# Dimensionality reduction for acoustic vehicle classification with spectral embedding

## TL;DR

This paper introduces a spectral embedding-based dimensionality reduction technique for vehicle classification using roadside audio sensors, enabling efficient and accurate recognition of moving vehicles.

## Contribution

The paper presents a novel spectral embedding approach tailored for acoustic vehicle classification, improving data reduction and classification accuracy.

## Key findings

- Spectral embedding effectively reduces data dimensionality.
- K-nearest neighbors achieves high accuracy with reduced features.
- Method applicable to traffic analysis and surveillance.

## Abstract

We propose a method for recognizing moving vehicles, using data from roadside audio sensors. This problem has applications ranging widely, from traffic analysis to surveillance. We extract a frequency signature from the audio signal using a short-time Fourier transform, and treat each time window as an individual data point to be classified. By applying a spectral embedding, we decrease the dimensionality of the data sufficiently for K-nearest neighbors to provide accurate vehicle identification.