• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.17 no.6
• /
• pp.121-132
• /
• 2018

Weather is an important factor affecting roadway transportation in many aspects such as traffic flow, driver 's driving patterns, and crashes. This study focuses on the relationship between weather and road surface condition and develops a model to estimate the road surface condition using machine learning. A road surface sensor was attached to the probe vehicle to collect road surface condition classified into three categories as 'dry', 'moist' and 'wet'. Road geometry information (curvature, gradient), traffic information (link speed), weather information (rainfall, humidity, temperature, wind speed) are utilized as variables to estimate the road surface condition. A variety of machine learning algorithms examined for predicting the road surface condition, and a two - stage classification model based on 'Random forest' which has the highest accuracy was constructed. 14 days of data were used to train the model and 2 days of data were used to test the accuracy of the model. As a result, a road surface state prediction model with 81.74% accuracy was constructed. The result of this study shows the possibility of estimating the road surface condition using the existing weather and traffic information without installing new equipment or sensors.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.13-20
• /
• 2022

IEEE 802.11ay Wi-Fi is the next generation wireless technology and operates in mmWave band. It supports the MU-MIMO (Multiple User Multiple Input Multiple Output) transmission in which an AP (Access Point) can transmit multiple data streams simultaneously to multiple STAs (Stations). To this end, the AP should perform MU-MIMO beamforming training with the STAs. For efficient MU-MIMO beamforming training, it is important for the AP to estimate signal strength measured at each STA at which multiple beams are used simultaneously. Therefore, in the paper, we propose a deep learning-based link quality estimation scheme. Our proposed scheme estimates the signal strength with high accuracy by utilizing a deep learning model pre-trained for a certain indoor or outdoor propagation scenario. Specifically, to estimate the signal strength of the multiple concurrent beams, our scheme uses the signal strengths of the respective single beams, which can be obtained without additional signaling overhead, as the input of the deep learning model. For performance evaluation, we utilized a Q-D (Quasi-Deterministic) Channel Realization open source software and extensive channel measurement campaigns were conducted with NIST (National Institute of Standards and Technology) to implement the millimeter wave (mmWave) channel. Our simulation results demonstrate that our proposed scheme outperforms comparison schemes in terms of the accuracy of the signal strength estimation.

• Journal of the Korean Society of Radiology
• /
• v.16 no.6
• /
• pp.687-695
• /
• 2022

To find a 3D printer material that can replace lead used as a shield for high-energy electron beam treatment, the shielding composites were simulated by using MCNP6 programs. The Percent Depth Dose (PDD), Flatness, and Symmetry of linear accelerators emitting high-energy electron beams were measured, and the linear accelerator was compared with MCNP6 after simulation, confirming that the source term between the actual measurement and simulation was consistent. By simulating the lead shield, the appropriate thickness of the lead shield capable of shielding 95% or more of the absorbed dose was selected. Based on the absorption dose data for lead shield with a thickness of 3 mm, the shielding performance was analyzed by simulating 1, 5, 10, and 15 mm thicknesses of ABS+W (10%), ABS+Bi (10%), and PLA+Fe (10%). Each prototype was manufactured with a 3D printer, measured and analyzed under the same conditions as in the simulation, and found that when ABS+W (10%) material was formed to have a thickness of at least 10mm, it had a shielding performance that could replace lead with a thickness of 3mm. The surface morphology and atomic composition of the ABS+W (10%) material were evaluated using a scanning electron microscope (SEM) and an energy dispersive X-ray spectrometer (EDS). From these results, it was confirmed that replacing the commercialized lead shield with ABS+W (10%) material not only produces a shielding effect such as lead, but also can be customized to patients using a 3D printer, which can be very useful for high-energy electron beam treatment.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1063-1069
• /
• 2022

