• IEIE Transactions on Smart Processing and Computing
• /
• v.3 no.6
• /
• pp.366-371
• /
• 2014

This paper reports a machine learning approach for image object detection. Object detection and localization in a wild image, such as a STL-10 image dataset, is very difficult to implement using the traditional computer vision method. A convolutional neural network is a good approach for such wild image object detection. This paper presents an object detection application using a convolutional neural network with pretrained feature vector. This is a very simple and well organized hierarchical object abstraction model.

• Proceedings of the Korean Biophysical Society Conference
• /
• 2003.06a
• /
• pp.77-77
• /
• 2003

Gene expression in a cell is regulated by mutual activations or repressions between genes. Identifying the gene regulation network will be one of the most important research topics in the post genomic era. We propose a linear dynamic model of gene regulation for the yeast cell cycle. A small gene network consisting of about 40 genes is reconstructed from the analysis of micro-array gene expression data of yeast S. cerevisiae published by P. Spellman et al. We show that the network construction is consistent with the result of the hierarchical cluster analysis.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.22 no.5
• /
• pp.654-666
• /
• 2019

The tactical network has several different characteristics compared with commercial internet network such as hierarchical topology, dynamic topology changing and wireless link based connectivity. For considering IP mobility management in the tactical network, current mobility management using Mobile IP(MIP) is not suitable with some reasons such as non-optimal routing paths and single point of failure. Proxy Mobile IP(PMIP) which supporting network-based mobility in hierarchical manner can provide optimal routing path in the tactical network environment, but centralized anchor is still remained a threat to the stability of the tactical network which changes its topology dynamically. In this paper, we propose PMIP-based distributed mobility management for the tactical network environment. From our design, routing paths are always configured in optimized way, as well as path is recovered quickly when the mobility anchor of user is failed. From numerical analysis, comparing to other mobility scheme, result shows that the proposed scheme can reduce packet transmission cost and latency in tactical network model.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.16 no.2
• /
• pp.86-102
• /
• 1991

The purpose of this paper is to present a branch and bound algorithm for the hierarchical transportation network design problem in 2-level directed networks. This problem is to find the least cost of hierarchical transportation networks which consist of a primary path and a secondary path. The primary path is a simple path from a prespecified orgin node to a prespecified terminal node. All nodes must be either a transsipment node on the primary path or connected to that path via secondary arcs. This problem is formulated to a 0-1 inter programming problem with assignment and illegal subtour elimination equations as constaints. We show that the subproblem relaxing subtour elimination constraints is transformed to a linear programming problem by means of the totally unimodularity. Optimal solutions of this subproblem are polynoially obtained by the assignment algorithm and complementary slackness conditions. Therefore, the optimal value of this subproblme is used as a lower bound. When an optimal solution of the subproblem has an illegal subtour, a better disjoint rule is adopted as the branching strategy for reducing the number of branched problems. The computational comparison between the least bound rule and the depth first rule for the search strategy is given.

• Proceedings of the Korea Information Assurance Society Conference
• /
• 2004.05a
• /
• pp.199-204
• /
• 2004

Operating systems and application programs have security vulnerabilities derived from the software development process. Recently, incident cases related with the abuses of these vulnerabilities are increasing and the damages caused by them are becoming very important security issues all over the nations. Patch management is one of the most important processes to fix vulnerabilities of softwares and to ensure a security of systems. Since an institute or a company has distributed hierarchical and heterogeneous systems, it is not easy to update patches promptly. In this paper, we propose patch management framework to safely distribute and install the patches on Windows, Linux, and Solaris client systems. Besides, we censidered extensibility and hierarchical structure for our patch management framework to support large scaled network environment.

