• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.17-33
• /
• 2005

This paper presents the proposed a classifier of liver cirrhotic step using MR(magnetic resonance) imaging and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were analysis in the number of data was 231. We extracted liver region and nodule region from T1-weight MR liver image. Then objective interpretation classifier of liver cirrhotic steps. Liver cirrhosis classifier implemented using hierarchical neural network which gray-level analysis and texture feature descriptors to distinguish normal liver and 3 types of liver cirrhosis. Then proposed Neural network classifier learned through error back-propagation algorithm. A classifying result shows that recognition rate of normal is $100\%$, 1type is $82.8\%$, 2type is $87.1\%$, 3type is $84.2\%$. The recognition ratio very high, when compared between the result of obtained quantified data to that of doctors decision data and neural network classifier value. If enough data is offered and other parameter is considered this paper according to we expected that neural network as well as human experts and could be useful as clinical decision support tool for liver cirrhosis patients.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.5
• /
• pp.2422-2429
• /
• 2013

WMN is considered as a core methodology to provide mobile wireless network service with multi-hop routing feature. It has a merit that can be easily deployed by utilization of protocols for MANET. However, it has differences in supporting multiple networks and channels, network architecture, and so on. Especially, in case of routing protocols, to apply them intactly to WMN can be a cause of low performance because of do not moving mesh routers. AODV seems like suitable for WMN among the various routing protocols for MANET. However, it has a defect in scalability. In this paper, an enhanced AODV routing method for WMN was proposed. The proposed method was designed to be suitable to the architecture of WMN by use of layering and localizing the broadcasting domain.

• Journal of Korea Technology Innovation Society
• /
• v.11 no.4
• /
• pp.476-509
• /
• 2008

This research investigates the determinant factors of technology licensing contracts and the relative importance of each factor. To accomplish this objective we classify various factors affecting technology licenses into two categories, technology and environment, and conduct an Analytic Hierarchy Process (AHP) with a Korean expert survey. From the AHP results, we find that the possibility of commercial success, as well as the scope and levels of exclusive rights which are transferred together with technology to the licensee, are very important among technological factors in technology transfer. Moreover, we conclude that the technology utilization capacity and the learning capabilities of the licensee are also important environmental factors. Finally, we conclude that the factors which the licensor and licensee consider in technology transfer are different from each other. Based on this result, we discuss implications with regard to reducing this factor gap between the licensor and licensee as a means of promoting and improving technology transfer in the Republic of Korea.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.3B
• /
• pp.144-152
• /
• 2005

Mobile IP(MIP) and SIP have been proposed to support mobility in the wireless internet working at different layers of the protocol stack. However MIP has some problems such as triangle routing, the need of each host's home address, the overhead of tunneling and the lack of wide deployment. Thus we proposed a scheme for supporting mobility based on SIP in this research. A novel SIP system to provide a hierarchical registration has been designed according to this scheme. Our SIP system has been established by implementing JAIN technologies which follow next generation network standards to support the mobility of wireless terminal. This system successfully satisfied ITU-T recommendation.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.42 no.4 s.334
• /
• pp.7-14
• /
• 2005

Earlier researches have typically concentrated on discovering IP network topology, which implies that the connectivity of all Ethernet devices is ignored. But automatic discovery of Physical topology Plays a crucial role in enhancing the manageability of modem Metro Ethernet mesh networks due to the benefits of Ethernet services, including: Ease of use, Cost Effectiveness and flexibility. Because of proprietary solutions targeting specific product families and related algorithm which depends on Layer 2 forwarding table information it is impossible to discover physical topology in the Ethernet mesh networks. To cope with these shortcomings, in this paper we propose a novel and practical algorithmic solution that can discover accurate physical topology in the Ethernet mesh networks. Our algorithm divides the Ethernet mesh networks into bridged networks and host networks and those bridges located in boundary are named edge bridges. Our algorithm uses the standard spanning tree protocol MIB information for the bridged networks and uses the standard Layer 2 forwarding table MIB information for the host networks. As using the standard MIB information to discover physical topology we can offer interoperability guarantee in the Ethernet mesh networks composed of the various vendors' products.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.12B
• /
• pp.1514-1523
• /
• 2009