According to domestic air pollutant emission statistics, a considerable amount of air pollutants is generated by ships. Therefore, various policies are being implemented to limit air pollutant emissions from ships and improve the air quality in ports. In addition, international conventions are carried out for the prevention of marine pollution by ships. However, because few studies and experiments have been conducted on the measurement of air pollutants emitted from actually operating ships, this study presented a method and possibility for evaluating air pollutant emissions from a 9,196GT ship actually operating using a portable emission measurement system (PEMS). A difference in emission occurred depending on the RPM and load, and the emission of NO_X was 497-2,060ppm, CO₂ was 1.55-6.9%, and CO was 0.002-0.14%. The emission specified in the shop test provided by the engine manufacturer differed from the actual emission measured. This study proved that the maximum emission of each air pollutant generated in the entire sailing section of the ship was included in the PEMS measurement range, and the possibility of using PEMS for ships within 10,000GT was verified.

• Resources Recycling
• /
• v.31 no.3
• /
• pp.81-87
• /
• 2022

Energy consumption per unit weight of metal (kwh/kg of metal) is one of the most important economic indicators in the process of molten salt electrolysis. It is related to the heat loss of salt bath and the current efficiency of the process. The current efficiency is highly dependent on electrolysis temperature. On the other hand, the temperature of salt bath may increase significantly due to the difference (larger energy input than consumption) in heat balance at the beginning of electrolysis, which may cause different electrolysis temperature from an initially targeted value. This results in a bad effect on current efficiency. Therefore, it will be helpful to the reduction of energy consumption to compare the calculated and measured values of the temperature change of salt bath through the heat balance review at the early stage of electrolysis and to evaluate the energy loss to outside. In this study, based on the authors' experimental data, the heat balance was reviewed at the beginning of the electrolysis, and it was possible to evaluate the energy loss to the outside and the increase of the temperature of the salt bath quantitatively. Through such a method, heat loss reduction plan can be derived and current efficiency can be improved so that energy consumption can be reduced.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.4
• /
• pp.161-167
• /
• 2007

In this study, ultimate lateral load capacity of piles is analyzed with consideration of lateral stress effect. Based on results obtained in this study, a method for the estimation of ultimate lateral load capacity is proposed. This makes it possible to more realistically estimate the ultimate lateral load capacity under various stress states caused by in-situ soil condition and pile installation process. Calibration chamber test results with various soil conditions were used in the analysis. From the test results, it was found that effect of the lateral stress was greater than that of the vertical stress on the ultimate lateral load capacity of piles. It was also found that, as the relative density increases, displacements required to reach the ultimate state increases, showing relative displacements of around 14% and 18-25% for $D_R$ : 55% and 86%, respectively. Based on results obtained in this study, a methodology for the estimation of ultimate lateral load capacity of piles using correction factors was proposed. Results from proposed method matched well measured results.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.6
• /
• pp.5-16
• /
• 2008

This study investigated the existing theoretical backgrounds in order to examine the stability control method of lateral flow caused by the Plasticity of soils when unsymmetrical surcharge works on polluted soils and then compared and analyzed the results measured through model tests. Ultimate bearing power of ML and $ML_{p1}$ and $ML_{p2}$ obtained at surcharge(q)-settlement$(S_v)$ curve showed similar trends to ultimate bearing power obtained from control chart of deflection $(S_v-Y_m)$ by Tominaga.Hashimoto, that of $S_v-(Y_m/S_v)$ by Matsuo.Kawamura and that of $(q/Y_m)-q$ by Shibata.Sekiguchi and so it is considered that it has no problem in actual applicability. ${S_v-(Y_m/S_v)}$ of control chart of $ML_{p1}$ by Matsuo.Kawamura showed smaller value than ultimate bearing capacity value from surcharge-settlement curve $(q-S_v)$. Expression of ML of fracture baseline at stability control charge by Matsuo Kawamura is ${S_v=3.21exp}\{-0.48(Y_m/S_v)\}$ and expression of $ML_{p1}$ is ${S_v=3.26exp}\{-0.96(Y_m/S_v)\}$ and expression of $ML_{p2}$ is ${S_v=6.33exp}\{-0.45(Y_m/S_v)\}$.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.25-25
• /
• 2021

