• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3211-3229
• /
• 2022

To solve the problems existing in the process of Weibo disaster rumor recognition, such as lack of corpus, poor text standardization, difficult to learn semantic information, and simple semantic features of disaster rumor text, this paper takes Sina Weibo as the data source, constructs a dataset for Weibo disaster rumor recognition, and proposes a deep learning model BERT_AT_Stacked LSTM for Weibo disaster rumor recognition. First, add adversarial disturbance to the embedding vector of each word to generate adversarial samples to enhance the features of rumor text, and carry out adversarial training to solve the problem that the text features of disaster rumors are relatively single. Second, the BERT part obtains the word-level semantic information of each Weibo text and generates a hidden vector containing sentence-level feature information. Finally, the hidden complex semantic information of poorly-regulated Weibo texts is learned using a Stacked Long Short-Term Memory (Stacked LSTM) structure. The experimental results show that, compared with other comparative models, the model in this paper has more advantages in recognizing disaster rumors on Weibo, with an F1_Socre of 97.48%, and has been tested on an open general domain dataset, with an F1_Score of 94.59%, indicating that the model has better generalization.

• Proceedings of the KIEE Conference
• /
• 2005.07e
• /
• pp.124-126
• /
• 2005

본 논문에서는 지하구내에 설치된 전기설비의 국내 외 설치기준 및 침수로 인한 피해실태에 대해 검토하였다. 검토과정에서는 이미 보고된 바 있는 다양한 자료 및 인터넷 기사를 근거로 하여 국내 외 기준 및 수해실태를 비교 분석함으로써 침수피해의 근본적인 원인을 규명하였다.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.69-77
• /
• 2017

In this paper, a disaster response scheme based on deep learning and augmented reality technology is proposed and a network resource reservation scheme is presented accordingly. The features of deep learning, augmented reality technology and its relevance to the disaster areas are explained. Deep learning technology can be used to accurately recognize disaster situations and to implement related disaster information as augmented reality, and to enhance disaster response capabilities by providing disaster response On-site disaster response agent, ICS (Incident Command System) and MCS (Multi-agency Coordination Systems). In the case of various disasters, the fire situation is focused on and it is proposed that a plan to strengthen disaster response capability effectively by providing fire situation recognition based on deep learning and augmented reality information. Finally, a scheme to secure network resources to utilize the disaster response method of this paper is proposed.

• Journal of Internet Computing and Services
• /
• v.17 no.4
• /
• pp.61-68
• /
• 2016

In this paper, an implementation method of augmented reality (AR) technology using Web 3.0 information services in the field of disaster response is proposed. The structure and characteristics of semantic web-based Web 3.0 are realized and a AR based mobile visual search (MVS) applied in the disaster sites is described. Based on Web 3.0 and AR MVS, a semantic web ontology oriented configuration scheme for disaster-related information and the communication scheme of information provided by AR technology are proposed. For the purpose of providing disaster-related and customized information to the disaster response site quickly and accurately, a method of leveraging Web 3.0 information services in AR technology is presented.

• Journal of Internet Computing and Services
• /
• v.18 no.4
• /
• pp.35-42
• /
• 2017

In this paper, a building disaster notification system with MEC (Mobile Edge Computing) technology is proposed, which informs people in a building about the disaster. The overview of MEC is presented, and the structure and characteristics of network using MEC are described. In addition, the characteristics of a enterprise integration pattern based Apache Camel is described, and how to implement MEC with Apache Camel is presented. Finally, an implementation method of building disaster notification system with Apache Camel based MEC is proposed to quickly recognize disasters through sensors and to rapidly evacuate people from buildings.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.5C no.5
• /
• pp.191-195
• /
• 2005

This paper presents an assessment method in integrity of the windings in cast resin molded transformers by using vertical analysis of thermal distribution. The proposed method is to compare the temperature distribution in a sound specimen with that in the faulted specimen with a layer to layer short circuit. Temperature distribution was acquired by an infrared thermography system, and the Arrhenius equation was adopted to the accelerated test. The proposed method can be used to detect the failures in the transformers.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.26 no.9
• /
• pp.662-668
• /
• 2013

Reported here are results of the mechanical and electrical properties of both of intact and thermally degraded epoxy-coated copper busducts that are made by fluidized bed process. To elucidate and compare the properties mentioned above, electrical breakdown by thermal and water aging, v-t characteristic, bending test, impact test and cross cut test are carried out. Although the performance of electrical and mechanical properties are gradually decreased in increasing the severe conditions such as temperature, aging time, and so forth, sample C has a better performance in both mechanical and electrical properties.

• Proceedings of the KIEE Conference
• /
• 2011.07a
• /
• pp.2144-2145
• /
• 2011

We carry out a demonstration project to verify performance of a Home- Smart Cabinet Panel(H-SCP) at the child care facility. It is difficult to prevent an electrical disaster using a existing cabinet panel because electrical events are invisible and unforeseeable. So we construct a integrated information system with a Home-Smart Cabinet Panel(H-SCP) for management of low-voltage customers. The integrated information system with the H-SCP maintain the transmitted data from H-SCP, alert a electrical event to a administrator and show a state of customer health in real time respectively. A manager of electrical safety can prevent electrical disaster to maintain electrical facilities after analysis on the integrated information system.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2007.04a
• /
• pp.294-301
• /
• 2007

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.59 no.3
• /
• pp.335-339
• /
• 2010

In this paper, in order to reduce the electrical disaster damage which is caused by with electrical equipment of traditional markets, we developed the cabinet panel and the electrical safety monitoring system which is able to monitor the electrical equipments condition(over current, leakage current, arc, WH, electrical fire factor etc.) at traditional markets. We constructed Test-bed for testing reliability of electrical safety monitoring system and cabinet panel. And we tested the cabinet for over current, leakage current and arc under the traditional markets actual condition. This paper will be used with the data for an demonstration project after compensating the defects which are occurred to operation of traditional markets actual loads.