• Journal of information and communication convergence engineering
• /
• v.11 no.1
• /
• pp.7-11
• /
• 2013

Wearable computer systems use the wireless universal serial bus (WUSB), which refers to USB technology that is merged with WiMedia physical layer and medium access control layer (PHY/MAC) technical specifications. WUSB can be applied to wireless personal area network (WPAN) applications as well as wired USB applications such as PAN. WUSB specifications have defined high-speed connections between a WUSB host and WUSB devices for compatibility with USB 2.0 specifications. In this paper, we focus on an integrated system with a WUSB over an IEEE 802.15.6 wireless body area network (WBAN) for wireless wearable computer systems. Due to the portable and wearable nature of wearable computer systems, the WUSB over IEEE 802.15.6 hierarchical medium access control (MAC) protocol has to support power saving operations and integrate WUSB transactions with WBAN traffic efficiently. In this paper, we propose a low-power hibernation technique (LHT) for WUSB over IEEE 802.15.6 hierarchical MAC to improve its energy efficiency. Simulation results show that the LHT also integrates WUSB transactions and WBAN traffic efficiently while it achieves high energy efficiency.

• KIPS Transactions on Computer and Communication Systems
• /
• v.3 no.2
• /
• pp.47-56
• /
• 2014

Internet traffic has rapidly increased due to the supplying wireless devices and the appearance of various applications and services. By increasing internet traffic rapidly, the need of Internet traffic classification becomes important for the effective use of network resource. However, the traffic classification scheme is not much studied comparing to the study for classification method. This paper proposes novel classification scheme for multilateral and hierarchical traffic identification. The proposed scheme can support multilateral identification with 4 classification criteria such as service, application, protocol, and function. In addition, the proposed scheme can support hierarchical analysis based on roll-up and drill-down operation. We prove the applicability and advantages of the proposed scheme by applying it to real campus network traffic.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.8
• /
• pp.319-330
• /
• 2021

Recently, in the field of open domain natural language question answering, multi-task, multi-hop question answering has been studied extensively. In this paper, we propose a novel deep neural network model using hierarchical graphs to answer effectively such multi-task, multi-hop questions. The proposed model extracts different levels of contextual information from multiple paragraphs using hierarchical graphs and graph neural networks, and then utilize them to predict answer type, supporting sentences and answer spans simultaneously. Conducting experiments with the HotpotQA benchmark dataset, we show high performance and positive effects of the proposed model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4275-4291
• /
• 2021

With the unprecedented growth of textual information on the Internet, an efficient automatic summarization system has become an urgent need. Recently, the neural network models based on the encoder-decoder with an attention mechanism have demonstrated powerful capabilities in the sentence summarization task. However, for paragraphs or longer document summarization, these models fail to mine the core information in the input text, which leads to information loss and repetitions. In this paper, we propose an abstractive document summarization method by applying guidance signals of key sentences to the encoder based on the hierarchical encoder-decoder architecture, denoted as KI-HABS. Specifically, we first train an extractor to extract key sentences in the input document by the hierarchical bidirectional GRU. Then, we encode the key sentences to the key information representation in the sentence level. Finally, we adopt key information representation guided selective encoding strategies to filter source information, which establishes a connection between the key sentences and the document. We use the CNN/Daily Mail and Gigaword datasets to evaluate our model. The experimental results demonstrate that our method generates more informative and concise summaries, achieving better performance than the competitive models.

• Journal of Korea Multimedia Society
• /
• v.25 no.8
• /
• pp.1069-1074
• /
• 2022

IP mobility can be handled in different layers of the protocol. Mobile IP has been proposed to handle the mobility of Internet hosts in the network layer. Recently, a new method based on the SIGMA mobility architecture has been proposed to support mobility management with reduced packet loss and latency. The location management structure is not suitable for frequent mobile handover due to the high mobility of the user with this transport layer solution. In this paper, we propose a location management optimization method in a mobile communication network by applying hierarchical location management using MMPs(Mobility Management Points) for transport layer mobility management. Therefore, we propose an efficient hierarchical mobility management structure even between heterogeneous wireless networks using MMPs for the probability that a mobile terminal can change multiple location areas between two messages and calls. The proposed method shows reduction in location update cost and data retrieval cost using MMPs, and as opposed to mobility appearing in time intervals with the minimum cost required to reach 90% of the stabilized cost, the mobility location update search, location It was found that the message processing cost per area was reduced.