Table 4.

Analysis of the statistical significance of the respiratory/wheezing SDR, SIR and SAR results comparing the proposed method (IIS-NMPCF) with the other evaluated methods using an one-sided paired t-test in the databases T1H (see Figure 7).

Method	SDR${}_{\mathit{r}}$	SIR${}_{\mathit{r}}$	SAR${}_{\mathit{r}}$	SDR${}_{\mathit{w}}$	SIR${}_{\mathit{w}}$	SAR${}_{\mathit{w}}$
NMF	$6.1\times {10}^{-10}$	$4.1\times {10}^{-10}$	$5.4\times {10}^{-3}$	$1.9\times {10}^{-11}$	$1.8\times {10}^{-11}$	$4.8\times {10}^{-7}$
SSNMF	$1.4\times {10}^{-7}$	$5.5\times {10}^{-8}$	$4.8\times {10}^{-3}$	$3.2\times {10}^{-10}$	$4.4\times {10}^{-12}$	$8.9\times {10}^{-8}$
SNMF	$1\times {10}^{-7}$	$3.1\times {10}^{-7}$	$4.5\times {10}^{-8}$	$7.9\times {10}^{-12}$	$1.4\times {10}^{-10}$	$1.2\times {10}^{-2}$
2S-NMPCF	$3.3\times {10}^{-7}$	$5.5\times {10}^{-6}$	$4.9\times {10}^{-7}$	$2.6\times {10}^{-11}$	$1.7\times {10}^{-10}$	$1.8\times {10}^{-3}$
1S-NMPCF	$6\times {10}^{-6}$	$4\times {10}^{-7}$	$2.7\times {10}^{-6}$	$5.2\times {10}^{-10}$	$9.2\times {10}^{-11}$	$4.9\times {10}^{-3}$
T-NMPCF	$3.8\times {10}^{-5}$	$5.7\times {10}^{-5}$	$3.3\times {10}^{-4}$	$4.4\times {10}^{-9}$	$8.9\times {10}^{-9}$	$2.9\times {10}^{-2}$
CNMF	$1.6\times {10}^{-4}$	$1.7\times {10}^{-3}$	$1.8\times {10}^{-7}$	$2.6\times {10}^{-6}$	$1.3\times {10}^{-6}$	$7.2\times {10}^{-4}$
ST-NMPCF	$1.5\times {10}^{-4}$	$9.5\times {10}^{-6}$	$5.2\times {10}^{-2}$	$3.9\times {10}^{-5}$	$5.3\times {10}^{-7}$	$2.2\times {10}^{-2}$
IIS${}_0$-NMPCF	$4\times {10}^{-2}$	$2.2\times {10}^{-3}$	$1\times {10}^{-1}$	$4.2\times {10}^{-2}$	$8.2\times {10}^{-3}$	$1.1\times {10}^{-1}$

Each cell shows the parameter $\rho$ that represents the probability of setting a statistically significant result. Considering a confidence interval of 95%, small values of $\rho$ < 0.05 indicate that there exists statistical significance of the results evaluated.