Algorithm 1	Frequency Domain Feature Matching Algorithm
Input:	Training dataset: $D_{train}=\left\{\left(X_{train}\left(i\right),Y_{train}\left(i\right)\right),i=1,2,3,\cdots ,k\right\}$; length of training dataset:$k$; Test dataset: $D_{test}=\left\{\left(X_{test}\left(i\right),Y_{test}\left(i\right)\right),i=1,2,3,\cdots ,s\right\}$; length of test dataset:$s$; Fast Fourier transform (FFT): $ℱ(·)$; The number of selected feature frequencies for each sample: $FN=10$; The function that returns the index of the array sorted in ascending order: $argsort(·)$; The function that reverses the array and returns the first $FN$ elements:$Revers{e}^{FN}(·)$; The number of categories: $m$; The number of selected feature frequencies for each category: $n$; Scoring function with scoring rules 1, 2 and 3: $SR\left\{A,B\right\}$; A is feature frequencies; B is feature matrix.
Output:	Feature matrix with size of $m\times n$; Scoreboard of all test samples.
Training stage:	Obtain feature matrix with size of $\mathit{m}\mathbf{\times }\mathit{n}$
	for $i\in \left[1,k\right]$ do       $X_{trainFFT}\left(i\right)=ℱ\left(X_{train}\left(i\right)\right)$ (Obtain the frequency spectrums of $k$ training samples by FFT);       $\left[f_1^i,f_2^i,\cdots ,f_{FN}^i\right]=Revers{e}^{FN}\left\{argsort\left[X_{trainFFT}\left(i\right)\right]\right\}$;       $Feature Frequencie{s}_{\left(i\right)}=\left[f_1^i,f_2^i,\cdots ,f_{FN}^i\right]$       (Extract $FN$ feature frequencies from frequency spectrum of each training sample); end for for $label\in \left[1,m\right]$ do       $A{F}_{label}=[ ]$;       for $i\in \left[1,k\right]$ do           if $Y_{train}\left(i\right)==label$ then           Append $Feature Frequencie{s}_{\left(i\right)}$ to the end of the list $A{F}_{label}$; end if end for       Count the occurrence times of feature frequencies in $A{F}_{label}$ and sort them in descending order;       The feature sequence $F_{label}$ consists of the first $n$ feature frequencies;       $F_{label}=\left[F_{label1},F_{label2},\cdots ,F_{labeln}\right]$; end for $\mathrm{Feature} \mathrm{Matrix}=\left[\begin{array}{cc}\begin{array}{cc}{F}_{11}& F_{12}\\ F_{21}& F_{22}\end{array}& \begin{array}{cc}\cdots & F_{1n}\\ \cdots & F_{2n}\end{array}\\ \begin{array}{cc}⋮& ⋮\\ F_{m1}& F_{m2}\end{array}& \begin{array}{cc}\ddots & ⋮\\ \cdots & F_{mn}\end{array}\end{array}\right]$; return $\mathrm{Feature} \mathrm{Matrix}$
Test stage:	Calculate scoreboard of all test samples
	$Scoreboard=[ ]$; for $j\in \left[1,s\right]$ do       $X_{testFFT}\left(j\right)=ℱ\left(X_{test}\left(j\right)\right)$ (Obtain the frequency spectrums of $s$ test samples by FFT);       $\left[f_1^j,f_2^j,\cdots ,f_{FN}^j\right]=Revers{e}^{FN}\left\{argsort\left[X_{testFFT}\left(j\right)\right]\right\}$;       $Feature Frequencie{s}_{\left(j\right)}=\left[f_1^j,f_2^j,\cdots ,f_{FN}^j\right]$       (Extract $FN$ feature frequencies from frequency spectrum of each test sample);       $Scor{e}_j=0$ (Initialize score);       $\left[S_{j1},S_{j2},\cdots ,S_{jm}\right]=$ $SR\left\{Feature Frequencie{s}_{\left(j\right)}, \mathrm{Feature} \mathrm{Matrix}\right\}$;       $Scor{e}_j=\left[S_{j1},S_{j2},\cdots ,S_{jm}\right]$;       Append $Scor{e}_j$ to the end of the list $Scoreboard$; end for $Scoreboard=\left[\begin{array}{cc}\begin{array}{cc}{S}_{11}& S_{12}\\ S_{21}& S_{22}\end{array}& \begin{array}{cc}\cdots & S_{1m}\\ \cdots & S_{2m}\end{array}\\ \begin{array}{cc}⋮& ⋮\\ S_{s1}& S_{s2}\end{array}& \begin{array}{cc}\ddots & ⋮\\ \cdots & S_{sm}\end{array}\end{array}\right]$; return $Scoreboard$