Thadeu Brito

Abstract
Worldwide, forests have been harassed by fire in recent years. Either by human intervention or other reasons, the history of the burned area is increasing considerably, harming fauna and flora. It is essential to detect an early ignition for fire-fighting authorities can act quickly, decreasing the impact of forest damage impacts. The proposed system aims to improve nature monitoring and improve the existing surveillance systems through satellite image recognition. The soil recognition via satellite images can determine the sensor modules’ best position and provide crucial input information for artificial intelligence-based systems. For this, satellite images from the Sentinel-2 program are used to generate forest density maps as updated as possible. Four classification algorithms make the Tree Cover Density (TCD) map, consisting of the Gaussian Mixture Model (GMM), Random Forest (RF), Support Vector Machine (SVM), and K-Nearest Neighbors (K-NN), which identify zones by training known regions. The results demonstrate a comparison between the algorithms through their performance in recognizing the forest, grass, pavement, and water areas by Sentinel-2 images. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

Abstract

Abstract
Developing innovative systems and operations to monitor forests and send alerts in dangerous situations, such as fires, has become, over the years, a necessary task to protect forests. In this work, a Wireless Sensor Network (WSN) is employed for forest data acquisition to identify abrupt anomalies when a fire ignition starts. Even though a low-power LoRaWAN network is used, each module still needs to save power as much as possible to avoid periodic maintenance since a current consumption peak happens while sending messages. Moreover, considering the LoRaWAN characteristics, each module should use the bandwidth only when essential. Therefore, four algorithms were tested and calibrated along real and monitored events of a wildfire. The first algorithm is based on the Exponential Smoothing method, Moving Averages techniques are used to define the other two algorithms, and the fourth uses the Least Mean Square. When properly combined, the algorithms can perform a pre-filtering data acquisition before each module uses the LoRaWAN network and, consequently, save energy if there is no necessity to send data. After the validations, using Wildfire Simulation Events (WSE), the developed filter achieves an accuracy rate of 0.73 with 0.5 possible false alerts. These rates do not represent a final warning to firefighters, and a possible improvement can be achieved through cloud-based server algorithms. By comparing the current consumption before and after the proposed implementation, the modules can save almost 53% of their batteries when is no demand to send data. At the same time, the modules can maintain the server informed with a minimum interval of 15 min and recognize abrupt changes in 60 s when fire ignition appears.

Abstract
Indoor Air Quality (IAQ) describes the air quality of a room, and it refers to the health and comfort of the occupants. Typically, people spend around 90% of their time in indoor environments where the concentration of air pollutants and, occasionally, more than 100 times higher than outdoor levels. According to the World Health Organization (WHO), indoor air pollution is responsible for the death of 3.8 million people annually. It has been indicated that IAQ in residential areas or buildings is significantly affected by three primary factors, they are outdoor air quality, human activity in buildings, and building and construction materials. In this context, this work consists of a real-time IAQ system to monitor thermal comfort and gas concentration. The system has a data acquisition stage, captured by the WSN with a set of sensors that measures the data and send it to be stored on the InfluxDB database and displayed on Grafana. A Linear Regression (LR) algorithm was used to predict the behavior of the measured parameters, scoring up to 99.7% of precision. Thereafter, prediction data is stored on InfluxDB in a new database and displayed on Grafana. In this way, it is possible to monitor the actual measurement data and prediction data in real-time. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

Abstract
Forests worldwide have been suffering from fires damages, provoking incalculable losses in fauna and flora, economic losses, people and animals' deaths, among other problems. To avoid forest fires catastrophes, it is fundamental to develop innovative operations, such as a forest fire monitoring system. This work concentrates efforts on defining the optimum sensor allocation in a forest fires monitoring system based on a wireless sensor network. Thus, a bi-objective mathematical model is developed to solve the problem, in which the first objective consists of minimising the forest fire hazard of a given forest region, and the second objective refers to the sensors spreading into this region. The developed mathematical model was solved by genetic algorithm and the results demonstrated that the methodology was capable of presenting suitable solutions for the problem. © 2023 American Institute of Physics Inc.. All rights reserved.