Early Fire Detection Research Articles

Implementasi NodeMCU dan Blynk Dalam Sistem Pendeteksi Kebakaran Berbasis IoT

Fires can cause material losses and human lives. Therefore, an effective fire early detection system is needed to prevent greater losses. In this research, ESP8266 is used as a microcontroller to connect fire detection sensors such as KY-026 Fire Sensor and MQ-2 Smoke Sensor. This early fire detection system is also equipped with a buzzer as an alarm and NodeMCU as a platform to connect the system to the Internet network and Blynk as a medium to provide real-time fire notifications to users. Tests were conducted by comparing the response time and accuracy of fire detection at different distances. The test results show that the fire early detection system built has an average response time of 2 seconds and a detection accuracy rate of 95%.

A hybrid LBP-CNN with YOLO-v5-based fire and smoke detection model in various environmental conditions for environmental sustainability in smart city.

Smart, secure, and environmentally friendly smart cities are all the rage in urban planning. Several technologies, including the Internet of Things (IoT) and edge computing, are used to develop smart cities. Early and accurate fire detection in a Smart city is always desirable and motivates the research community to create a more efficient model. Deep learning models are widely used for fire detection in existing research, but they encounter several issues in typical climate environments, such as foggy and normal. The proposed model lends itself to IoT applications for authentic fire surveillance because of its minimal configuration load. A hybrid Local Binary Pattern Convolutional Neural Network (LBP-CNN) and YOLO-V5 model-based fire detection model for smart cities in the foggy scenario is presented in this research. Additionally, we recommend a two-part technique for extracting features to be applied to YOLO throughout this article. Using a transfer learning technique, the first portion of the proposed approach for extracting features retrieves standard features. The section part is for retrieval of additional valuable information related to the current activity using the LBP (Local Binary Pattern) protective layer and classifications layers. This research utilizes an online Kaggle fire and smoke dataset with 13950 normal and foggy images. The proposed hybrid model is premised on a two-cascaded YOLO model. In the initial cascade, smoke and fire are detected in the normal surrounding region, and the second cascade fire is detected with density in a foggy environment. In experimental analysis, the proposed model achieved a fire and smoke detection precision rate of 96.25% for a normal setting, 93.2% for a foggy environment, and a combined detection average precision rate of 94.59%. The proposed hybrid system outperformed existing models in terms of better precision and density detection for fire and smoke.

Effective flame detection and classification using deep feature of QuickDenseNet and Ensemble Score Voted SVM

Fire poses a significant threat to both lives and property, necessitating effective early detection measures. Despite challenges in identifying smoke and fire in their initial stages, we have devised a cost-efficient visual detection system. Early fire detection enhances its potential effectiveness. CCTV surveillance systems are now commonplace in developed countries, serving as tools for periodic monitoring of various locations. However, fluctuating ambient light conditions, camera angles, and seasonal variations can introduce data distortions, occlusions, and impact model accuracy. To address these issues, we’ve implemented a method combining deep learning networks and machine learning strategies for flame detection and direction classification. Our innovative QuickDenseNet extracts dense features from segmented flame video frames. We introduce the Ensemble Score Voted SVM (ESV-SVM), employing SVM as the primary learner and score voting as the auxiliary learner. Our approach is rigorously evaluated through simulations, measuring accuracy and various Key Performance Indices (KPIs), including Precision, F1-score, Recall, Correlation, Error, FPR, and Correlation Coefficients. Remarkably, our proposed method achieves an impressive precision rate of approximately 99.5%.

Forest Fire Detection using UAV Imaginary Data

Forest fires are a major threat to ecosystems and human lives. Early detection of forest fires can greatly reduce their impact and detection is crucial in minimizing their damage. In recent years, the application of unmanned aerial vehicles (UAVs) with cameras with high resolution has become an effective tool for forest fire detection. However, manual detection and analysis of these images can be time-consuming and errorprone. In this study, we propose a forest fire detection method that uses Convolution Neural Networks (CNNs) to automatically analyze UAV imagery. The proposed method involves preprocessing the images to enhance the features of interest and then feeding them into the CNN for classification. We trained & tested our model using a dataset of UAV images and obtained a classification precision of 95%. The results indicate that our proposed method is effective in detecting forest fires using UAV imagery and can provide a fast and accurate means of early detection, which is critical in preventing the spread of wildfires. Forests are critical components of biosphere protection all around the planet. They provide significant contributions to the carbon cycle worldwide and support a diverse range of the animal and plant kingdoms. Fires in forests are among the most serious risks to living organisms in many parts of the world; they jeopardise the environment, including people, plants, and animals. Wildfires ravaged the regions of North Africa and the Mediterranean last year. Early detection of forest fires is critical for saving lives and property. The detection and prediction of forest fires are challenging undertakings given that wildfires begin tiny and are difficult to spo tin the distance. Fires can start small and spread swiftly to become enormous and dangerous. The combination of drones and high accuracy wildfire detection can be achieved by deep learning utilizing photos. UAVs can be used to help determine the fire’s location and the extent of its spread region, even though deep learning can be utilised to determine the fire’s qualities. This pairing is a critical building block for developing a system capable of more precise detection of wildfires. The recent published state-ofthe-art research publications on employing drones and deep learning to identify forest fires are examined in this paper.

