• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.317-318
• /
• 2023

본 논문에서는 CNN(Convolutional Neural Network)을 활용하여 자율주행 자동차가 각 국가별 교통 규칙 및 도로 표시를 이해하고 정확한 주행을 할 수 있도록, Deep Neural Network 시스템을 설계하고 구현하는 방법을 제안한다. 연구 방법으로는 한국도로교통공단(koroad)에서 제공하는 교통안전표지 일람표 이미지를 학습하여, 차량이 자율주행을 하기 위해 요구되는 표지판을 인식할 수 있도록 하였다. 본 논문에서 설계한 학습 시스템으로 도로교통표지판의 인식에 성공했으며, 이를 통해 자율주행차량이 표지판을 인식할 수 있으며, 시각장애인 및 고령운전자를 위한 지원 역시 가능하다고 사료된다.

• Journal of Industrial Technology
• /
• v.21 no.A
• /
• pp.117-122
• /
• 2001

Currently, the VHE (suggested for global roaming user to provide personal service environment) implementation scenario is being proposed to realize 3G network requirements. However, developing VHE scenarios are focused on signal flow between node and network, and network and network. this case may result in weakness to protect subscriber's privacy in 3G network which commonly uses visited network. In this paper, we reanalyze a several VHE implementation scenarios for user profile protection, indicate a problem concerning user privacy, and finally, design a procedure to cope with vulnerability in VHE implementation scenario.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.187-188
• /
• 2006

In CDMA based mobile communication network, signaling messages are routed through Signaling Transfer Point(STP) which is responsible for MTP layer 3 switching. As WCDMA based UMTS network is considered as next generation technology allowing global roaming services, all nodes in networks have their own identity number called Global Title(GT). Therefore, it is essential to introduce Signaling Gateway(SG) responsible for SCCP layer switching to solve the problem each node has all GT tables including even all overseas nodes. In this paper, we propose the signaling network architecture in UMTS networks using SG and we show that we can reduce CAPEX and OPEX in each node. To show the validity of the proposed method some simulations are given in which the results can be expected by intuitive observation.

• Journal of the Korean Regional Science Association
• /
• v.15 no.2
• /
• pp.5-19
• /
• 1999

This paper identifies five factors that limited urban network formation in Northeast Asia over the past half millennium, questions the extent to which they are being overcome in the 1990s, and sketches a network of cities that could boost regionalism. It briefly traces the historical evolution of these factors, including comparisons with European integration, while focusing primarily on the policies of the 1990s that have affected their continuing role. First is the factor of closed national markets with weak regional integration. Second is the preeminence of administrative means of integration over commercial ones. Third is the character of localism, shackled by overcentralization and weak cross-border linkages. Fourth is the limited nature of internationalism, dominated by state catch-up policies with one-sided global involvement. Fifth is a lack of regional consciousness. Just as national urban integration was essential for regional networks to form, without regional integration it is difficult to contemplate Northeast Asian cities taking their rightful place in a global urban network. After noting the failures of the 1990s, the paper points to the potential role as dragon's heads for sub-regional urban networks of potential front-line cities: Tumen, Sapporo, Irkutsk, and what I call the Amur triangle. Also of interest are how the capitals of Beijing, Moscow, Seoul, and Tokyo will adjust to a transformed urban network. After all, their current skepticism must be overcome with a program that links the benefits on all sides in order to build trust in regionalism. This requires internationalism and symbols of a balanced approach to each country's needs.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.403-413
• /
• 2022

Classification and analysis are improved factors for the realtime automation system. In the field of agriculture, the cultivation of different paddy crop depends on the atmosphere and the soil nature. We need to analyze the moisture level in the area to predict the type of paddy that can be cultivated. For this process, Ensemble Modulation Pattern system and Block Probability Neural Network based classification models are used to analyze the moisture and temperature of land area. The dataset consists of the collections of moisture and temperature at various data samples for a land. The Ensemble Modulation Pattern based feature analysis method, the extract of the moisture and temperature in various day patterns are analyzed and framed as the pattern for given dataset. Then from that, an improved neural network architecture based on the block probability analysis are used to classify the data pattern to predict the class of paddy crop according to the features of dataset. From that classification result, the measurement of data represents the type of paddy according to the weather condition and other features. This type of classification model assists where to plant the crop and also prevents the damage to crop due to the excess of water or excess of temperature. The result analysis presents the comparison result of proposed work with the other state-of-art methods of data classification.

• Journal of IKEEE
• /
• v.12 no.1
• /
• pp.18-26
• /
• 2008

With the advent of Ubiquitous environment, wired-wireless combination network is being studied very actively in which mobile nodes having multi-hop communication capability connect wired internet network easily, and shares the information. The study of wired and wireless combination network between MANET(Mobile Ad Hoc Network) and wired network is being focused only on the configuration of heterogeneous network interface. The proposed algorithm establishes independent multi-paths between source node and destination node to prevent data loss when errors happen in route. As the result, it shows that the reliability of the combination network can be improved by making data transmit continuously on the route error.

• Knowledge Management Research
• /
• v.12 no.1
• /
• pp.77-89
• /
• 2011

The purpose of this study is to examine the effects of social capital on the economic performance of Korean Business Residents in Japan and global competitiveness of Korea, and to find out social capital is the antecedent factor of these two variables. To serve the purpose of this study, we conducted the extensive survey on 153 Korean Business Residents in Japan in diverse industries. From the result, we identified that the economic performance becomes higher as the level of social capital increase, and the Korean Business Residents which has good performance affect the global competitiveness of Korea.

• International Journal of Computer Science & Network Security
• /
• v.21 no.12spc
• /
• pp.443-450
• /
• 2021

The study is devoted to the formation of a economic principles cargo delivery management in global supply chains. Mathematical model of delivering special categories of goods by road is a key element of these principles. The article analyzes the existing studies on solving the problem of cargo delivery in various aspects. It was noted that the greatest attention is paid to legal regulation, last mile delivery, optimization of routes and delivery schemes, information support, technological innovations, cluster routing, etc. In the developed mathematical model a minimum of total costs of forming loading units and freight shipments was defined as the criterion of optimality of organizing delivery by motor transport. The authors propose the creation of logistics clusters allowing the integration of urban transport flows and global supply chains.

• Proceedings of the Korean Nuclear Society Conference
• /
• 2004.10a
• /
• pp.217-218
• /
• 2004

• Journal of KIISE:Software and Applications
• /
• v.29 no.5
• /
• pp.289-294
• /
• 2002

It is known that restructuring feed-forward neural network affects generalization capability and efficiency of the network. In this paper, we introduce a new approach to restructure a neural network using abstraction of the hidden knowledge that the network has teamed. This method involves extracting local rules from non-input nodes and aggregation of the rules into global rule base. The extracted local rules are used for pruning unnecessary connections of local nodes and the aggregation eliminates any possible redundancies arid inconsistencies among local rule-based structures. Final network is generated by the global rule-based structure. Complexity of the final network is much reduced, compared to a fully-connected neural network and generalization capability is improved. Empirical results are also shown.