查看更多>>摘要：Neighborhood Learning (NL) is a paradigm covering theories and techniques of neighborhood, which facilitates data organization, representation and generalization. While delivering impressive performances across various fields such as granular computing, cluster analysis, NL is argued to be computationally demanding, thereby limiting its utility and applicability. In this study, a simple and generic scheme named granular cabin is proposed for drastically speeding up the algorithmic implementation of NL. Specifically, this scheme is deployed to Neighborhood Rough Set (NRS) which is a typical NL methodology. And three major applications of NRS are concerned including approximation computation, neighborhood classification and feature selection. Extensive experiments demonstrate that NRS methodology enhanced by granular cabin consumes much less time. This study offers a promising solution that ensures the great potential of NL in big data. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：In recent years, the dielectric elastomer actuators (DEAs) have been increasingly used to drive the soft robots. This paper proposes a tracking control method for the DEA based on the inverse dynamic compensation method. Firstly, a dynamical model of the DEA is established to depict its asymmetric hysteresis, rate dependent hysteresis and creep non -linear behaviors simultaneously. Next, according to the inverse of the dynamical model, an inverse dynamic feedforward compensator (IDFC) is devised to compensate the hysteresis nonlinearity and creep nonlinearity of the DEA. Then, a PI feedback controller is designed to collaborate with the IDFC, which can enhance the robust performance of the whole control system. Finally, the tracking control experiments with different target trajectories are car-ried out. The root-mean-square errors of all control results are less than 1% and the max-imum value of the relative tracking errors is less than 8%, which illustrates that the proposed tracking control method is effective and excellent. (c) 2021 Elsevier Inc. All rights reserved.
Ibarguren, IgorPerez, Jesus M.Muguerza, JavierArbelaitz, Olatz...
20页
查看更多>>摘要：The use of decision trees considerably improves the discriminating capacity of ensemble classifiers. However, this process results in the classifiers no longer being interpretable, although comprehensibility is a desired trait of decision trees. Consolidation (consolidated tree construction algorithm, CTC) was introduced to improve the discriminating capacity of decision trees, whereby a set of samples is used to build the consolidated tree without sacrificing transparency. In this work, PCTBagging is presented as a hybrid approach between bagging and a consolidated tree such that part of the comprehensibility of the consolidated tree is maintained while also improving the discriminating capacity. The consolidated tree is first developed up to a certain point and then typical bagging is performed for each sample. The part of the consolidated tree to be initially developed is configured by setting a consolidation percentage. In this work, 11 different consolidation percentages are considered for PCTBagging to effectively analyse the trade-off between comprehensibility and discriminating capacity. The results of PCTBagging are compared to those of bagging, CTC and C4.5, which serves as the base for all other algorithms. PCTBagging, with a low consolidation percentage, achieves a discriminating capacity similar to that of bagging while maintaining part of the interpretable structure of the consolidated tree. PCTBagging with a consolidation percentage of 100% offers the same comprehensibility as CTC, but achieves a significantly greater discriminating capacity. (c) 2021 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
查看更多>>摘要：Clustering of cell types from a large number of high-dimensional heterogeneous cells is a vital step in analyzing single-cell RNA-seq data. Although several computational methods have been proposed to evolve such data, most of them suffer from some limitations such as high-level noise, high dimensionality, and low generalization. To address these challenges, a multiobjective robust continuous clustering algorithm (MORCC) is presented to discriminate the different cell types in a single-cell RNA-seq dataset. Stepwise, first a dimensionality reduction method is applied to map the high-dimensional heterogeneous cells into a desired low-dimensional space while preserving the features of the original space. Then, to overcome the instability of trial-and-error connectivity weights in the robust continuous clustering, MORCC proposes applying evolutionary operators to optimize the connectivity weights dynamically, and to select the suitable parameters with two cluster validity indices. To demonstrate the effectiveness of MORCC, we compare it to several state-ofthe-art methods on six single-cell RNA-seq datasets, revealing its superior clustering ability from several perspectives. In addition, we carry out a parameter analysis, a case study, and visualization and biological interpretability analyses to validate MORCC's cell identification capability on single-cell RNA-seq data. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Following two decades of sustained studies, metaheuristic algorithms have made considerable achievements in the field of multi-objective optimization problems (MOPs). However, under most existing metaheuristic frameworks, an improved scheme introduced to address specific defects usually leads to additional problems that need to be solved further. Emerging optimization mechanisms should be considered to break the bottleneck, and an adaptive multi-objective competitive swarm optimization (AMOCSO) algorithm, a promising option for solving MOPs, is proposed in this paper. Firstly, the competitive mechanism is modified so that it can perform well on MOPs, and an improved learning scheme is designed for the winners and the losers, which can greatly enhance the optimization efficiency and balance the convergence and the diversity of the proposed algorithm. Then, an external archive and its maintenance schemes are introduced to prevent the population from degenerating and make the algorithm framework more comprehensive. Moreover, a practical adaptive strategy is proposed to fill the blank of parameter research, and no human factors exist in AMOCSO, which means that an amazing promotion can be achieved in generalization. Finally, abundant experimental studies are carried out, and the results of comparative experiments show that the proposed algorithm has significant advantages over several state-of-the-art algorithms. