A multi-objective evolutionary approach to training set selection for support vector machine

A Non-Dominated Sorting Based Multi-Objective Neural Network Algorithm

Neural Network Algorithm (NNA) is a recently proposed Metaheuristic that is inspired by the idea of artificial neural networks. The performance of NNA on single-objective optimization problems is very promising and effective. In this article, a maiden attempt is made to restructure NNA for its possible use to address multi-objective optimization problems. To make NNA suitable for MOPs several fundamental changes in the original NNA are proposed. A novel concept is proposed to initialize the candidate solution, position update, and selection of target solution. To examine the optimization ability of the proposed scheme, it is tested on several benchmark problems and the results are compared with eight state-of-the-art multi-objective optimization algorithms. Inverse generational distance(IGD) and hypervolume (HV) metrics are also calculated to understand the optimization ability of the proposed scheme. The results are statistically validated using Wilcoxon signed rank test. It is observed that the overall optimization ability of the proposed scheme to solve MOPs is very good.•This paper proposes a method to solve multi-objective optimization problems.•A multi-objective Neural Network Algorithm method is proposed.•The proposed method solves difficult multi-objective optimization problems.

FDR2-BD: A Fast Data Reduction Recommendation Tool for Tabular Big Data Classification Problems

In this paper, a methodological data condensation approach for reducing tabular big datasets in classification problems is presented, named FDR2-BD. The key of our proposal is to analyze data in a dual way (vertical and horizontal), so as to provide a smart combination between feature selection to generate dense clusters of data and uniform sampling reduction to keep only a few representative samples from each problem area. Its main advantage is allowing the model’s predictive quality to be kept in a range determined by a user’s threshold. Its robustness is built on a hyper-parametrization process, in which all data are taken into consideration by following a k-fold procedure. Another significant capability is being fast and scalable by using fully optimized parallel operations provided by Apache Spark. An extensive experimental study is performed over 25 big datasets with different characteristics. In most cases, the obtained reduction percentages are above 95%, thus outperforming state-of-the-art solutions such as FCNN_MR that barely reach 70%. The most promising outcome is maintaining the representativeness of the original data information, with quality prediction values around 1% of the baseline.

An early fault detection method for induced draft fans based on MSET with informative memory matrix selection

Early fault detection of induced draft (ID) fans is very important to improve the reliability by providing predictive maintenance and reducing unscheduled shutdowns. This study proposed an early fault detection method for ID fans based on MSET with informative memory matrix selection. Firstly, to obtain an informative memory matrix, the discrete particle swarm optimization (DPSO) was utilized to search samples with large condition information. An accurate MSET model was then developed based on the memory matrix to produce predictions of the feature variables. Finally, a similarity index that represents the health status of the equipment was defined to give warnings of early faults. An application to detect the early faults of an ID fan in a coal-fired power plant was demonstrated to illustrate the effectiveness of proposed method.