Classifying Multi-Gas Spectrums using Monte Carlo KNN and Multi-Resolution CNN

TL;DR

This paper introduces a novel approach combining Monte Carlo optimized KNN and multi-resolution CNNs to accurately classify multiple gases in near-infrared spectrums, demonstrating superior performance over traditional methods.

Contribution

The paper presents a new multi-resolution CNN architecture optimized with Monte Carlo KNN for multi-gas spectrum classification, improving accuracy over existing models.

Findings

Multi-resolution CNN outperforms multilayer perceptron.

Monte Carlo KNN effectively determines optimal kernel parameters.

Proposed method achieves higher classification accuracy.

Abstract

A Monte Carlo k-nearest neighbours (KNN) and a multi-resolution convolutional neural network (CNN) were developed to detect the presences of multiple gasses in near infrared (IR) spectrums. High Resolution Transmission database was used to synthesize the near IR spectrums. Monte Carlo KNN determined the optimal kernel sizes and the optimal number of channels. The multi-resolution CNN, composed of multiple different kernels, was created using the optimal kernel sizes and the optimal number of channels. The multi-resolution CNN outperforms the multilayer perceptron and the partial least squares.