• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.6
• /
• pp.175-181
• /
• 2022

The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built during the period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safety accidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for research to detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomous inspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular, the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026 damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04% and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the near future.

• Journal of Industrial Convergence
• /
• v.22 no.1
• /
• pp.1-20
• /
• 2024

Regarding the discourse on the correlation between governmental financial support and firm performance, much emphasis has been placed on the role of individual corporate characteristics as well as spatial features. However, there is a notable scarcity of empirical research examining the integrated impact of corporate and cluster characteristics on managerial performance. This study addresses this gap by empirically analyzing the financial and non-financial outcomes resulting from specific allocations of governmental financial support. Additionally, it explores corporate and cluster characteristics predicted to moderate the influence between governmental financial support and firm performance. The analysis employs a two-level hierarchical linear model (HLM) at individual and group levels. The data, reorganized based on business registration numbers at the firm and cluster levels, ultimately utilized panel data from 83,395 firms and 641 clusters. The research findings indicate that governmental financial support demonstrates a positive effect (+) on both sales and patents for firms, suggesting its effectiveness in complementing market failures. Results from the hierarchical linear model analysis show that when combined with human capital capacity, absorptive capacity, and cluster network density, governmental financial support exhibits significant positive effects on sales. This study contributes theoretical and practical insights by analyzing the relationship between governmental financial support and firm performance using a two-level hierarchical linear model. It highlights the role of corporate characteristics such as human capital and absorptive capacity, along with cluster characteristics like cluster network density, in moderating the effects of governmental financial support on firm performance.

• Journal of radiological science and technology
• /
• v.26 no.1
• /
• pp.71-82
• /
• 2003

In this paper, I proposed a classifier of liver cirrhotic step using T1-weighted MRI(magnetic resonance imaging) and hierarchical neural network. The data sets for classification of each stage, which were normal, 1type, 2type and 3type, were obtained in Pusan National University Hospital from June 2001 to december 2001. And the number of data was 46. We extracted liver region and nodule region from T1-weighted MR liver image. Then objective interpretation classifier of liver cirrhotic steps in T1-weighted MR liver images. 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 teamed through error back-propagation algorithm. A classifying result shows that recognition rate of normal is 100%, 1type is 82.3%, 2type is 86.7%, 3type is 83.7%. 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 Institute of Information Security & Cryptology
• /
• v.22 no.1
• /
• pp.43-56
• /
• 2012

Wireless sensor networks consist of numerous small-sized nodes equipped with limited computing power and storage as well as energy-limited disposable batteries. In this networks, nodes are deployed in a large given area and communicate with each other in short distances via wireless links. For energy efficient networks, dynamic clustering protocol is an effective technique to achieve prolonged network lifetime, scalability, and load balancing which are known as important requirements. this technique has a characteristic that sensing data which gathered by many nodes are aggregated by cluster head node. In the case of cluster head node is exposed by attacker, there is no guarantee of safe and stable network. Therefore, for secure communications in such a sensor network, it is important to be able to encrypt the messages transmitted by sensor nodes. Especially, cluster based sensor networks that are designed for energy efficient, strongly recommended suitable key management and authentication methods to guarantee optimal stability. To achieve secured network, we propose a key management scheme which is appropriate for hierarchical sensor networks. Proposed scheme is based on polynomial key pool pre-distribution scheme, and sustain a stable network through key authentication process.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.1
• /
• pp.10-17
• /
• 1993

This paper analyzes succinct graph descriptions and its complexity of connectivity problems on context free graph languages under various restrictions. It defines SNLC(Simple Context Free Node Label Controlled) grammar and presents reduction method that solves graph problems without expanding the hierarchical description. It exemplifies the method by giving efficient solutions to connectivity problems on graphs and presents parallel algorithm for reduction and analyzes the complexity. Its results will help application of desing for NETWORK. CAD. VLSI and other engineering problems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06d
• /
• pp.118-120
• /
• 2006

무선 센서 네트워크에서는 에너지 소모를 최소화 하는 것이 매우 중요한 연구 과제이며, 많은 연구들을 통하여 효율적인 방법들이 제안 되었고, 이 방법들은 대부분 단일 계층 상에서의 최적화에 초점이 맞춰져 있었다. 본 논문에서는 네트워크 계층의 정보를 이용하는 새로운 MAC 프로토콜을 제안한다. 여기서 제안하는 프로토콜은 MAC 계층의 송/수신 단의 비활성화 상태를 최대화 하고 제어 패킷의 수를 최소화 하는 방법으로 클러스터 기반의 경로 탐색 기법을 이용한다.

• Proceedings of the IEEK Conference
• /
• 2000.11a
• /
• pp.477-480
• /
• 2000

Open Shortest Path First(OSPF) is a dynamic, hierarchical routing protocol designed to support routing in TCP/IP networks. Currently, OSPF is used as Interior Gateway Protocol(IGP) in many routers. In this paper, we analyze the variation of number of OSPF routing packets in case of changing the network configuration. The results show that the number of packets in case of adding new link increase five times than one in case of normal operation.

• Journal of Korean Institute of Industrial Engineers
• /
• v.12 no.1
• /
• pp.55-61
• /
• 1986

Mathematical forecasting models and a practical computer based forecasting system are developed for planning production in a manufacturing and distribution network. The forecasting system works at the highest level of a hierarchical computer-based decision support system consisting of the forecasting system, an aggregate planning system and a shop floor scheduling system. The dynamics of business operations for an actual company have been considered to make this study a unique comprehensive analysis of a real world forecasting problem.

• Journal of the Korean Society of Safety
• /
• v.13 no.1
• /
• pp.77-84
• /
• 1998

Hazard and operability (HAZOP) analysis is one of the safety analysis method that is used in the chemical complex, because it can systematically identify causes and consequences of all the deviation that could occur. Since this method needs to hire specialized experts, it is costly and time-consuming. Therefore HAZOP Expert System has been developed to automate this analysis. This approach introduced object-oriented method and knowledge representation which is hierarchical tree of units to supply flexibility in the system, functional semantic network, propagation equation and rule-chaining method to set up the expert system for automating HAZOP analysis.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.10a
• /
• pp.737-740
• /
• 2007

A s wireless communications and mobile multimedia services are booming nowadays, systematic research of the overall aspects of mobile security is crucial. This paper presents a frame model for guising the systematic investigation of mobile security. Based on the introduction of some background viewpoints of security targets from n novel perspective, the framework is described as a hierarchical model in which mobile security research is partitioned into three different layers.