Improving the organization of communication in the forest fire monitoring system

The article discusses the issues of early detection of forest fires. Currently, traditional monitoring methods are gradually being replaced by modern technologies based on automation and the use of artificial intelligence. The system of remote video monitoring “Lesohranitel”, which has been widely used in many regions of Russia, is considered in detail. The main advantages of this system and the basic principle of operation are considered. The scheme of communication organization of the considered system is presented, the main ways for its improvement are defined.

An AI-based Image Recognition System for Early Detection of Forest and Field Fires

Forest fires and field fires (agricultural areas, grasslands, etc.) have severe global implications, causing significant environmental and economic harm. Traditional fire detection methods often rely on human personnel, which can pose safety risks and reduce their efficiency in large-scale monitoring. There is an urgent need for real-time fire detection technology to address these challenges and minimize losses. In this research, we propose the utilization of artificial intelligence techniques, specifically Deep Learning with Convolutional Neural Networks (CNN), to tackle this issue. Our proposed system analyzes real-time images captured by IP cameras and stored on a cloud server. Its primary objective is to detect signs of fires and promptly notify users through a mobile application, ensuring timely awareness. We meticulously assembled a dataset to train our model by merging three existing datasets comprising both fire and non-fire images. Also, we incorporated images that could potentially be misinterpreted as fire, such as red trees, individuals wearing red clothing, and red flags. Furthermore, we supplemented the dataset with images of unaffected areas obtained from online sources. The final dataset consisted of 1,588 fire images and 909 non-fire images. During evaluations, our model achieved an accuracy of 93.07%. This enables effective detection, thus rapid intervention and damage reduction. It is a proactive and preventive solution to combat these devastating fires.

Features of the coefficient of variation of parameters of the gas environment in fire in the premises

The object of the study is the selective coefficient of variation of dangerous parameters of the gas environment during the ignition of materials. The measure of the sample coefficient of variation of an arbitrary hazardous parameter of the gas environment observed at an arbitrary time interval is substantiated. The representativeness error of the measure of the sampling coefficient of variation, which depends on the value of the measure and the sample size, was determined. The measure allows you to numerically determine its value for an arbitrary observation interval. The difference in the measure at the intervals corresponding to the reliable absence and occurrence of ignition allows to detect the occurrence of ignition of the material. According to the results of laboratory studies, the measures of the sample coefficient of variation for carbon monoxide concentration, smoke density, and temperature of the gas medium in the laboratory chamber at intervals of absence and appearance of ignition of alcohol, paper, wood, and textiles were determined. It was established that the dangerous parameters of the gas environment at the intervals of absence and presence of ignition are characterized by different values of the increase in the measure of the sample coefficient of variation. For example, it is determined that the ignition of alcohol causes the maximum increase in the measure for carbon monoxide concentration from 0.135 to 0.441, for smoke density from 0.629 to 0.805, and for temperature from 0.001 to 0.115. When paper catches fire, the measure for carbon monoxide concentration and temperature increases from 0.0026 to 0.140 and from 0.0019 to 0.05, respectively. When burning wood, the measure for carbon monoxide concentration and temperature increases from 0.0072 to 0.177 and from 0.0067 to 0.016, respectively. The obtained results, provided that the hazardous parameters of the gas environment in the premises are measured and the sample coefficient of variation is calculated in practice, make it possible to use them in the creation of early fire detection systems

IoT Framework for Early Fire Detection and Control in Public Large Buildings: A Review

