Smart Fire Detector utilizing IoT-based Zigbee Sensor

<pre>There are several differences between the two types of alarm systems, conventional systems and addressable systems. It is important to carefully determine the introduction of a fire alarm system according to the installation environment. Talking about the main difference relates to how the connected device communicates with the main control panel by sending a signal. Cost is another factor that can be a determinant of your chosen fire alarm system. In this paper, we proposed smart addressable fire detection system. In the proposed system, <span>IoT</span> was used and the network was constructed using <span>ZigBee</span> module. In the configured network, it consists of a local server and a control server. The local server controls the addressing sensor and sends the information obtained from the sensor to the control server. The control server receives data transmitted from the local server and enables quick fire action. In the actual implementation, the local server used the Lycra controller and <span>ZigBee</span> module. In addition, the control server used the Raspberry Pi and <span>ZigBee</span> modules and connected to the Ethernet so that the administrator could monitor or control the local server.</pre>

Forest Fire Detection via Feature Entropy Guided Neural Network

Forest fire detection from videos or images is vital to forest firefighting. Most deep learning based approaches rely on converging image loss, which ignores the content from different fire scenes. In fact, complex content of images always has higher entropy. From this perspective, we propose a novel feature entropy guided neural network for forest fire detection, which is used to balance the content complexity of different training samples. Specifically, a larger weight is given to the feature of the sample with a high entropy source when calculating the classification loss. In addition, we also propose a color attention neural network, which mainly consists of several repeated multiple-blocks of color-attention modules (MCM). Each MCM module can extract the color feature information of fire adequately. The experimental results show that the performance of our proposed method outperforms the state-of-the-art methods.

Integrated Satellite System for Fire Detection and Prioritization

Several studies have shown the relevance of satellite systems in detecting, monitoring, and characterizing fire events as support to fire management activities. On the other hand, up to now, only a few satellite-based platforms provide immediately and easily usable information about events in progress, in terms of both hotspots, which identify and localize active fires, and the danger conditions of the affected area. However, this kind of information is usually provided through separated layers, without any synthetic indicator which, indeed, could be helpful, if timely provided, for planning the priority of the intervention of firefighting resources in case of concurrent fires. In this study, we try to fill these gaps by presenting an Integrated Satellite System (ISS) for fire detection and prioritization, mainly based on the Robust Satellite Techniques (RST), and the Fire Danger Dynamic Index (FDDI), an original re-structuration of the Índice Combinado de Risco de Incêndio Florestal (ICRIF), for the first time presented here. The system, using Moderate Resolution Imaging Spectroradiometer (MODIS), Advanced Very High Resolution Radiometer (AVHRR), and Spinning Enhanced Visible and InfraRed Imager (SEVIRI) data, provides near real-time integrated information about both the fire presence and danger over the affected area. These satellite-based products are generated in common formats, ready to be ingested in Geographic Information System (GIS) technologies. Results shown and discussed here, on the occasion of concurrent winter and summer fires in Italy, in agreement with information from independent sources, demonstrate that the ISS system, operating at a regional/national scale, may provide an important contribution to fire prioritization. This may result in the mitigation of fire impact in populated areas, infrastructures, and the environment.

Forest fire detection system using wireless sensor networks and machine learning

Forest fires have become a major threat around the world, causing many negative impacts on human habitats and forest ecosystems. Climatic changes and the greenhouse effect are some of the consequences of such destruction. Interestingly, a higher percentage of forest fires occur due to human activities. Therefore, to minimize the destruction caused by forest fires, there is a need to detect forest fires at their initial stage. This paper proposes a system and methodology that can be used to detect forest fires at the initial stage using a wireless sensor network. Furthermore, to acquire more accurate fire detection, a machine learning regression model is proposed. Because of the primary power supply provided by rechargeable batteries with a secondary solar power supply, a solution is readily implementable as a standalone system for prolonged periods. Moreover, in-depth attention is given to sensor node design and node placement requirements in harsh forest environments and to minimize the damage and harmful effects caused by wild animals, weather conditions, etc. to the system. Numerous trials conducted in real tropical forest sites found that the proposed system is effective in alerting forest fires with lower latency than the existing systems.

Random Forest Feature Selection and Back Propagation Neural Network to Detect Fire Using Video

As the most common serious disaster, fire may cause a lot of damages. Early detection and treatment of fires are of great significance to ensure public safety and to reduce losses caused by fires. However, traditional fire detectors are facing some focus issues such as low sensitivity and limited detection scenes. To overcome these problems, a video fire detection hybrid method based on random forest (RF) feature selection and back propagation (BP) neural network is proposed. The improved flame color model in RGB and HSI space and the visual background extractor (ViBe) in moving target detection algorithm are used to segment the suspected flame regions. Then, multidimensional features of flames are extracted from the suspected regions, and these extracted features are combined and selected according to the RF feature importance analysis. Finally, a BP neural network model is constructed for multifeature fusion and fire recognition. The test results on several experimental video sets show that the proposed method can effectively avoid feature interference and has an excellent recognition effect on fires in a variety of scenarios. The proposed method is applicable for fire recognition applied in video surveillance and detection robots.

Remote Sensing Mapping of Peat-Fire-Burnt Areas: Identification among Other Wildfires

Peat fires differ from other wildfires in their duration, carbon losses, emissions of greenhouse gases and highly hazardous products of combustion and other environmental impacts. Moreover, it is difficult to identify peat fires using ground-based methods and to distinguish peat fires from forest fires and other wildfires by remote sensing. Using the example of catastrophic fires in July–August 2010 in the Moscow region (the center of European Russia), in the present study, we consider the results of peat-fire detection using Terra/Aqua Moderate Resolution Imaging Spectroradiometer (MODIS) hotspots, peat maps, and analysis of land cover pre- and post-fire according to Landsat-5 TM data. A comparison of specific (for detecting fires) and non-specific vegetation indices showed the difference index ΔNDMI (pre- and post-fire normalized difference moisture Index) to be the most effective for detecting burns in peatlands according to Landsat-5 TM data. In combination with classification (both unsupervised and supervised), this index offered 95% accuracy (by ground verification) in identifying burnt areas in peatlands. At the same time, most peatland fires were not detected by Terra/Aqua MODIS data. A comparison of peatland and other wildfires showed the clearest differences between them in terms of duration and the maximum value of the fire radiation power index. The present results may help in identifying peat (underground) fires and their burnt areas, as well as accounting for carbon losses and greenhouse gas emissions.