• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.8
• /
• pp.2030-2052
• /
• 2023

Analysis of a bipartite (two-mode) network is a significant research area to understand the formation of social communities, economic systems, drug side effect topology, etc. in complex information systems. Most of the previous works talk about a projection-based model or latent feature model, which predicts the link based on singular similarity. The projection-based models suffer from the loss of structural information in the projected network and the latent feature is hardly present. This work proposes a novel method for link prediction in the bipartite network based on an ensemble of composite similarities, overcoming the issues of model-based and latent feature models. The proposed method analyzes the structure, neighborhood nodes as well as latent attributes between the nodes to predict the link in the network. To illustrate the proposed method, experiments are performed with five real-world data sets and compared with various state-of-art link prediction methods and it is inferred that this method outperforms with ~3% to ~9% higher using area under the precision-recall curve (AUC-PR) measure. This work holds great significance in the study of biological networks, e-commerce networks, complex web-based systems, networks of drug binding, enzyme protein, and other related networks in understanding the formation of such complex networks. Further, this study helps in link prediction and its usability for different purposes ranging from building intelligent systems to providing services in big data and web-based systems.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.24 no.6
• /
• pp.513-524
• /
• 2022

Recently, detecting damages of civil infrastructures from digital images using deep learning technology became a very popular research topic. In order to adapt those methodologies to the field, it is essential to explain robustness of deep learning models. Our research points out that the existing pixel-based deep learning model evaluation metrics are not sufficient for detecting cracks since cracks have linear appearance, and proposes a new evaluation methodology to explain crack segmentation deep learning model more rationally. Specifically, we design, implement and validate a methodology to generate tolerance buffer alongside skeletonized ground truth data and prediction results to consider overall similarity of topology of the ground truth and the prediction rather than pixel-wise accuracy. We could overcome over-estimation or under-estimation problem of crack segmentation model evaluation through using our methodology, and we expect that our methodology can explain crack segmentation deep learning models better.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.24 no.12A
• /
• pp.1883-1890
• /
• 1999

Wireless communication in an urban area, the accurate prediction of wave propagation characteristics are very important to determine communication service areas, select optimal base-stations, and design cells, etc. The CCIR model is a propagation prediction model using a shadowing by the buildings in an urban area. This model represent the shadowing rate by the means of the effect of shadowing between base-station and mobile unit in a shaped linear plane. But, This one occurred a lot of prediction error because it did not consider that density area by the buildings and terrain configurations by the hill and mountain on Line-Of-Sight. In this thesis, an improved propagation prediction model is proposed to reduce prediction error. We presents a new equation, which is using the SAS. This equation is associated with the shadow height by the buildings that considers the topology and the number of blocks that can affect the building shadow in the Line-Of-Sight. We measure the received electrical field level of base-station that high density area, medium density area, and low density area, and then compare and analysis the result to prediction of CCIR model and proposed model. The result compared with the measurement, the proposed model has the improvement of 9.71dB in a high density area, 9.66dB in a medium density area, and 4.02dB in a low density area better than the CCIR model. The result compared with the measurement, the proposed model has the improvement of 9.71dB in a high density area, 9.66dB in a medium density area, and 4.02dB in a low density area better than the CCIR model.

• Cartoon and Animation Studies
• /
• s.49
• /
• pp.247-265
• /
• 2017

With the increasingly diverse, sophisticated and complex character animations that can be represented in 3D animations, the importance of rigging, which can most directly affect animating quality, is becoming more and more important. In addition, rapidity is another crucial aspect of 3D animation production. So, the importance of technical director's role which is accurate and rapid handling of rigging pipeline building and immediate application and, corrections of errors during the longest and manpower consuming animation production is more becoming key. Baek Ji Won and Kim Jae-woong (2014) said, "The technical director is adding new importance to the new job, which is created by 3D animation, in conjunction with the limited production period, manpower, budget and production process." Most major overseas studios are developing in-house software to handle rigging and animation processes. Software development code is used to freely develop and modify production pipelines in accordance with the direction of the work. They are making efforts to build an optimal environment for animators. However, too many efforts and ineffective efforts have been made to develop, adapt, and stabilize the rigging process for small producers, creators, and students who do not have the capacity to develop their own in-house software or hire a technical director. This study suggests the most suitable auto-rigging tool among the many auto-rigging tools released in the market, and suggests the most accurate and quick auto-rigging process setting method for those who have insufficient knowledge about 3D character rigging. The efficiency of use of auto-rigging tool was examined.

• Journal of KIISE:Software and Applications
• /
• v.35 no.2
• /
• pp.118-127
• /
• 2008

In this paper, we propose a method for construction of robust 3D statistical shape model in the mandible CT datasets. Our method consists of following four steps. First, we decompose a 3D input shape Into patches. Second, to generate a corresponding shape of a floating shape, all shapes in the training set are parameterized onto a disk similar to the patch topology. Third, we generate the corresponding shape by one-to-one mapping between the reference and the floating shapes. We solve the problem failed to generate the corresponding points near the patch boundary Finally, the corresponding shapes are aligned with the reference shape. Then statistical shape model is generated by principle component analysis. To evaluate the accuracy of our 3D statistical shape model of the mandible, we perform visual inspection and similarity measure using average distance difference between the floating and the corresponding shapes. In addition, we measure the compactness of statistical shape model using the modes of variation. Experimental results show that our 3D statistical shape model generated by the mandible CT datasets with various characteristics has a high similarity between the floating and corresponding shapes and is represented by the small number of modes.