Classifying Multi-Gas Spectrums using Monte Carlo KNN and Multi-Resolution CNN
This work addresses gas detection in spectroscopy, an incremental improvement for environmental monitoring or safety applications.
The researchers tackled the problem of detecting multiple gases in near-infrared spectrums by developing a Monte Carlo KNN and a multi-resolution CNN, which outperformed multilayer perceptron and partial least squares methods.
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.