• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• pp.1365-1377
• /
• 2019

Summarizing the differences in Chinese-Vietnamese bilingual news plays an important supporting role in the comparative analysis of news views between China and Vietnam. Aiming at cross-language problems in the analysis of the differences between Chinese and Vietnamese bilingual news, we propose a new method of summarizing the differences based on an undirected graph model. The method extracts elements to represent the sentences, and builds a bridge between different languages based on Wikipedia's multilingual concept description page. Firstly, we calculate the similarity between Chinese and Vietnamese news sentences, and filter the bilingual sentences accordingly. Then we use the filtered sentences as nodes and the similarity grade as the weight of the edge to construct an undirected graph model. Finally, combining the random walk algorithm, the weight of the node is calculated according to the weight of the edge, and sentences with highest weight can be extracted as the difference summary. The experiment results show that our proposed approach achieved the highest score of 0.1837 on the annotated test set, which outperforms the state-of-the-art summarization models.

• Journal of the Korean Ceramic Society
• /
• v.47 no.5
• /
• pp.445-449
• /
• 2010

The purpose of this study is to improve recycling rate of the waste glasses by investigating bloating mechanism. In this study, we use waste glass(W/G) and hard clay(H/C) as raw materials. The artificial lightweight aggregates were formed by plastic forming($\phi$=10 mm) and sintered by fast firing method at different temperatures(between 700 and $1250^{\circ}C$). The physical properties of the aggregates such as bulk specific gravity, adsorption and microstructure of surface and cross-section are investigated with the sintering temperature and rate of W/G-H/C contents. As the result of the bulk specific gravity graphs, we can found out the inflection point at content of W/G 60 wt%. From the microstructure images, we considered the artificial lightweight aggregates content of W/ G over 60wt% are distributed numerous micro-pores by organic oxidation without Black Core and the artificial lightweight aggregates of W/G below 60 wt% are distributed macro-pores with Black Core.

• Geomechanics and Engineering
• /
• v.25 no.4
• /
• pp.295-302
• /
• 2021

Cross-borehole electrical resistivity tomography (ERT) is an effective groundwater detection tool in geophysical investigations. In this paper, an artificial water injection test was conducted on a small clay sample, where the high-resolution cross-borehole ERT was used to investigate the moisture migration law over time. The moisture migration path can be two-dimensionally imaged based on the relationship between resistivity and saturation. The hydraulic conductivity was estimated, and the magnitude ranged from 10^-11 m/s to 10^-9 m/s according to the comparison between the simulation flow and the saturation distribution inferred from ERT. The results indicate that cross-borehole ERT could help determine the resistivity distribution of small size clay samples. Finally, the cross-borehole ERT technique has been applied to investigate the self-sealing characteristics of clay.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.363-366
• /
• 2004

The purpose of this study is to reveal the spatial relationship between landslides and geospatial data set and to map the landslide susceptibility using this relationship, and the landslide occurrence data in Kangneung area in 2002. Landslide locations were identified from interpretation of satellite images. Landslide susceptibility was analyzed using an artificial neural network. The weights of each factor were determined by the back-propagation training method. Susceptibility maps were constructed from Geographic Information System (GIS), The cases were overlaid and cross overlaid for landslide susceptibility mapping in each study area in Kangneung.

• Journal of Ocean Engineering and Technology
• /
• v.1 no.2
• /
• pp.60-66
• /
• 1987

The object of this study is to investigate behaviors of beach fill replenished at three coasts of different configurations by analyzing successively measured beach profiles. The main results obtained in this study are summarized as follows; 1) The amount of nourishing sand moved in the longshore direction surpasses the amount of nourishing sand transported in the cross-shore direction regardless of shapes of the coasts and types of the structures. 2) A clear correlation between displacements of shoreline and changes of sectional areas can be found soon after the placement of beach fill in the fields. This implies that the deformation of the artificial nourishment and dissipation or remaining rate of nourishing sand can be predicated by the one-line theory. 3) The patterns of sediment movements in the artificially nourished beaches are clearly found by the analysis of empirical eignfuncitions.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.100-105
• /
• 2024

In this study, we propose an alternative approach using Artificial Neural Networks (ANN) for determining Mass Attenuation Coefficients (MAC) in various glass systems. This method takes into account the weights of glass compositions, density, and photon energy as input features. The ANN model was trained and tested on a dataset consisting of 650 data points and subsequently validated through a K-fold cross-validation procedure. Our findings demonstrate a high level of accuracy, with R² values ranging from 0.90 to 0.99. Additionally, the model exhibits robust extrapolation capabilities with an R² score of 0.87 for predicting MAC values in a new glass system. Furthermore, this approach significantly reduces the need for costly and time-consuming computations and experiments, making it a potential tool for selecting materials for effective radiation protection.

• Journal of Ocean Engineering and Technology
• /
• v.21 no.4
• /
• pp.21-27
• /
• 2007

The multiplication equipment of marine products with artificial upwelling structures could be useful in the fishing grounds near coastal areas. Artificial upwelling structures could move the inorganic nutrients from the bottom to the surface. Artificial upwelling structures have been used to improve the productivity of fishing grounds. Until now, research on artificial upwelling structures has been related to the distribution of the upwelling region, upwelling structures, and the marine environment. However, little work on the optimum design of the rubber-mound artificial upwelling structures has been done to increase the efficiency of drawing up the inorganic nutrients. This study investigated the optimum cross-section of rubber-mound artificial upwelling structures by means of hydraulic experiments. The hydraulic experiments include the falling test of rubber. Based on the results of the falling test, the relationship between the length of the rubber mound and water velocity, and the relationship between the shape of the rubber and the stratification parameter were established. In addition, the effect of the void ratio of various artificial structures on the stratification parameter was studied. From the experiment, it was found that upwelling could be enhanced when the ratio of structure height to water depth was 0.3 and stratification parameter was 3.0. The upwelling was not improved when the void ratio exceeded 0.43. The optimum size of rubber mounds was determined when the incident velocity was influenced by the mean horizontal length rather than size of block.

• 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.