• Journal of Sensor Science and Technology
• /
• v.33 no.3
• /
• pp.119-124
• /
• 2024

Effective fire sensing is important to protect lives and property from the disaster. In this paper, we present an intelligent visual sensing method for detecting fires based on machine learning techniques. The proposed method involves a two-step process. In the first step, fire and non-fire images are used to train a convolutional neural network (CNN), and in the next step, feature vectors consisting of 256 values obtained from the CNN are used for the learning of a support vector machine (SVM). Linear and nonlinear SVMs with different parameters are intensively tested. We found that the proposed hybrid method using an SVM with a linear kernel effectively increased the recall rate of fire image detection without compromising detection accuracy when an imbalanced dataset was used for learning. This is a major contribution of this study because recall is important, particularly in the sensing of disaster situations such as fires. In our experiments, the proposed system exhibited an accuracy of 96.9% and a recall rate of 92.9% for test image data.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.406-410
• /
• 1998

정보통신의 모든 분야에 걸쳐 활용될 수 있는 차세대 핵심기술이라고 할 수 있는 에이전트는 자율성, 지능성, 반응성, 협동성을 갖는 독립된 프로그램으로 지식과 추론 능력을 가진다. 본 논문은 동적환경에서 환경에서 지능적인 행위와 반작용적인 행위도 가능한 혼합형 에이전트를 재난관리 에이전트 시스템에 도입 설계한다. 이를 위하여, 재난관리를 위한 에이전트를 재난 발생시 즉각적인 반응을 하는 반응 요소(reflexive component)와 플랜라이브러리에 저장된 여러 가지 사례들을 탐색해 문제를 해결하는 인지 요소(cognitive component)로 구성된 혼합형 에이전트(hybrid agent)기술을 재난관리에 적용한다. 인지요소에서 행동계획을 탐색하고, 조건에 맞는 계획을 결정하는 과정을 살펴본다. 탐색 방법은 계획-기반 탐색(plan based search)이며, 계획기의 지식 요소들은 슬롯을 가진 프레임구조를 하고 있다.

• Journal of Environmental Science International
• /
• v.24 no.8
• /
• pp.1023-1036
• /
• 2015

A reliable streamflow forecasting is essential for flood disaster prevention, reservoir operation, water supply and water resources management. This study proposes a hybrid model for river stage forecasting and investigates its accuracy. The proposed model is the wavelet packet-based artificial neural network(WPANN). Wavelet packet transform(WPT) module in WPANN model is employed to decompose an input time series into approximation and detail components. The decomposed time series are then used as inputs of artificial neural network(ANN) module in WPANN model. Based on model performance indexes, WPANN models are found to produce better efficiency than ANN model. WPANN-sym10 model yields the best performance among all other models. It is found that WPT improves the accuracy of ANN model. The results obtained from this study indicate that the conjunction of WPT and ANN can improve the efficiency of ANN model and can be a potential tool for forecasting river stage more accurately.

• Journal of Korea Multimedia Society
• /
• v.22 no.2
• /
• pp.281-291
• /
• 2019

In order to reflect complex and diverse building types, resident characteristics and disaster factors, it is necessary to introduce a flexible situation-based response system based on real-time information. Intelligent CCTV, hybrid sensor, location scanner, and customized broadcasting device were examined to introduce for the real-time response intelligent response system and its feasibility was verified through field test. In addition, based on the real-time information, the evacuation simulation was executed by assuming the dormitory building and the resident of the school, and the safety of the evacuation and the shortening of the pinnacle time were confirmed. The feasibility of real time information based evacuation comparing with the existing evacuation system were verified in the case of evacuation.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.146-158
• /
• 2022

With the success of the digital economy and the rapid development of its technology, network security has received increasing attention. Intrusion detection technology has always been a focus and hotspot of research. A hybrid model that combines particle swarm optimization (PSO) and kernel extreme learning machine (KELM) is presented in this work. Continuous-valued PSO and binary PSO (BPSO) are adopted together to determine the parameter combination and the feature subset. A fitness function based on the detection rate and the number of selected features is proposed. The results show that the method can simultaneously determine the parameter values and select features. Furthermore, competitive or better accuracy can be obtained using approximately one quarter of the raw input features. Experiments proved that our method is slightly better than the genetic algorithm-based KELM model.

• ETRI Journal
• /
• v.45 no.3
• /
• pp.433-447
• /
• 2023

Critical issues such as connection congestion, long transmission delay, and packet loss become even worse during epidemic, disaster, and so on. In this study, a link load balancing method is proposed to address these issues on the data plane, a plane of the software-defined network (SDN) architecture. These problems are NP-complete, so a meta-heuristic approach, discrete particle swarm optimization, is used with a novel hybrid cost function. The superiority of the proposed method over existing methods in the literature is that it provides link and switch load balancing simultaneously. The goal is to choose a path that minimizes the connection load between the source and destination in multipath SDNs. Furthermore, the proposed work is dynamic, so selected paths are regularly updated. Simulation results prove that with the proposed method, streams reach the target with minimum time, no loss, low power consumption, and low memory usage.

