Mixture Correntropy-Based Kernel Extreme Learning Machines

Modeling risk assessment of soil heavy metal pollution using partial least squares and fuzzy logic: A case study of a gully type coal-based solid waste dumpsite

Continuous release and migration of heavy metals from coal-based solid waste (CSW) dumpsites often results in significant encroachment on ecological lands and pollution of natural environments. As a result, there is an urgent need for long-term and rapid monitoring, analysis, and assessment to control environmental risks associated with large CSW dumpsites. We constructed a new composite model (PLS-FL) that uses partial least squares regression (PLSR) and fuzzy logic inference (FLI) to accurately predict heavy metal concentrations in soils and assess pollution risk levels. The potential application of the PLS-FL was tested through a gully type CSW case study. We compared 20 modeling strategies using the PLS-FL: five types heavy metals (Cd, Zn, Pb, Cr and As) * four spectral transformation methods (first derivative (FD), second derivative (SD), reverse logarithm (RL), and continuum removal (CR)) * one variable selection method (competitive adaptive reweighted sampling (CARS)). The results showed that the combination of derivative transformation and CARS was recommended for estimation, with R2C > 0.80 and R2P > 0.50. When comparing the PLSR model with four traditional machine learning methods (Support Vector Machines (SVM), Random Forests (RF), Extreme Learning Machines (ELM), and KNN), the PLSR model demonstrated the highest average prediction accuracy. Additionally, the FLI process no longer relies on human perception and expert opinion, enhancing the model's objectivity and reliability. The evaluation results revealed that the heavy metal contamination areas of the CSW dumpsite are concentrated at the bottom of the gully, with more severe contamination in the north. Furthermore, a high-risk zone exists in the interim storage area for CSW to the east of the dump. These findings align with the initial detections at the sampling sites and highlight the need for targeted monitoring and control in these areas. The application of the model will empower regulators to quickly assess the overall situation of large-scale heavy metal pollution and provide scientific program and data support for continuous large-scale pollution risk monitoring and sustainable risk management.

Computationally efficient robust adaptive filtering algorithm based on improved minimum error entropy criterion with fiducial points

Recently, there has been a strong interest in the minimum error entropy (MEE) criterion derived from information theoretic learning, which is effective in dealing with the multimodal non-Gaussian noise case. However, the kernel function is shift invariant resulting in the MEE criterion being insensitive to the error location. An existing solution is to combine the maximum correntropy (MC) with MEE criteria, leading to the MEE criterion with fiducial points (MEEF). Nevertheless, the algorithms based on the MEEF criterion usually require higher computational complexity. To remedy this problem, an improved MEEF (IMEEF) criterion is devised, aiming to avoid repetitive calculations of the aposteriori error, and an adaptive filtering algorithm based on gradient descent (GD) method is proposed, namely, GD-based IMEEF (IMEEF-GD) algorithm. In addition, we provide the convergence condition in terms of mean sense, along with an analysis of the steady-state and transient behaviors of IMEEF-GD in the mean-square sense. Its computational complexity is also analyzed. Simulation results demonstrate that the computational requirement of our algorithm does not vary significantly with the error sample number and the derived theoretical model is highly consistent with the learning curve. Ultimately, we employ the IMEEF-GD algorithm in tasks such as system identification, wind signal magnitude prediction, temperature prediction, and acoustic echo cancellation (AEC) to validate the effectiveness of the IMEEF-GD algorithm.

A runoff prediction method based on hyperparameter optimisation of a kernel extreme learning machine with multi-step decomposition

To improve the accuracy of runoff forecasting, a combined forecasting model is established by using the kernel extreme learning machine (KELM) algorithm optimised by the butterfly optimisation algorithm (BOA), combined with the variational modal decomposition method (VMD) and the complementary ensemble empirical modal decomposition method (CEEMD), for the measured daily runoff sequences at Jiehetan and Huayuankou stations and Gaochun and Lijin stations. The results show that the combined model VMD-CEEMD-BOA-KELM predicts the best. The average absolute errors are 30.02, 23.72, 25.75, 29.37, and the root mean square errors are 20.53 m3/s, 18.79 m3/s, 18.66 m3/s, and 21.87 m3/s, the decision coefficients are all above 90 percent, respectively, and the Nash efficiency coefficients are all more than 90%, from the above it can be seen that the method has better results in runoff time series prediction.