Fire destruction in large public and private buildings, particularly in markets, public offices, education, and industries, has devastated properties, costing millions while taking people’s lives. Fire destruction also extends to environmental degradation. Complete fire prevention is unattainable. However, an effort could be made to early fire detection and control to lessen the tragedy. There are several technologies for real-time fire detection, like heat detection, gas detection, flame detection, and smoke detection. A maximal mix of fire-detecting algorithms should be utilized to maximize accuracy and eliminate false fire confirmation. This research paper presents an early fire detection and control framework for large public and private buildings that utilizes the available fire detection technologies reviewed from various pieces of literature. In justification of the framework adaptability, the research paper examined the current state of firefighting infrastructures in large and private buildings. The review was based on ten (10) large public and private buildings. The buildings were divided into four strata (business center's, public offices, education and industries). In addition, information from the Fire and Rescue Force (Mbeya Office) was used to further envision the possibility of the framework adaptation. Generally, effort should be made to ensure old and new large public and private buildings have well-functioning firefighting infrastructures as stipulated in policies and laws for public safety. Furthermore, slight infrastructure improvement is required, particularly in sustainable power supply, internet connectivity, and automatic fire detection and alarm systems, to adapt the presented early fire detection and control framework smoothly.

Contemporary Fire Safety Engineering in Timber Structures: Challenges and Solutions

As environmental conservation and sustainability gain prominence globally, modern timber structures are receiving increased focus. Nonetheless, the combustible nature of timber raises significant fire safety concerns. This review explores the recent advancements in fire safety engineering for timber structures, emphasizing both contemporary high-rise buildings and historical timber constructions. It covers topics like inherently safer design principles, fire risk prediction, and evacuation methodologies. The review emphasizes the criticality of selecting suitable materials, structural design, firefighting systems, and advanced sensor technologies for early fire detection. Additionally, we analyze and compares various evacuation strategies, offering insights into the challenges and future directions for fire safety in modern timber structures.

RANCANG BANGUN ALAT PENDETEKSI DINI PONTENSI KEBAKARAN SECARA OTOMATIS pada RUANGAN TERINTGRASI dengan INTERNET of THINGS

In an effort to enhance safety and early detection of potential fires in indoor spaces, this research designs and constructs an automatic early fire detection device integrated with the Internet of Things (IoT). The device incorporates a flame sensor, MQ2 sensor, DHT11 temperature and humidity sensor, buzzer, LCD 16x2, and Node MCU to provide an effective and efficient solution. The flame sensor is utilized to detect the presence of fire, while the MQ2 sensor is employed to detect potentially hazardous gases associated with fires. The DHT11 sensor provides temperature and humidity information in the surrounding environment, aiding in identifying potential conditions conducive to fires. The Node MCU serves as the central processing unit of the system, collecting data from the sensors and transmitting it to the IoT platform via Wi-Fi connectivity. This data can be accessed and monitored in real-time through applications or online platforms. Upon detecting a potential fire, the buzzer issues an audible alert, and the LCD 16x2 displays detection information for the user. The primary advantage of this device lies in its ability to provide prompt and efficient detection information, accessible remotely through internet connectivity. With the integration of IoT, the device offers a smarter and more responsive solution for addressing potential fires in indoor spaces. The implementation of this device is anticipated to enhance safety and provide better protection against the risk of fires.

A lightweight early forest fire and smoke detection method

A lightweight early forest fire and smoke detection method

Computational design of a smoke detector with high sensitivity considering three-dimensional flow characteristics

Early fire detection is essential for preventing catastrophic events, and fire detectors play a critical role in ensuring fire safety. Among the various types of fire detectors, photoelectric smoke detectors are widely used because of their ability to detect smoke at an early stage. The present study investigates the effects of changes in flow directions and inlet size on the smoke detection ability of a photoelectric smoke detector by conducting computational fluid dynamics (CFD) simulations. The results indicated that when the flow direction changes, the components in the optical chamber may hinder the smoke inflow and increase the detector activation time. Moreover, the smoke inlet size was found to affect the carbon monoxide concentration inside the chamber. The velocity magnitude distributions confirmed the correlation between the smoke velocity in the labyrinth structures entering the optical chamber and the detection ability of the smoke detector. These findings suggested that when optimizing the performance of a smoke detector, flow direction, inlet size, and amount of smoke introduced into the optical chamber should be considered. The current study suggested the modified design of the smoke detector to have superior detection ability in both directions compared to the base case in terms of activation time.

