Summary Acoustic Based Emergency Vehicle Detection Using Ensemble of deep Learning Models - ScienceDirect pdf.sciencedirectassets.com
1,296 words - html page - View html page
One Line
The article explores the use of deep learning models to analyze and classify sound events for the detection of emergency vehicles based on their siren sounds, referencing previous studies on convolutional neural networks.
Slides
Slide Presentation (11 slides)
Key Points
- Acoustic-based emergency vehicle detection is done using an ensemble of deep learning models.
- The temporal and spectral structure of sound events is analyzed and classified in the time-frequency domain.
- Mel-frequency cepstral coefficient (MFCC) is used to extract features from the collected dataset.
- Three deep neural network (DNN) models (dense layer, convolutional neural network (CNN), and recurrent neural network (RNN)) are investigated.
- An ensemble model is designed with optimum selected models to achieve the highest accuracy of 98.7%.
- Performance analysis is done comparing deep learning models with other machine learning models like perceptron, SVM, and decision tree.
Summaries
45 word summary
This article presents a study on acoustic-based emergency vehicle detection using deep learning models. It discusses the analysis and classification of sound events to detect emergency vehicles based on their siren sounds. The article references previous studies on the use of convolutional neural networks for
86 word summary
This article presents a study on the use of deep learning models for acoustic-based emergency vehicle detection. The researchers focused on analyzing and classifying sound events in the time-frequency domain to detect emergency vehicles based on their siren sounds. They collected a dataset from
This article discusses the use of deep learning models for acoustic-based emergency vehicle detection. It references several studies that have utilized convolutional neural networks (CNNs) for sound classification, including environmental sound classification and speech recognition. The authors also mention the use of