PSO-SVM applied to SWASV studies for accurate detection of Cd(II) based on disposable electrode

Abstract

Square wave anodic stripping voltammetry (SWASV) is an effective method for the detection of Cd(II), but the presence of Pb(II) usually has some potential and negative interference on the SWASV detection of Cd(II). In this paper, a novel method was proposed to predict the concentration of Cd(II) in the presence of Pb(II) based on the combination of chemically modified electrode (CME), machine learning algorithms (MLA) and SWASV. A Bi film/ionic liquid/screenprinted electrode (Bi/IL/SPE) was prepared and used for the sensitive detection of trace Cd(II). The parameters affecting the stripping currents were investigated and optimized. The morphologies and electrochemical properties of the modified electrode were characterized by scanning electron microscopy (SEM) and SWASV. The measured SWASV spectrograms obtained at different concentrations were used to build the mathematical models for the prediction of Cd(II), which taking the combined effect of Cd(II) and Pb(II) into consideration on the SWASV detection of Cd(II), and to establish a nonlinear relationship between the stripping currents of Pb(II) and Cd(II) and the concentration of Cd(II). The proposed mathematical models rely on an improved particle swarm optimization-support vector machine (PSO-SVM) to assess the concentration of Cd(II) in the presence of Pb(II) in a wide range of concentrations. The experimental results suggest that this method is suitable to fulfill the goal of Cd(II) detection in the presence of Pb(II) (correlation coefficient, mean absolute error and root mean square error were 0.998, 1.63 and 1.68, respectively). Finally, the proposed method was applied to predict the trace Cd(II) in soil samples with satisfactory results.

RETRACTED: Extreme learning machine for stock price prediction

“…A lot of current research focuses on further developing this technology by either subtly modify its implementation details or hybridizing it with other methods. For example, Yongjun, Li, et al 1 manage to improve traditional support vector machine's performance for increment learning by decomposing its sample space with different weight attached, Guo, Z., et al 2 exploit support vector machine optimized by PSO to financial time series forecasting, and Honghai, Y. and Haifei, L. 3 attempt to predict stock market assisted by a combination of support vector machine and empirical model decomposition.…”