• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.444-452
• /
• 2024

This study proposes a deep learning architecture optimized for fire detection derived through Layer Importance Evaluation. In order to solve the problem of unnecessary complexity and operation of the existing Convolutional Neural Network (CNN)-based fire detection system, the operation of the inner layer of the model based on the weight and activation values was analyzed through the Layer Importance Evaluation technique, the layer with a high contribution to fire detection was identified, and the model was reconstructed only with the identified layer, and the performance indicators were compared and analyzed with the existing model. After learning the fire data using four transfer learning models: Xception, VGG19, ResNet, and EfficientNetB5, the Layer Importance Evaluation technique was applied to analyze the weight and activation value of each layer, and then a new model was constructed by selecting the top rank layers with the highest contribution. As a result of the study, it was confirmed that the implemented architecture maintains the same performance with parameters that are about 80% lighter than the existing model, and can contribute to increasing the efficiency of fire monitoring equipment by outputting the same performance in accuracy, loss, and confusion matrix indicators compared to conventional complex transfer learning models while having a learning speed of about 3 to 5 times faster.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.6
• /
• pp.1167-1174
• /
• 2009

In the monitoring of a patient in a sickroom, not only the physiologic and environmental data of the patient, which is automatically measured, but also the clinical data(clinical chart)of the patient, which is drew up by a doctor or nurse, are recognized as important data. However, since in the current environment of a sickroom, clinical data is collected being divided from the data that is automatically measured, the two data are used without an effective integration. This is because the integration of the two data is difficult due to their different collection times, which leads the reconstruction of clinical data to be remarkably uncertain. In order to solve these problems, a method to synchronize the continuous environmental data of a sickroom and clinical data is appearing as an important measure. In addition, the increase of use of small machines and the development of solutions based on wireless communications provide a communication platform to the developers of health care. Thus, this paper realizes a remote system for taking care of patients based on a web that uses mobile phones. That is, clinical data made by a nurse or doctor and the environmental data of a sick room comes to be collected by a collection module through a wireless sensor network. An observer can see clinical data and the environmental data of a sickroom through his/her mobile phone, integrating and storing his/her data into the database. Families of a patient can see clinical data made by hospital and the environment of the sick room of the patent through their computers or mobile phones outside the hospital. Through the system,hospital can provide better medical services to patients and their families.

• Journal of Internet Computing and Services
• /
• v.9 no.6
• /
• pp.37-48
• /
• 2008

VoIP service is a transmission of voice data using SIP protocol on IP based network, The SIP protocol has many advantages such as providing IP based voice communication and multimedia service with cheap communication cost and so on. Therefore the SIP protocol spread out very quickly. But, SIP protocol exposes new forms of vulnerabilities on malicious attacks such as Message Flooding attack and protocol parsing attack. And it also suffers threats from many existing vulnerabilities like on IP based protocol. In this paper, we propose a new Virtual Proxy Server system in front of the existed Proxy Server for anomaly detection of SIP attack and stateful management of SIP session with enhanced security. Based on stateful virtual proxy server, out solution shows promising SIP Message Flooding attack verification and detection performance with minimized latency on SIP packet transmission.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.3
• /
• pp.89-97
• /
• 2012

In recent years, efficient energy management technologies are required, as environmental problems have emerged worldwide. In response to this, smart home services focused on efficient energy management technology seems to be emerging. And the integration of technology of user-oriented real-time energy monitoring and control systems is required. In this paper, we present a location-based green home service using smart phones for efficient energy management in a house. We design a green home network system to apply the green home service, and implement an integrated gateway system which connects and controls each appliance in a house. We develop appliance control services and indoor location services on smart phones, and determine whether user's occupancy of each room by measuring the location according to the variation of signal strength. In order to evaluate the performance of the energy savings, we have set up the scenarios of energy usage pattern and have compared the energy variation resulting from the application of the indoor location services with smart meters. A comparison of energy usage demonstrated that the energy saving of a house with the proposed location-based green home service was down up to 30%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.2 no.3
• /
• pp.202-208
• /
• 2007

Recently, a lot of research have been studied to apply wireless sensor networks to USN applications. The characteristics of USN applications is that they are varied according to the sort of sensors and sensing objects. They includes military applications, water pollusion monitoring, intelligent traffic system, farm, logistics, location position applications, and so on. There is no traditional method to classify these applications. In this paper, we propose a taxonomy scheme to classify USN applications. The criteria is based on 3 properties, the criticalness of services, the mobility of sensing entity, and the mobility of sensed objects, to classify them into 8 groups. We also describe the technical issues and related works in them. Our taxonomy can make USN applications to be easily understood and memorized.