Early Detection of Forest and Land Fires Using Hotspots Data from S-NPP VIIRS Satellite Imagery Recording in the New Capital City Location

Forest and land fires are a natural disaster whose frequency is increasing annually, especially during dry season, forest and land fires also impact the new capital city in East Kalimantan as well. Early detection is very critical to prevent increasing impact of forest and land fires. Early detection can be done using hotspot data from satellite image recording. Based on this, it is very necessary to conduct research entitled Early Detection of Forest and Land Fires Using Hot Spots from “S-NPP VIIRS Image Records in the New Capital City Location”. The research was conducted in the new capital city location in East Kalimantan Province which consists of several sub-districts and 10 districts / cities. Descriptive quantitative method is used to analysed secondary data consist of hotspot data in each sub-district from satellite imagery data record namely S-NPP VIIRS from 2012-2022. Population number is same as the number of samples, namely hotspots number in each sub-district. Descriptive geostatistical analysis technique in ArcGIS software is used to process hotspot data. It is known that from 2012-2022, Kutai Kartanegara has the highest hotspots number with 38,694 spots, it followed by East Kutai with 36,915 spots, both are viewed from district/city scope. When viewed on the district scope, the highest was in Bengalon district from East Kutai District with 9,027 spots, it followed by Muarakaman District from Kutai Kartanagara District with 7,713 spots. The number of hotspots varies quite a lot amongst sub-district in the new capital city location, whose each have a numerous number that needs serious attention in order to minimize the loss of life and property. From analysis above, early detection is very important as a form of early warning system.

Forest Monitoring and Fire Detection System

Forest fires/Wildfires are the most common disaster in forests which lead to severe destruction of forest wealth, natural habitat and bio-diversity. Our concept is to create a system which will help in early detection of forest fire by measuring natural factors which lead to forest fire. Our Forest Monitoring and Fire Detection System uses various sensors like heat, smoke, wind, temperature and humidity to predict and detect forest fire on an early basis. The sensors are connected to Esp8266 wi-fi module which after detecting sends data to cloud. The cloud then sends the data to the website. The website displays an alert so that immediate action can be taken. Early detection and preventive measures are necessary to protect forests from fires which will be done using this system.

A Survey: Fire Detection Alarm System Using OpenCV

The Fire Detection Alarm System using OpenCV is a computer vision-based solution designed to provide early detection of fires in real-time video streams. Fires pose substantial threats to both human safety and property, underscoring the importance of timely intervention. This system leverages OpenCV, a powerful computer vision library, to identify flames and smoke patterns in video frames, triggering alerts upon detection. So, we propose a smoke and fire detection method based on YOLOv5 network as a solution to address this problem.

Long Range (LoRa) and Alert Network System for Forest Fire Prediction

Forest fires are a regular occurrence throughout the year with an increasing intensity in the summer and fall periods. Forest fires pose a significant threat to ecosystems, property and human lives. Early detection and rapid response are critical to mitigate the devastating effects of these fires. This article presents a Long Range (LoRa) Alert Network System designed for the early prediction and timely notification of forest fires. The system leverages LoRa technology to create a robust and cost-effective wireless communication network in remote forested areas. These fires primarily stem from various natural and environmental phenomena and natural disasters. The timely dissemination of forest fire alerts was hampered, resulting in delays in fire management. In order to address this issue, efforts were made to enhance the capability for prompt forest fire detection. The challenges predominantly revolve around forested regions where data communication infrastructure is deficient. In the event of a forest fire, there exists a network barrier that impedes information transmission. Consequently, forest fire detection systems leveraging Mesh LoRa networks and image processing networks have been devised. An integrated module within the LoRa/GPS HAT has been explored as a potential solution to the fire predicament. The Flame Sensor Module, functioning as a fire detection sensor component, and the LoRa/GPS HAT, serving as a hardware medium for radio frequency data transmission communication, have been employed. The interconnection of these devices within a network facilitates the development of a prototype fire detection system. Combining a Flame Sensor Module with a LoRa/GPS HAT is indeed a viable approach to creating a prototype fire detection and alert system. By combining the Flame Sensor Module with the LoRa/GPS HAT, a scalable and cost-effective fire detection and alert system appropriate for distant and wooded locations with limited traditional communication infrastructure is created. This system can play a crucial role in early fire detection, potentially reducing the severity of forest fires and protecting both natural resources and human lives.

