Analytics Features

Table of contents

  1. Introduction

Introduction

Analytics features summarize, transform, compare, and fit processed spectra. General analytics includes average and interval plots, spectral derivation, FFT analysis, spectrum calculation, correlation heatmaps, peak identification, and full spectrum fitting. Machine learning methods are grouped separately under Machine Learning Feature.

Feature Utility Overview Documentation Video Tutorial
Average Plot with Original Spectra Visualize original data, visualize standard deviation and mean spectrum Average Plot  
Confidence Interval Plot Visualize standard deviation and mean spectrum Confidence Interval Plot  
Spectral Derivation Visualize the first and second derivatives of your data Spectral Derivation  
Fast Fourier Transform (FFT) analysis Transform one selected spectrum into the frequency domain Fast Fourier Transform  
Spectrum Calculation Apply arithmetic to spectral intensities or shift the wavenumber axis Spectrum Calculation  
Correlation Heatmap Quantify similarities between spectra trends in a grid format Correlation Heatmap  
Peak Identification and Stats Identify and classify peaks in spectra intensity Peak Identification  
Full Spectrum Fitting Fit Gaussian, Lorentzian, or Pseudovoigt peak components across a spectrum Full Spectrum Fitting  

Machine learning methods are grouped under Machine Learning Feature, including Hierarchically-clustered Heatmap, Principal Components Analysis (PCA), T-SNE Dimensionality Reduction, Random Forest(RF) Classification, K-Nearest Neighbors(KNN) Classification, and Support Vector Machine(SVM) Classification.

Please find more detailed information in child documents.

Table of contents