• ETRI Journal
• /
• v.27 no.6
• /
• pp.651-665
• /
• 2005

This paper proposes a generic security architecture designed for a multidomain and multiservice network based on programmable networks. The multiservice network allows users of an IP network to run programmable services using programmable nodes located in the architecture of the network. The programmable nodes execute codes to process active packets, which can carry user data and control information. The multiservice network model defined here considers the more pragmatic trends in programmable networks. In this scenario, new security risks that do not appear in traditional IP networks become visible. These new risks are as a result of the execution of code in the programmable nodes and the processing of the active packets. The proposed security architecture is based on symmetric cryptography in the critical process, combined with an efficient manner of distributing the symmetric keys. Another important contribution has been to scale the security architecture to a multidomain scenario in a single and efficient way.

• ETRI Journal
• /
• v.39 no.6
• /
• pp.832-840
• /
• 2017

Recently, deep recurrent neural networks have achieved great success in various machine learning tasks, and have also been applied for sound event detection. The detection of temporally overlapping sound events in realistic environments is much more challenging than in monophonic detection problems. In this paper, we present an approach to improve the accuracy of polyphonic sound event detection in multichannel audio based on gated recurrent neural networks in combination with auditory spectral features. In the proposed method, human hearing perception-based spatial and spectral-domain noise-reduced harmonic features are extracted from multichannel audio and used as high-resolution spectral inputs to train gated recurrent neural networks. This provides a fast and stable convergence rate compared to long short-term memory recurrent neural networks. Our evaluation reveals that the proposed method outperforms the conventional approaches.

• Journal of the Korea Institute of Building Construction
• /
• v.7 no.3
• /
• pp.131-137
• /
• 2007

To predict deep excavation wall movements is important in the urban areas considering the cost and the safety in construction. Failing to estimate deep excavation wall movements in advance causes too many problems in the projects. The purpose of this study is to propose the forecast model of deep excavation wall movements using artificial neural networks. The data of the Deep Excavation Wall Movements which were done form Long research is used of Artificial neural networks training and apply the real construction work measured data to the Artificial neural networks model. Applying the artificial neural networks to forecast the deep excavation wall movements can significantly contribute to identifying and preventing the accident in the overall construction work.

• Proceedings of the IEEK Conference
• /
• 2000.07b
• /
• pp.1053-1056
• /
• 2000

In general, neural networks based modeling involves trying multiple networks with different architectures and/or training parameters in order to achieve the best accuracy. Only the single best-trained neural network is chosen, while the rest are discarded. However, using only the single best network may never give the best solution in every situation. Many researchers, therefore, propose methods to improve the accuracy of neural networks based modeling. In this paper, the idea of the logical combinations of neural networks is proposed and discussed in detail. The logical combination is constructed by combining the corresponding outputs of the neural networks with the logical “And” node. The experimental results based on simulated data show that the modeling accuracy is significantly improved when compared to using only the single best-trained neural network.

• ETRI Journal
• /
• v.44 no.6
• /
• pp.977-990
• /
• 2022

This study proposes a novel method for identifying the primary conspirators involved in terrorist activities. To map the information related to terrorist activities, we gathered information from different sources of real cases involving terrorist attacks. We extracted useful information from available sources and then mapped them in the form of terrorist networks, and this mapping provided us with insights in these networks. Furthermore, we came up with a novel centrality measure for identifying the primary conspirators of a terrorist attack. Because the leaders of terrorist attacks usually direct conspirators to conduct terrorist activities, we designed a novel algorithm that can identify such leaders. This algorithm can identify terrorist attack leaders even if they have less connectivity in networks. We tested the effectiveness of the proposed algorithms on four real-world datasets and conducted an experimental evaluation, and the proposed algorithms could correctly identify the primary conspirators and leaders of the attacks in the four cases. To summarize, this work may provide information support for security agencies and can be helpful during the trials of the cases related to terrorist attacks.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.2
• /
• pp.128-132
• /
• 2023

