@inbook{10498/37705,
year = {2025},
month = {8},
url = {http://hdl.handle.net/10498/37705},
abstract = {With the increasing adoption of AI in safety-critical applications within urban environments, the interpretability of these systems is paramount. This study explores the application of Explainable Artificial Intelligence (XAI) techniques to enhance transparency in audio-based detection of emergency vehicle sirens, a crucial component in urban sound management. Adopting methods such as SHAP (SHapley Additive exPlanations) values, Permutation Feature Importance, and model-specific feature scores, this research identifies key audio features, including mid-frequency spectral contrasts and targeted chroma components, which significantly help in distinguishing siren sounds among urban noise. The study examines various machine learning models, identifying K-Nearest Neighbors (KNN) and XGBoost as top performers; KNN excelled in class-specific precision, while XGBoost demonstrated strong cross-class discrimination. The findings highlight the potential of XAI in improving both accuracy and accountability for sound detection systems in safety-critical urban applications, advancing the deployment of transparent AI within smart city infrastructures.},
publisher = {IEEE Xplore},
keywords = {Explainable Artificial Intelligence (XAI)},
keywords = {audio-based emergency detection},
keywords = {urban sound classification},
keywords = {machine learning},
keywords = {feature importance analysis},
title = {Explainable Artificial Intelligence for Audio-based Detection of Emergency Vehicles},
doi = {10.1109/IE64880.2025.11130127},
author = {Balderas Díaz, Sara and Guerrero Contreras, Gabriel José and Muñoz Ortega, Andrés and Durães, Dalila and Novais, Paulo},
}