M+N theory can be used as a method to improve the prediction accuracy in spectral analysis. The measured component, M kinds of non-measurement component, and N kinds of outside interference are induced into the entire measuring system, with the impact of "M" factors and "N" factors on the measurement accuracy considered systematically and comprehensively. Our human experiment system testing blood oxygen saturation based on "M+N" theory has been established. Dynamic spectrum method was used to eliminate the effects of different persons and different measuring parts which belonged to the system error of "N" factors. And then the D-value estimation was used to eliminate the effects of motion pseudo signal which belonged to the random error of "M" factors. Sixty two groups of valid data were obtained. The prediction model of blood oxygen saturation was built based on partial least squares regression method. The correlation coefficient and relative error were 0.796 8 and ±0.026 6, while the result of oximeter was 0.595 7 and relative error was ±0.076 0, respectively. The results show that the prediction accuracy of the measurement method based on the "M+N" theory is much higher than that of the oximeter.
Partial least square (PLS) combining with Raman spectroscopy was applied to develop predictive models for plasma paclitaxel concentration detection. In this experiment, 312 samples were scanned by Raman spectroscopy. High performance liquid chromatography (HPLC) was applied to determine the paclitaxel concentration in 312 rat plasma samples. Monte Carlo partial least square (MCPLS) method was successfully performed to identify the outliers and the numbers of calibration set. Based on the values of degree of approach (Da), moving window partial least square (MWPLS) was used to choose the suitable preprocessing method, optimum wavelength variables and the number of latent variables. The correlation coefficients between reference values and predictive values in both calibration set (Rc2) and validation set (Rp2) of optimum PLS model were 0.933 1 and 0.926 4, respectively. Furthermore, an independent verification test was performed on the prediction model. The results showed that the correlation error of the 20 validation samples was 9.36%±2.03%, which confirmed the well predictive ability of established PLS quantitative analysis model.
Electrocardiogram (ECG) is easily submerged in noise of the complex environment during remote medical treatment, and this affects the intelligent diagnosis of cardiovascular diseases. Considering this situation, this paper proposes an echo state network (ESN) denoising algorithm based on recursive least square (RLS) for ECG signals. The algorithm trains the ESN through the RLS method, and can automatically learn the deep nonlinear and differentiated characteristics in the noisy ECG data, and then the network can use these characteristic to separate out clear ECG signals automatically. In the experiment, the proposed method is compared with the wavelet transform with subband dependent threshold and the S-transform method by evaluating the signal-to-noise ratio and root mean square error. Experimental results show that the denoising accuracy is better and the low frequency component of the signal is well preserved. This method can effectively filter out complex noise and effectively preserve the effective information of ECG signals, which lays a foundation for the recognition of ECG signal feature waveform and the intelligent diagnosis of cardiovascular disease.
