Machine olfaction using time scattering of sensor multiresolution graphs

TL;DR

This paper introduces a novel learning architecture combining wavelet decomposition on sensor graphs and scattering networks to improve classification in high-dimensional time series data, specifically for machine olfaction.

Contribution

The paper presents a new method that integrates graph-based wavelet features with scattering networks for enhanced sensor data analysis.

Findings

Outperforms classical machine learning techniques in gas classification tasks

Effectively exploits mutual information between sensors

Demonstrates superior accuracy in sensor array data analysis

Abstract

In this paper we construct a learning architecture for high dimensional time series sampled by sensor arrangements. Using a redundant wavelet decomposition on a graph constructed over the sensor locations, our algorithm is able to construct discriminative features that exploit the mutual information between the sensors. The algorithm then applies scattering networks to the time series graphs to create the feature space. We demonstrate our method on a machine olfaction problem, where one needs to classify the gas type and the location where it originates from data sampled by an array of sensors. Our experimental results clearly demonstrate that our method outperforms classical machine learning techniques used in previous studies.