• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.10a
• /
• pp.1532-1548
• /
• 2008

The tunnel type spillways is under construction to increasing water reservoir capacity in Dae-am dam. The tunnel outlet was planned to be made after installing slope stabilization system on natural slope there. Generally, the tunnel outlet is made perpendicularly to the slope, but in this case, it had to be made obliquely to the slope for not interrupting flow of river. Because of excavation in condition of natural slope caused to deflecting earth pressure, the outlet couldn't be made. So, artificial ground made with concrete that it was constructed in the outside of tunnel for producing the arching effect which enables to make a outlet. We were planned tunnel excavation was carried out after artificial ground made. Artificial ground made by poor mix concrete of which it was planned that the thickness was at least 3.0m height from outside of tunnel lining and 30cm of height per pouring. Spreading and compaction was planned utilized weight of 15 ton roller machine. In order to access of working truck, slope of artificial ground was designed 1:1.0 and applied 2% slope in upper pert of it for easily drainage of water. In addition to, upper pert of artificial ground was covered with soil, because of impaction of rock fall from upper slope was made minimum. The tunnel excavation of the artificial ground was designed application with special blasting method that it was Super Wedge and control blasting utilized with pre-percussion hole.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.670-684
• /
• 2024

3D Cross-Modal Retrieval (3DCMR) is a task that retrieves 3D objects regardless of modalities, such as images, meshes, and point clouds. One of the most prominent methods used for 3DCMR is the Cross-Modal Center Loss Function (CLF) which applies the conventional center loss strategy for 3D cross-modal search and retrieval. Since CLF is based on center loss, the center features in CLF are also susceptible to subtle changes in hyperparameters and external inferences. For instance, performance degradation is observed when the batch size is too small. Furthermore, the Mean Squared Error (MSE) used in CLF is unable to adapt to changes in batch size and is vulnerable to data variations that occur during actual inference due to the use of simple Euclidean distance between multi-modal features. To address the problems that arise from small batch training, we propose a Noisy Center Loss (NCL) method to estimate the optimal center features. In addition, we apply the simple Siamese representation learning method (SimSiam) during optimal center feature estimation to compare projected features, making the proposed method robust to changes in batch size and variations in data. As a result, the proposed approach demonstrates improved performance in ModelNet40 dataset compared to the conventional methods.

• International Journal of Aeronautical and Space Sciences
• /
• v.8 no.1
• /
• pp.54-65
• /
• 2007

Parameter optimization technique is applied to planning UAVs(Unmanned Aerial Vehicles) path under artificial enemy radar threats. The ground enemy radar threats are characterized in terms of RCS(Radar Cross Section) parameter which is a measure of exposure to the radar threats. Mathematical model of the RCS parameter is constructed by a simple mathematical function in the three-dimensional space. The RCS model is directly linked to the UAVs attitude angles in generating a desired trajectory by reducing the RCS parameter. The RCS parameter is explicitly included in a performance index for optimization. The resultant UAVs trajectory satisfies geometrical boundary conditions while minimizing a weighted combination of the flight time and the measure of ground radar threat expressed in RCS.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2115-2127
• /
• 2021

Although significant progress has been made in synthesizing visually realistic face images by Generative Adversarial Networks (GANs), there still lacks effective approaches to provide fine-grained control over the generation process for semantic facial attribute editing. In this work, we propose a novel cross channel self-attention based generative adversarial network (CCA-GAN), which weights the importance of multiple channels of features and archives pixel-level feature alignment and conversion, to reduce the impact on irrelevant attributes while editing the target attributes. Evaluation results show that CCA-GAN outperforms state-of-the-art models on the CelebA dataset, reducing Fréchet Inception Distance (FID) and Kernel Inception Distance (KID) by 15~28% and 25~100%, respectively. Furthermore, visualization of generated samples confirms the effect of disentanglement of the proposed model.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.1
• /
• pp.101-110
• /
• 2022

For this purpose, the authors proposed and proved usefulness of the modified mean skin temperature which is integrated mean radiation temperature and the effect of floor contacted heat conduction. The mean radiation temperature is applied form factor between half cross-legged human body and surrounding wall of indoor. In addition the floor contacted heat conduction is applied heat transfer coefficient of half cross-legged human body. Eight Korean young men were targeted for the experiment. From the experiment the authors excerpted physiological reaction and psychological reaction in Ondol environment which is combined physiccal environmental factor of artificial climate chamber, air and floor temperature. As a result of the experiment it is confirmed that heat conduction has more impact than heat exchange from existing research for the heat exchange between half cross-legged human body and surrounding wall in Ondol thermal environment. Thereby, it is proved the effectiveness of the modified mean skin temperature which is added floor contacted temperature to the Ondol thermal environmental evaluation index.

• ETRI Journal
• /
• v.46 no.2
• /
• pp.263-276
• /
• 2024

Different diseases occur in the brain. For instance, hereditary and progressive diseases affect and degenerate the white matter. Although addressing, diagnosing, and treating complex abnormalities in the brain is challenging, different strategies have been presented with significant advances in medical research. With state-of-art developments in artificial intelligence, new techniques are being applied to brain magnetic resonance images. Deep learning has been recently used for the segmentation and classification of brain images. In this study, we classified normal and pathological brain images using pretrained deep models through transfer learning. The EfficientNet-B5 model reached the highest accuracy of 98.39% on real data, 91.96% on augmented data, and 100% on pathological data. To verify the reliability of the model, fivefold cross-validation and a two-tier cross-test were applied. The results suggest that the proposed method performs reasonably on the classification of brain magnetic resonance images.

• Journal of Biomedical Engineering Research
• /
• v.33 no.1
• /
• pp.1-7
• /
• 2012

Hemorrhagic shock is a common cause of death in emergency rooms. Early diagnosis of hemorrhagic shock makes it possible for physicians to treat patients successfully. Therefore, the purpose of this study was to select an optimal survival prediction model using physiological parameters for the two analyzed periods: two and five minutes before and after the bleeding end. We obtained heart rates, mean arterial pressures, respiration rates and temperatures from 45 rats. These physiological parameters were used for the training and testing data sets of survival prediction models using an artificial neural network (ANN) and support vector machine (SVM). We applied a 5-fold cross validation method to avoid over-fitting and to select the optimal survival prediction model. In conclusion, SVM model showed slightly better accuracy than ANN model for survival prediction during the entire analysis period.

• Korean Chemical Engineering Research
• /
• v.59 no.4
• /
• pp.532-541
• /
• 2021

Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.19 no.4
• /
• pp.266-273
• /
• 2016

Two-dimensional hydraulic experiments were performed to assess the impact of artificial seaweed on wave energy attenuation, and coastal erosion prevention. In this experimental study, erosion geometry and wave reflection coefficients were determined for normal and stormy incident waves, with and without artificial seaweed. The coastline of beaches without artificial vegetation was observed to retreat, and the longshore bar height increased in normal and stormy conditions. Through the introduction of artificial seaweed (of widths 0.8 m, and 1.6 m), the coastline was found to advance in the offshore direction due to material deposition. From these results, it is shown that artificial seaweed alters the cross-section of beaches, such that it is possible to prevent coastline erosion.