FuF-Det: An Early Forest Fire Detection Method under Fog

In recent years, frequent forest fires have seriously threatened the earth’s ecosystem and people’s lives and safety. With the development of machine vision and unmanned aerial vehicle (UAVs) technology, UAV monitoring combined with machine vision has become an important development trend in forest fire monitoring. In the early stages, fire shows the characteristics of a small fire target and obvious smoke. However, the presence of fog interference in the forest will reduce the accuracy of fire point location and smoke identification. Therefore, an anchor-free target detection algorithm called FuF-Det based on an encoder–decoder structure is proposed to accurately detect early fire points obscured by fog. The residual efficient channel attention block (RECAB) is designed as a decoder unit to improve the problem of the loss of fire point characteristics under fog caused by upsampling. Moreover, the attention-based adaptive fusion residual module (AAFRM) is used to self-enhance the encoder features, so that the features retain more fire point location information. Finally, coordinate attention (CA) is introduced to the detection head to make the image features correspond to the position information, and improve the accuracy of the algorithm to locate the fire point. The experimental results show that compared with eight mainstream target detection algorithms, FuF-Det has higher average precision and recall as an early forest fire detection method in fog and provides a new solution for the application of machine vision to early forest fire detection.

EKSTRAKSI FITUR CITRA API BERBASIS EKSTRAKSI WARNA PADA RUANG WARNA HSV dan RGB

The potential for fires increased at this time. Many factors cause fire, both small sale and large scale, such as forest fires. Early detection of fire is one of the right solutions. The Research about detection fire use any methods, you can use UAVs (Unmanned Aerial Vehicle), Android devices, and other technologies that are mostly based on image processing. This is one of the research based on image processing with fire objects. Fire image will be processed in the features extraction with the source of the fire coming from the candle. The candle is used as a detection object because the color characteristics of the fire in the candle as same as a larger scale fire. The method used is feature extraction based on colour extraction in HSV color space (Hue Saturation Value) and RGB color space (Red Green Blue). The result of this research are parameters of each color space for fire detection, there are HSV color space get 0,2≥Hue≥0,1; 0,85≥Saturation≥0,5; and 1≥Value≥0,9, and also for RGB color space get 255≥Red≥230; 250≥Green≥100; and 130≥Blue.

Laypeople in fire protection: Their motivation, their emotions, their value

Fire events, a specific type of emergency situation, occur regularly and often cost people's lives. Early fire detection and involvement of (trained) laypeople in very early stages is essential, especially in fire-prone historical buildings. In an interview study (N = 25) and a quantification study (N = 238), we examined laypeople's motivation to help, their emotions, and their value – especially regarding behaviors – during fires. In Study 1, based on in-depth interviews using the critical incident technique, we inductively developed three category systems: 1) Key motivators included one's emotional bond to the object, altruism, self-protection, and self-efficacy. 2) Laypeople's emotions, such as stress at first but also calmness, were categorized. 3) We found that laypeople's primary value during fire incidents was their ability to provide support, e.g., knowledge of the building. In Study 2, we found quantitative support for the findings derived from Study 1. Additionally, we compared laypeople's and experts' assessments and compared reactions depending on fire size. Thus, our research shifts the focus from evacuation to active – and safe – involvement of laypeople. Our results are helpful for executives in emergency management, as they may find value in including laypeople when coping with emergencies.

Early Fire Detection Using Long Short-Term Memory-Based Instance Segmentation and Internet of Things for Disaster Management.

Fire outbreaks continue to cause damage despite the improvements in fire-detection tools and algorithms. As the human population and global warming continue to rise, fires have emerged as a significant worldwide issue. These factors may contribute to the greenhouse effect and climatic changes, among other detrimental consequences. It is still challenging to implement a well-performing and optimized approach, which is sufficiently accurate, and has tractable complexity and a low false alarm rate. A small fire and the identification of a fire from a long distance are also challenges in previously proposed techniques. In this study, we propose a novel hybrid model, called IS-CNN-LSTM, based on convolutional neural networks (CNN) to detect and analyze fire intensity. A total of 21 convolutional layers, 24 rectified linear unit (ReLU) layers, 6 pooling layers, 3 fully connected layers, 2 dropout layers, and a softmax layer are included in the proposed 57-layer CNN model. Our proposed model performs instance segmentation to distinguish between fire and non-fire events. To reduce the intricacy of the proposed model, we also propose a key-frame extraction algorithm. The proposed model uses Internet of Things (IoT) devices to alert the relevant person by calculating the severity of the fire. Our proposed model is tested on a publicly available dataset having fire and normal videos. The achievement of 95.25% classification accuracy, 0.09% false positive rate (FPR), 0.65% false negative rate (FNR), and a prediction time of 0.08 s validates the proposed system.