This paper presents a novel method, named wavelet packet transform based multilayer feedforward neural network with Levenberg-Marquardt and back propagation algorithm (WPTLMBP), developed for simultaneous kinetic determination of Cu(II), Fe(III), and Ni(II). Wavelet packet representations of signals provided a local time-frequency description, thus in the wavelet packet domain the quality of noise removal can be improved. The artificial neural network was applied for non-linear multivariate calibration. In this study, by optimization, wavelet packet function, decomposition level and number of hidden nodes for WPTLMBP method were selected as Db2, 2, and 4 respectively. A program PWPTLMBP was designed to perform simultaneous kinetic determination of Cu(II), Fe(III), and Ni(II). The relative standard error of prediction (RSEP) for all components with WPTLMBP, LM-BP-MLFN, and PLS methods were 6.39, 10.4, and 8.30%, respectively. Experimental results showed the proposed method to be successful and better than the others.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1007/s00216-003-2395-y | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Discrimination of Real and Deep Fake Videos using EEG Signals.
Annu Int Conf IEEE Eng Med Biol Soc
July 2024
Deepfake technology can create highly realistic fabricated videos, presenting serious ethical concerns and threats of misinformation. Reliably distinguishing deepfakes from genuine videos is therefore critical yet challenging. This study explored electroencephalography (EEG)-based deepfake detection by analyzing EEG responses in 10 participants viewing 100 videos (50 real, 50 deepfakes).
View Article and Find Full Text PDFAutoVMDPgram: An Effective Method for Fault Diagnosis of Rolling Bearing.
IEEE Trans Neural Netw Learn Syst
December 2024
In previous studies, the VMDPgram was creatively proposed by combining variational mode decomposition (VMD) with wavelet packet transform (WPT). Although the VMDPgram demonstrates excellent performance in bearing fault diagnosis, there are still some issues that need to be further studied. In light of this, this work conducts the in-depth studies of VMDPgram for the unresolved issues.
View Article and Find Full Text PDFResearch on blasting damage to tunnel surrounding rock based on acoustic full waveform signal analysis.
Sci Rep
February 2025
Hebei University of Architecture, Hebei, 075000, China.
In order to study the application of Acoustic Full Waveform Signal analysis in blasting damage to tunnel surrounding rock, a formula for blasting damage increment considering cumulative effects was proposed by analyzing the Acoustic Full Waveform Signal before and after blasting, based on the concepts of elastic waves and damage degree. This formula allows the cumulative damage law of surrounding rock blasting to be calculated and analyzed. Furthermore, by introducing the Lorentz curve, Gini coefficient, and fractal theory, and combining them with the surrounding rock blasting damage law, their practicality in studying blasting damage was verified.
View Article and Find Full Text PDFOptimization of the Entropy-Based Wavelet Method for Removing Strong RF and AC Interferences in a Charge Detection Linear Ion Trap Mass Spectrometer.
Anal Chem
March 2025
Department of Physics, National Dong Hwa University, Shoufeng, Hualien 97401, Taiwan.
We developed an entropy-based wavelet method to effectively remove interference from strong radio frequency (RF) and auxiliary alternating current (AC) fields in a linear ion trap (LIT) mass spectrometer coupled to a charge sensing particle detector (CSPD). By optimizing the energy-to-Shannon entropy, we identified the optimal mother wavelet family and decomposition level and determined suitable threshold values based on the median of sub-band coefficients at each decomposition level. These thresholds were applied as rigid criteria across all decomposition levels to eliminate noise interferences and avoid the arbitrary choice of the threshold.
View Article and Find Full Text PDFMethod for EEG signal recognition based on multi-domain feature fusion and optimization of multi-kernel extreme learning machine.
Sci Rep
February 2025
School of Mechanic Engineering, Northeast Electric Power University, Jilin, 132012, China.
In response to the current issues of one-sided effective feature extraction and low classification accuracy in multi-class motor imagery recognition, this study proposes an Electroencephalogram (EEG) signal recognition method based on multi-domain feature fusion and optimized multi-kernel extreme learning machine. Firstly, the EEG signals are preprocessed using the Improved Comprehensive Ensemble Empirical Mode Decomposition (ICEEMD) algorithm combined with the Pearson correlation coefficient to eliminate noise and interference. Secondly, multivariate autoregressive (MVAR) model, wavelet packet decomposition, and Riemannian geometry methods are used to extract features from the time domain, frequency domain, and spatial domain, respectively, to construct a joint time-frequency-space feature vector.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!