Accurate Nonlinearity and Temperature Compensation Method for Piezoresistive Pressure Sensors Based on Data Generation

Piezoresistive pressure sensors exhibit inherent nonlinearity and sensitivity to ambient temperature, requiring multidimensional compensation to achieve accurate measurements. However, recent studies on software compensation mainly focused on developing advanced and intricate algorithms while neglecting the importance of calibration data and the limitation of computing resources. This paper aims to present a novel compensation method which generates more data by learning the calibration process of pressure sensors and uses a larger dataset instead of more complex models to improve the compensation effect. This method is performed by the proposed aquila optimizer optimized mixed polynomial kernel extreme learning machine (AO-MPKELM) algorithm. We conducted a detailed calibration experiment to assess the quality of the generated data and evaluate the performance of the proposed method through ablation analysis. The results demonstrate a high level of consistency between the generated and real data, with a maximum voltage deviation of only 0.71 millivolts. When using a bilinear interpolation algorithm for compensation, extra generated data can help reduce measurement errors by 78.95%, ultimately achieving 0.03% full-scale (FS) accuracy. These findings prove the proposed method is valid for high-accuracy measurements and has superior engineering applicability.

Daily runoff prediction during flood seasons based on the VMD-HHO-KELM model

Improving the accuracy of daily runoff in the lower Yellow River is important for flood control and reservoir scheduling in the lower Yellow River. Influenced by factors such as meteorology, climate change, and human activities, runoff series present non-stationary and non-linear characteristics. To weaken the non-linearity and non-smoothness of runoff time series and improve the accuracy of daily runoff prediction, a new combined runoff prediction model (VMD-HHO-KELM) based on the ensemble Variational Modal Decomposition (VMD) algorithm and Harris Hawk Optimisation (HHO) algorithm-optimised Kernel Extreme Learning Machine (KELM) is proposed and applied to Gaocun and Lijin hydrological stations. The VMD-HHO-KELM model has the highest prediction accuracy, with the prediction model R2 reaching 0.95, mean absolute error reaching 13.3, and root mean square error reaching 33.83 at the Gaocun hydrological station, and R2 reaching 0.96, mean absolute error reaching 8.03, and root mean square error reaching 38.45 at the Lijin hydrological station.

Heterogeneous Ensemble-Based Spike-Driven Few-Shot Online Learning

Spiking neural networks (SNNs) are regarded as a promising candidate to deal with the major challenges of current machine learning techniques, including the high energy consumption induced by deep neural networks. However, there is still a great gap between SNNs and the few-shot learning performance of artificial neural networks. Importantly, existing spike-based few-shot learning models do not target robust learning based on spatiotemporal dynamics and superior machine learning theory. In this paper, we propose a novel spike-based framework with the entropy theory, namely, heterogeneous ensemble-based spike-driven few-shot online learning (HESFOL). The proposed HESFOL model uses the entropy theory to establish the gradient-based few-shot learning scheme in a recurrent SNN architecture. We examine the performance of the HESFOL model based on the few-shot classification tasks using spiking patterns and the Omniglot data set, as well as the few-shot motor control task using an end-effector. Experimental results show that the proposed HESFOL scheme can effectively improve the accuracy and robustness of spike-driven few-shot learning performance. More importantly, the proposed HESFOL model emphasizes the application of modern entropy-based machine learning methods in state-of-the-art spike-driven learning algorithms. Therefore, our study provides new perspectives for further integration of advanced entropy theory in machine learning to improve the learning performance of SNNs, which could be of great merit to applied developments with spike-based neuromorphic systems.