Abstract
<title>Abstract</title> <p>Environmental noise pollution is a growing environmental and public health concern driven by rapid urbanisation, expanding transportation networks, and increasing industrial and construction activities. In recent years, advances in low-cost sensing technologies, the Internet of Things (IoT), and artificial intelligence (AI) have transformed environmental noise monitoring from periodic measurements to continuous, data-driven assessment systems. The growing volume of research in this area highlights the need for a comprehensive review of emerging technologies, methodologies, and applications. Accordingly, this review presents a systematic overview of recent developments in environmental noise monitoring, classification, and control using low-cost acoustic sensors, IoT architectures, and AI-based techniques. It offers a thorough, methodical overview of the latest research in these areas. Acoustic sensor technologies, electronic processor platforms, power and calibration methodologies, and IoT-based architectures for real-time data collection and management are all critically examined in this article. In addition, a review of machine learning (ML) and deep learning (DL) approaches for ambient noise classification is conducted, focusing on feature extraction techniques, model performance, the real-time deployment, and edge-computing viability. The review also covers data visualisation, alert generation, and interoperability mechanisms that support regulatory enforcement, occupational safety, and public awareness. Furthermore, both active noise control (ANC) and passive approaches, including recent deep learning-based ANC systems, are analysed in terms of effectiveness, practical limitations, and real-time deployment challenges. By critically examining current technologies and methodologies, this review provides a valuable resource for researchers and practitioners working toward intelligent, scalable, and cost-effective environmental noise-management solutions for smart cities and industrial environments, while identifying key technological trends, performance trade-offs, existing research gaps, and future directions for advancing the field.</p>