• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.65-70
• /
• 2023

In this paper, we used a deep learning model to detect and segment flame and smoke in real time from fires. To this end, well known U-NET was used to separate and divide the flame and smoke of the fire using multi-class. As a result of learning using the proposed technique, the values of loss error and accuracy are very good at 0.0486 and 0.97996, respectively. The IOU value used in object detection is also very good at 0.849. As a result of predicting fire images that were not used for learning using the learned model, the flame and smoke of fire are well detected and segmented, and smoke color were well distinguished. Proposed method can be used to build fire prediction and detection system.

• Fire Science and Engineering
• /
• v.16 no.4
• /
• pp.28-32
• /
• 2002

The performance based design in fire detection system, the effect of high airflow and dilution of smoke produced in any fire situation serve to increase the response time of point-type smoke detectors. This study investigated the smoke density of ceiling, under the air stream and in normal status when fire type is smoldering fires. The result of study, smoke generated in the fire was swept away from nearby spot type smoke detector which failed to actuate because dispersed in diluted form around the room. The concept of performance based design in fire detection system of protected area influenced by high airflow provided the need of active fire detection system such as air sampling smoke detection system.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.12
• /
• pp.1596-1603
• /
• 2018

Rapidly detecting and warning of fires is necessary for minimizing human injury and property damage. Generally, when fires occur, both the smoke and the flames are generated, so fire detection systems need to detect both the smoke and the flames. However, most fire detection systems only detect flames or smoke and have the disadvantage of slower processing speed due to additional preprocessing task. In this paper, we implemented a fire detection system which predicts the flames and the smoke at the same time by constructing a CNN model that supports multi-labeled classification. Also, the system can monitor the fire status in real time by using Grad-CAM which visualizes the position of classes based on the characteristics of CNN. Also, we tested our proposed system with 13 fire videos and got an average accuracy of 98.73% and 95.77% respectively for the flames and the smoke.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.3
• /
• pp.310-315
• /
• 2007

When a mail was given to users, each user's response could be different according to his or her preference. This paper presents a solution for this situation by constructing a u!;or preferred ontology for anti-spam systems. To define an ontology for describing user behaviors, we applied associative classification mining to study preference information of users and their responses to emails. Generated classification rules can be represented in a formal ontology language. A user preferred ontology can explain why mail is decided to be spam or non-spam in a meaningful way. We also suggest a nor rule optimization procedure inspired from logic synthesis to improve comprehensibility and exclude redundant rules.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.04a
• /
• pp.367-371
• /
• 2007

최근 여러 지역에서 발생되는 지하철 참사 및 대형화재 또는 지하철 역사, 대형 지하상가, 백화점, 지하공간, 대형쇼핑센터, 숙박업소, 공공건물등 대형 다중이용시설 등에서 발생될 수 있는 예측 불가능한 인재, 천재지변에 안전하게 대피하기 위한 수단으로 비상등 및 여러 감지기들이 소방법 개정으로 의무설치 하고 있다. 비상등 및 감지기들은 비상시 위험 감지 및 경고 전파를 위해 사용되는데 방음벽이나 격벽, 경고 거리의 제한으로 인해 경고 전달의 어려움이 있다. 본 논문에서는 무선 데이터 전송기능 및 경고등, 음성전파 기능을 갖는 무선 지능형 화재 감지/경고시스템을 설계하고자 한다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.235-238
• /
• 2020

In the smart home era, fire safety is very important for human life and facility safety. Casualties and property damage from the fire would be a huge national loss. In this paper, we propose to predict the risk by determining the operating time of the fire detector according to the fire in the smart home. Among IoT fire detectors, heat detectors and smoke detectors, the risk can be predicted due to the difference in the operating time depending on the fire. Based on the results of this experiment, the ion-type smoke detector shows very fast characteristics, so it would be good to use the results in future fire prevention facility.

• Fire Science and Engineering
• /
• v.27 no.4
• /
• pp.27-34
• /
• 2013

The high prediction performance of fire detector models is essentially needed to assure the reliability of fire and evacuation modeling in the process of PBD (Performance Based fire safety Design). The main objective of the present study is to measure input information in order to predict the accurate activation time of smoke detector into a Large Eddy Simulation (LES) fire model such as FDS (Fire Dynamics Simulator). To end this, FDE (Fire Detector Evaluator) which can measure the device properties of detector was developed, and the input information of Heskestad and Cleary's models was measured for a ionization smoke detector. In addition, the activation times of smoke detectors predicted using default values into FDS and measured values in the present study were systematically compared. As a result, the device properties of smoke detector examined in the present study showed a significant difference compared to the default values used into FDS, which resulted in the considerable difference of up to 15 minutes or more in terms of the activation time of smoke detector. The database (DB) on device properties of various smoke and heat detectors will be built to improve the reliability of PBD in future studies.

• Fire Science and Engineering
• /
• v.31 no.2
• /
• pp.44-51
• /
• 2017

Accurate predictions of the activation time for smoke detectors using a fire simulation is are required to ensure the reliability of the RSET (Required Safe Egress Time) calculation in the process of PBD (Performance-Based Design). The objective of this study was to enhance the accuracy of input parameters for the numerical models of smoke detector based on the FDS. To this end, a Fire Detector Evaluator (FDE) developed in previous studies was improved. The uniformities of flow and smoke inside the FDE were improved and accurate measurements of the obscuration per meter (OPM) related to detector operation were also performed through a decrease in the forward scattering of smoke particles. The input parameters using the improved FDE showed a significant difference from the previous FDE quantitatively. In particular, a larger difference was found in a photoelectric detector compared to an ionization detector. Considering that the operating conditions of smoke detectors are affected by the detector type, combustibles, smoke particulars, and color, the database (DB) on the input parameters for various detectors and combustibles should be built to improve the reliability of PBD in future studies.

• Fire Science and Engineering
• /
• v.28 no.6
• /
• pp.62-68
• /
• 2014

The high predictive performance of fire detector models is essentially required for the reliable design of evacuation safety using the fire modeling. The main objective of the present study is to measure input information in order to predict the accurate activation time of photoelectric smoke detector adopted in fire dynamics simulator (FDS) recognized a representative fire model. To end this, the fire detector evaluator (FDE) which could be measured the device properties of detector was used, and the input information of Heskestad and Cleary's models was obtained for a spot-type photoelectric smoke detector. In addition, the activation times of smoke detector predicted using default values into FDS and measured values in the present study were quantitatively compared. As a result, the Heskestad model could result in an inaccurate the activation time of photoelectric smoke detector compared to the Cleary model. In addition, there was a distinct difference between the default values used into FDS and the measured values in terms of device properties of smoke detector, and thus the activation time also showed a significant difference.