Modelamiento del ruido ambiental en zonas urbanas y sectorización de los puntos críticos en la ciudad de Guayaquil.

Abstract

Sound noise is an increasing environmental problem that affects both the quality of human life and natural ecosystems. In urban and industrial areas, prolonged exposure to high noise levels can cause stress, cardiovascular issues, and sleep disorders in humans. In the wild, noise disrupts communication, reproduction, and behavioral patterns of many species, putting biodiversity at risk. To address this issue, a systematic noise measurement is proposed using Internet of Things (IoT) tools and Machine Learning (ML) techniques. IoT devices will enable real-time data collection on the intensity, frequency, and duration of noise across various locations, creating a dynamic sound map. These devices, equipped with acoustic sensors, will be strategically distributed to ensure representative coverage. With the collected data, Machine Learning models will be applied to analyze patterns and trends in noise generation. This will include identifying primary sources, critical timeframes, and assessing the impact on urban and natural areas. Predictive models will allow for anticipating future scenarios and simulating the effectiveness of potential solutions. Finally, mitigation techniques will be developed based on the analysis results. These could include intelligent acoustic barriers, adjustments in urban planning, and strategies to minimize noise emissions in critical areas. This approach combines advanced technology with a sustainable vision, aiming to reduce the negative effects of noise on human health and ecosystems. The use of IoT and ML not only enhances the precision and efficiency of noise measurement but also facilitates the implementation of preventive and corrective measures, fostering a healthier and more balanced environment. Keywords: Noise pollution, Urban noise, Machine Learning, Internet of Things