psu ~ 25.7psu로 대조기와 비교하여 크게 증가됨을 나타냈다. 본 연구의 결과는 객관적인 생태환경 보전을 위한 적정염분농도 범위가 도출된다면 이를 유지하기 위한 필요유량과 필요유량을 확보하기 위한 장단기적인 대책수립이 가능할 것으로 기대된다.

• Journal of Navigation and Port Research
• /
• v.47 no.1
• /
• pp.18-24
• /
• 2023

After the Great East Japan Earthquake, many reports and books that compiled testimonies of adult victims were published. Thus, refugee situations are well known, but information on the refugee situations of Japanese students is not. This is because what actions the students took and how they sought refuge from an earthquake or tsunami have not been fully recognized. The purpose of this study was to examine and analyze students' refuge behavior in the Great East Japan Earthquake and to predict the refuge behavior of students affected by future disasters. The results of the study showed that students passively acquired information about earthquakes and tsunamis and that their refuge behavior was highly dependent on adults. Immediately after an earthquake, people tended to protect themselves and stay in place until the shaking stopped. However, they tended to move to another place after the shaking occurred frequently. Students living on ria coastlines were likely to move to high places to escape the threat of earthquakes and tsunamis, whereas students living in plain regions were likely to move vertically to tall buildings, such as schools. As for the mode of movement to refugee shelters, the students arrived at the final refugee shelters in one move, and it is assumed that the refugee shelters should be decided in advance and the students should move there.

• Journal of the Korean Geotechnical Society
• /
• v.25 no.11
• /
• pp.105-115
• /
• 2009

The Jeju sand was sampled from the beach in Jeju Island and its basic properties were analyzed. The cementation effect of Jeju coastal sediments was evaluated from in-situ tests such as SPT, CPT, and the Suspension-PS test. It was shown from test results that the Jeju sand has high extreme void ratios due to the angularity of grains and the intra-particle voids of hollow particles, similar to typical calcareous sands. From cone penetration test in the calibration chamber, it was found that the cone resistance($q_c$)-relative density($D_R$)-vertical effective stress(${\sigma}_v'$) relation of Jeju sand almost matches that of high compressible quartz sand. However, the $q_C-D_R-{\sigma}_v'$ correlation suggested for uncemented Jeju sand overestimates the relative density of coastal sediments of Jeju Island due to the cementation effect. From the analysis of the relation of cone resistance, N value, and small strain shear modulus measured in-situ, it seems reasonable to assume that the coastal sediment of Jeju Island is a naturally cemented one.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.1
• /
• pp.45-54
• /
• 2010

It is important to calculate the natural frequency of a piled structure in the design stage in order to prevent resonance-induced damage to the pile foundation and analyze the dynamic behavior of the piled structure during an earthquake. In this paper, a simple but relatively accurate method employing a mass-spring model is presented for the evaluation of the natural frequency of a pile-soil system. Greatly influencing the calculation of the natural frequency of a piled structure, the spring stiffness between a pile and soil was evaluated by using the coefficient of subgrade reaction, the p-y curve, and the subsoil elastic modulus. The resulting natural frequencies were compared with those of 1-g shaking table tests. The comparison showed that the natural frequency of the pile-soil system could be most accurately calculated by constructing a stiffness matrix with the spring stiffness of the Reese (1974) method, which utilizes the coefficient of the subgrade reaction modulus, and Yang's (2009) dynamic p-y backbone curve method. The calculated natural frequencies were within 5% error compared with those of the shaking table tests for the pile system in dry dense sand deposits and 5% to 40% error for the pile system in saturated sand deposits depending on the occurrence of excess pore water pressure in the soil.