It is well known that the current wireless sensor networks addressing methods do not work efficiently in networks more than a few hundred nodes. A standard protocol in ZigBee-Standard feature in ZigBee 2007 gives balanced tree based address assignment method with distributed manner. However, it was limited to cover less than hundreds of sensor nodes due to the wasteful use of available address space, because composed sensor networks usually make an unbalanced tree topology in the real deployment. In this paper, we proposed the hierarchical cluster tree based address assignment method to support large and scalable networks. This method provides unique address for each node with distributed manner and supports hierarchical cluster tree on-demand. Simulation results show that the proposed method reduces orphan nodes due to the address exhaustion and supports larger network with limited address space compared with the ZigBee distributed address assignment method defined in ZigBee-Standard feature in ZigBee 2007.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.6
• /
• pp.35-46
• /
• 2011

In this paper, we proposed the method of emotion recognition using staged classification model and Fisher's linear discriminant. By organizing the staged classification model, the proposed method improves the classification rate on the Fisher's feature space with high complexity. The staged classification model is achieved by the successive combining of binary classification model which has simple structure and high performance. On each stage, it forms Fisher's linear discriminant according to the two groups which contain each emotion class, and generates the binary classification model by using Adaboost method on the Fisher's space. Whole learning process is repeatedly performed until all the separations of emotion classes are finished. In experimental results, the proposed method provides about 72% classification rate on 8 classes of emotion and about 93% classification rate on specific 3 classes of emotion.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.13-23
• /
• 2001

In this paper, we design and implement a virtual environment which forms the basis of constructing a virtual world in a systematic fashion. Though virtual environments have been developed in several systems using the virtual reality, they are designed without a systematic method of constructing. In our framework, a virtual environment is structured in six layers according to their functions and ranges based on a classification of environmental factors of which the real world is composed. These layers compose a universal environment in our virtual world by operating independently and exchanging information with one another periodically. The designed environment shows that it Can provide diverse real life situations and is easily extensible to enhance its functionalities. We present effective design schemes for several important environmental factors. We demonstrate viability of our framework through implementing a plausible virtual world based on the proposed schemes.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.31 no.3
• /
• pp.79-99
• /
• 2020

The purpose of this study is to investigate the model of cluster analysis techniques for grouping public libraries and analyze their characteristics. Statistical data of public libraries of the National Library Statistics System were used, and three models of cluster analysis were applied. As a result of the study, cluster analysis was conducted based on the size of public libraries, and it was largely divided into two clusters. The size of the cluster was largely skewed to one side. For grouping based on size, the ward method of hierarchical cluster analysis and the k-means cluster analysis model were suitable. Three suggestions were presented as implications of the grouping method of public libraries. First, it is necessary to collect library service-related data in addition to statistical data. Second, an analysis model suitable for the data set to be analyzed must be applied. Third, it is necessary to study the possibility of using cluster analysis techniques in various fields other than library grouping.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.133-140
• /
• 2011

Recently, Web applications, such as Stock Image and Image Library, are developed to provide the integrated management for user's images. Image hash techniques are used for the image registration, management and retrieval as the identifier and many researches have been performed to raise the hash performance. This paper proposes GLOCAL image hashing method utilizing the hierarchical histogram which based on histogram bin population method. So far, many researches have proven that image hashing techniques based on histogram are robust image processing and geometrical attack. We modified existing image hashing method developed by our research team. The main idea is that it makes more fluent hash string if we have histogram bin of specific length as shown in the body of paper. Finally, we can raise the magnitude of hash string within same context or feature and strengthen the robustness of hash.