Data imbalance is a thorny issue in machine learning. SMOTE is a famous oversampling method of imbalanced learning. However, it has some disadvantages such as sample overlapping, noise interference, and blindness of neighbor selection. In order to address these problems, we present a new oversampling method, OS-CCD, based on a new concept, the classification contribution degree. The classification contribution degree determines the number of synthetic samples generated by SMOTE for each positive sample. OS-CCD follows the spatial distribution characteristics of original samples on the class boundary, as well as avoids oversampling from noisy points. Experiments on twelve benchmark datasets demonstrate that OS-CCD outperforms six classical oversampling methods in terms of accuracy, F1-score, AUC, and ROC.

Wastewater discharge is important in numerous areas of industries and in governance of the environmental sectors. Controlling and monitoring water pollution are essential for protecting the availability of water and upholding standards of sustainability. Thus, in the current study, the effects of pollutant discharge concentration (PDC) are considered while analyzing the flow of non-Newtonian nanofluids (NNNF) through the permeable Riga surface subject to heat radiation. Walter’s B fluid (WBF) and second-grade fluids (SGFs), two distinct types of NNNF, have been investigated. The fluid flow is expressed as a system of PDEs, which are simplified into lower order by employing similarity approach. These equations (ODEs) are solved using the Levenberg Marquardt back-propagation optimization algorithm (LMBOA) of the artificial neural network (ANN). The Matlab package “bvp4c” is used for generating the dataset in order to validate the results of the ANN-LMBOA. The dataset was developed for various flow scenarios, as well as ANN evaluation and validation. The accuracy of the ANN-LMBOA model is estimated though numerous statistical tools, i.e., histogram, regression measures, curve fitting, performance plots, and validation tables. The numerical outcomes of bvp4c package are also compared to the published literature. Which show best accuracy and resemblance with each other for the limiting case. The targeted date absolute error is accomplished within the range of 10^–4-10^–5 which confirms the outstanding accuracy of ANN-LMBOA. It is concluded form error histograms (EHs) that the EHs values for case 1–4 is lie about \(3 \cdot 6 \times 10^{{ - 7}}\), \(7 \cdot 83 \times 10^{{ - 9}}\), \(- 4.7 \times 10^{{ - 8}}\) and \(- 2 \cdot 9 \times 10^{{ - 6}}\) respectively.

Dropout and DropConnect are two techniques to facilitate the regularization of neural network models, having achieved the state-of-the-art results in several benchmarks. In this paper, to improve the generalization capability of spiking neural networks (SNNs), the two drop techniques are first applied to the state-of-the-art SpikeProp learning algorithm resulting in two improved learning algorithms called SPDO (SpikeProp with Dropout) and SPDC (SpikeProp with DropConnect). In view that a higher membrane potential of a biological neuron implies a higher probability of neural activation, three adaptive drop algorithms, SpikeProp with Adaptive Dropout (SPADO), SpikeProp with Adaptive DropConnect (SPADC), and SpikeProp with Group Adaptive Drop (SPGAD), are proposed by adaptively adjusting the keep probability for training SNNs. A convergence theorem for SPDC is proven under the assumptions of the bounded norm of connection weights and a finite number of equilibria. In addition, the five proposed algorithms are carried out in a collaborative neurodynamic optimization framework to improve the learning performance of SNNs. The experimental results on the four benchmark data sets demonstrate that the three adaptive algorithms converge faster than SpikeProp, SPDO, and SPDC, and the generalization errors of the five proposed algorithms are significantly smaller than that of SpikeProp. Furthermore, the experimental results also show that the five algorithms based on collaborative neurodynamic optimization can be improved in terms of several measures.