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：The idea of computable aggregation operators was introduced as a generalization of aggregation operators, allowing the replacement of the mathematical function usually considered for aggregation, by a program that performs the aggregation process. There are different reasons to justify this extension. One of them is the interest in exploring some computational properties not directly related to the aggregation itself but to its implementation (complexity, recursivity, parallelisation, etc). Another reason, the one driving to the present paper, is the need to define a framework where the quite common process of first sampling (over a large data set) and then aggregating the sample, could be analysed as a formal aggregation process. This process does not match with the idea of an aggregation function, due to its non-deterministic nature, but could easily be adapted to that of a (non-deterministic) computable aggregation. The idea of non-deterministic aggregation requires the extension of the concept of monotonicity (a key aspect of aggregation operators) to this new framework. The present paper will explore this kind of non-deterministic aggregation processes, first from an empirical point of view and then in terms of populations, adapting the idea of monotonicity to both of them and finally defining a common framework for its analysis. (c) 2021 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
查看更多>>摘要：Fuzzy Wavelet Neural Networks (FWNNs) have recently gained popularity as a powerful tool for various applications. Although the literature contains several effective FWNNs, there is still scope for improvement. This research proposes and implements a novel mod-ification called the Fuzzy Elman Wavelet Network (FEWN), which combines the appealing properties of Elman Neural Networks (ENNs), wavelet functions, and fuzzy membership functions (MFs). The integration suggests the use of interval type-2 fuzzy MFs and wavelet functions with self-recurrent and ENN's cross-coupled feedback loops to handle system uncertainties while accurately representing the intrinsic cross-coupled interferences of real dynamic nonlinear systems. However, it is worth noting that the proposed integration has no detrimental effect on the computational network load, which is critical for online applications. Furthermore, a thorough stability analysis is conducted, and the novel network is imple-mented and tested in various applications. Finally, the effectiveness of the proposed novel network is evaluated through extensive simulation studies using well-known benchmark functions and dynamic systems. These studies demonstrate the proposed FEWN's efficacy in function approximation, system identification, and as a damping controller for two benchmark large-scale nonlinear power systems. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Heterogeneous defect prediction (HDP) aims to transfer informative knowledge, namely the defect-proneness tendency of software metrics, from a source project to predict potential defects in a target project by matching metrics with similar distributions between different software projects. Nevertheless, the complex internal intrinsic structure hidden behind the defect data makes it difficult for the prior heterogeneous defect models to capture and migrate the most informative software metrics, and severely hinders HDP performance. To address these issues, we propose a robust data-driven HDP model called IVKMP in this study. We firstly adopt an advanced deep generation network - InfoGAN (Information maximizing GANs) for data augmentation, namely simultaneously achieving class balance and generating sufficient defect instances. Secondly, the multi-objective VaEA (Vector angle-based Evolutionary Algorithm) optimization is employed to select the fewest representative metric subsets while achieving the minimum error. Finally, a deep defect predictor for HDP based on the lightweight but effective deep network - PCANet (Principal Component Analysis Network) with the binary hashing and block-wise histogram is built to essentially capture more semantically related robust representations. We compare the IVKMP model with multiple state-of-the-art baseline models across 542 heterogeneous project pairs of 26 software projects. Experimental results demonstrate the superiority and robustness of our IVKMP model. (c) 2021 Published by Elsevier Inc.
查看更多>>摘要：As a powerful tool for data streams processing, the vast majority of existing evolving intelligent systems (EISs) learn prediction models from data in a supervised manner. However, high-quality labelled data can be difficult to obtain in many real-world classification applications concerning data streams, though unlabelled data is plentiful. To overcome the labelling bottleneck and construct a stronger classification model, a novel semi supervised EIS is proposed in this paper. After being primed with a small amount of labelled data, the proposed method is capable of continuously self-developing its system structure and self-updating the meta-parameters from unlabelled data streams chunk by-chunk in a non-iterative, exploratory manner by exploiting a novel pseudo-labelling strategy. Thanks to its transparent prototype-based structure and human understandable reasoning process, the proposed method can provide users high explain ability and interpretability while achieving great classification precision. Experimental investigation demonstrates the superior performance of the proposed method. (C) 2021 Elsevier Inc. All rights reserved.
NSTL
Elsevier