점착성 유사는 비점착성 유사에 비해 1차입자의 크기가 작아 1차입자간의 점착력이 중요한 역할을 하는 유사를 말한다. 점착성 유사는 비점착성 유사에 비해 크기가 작아 입자의 전자기적 점착력의 영향을 무시할 수 없으므로 점착력으로 인해 입자들은 서로 응집하는 동시에 입자들 간의 충돌에 의하여 파괴되는 과정을 거친다. 이러한 응집과 파괴가 지속되는 일련의 과정을 응집현상이라 한다. 점착성 유사는 응집과정을 통해 일차입자보다 크기가 크며 수십 개에서 수천 개의 일차입자와 물의 덩어리인 플럭을 형성하게 된다. 흐름 내 존재하는 플럭의 응집현상에 가장 지배적인 영향을 미치는 인자로 난류 거동이 알려진 바 있다. 본 연구에서는 난류 거동에 따른 점착성 플럭의 입도분포 변화를 살펴보고자 하였으며, 점착성 유사 입도분포 모형을 개발하였다. 수치모형의 개발은 확률과정(또는 추계과정)의 개념을 바탕으로 한다. 점착성 유사의 응집현상을 구성하는 응집과정은 다양한 연구를 통해 메커니즘들이 규명된 것과 달리 파괴과정은 난류로 인해 발생하며 무작위한 것으로 여겨진다. 무작위한 플럭의 파괴과정을 확률과정으로 가정하고 매개변수 중 하나를 대수정규분포를 따르는 난수로 고려하였다. 개발된 모형의 검증은 연안지역에서 점착성 플럭의 거동을 측정한 연구결과와의 비교를 통해 수행하였으며, 흐름 유속의 연직분포와 유사 농도의 연직분포, 응집현상 이후 플럭의 평형크기와 입도분포가 모두 합리적으로 계산되는 것이 확인되었다. 더불어 모의 결과에서는 대수정규분포를 따르는 동일한 난수를 적용하였음에도 불구하고 하상으로부터 거리가 가까워짐에 따라 플럭입도분포가 단봉분포(Unimodal Distribution)와 이봉분포(Bimodal Distribution)가 모두 계산되는 것으로 나타났다. 이는 모형의 개발과정에서 플럭의 가능 최대 크기를 콜모고로브 길이규모로 제한한 것과 관련이 있다. 난류 흐름 내 존재하는 플럭의 크기가 응집현상을 통해 난류의 콜모고로브 길이규모까지 성장하는 경우, 난류의 전단응력이 급격하게 증가하여 파괴과정이 활발해지고 응집과정이 저하된다는 것은 널리 알려진 사실이다. 이러한 사실을 바탕으로 플럭의 가능최대 크기를 콜모고로브 길이규모로 제한하였으며, 하상으로부터의 거리에 따라 콜모고로브 길이규모의 변화로 인해 콜모고로브 길이규모 부근에서 하나의 최빈값이 추가로 나타나는 것으로 이해된다. 수치모의 결과로부터 얻어진 콜모고로브 길이규모와 입도분포 형태의 상관관계를 보다 정확하게 이해하기 위해 실측 자료들을 검토해 본 결과, 균질한 재료를 이용한 실험실 실험결과에서 플럭 이봉분포의 최빈값이 콜모고로브 길이규모와 일치하는 것이 확인되었다. 연안지역에서 측정을 수행한 자료들에서도 이봉분포 또는 다봉분포와 콜모고로브 길이 규모와의 상관성을 찾아볼 수 있었다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.28 no.2D
• /
• pp.227-234
• /
• 2008

This study examines which models are more suitable for representing mechanical property of unbound materials to analyze behavior of asphalt pavement structure. Results from FWD (Falling Weight Deflectometer) test were used to apply to nonlinear elastic model. The new method which can deduct material constants of nonlinear elastic model is suggested from FWD test data rather than laboratory resilient modulus ($M_R$) test. It is confirmed that the material constants are within the common range in subbase. Test output from FWD and MDD (Multi-Depth Deflectometer) was used to verify reliability of the model. From the results of verification, this study shows that a non-linear elastic model agrees to MDD test data more than a linear elastic model does.