• Journal of the Korean Applied Science and Technology
• /
• v.29 no.4
• /
• pp.618-625
• /
• 2012

In this study, prepared synthesis waterborne acrylic resin and water soluble milk casein resin. And than extent of casein contents in acrylic resin. We measured property of these samples by Lamb leather which is coated by acrylic-casein resins. According to measure data for solvent resistance, WAR resin and Hybrid resins had good property. Among this result knew that increase of casein constant did not influence to big change of hybrid resin property. As test of tensile strength, WAR had lowest strength($1.399kg_f/mm^2$) and WAC-3 had highest strength($1.426kg_f/mm^2$). Also we knew that best property of abrasion was WAC-3(69.774 mg.loss). In elongation case, WAR had best property(820%) in this experiment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.191-196
• /
• 2019

In the case of urban railway facilities, the power supply should be maintained for the safe movement of passengers in communication facilities, disaster prevention facilities and boarding area security because of the confusion when power supply is cut off due to the nature of public transportation. In addition, considering that the number of trains is running on the urban railway line, it is necessary to operate at least 30 minutes for the bus stop and at least 1 hour for the communication and disaster prevention facilities. Therefore, it is essential to supply emergency power source to maintain stable operation of induction lamp and smoke exhaust system because main power is cut off in order to prevent further spread due to fire in case of the history of urban railway section or vehicle fires. Recently, UPS(Uninterruptible Power Supply) function to prevent power outage in emergency, emergency power generation combined with ESS function which saves electricity at nighttime price time, A hybrid power storage system with a UPS function.

• Journal of Plant Biotechnology
• /
• v.43 no.3
• /
• pp.317-331
• /
• 2016

Development of disease resistant plant is one of the important objectives in rice breeding programs because biotic stresses can adversely affect rice growth and yield losses. This study was conducted to identify lines with multiple-resistance genes to biotic stress among 173 hybrid rice breeding lines and germplasms using DNA-based markers. Our results showed that one hybrid rice line [IR98161-2-1-1-k1-3 (IR86409-3-1-1-1-1-1/IRBB66)] possessed 5 bacterial blight resistance genes (Xa4, xa5, Xa7, Xa13 and Xa21) while two hybrid rice lines [IR98161-2-1-1-k1-2 (IR86409-3-1-1-1-1-1/IRBB66) and 7292s (IR75589-31-27-8-33S(S1)/IR102758B)] possessed 3 bacterial blight resistance genes (Xa4, Xa7 and Xa21, and Xa3, Xa4 and xa5). Molecular survey on rice blast disease revealed that most of these lines had two different resistant genes. Only 11 lines possessed Pib, Pi-5, and Pi-ta. In addition, we further surveyed the distribution of insect resistant genes, such as Bph1, Bph18(t), and Wbph. Three hybrid breeding lines [IR98161-2-1-1-k1-3 (IR86409-3-1-1-1-1-1/IRBB66), IR98161-2-1-1-k1-2 (IR86409-3-1-1-1-1-1/IRBB66), and 7292s (IR75589-31-27-8-33S(S1) /IR102758B)] contained all three resistance genes. Finally, we obtained four hybrid rice breeding lines and germplasms [IR98161-2-1-1-k1-2 (IR86409-3-1-1-1-1-1/IRBB66), Damm-Noeub Khmau, 7290s, and 7292s (IR75589-31-27-8-33S(S1)/IR102758B)] possessing six-gene combination. They are expected to provide higher level of multiple resistance to biotic stress. This study is important for genotyping hybrid rice with resistance to diverse diseases and pests. Results obtained in this study suggest that identification of pyramided resistance genes is very important for screening hybrid rice breeding lines and germplasms accurately for disease and pest resistance. We will expand their cultivation safely through bioassays against diseases, pests, and disaster in its main export countries.

• Journal of the Korean Applied Science and Technology
• /
• v.29 no.2
• /
• pp.356-363
• /
• 2012

In this study we synthesis Hybrid resin(WPC) by milk casein and waterborne polyurethane(WPU). Then we experiment how casein effect to Hybrid resins in Full-Grain leather coatings. According to measured data for solvent resistance, WPU resin and Hybrid resins had good property. As test of tensile strength, WPU had most low strength(2.130 $kg_f/mm^2$) and WPC-3(WPU 91: casein resin 9) had most high strength(2.191 $kg_f/mm^2$). Also we knew that most good property of abrasion is WPC-3(50.090 mg.loss). In elongation case, WPU had most good result(637 %) in this experiment.