“…Frequency-modulated multi-dimensional feature extraction for 100% classi cation accuracy An inherent advantage of SMS over ensemble methods was the ability to record multi-dimensional features of the signal generated by an individual molecule 36 . The use of ve or more signal features was demonstrated recently as an effective approach to distinguish structurally similar compounds, e.g., achieving 92.4%-99.9% accuracy for the determination of saccharides 37 , riboses 38 , alditols 39 or benzenediols 40 . Herein, frequency modulation (using ve low-pass lters of 2000, 800, 500, 200 or 100 Hz, as well as the wavelet transform) was applied to extend the eight common features of singlemolecule signals, i.e., the magnitude (ΔI/I 0 ), duration (τ on ), standard deviation (I σ ), peak-to-peak (I pp ) of current blockade, and the peak (H peak ), full width at half maximum (H FWHM ), skewness (H skew ), kurtosis (H kurt ) of the all-points histograms of current blockade, to a total number of 43 (τ on remained constant at all frequencies), Fig.…”