• Proceedings of the KAIS Fall Conference
• /
• 2012.05b
• /
• pp.812-816
• /
• 2012

본 논문은 산사태 감지 및 붕괴예측을 위한 현장에 USN(Ubiquitous Sensor Network)을 적용한 실시간 모니터링 시스템 모델을 개발하였다. 이 시스템의 성능을 검증하기 위해 USN기반의 상시모니터링시스템모델을 제작하고 실험적 평가를 수행하였다. 성능평가는 지표변위 센서모듈 동작특성 실험적 평가, USN은 Data 수집 전송 효율성 실험적 평가, 개발한 상시감시모니터링 프로그램 동작성능 실험적 평가 등을 수행하였다. 성능평가 결과 지표변위 측정센서모듈은 변위각도에 일치성을 확인하고, USN은 지표변위 센서모듈로부터 측정된 Data를 상시모니터링시스템에 오류 없이 전송되는지를 확인하였으며, 개발한 상시모니터링 프로그램 동작기능은 실시간 모니터링 그래프, 임계동작 알고리즘, 위험성 통보 문자서비스(SMS)기능, 알람서비스기능, 현장 감시카메라 등 동작기능의 우수성을 실험으로 증명하였다. 따라서 본 연구에서 개발된 산사태 감지 예측을 위한 USN기반 실시간 모니터링 시스템 모델은 산사태위험성노출 지역에 원격 실시간 모니터링 시스템으로 널리 사용될 것으로 사료된다.

• Proceedings of the KAIS Fall Conference
• /
• 2011.12b
• /
• pp.679-682
• /
• 2011

본 논문에서는 완전제어형 식물공장에서 작물이 생육하는데 필요한 재배환경들의 모니터링 및 제어가 가능한 센서 네트워크 기반의 식물공장 통합 제어 시스템을 설계 및 구축한다. 제안한 시스템은 완전제어형 식물공장에서 각 재배단의 환경 정보를 수집하기 위해 통합 환경정보 센서 및 전력 제어 센서를 설치하고, 통합 컨트롤러를 통해 LED 조명의 제어가 가능하도록 설계 하였다. 환경정보 센서는 온도, 습도, CO2의 데이터가 실시간으로 수집되며 전력제어 센서는 실시간 사용되는 전력량 데이터가 수집 가능하며 센서를 통해 전력의 차단 및 공급이 가능하도록 설계 하였다. 본 시스템은 크게 모니터링과 제어로 구분되며 테스트 베드의 구축을 통해 실시간 환경정보 센서 데이터 수집이 가능하고, LED 조명 및 전력을 제어가 가능함을 확인하였다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.2118-2119
• /
• 2006

최근 이슈가 되고 있는 무선 센서 네트워크를 기반으로 빌딩 주변의 환경 정보를 감시하고, 실시간 관리가 가능한 시스템을 개발하였다. 센서에 의한 환경 정보는 빌딩의 안전감시와 진단 그리고 효율적 에너지관리를 위한 분석용 데이터로 사용된다. 이러한 환경 정보에는 온도, 습도, 진동, CO2 등과 같은 센서가 있으며, 이러한 센서들로부터 오는 환경 정보를 저전력, 저비용, 자가 구성이 가능한 무선 센서 네트워크기술을 이용함으로써 단기적으로는 빌딩의 안전진단이나 온, 습도와 같은 환경정보를 얻을 수 있으며, 장기적으로는 유지 보수의 비용문제를 효율적으로 줄일 수 있고, 실시간 정보 수집과 자가 구성에 의한 에너지 절감이 가능하다. 본 논문에서는 무선 센서 네트워크를 이용한 빌딩 모니터링 시스템을 정의하고, 시스템을 설계한 후 실험을 통하여 향후 무선 센서 네트워크의 빌딩 및 건축물로의 적용 가능성을 검증하였다.

• Journal of Korea Multimedia Society
• /
• v.20 no.11
• /
• pp.1811-1819
• /
• 2017

As the induction motor is the core production equipment of the industry, it is necessary to construct a fault prediction and diagnosis system through continuous monitoring. Many researches have been conducted on motor fault diagnosis algorithm based on signal processing techniques using Fourier transform, neural networks, and fuzzy inference techniques. In this paper, we propose a fault diagnosis method of induction motor using LPC and DNN. To evaluate the performance of the proposed method, the fault diagnosis was carried out using the vibration data of the induction motor in steady state and simulated various fault conditions. Experimental results show that the learning time of our proposed method and the conventional spectrum+DNN method is 139 seconds and 974 seconds each executed on the experimental PC, and our method reduces execution time by 1/8 compared with conventional method. And the success rate of the proposed method is 98.08%, which is similar to 99.54% of the conventional method.

• Annual Conference of KIPS
• /
• 2005.05a
• /
• pp.1319-1322
• /
• 2005

최근 컴퓨터 기술의 발달로 공공 분야에서 구조물 감시 시스템의 중요성이 대두 되고 있다. 현재 구조물 감시 시스템은 감지 능력, 데이터 처리, 피해의 양, 구조물의 상태 예상을 기본 목적으로 하여 운영된다. 기존 감시 시스템은 센서의 측정으로 얻은 데이터를 유선을 통해 기지노드로 전송한다. 유선으로 연결된 감시 시스템에는 많은 초기 설치비용, 네트워크 전송 케이블의 유실 문제와 같은 문제점이 있다. 본 논문에서는 이러한 문제점을 개선하기 위해 전송 장치, 센싱 보드, 무선 장치로 구성된 무선 네트워크 환경에서 동작하는 무선 감시 시스템을 구성하였다. 구현된 시스템은 하중에 따른 변화를 실시간으로 감시하므로 구조물의 안전성 향상에 기여한다.