Recently, with the development of deep learning technology, research on pedestrian attribute recognition technology using deep neural networks has been actively conducted. Existing pedestrian attribute recognition techniques can be obtained in such a way as global-based, regional-area-based, visual attention-based, sequential prediction-based, and newly designed loss function-based, depending on how pedestrian attributes are detected. It is known that the performance of these pedestrian attribute recognition technologies varies greatly depending on the type of backbone network that constitutes the deep neural networks model. Therefore, in this paper, several backbone networks are applied to the baseline pedestrian attribute recognition model and the performance changes of the model are analyzed. In this paper, the analysis is conducted using Resnet34, Resnet50, Resnet101, Swin-tiny, and Swinv2-tiny, which are representative backbone networks used in the fields of image classification, object detection, etc. Furthermore, this paper analyzes the change in time complexity when inferencing each backbone network using a CPU and a GPU.

• BMB Reports
• /
• v.37 no.1
• /
• pp.45-52
• /
• 2004

The goal of interaction proteomics that studies the protein-protein interactions of all expressed proteins is to understand biological processes that are strictly regulated by these interactions. The availability of entire genome sequences of many organisms and high-throughput analysis tools has led scientists to study the entire proteome (Pandey and Mann, 2000). There are various high-throughput methods for detecting protein interactions such as yeast two-hybrid approach and mass spectrometry to produce vast amounts of data that can be utilized to decipher protein functions in complicated biological networks. In this review, we discuss recent developments in analytical methods for large-scale protein interactions and the future direction of interaction proteomics.

• Genomics & Informatics
• /
• v.11 no.4
• /
• pp.200-210
• /
• 2013

Studying biological networks, such as protein-protein interactions, is key to understanding complex biological activities. Various types of large-scale biological datasets have been collected and analyzed with high-throughput technologies, including DNA microarray, next-generation sequencing, and the two-hybrid screening system, for this purpose. In this review, we focus on network-based approaches that help in understanding biological systems and identifying biological functions. Accordingly, this paper covers two major topics in network biology: reconstruction of gene regulatory networks and network-based applications, including protein function prediction, disease gene prioritization, and network-based genome-wide association study.

• Journal of the Korean Society for information Management
• /
• v.32 no.3
• /
• pp.317-340
• /
• 2015

This study clarified the knowledge structure of international collaboration in psychiatry based on analyzing networks in order to construct cooperation networks for international collaboration in psychiatry in South Korea. The result of analysis of knowledge structure at a state-level is as follows. First, this study found that the rate of collaboration for five years is high as 89.97%. Moreover, this study investigated the change of rate of collaboration and international collaboration according to the passage of time, and ascertained that while the rate of international collaboration has increased, Second, this study examined the trend of research on collaboration between Asian countries, and found that collaboration between Asian countries is on a low level. Third, the country (or group) that the number of papers of international collaboration and the value of centrality are the highest is EU-28. The result of analysis of knowledge structure at a research output-level is as follows. this study analyzed the correlation of centrality with research output, and found that positive correlation exists in the three indicators of centrality, and a country with high centrality has good research output.

• Journal of Communications and Networks
• /
• v.13 no.6
• /
• pp.552-566
• /
• 2011

The Internet is a very successful modern technology and is considered to be one of the most important means of communication. Despite that success, fundamental architectural and business limitations exist in the Internet's design. Among these limitations, we focus on a specific issue, the lack of manageability, in this paper. Although it is generally understood that management is a significant and important part of network and service design, it has not been considered as an integral part in their design phase. We address this problem with our future Internet management architecture called highly manageable network and service architecture for new generation (HiMang), which is a novel architecture that aims at integrating management capabilities into network and service design. HiMang is highly manageable in the sense that it is autonomous, scalable, robust, and evolutionary while reducing the complexity of network management. Unlike any other management framework, HiMang provides management support for the revolutionary networks of the future while maintaining backward compatibility for existing networks.