Quantum-inspired differential evolution (QDE) is an evolutionary algorithm, which can effectively solve complex optimization problems. However, sometimes, it easily leads to premature convergence and ...low search ability and falls to local optima. To overcome these problems, based on the MSIQDE (improved QDE with multistrategies) algorithm, an enhanced MSIQDE algorithm based on mixing multiple strategies, namely, EMMSIQDE is proposed in this article. In the EMMSIQDE, a new differential mutation strategy of a difference vector is proposed to enhance the search ability and descent ability. Then, a new multipopulation mutation evolution mechanism is designed to ensure the relative independence of each subpopulation and the population diversity. The feasible solution space transformation strategy is used to achieve the optimal solution by mapping the quantum chromosome from a unit space to solution space. Finally, some multidimensional unimodal and multimodal functions are selected to demonstrate the optimization performance of EMMSIQDE. The results demonstrate that the EMMSIQDE is significantly better than the DE, QDE, QGA, and MSIQDE, and has better optimization ability, scalability, efficiency, and stability.
•Proposing a binary differential evolution algorithm with self-learning strategy, called MOFS-BDE, to solve multi-objective feature selection problems.•Proposing a new binary mutation operator based ...on probability difference to guide the individuals to locate potentially optimal areas fast.•Proposing a new one-bit purifying search operator (OPS) for improving the self-learning capability of elite individuals.•Proposing an efficient non-dominated sorting operator with crowding distance to reduce the time consumption of the selection operator in differential evolution.
Feature selection is an important data preprocessing method. This paper studies a new multi-objective feature selection approach, called the Binary Differential Evolution with self-learning (MOFS-BDE). Three new operators are proposed and embedded into the MOFS-BDE to improve its performance. The novel binary mutation operator based on probability difference can guide individuals to rapidly locate potentially optimal areas, the developed One-bit Purifying Search operator (OPS) can improve the self-learning capability of the elite individuals located in the optimal areas, and the efficient non-dominated sorting operator with crowding distance can reduce the computational complexity of the selection operator in the differential evolution. Experimental results on a series of public datasets show that the effective combination of the binary mutation and OPS makes our MOFS-BDE achieve a trade-off between local exploitation and global exploration. The proposed method is competitive in comparison with some representative genetic algorithm-, particle swarm-, differential evolution-, and artificial bee colony-based feature selection algorithms.
Display omitted
The novel‐corona‐virus is presently accountable for 547,782 deaths worldwide. It was first observed in China in late 2019 and, the increase in number of its affected cases seriously disturbed almost ...every nation in terms of its economical, structural, educational growth. Furthermore, with the advancement of data‐analytics and machine learning towards enhanced diagnostic tools for the infection, the growth rate in the affected patients has reduced considerably, thereby making it critical for AI researchers and experts from medical radiology to put more efforts in this side. In this regard, we present a controlled study which provides analysis of various potential possibilities in terms of detection models/algorithms for COVID‐19 detection from radiology‐based images like chest x‐rays. We provide a rigorous comparison between the VGG16, VGG19, Residual Network, Dark‐Net as the foundational network with the Single Shot MultiBox Detector (SSD) for predictions. With some preprocessing techniques specific to the task like CLAHE, this study shows the potential of the methodology relative to the existing techniques. The highest of all precision and recall were achieved with DenseNet201 + SSD512 as 93.01 and 94.98 respectively.
The "curse of dimensionality" and the high computational cost have still limited the application of the evolutionary algorithm in high-dimensional feature selection (FS) problems. This article ...proposes a new three-phase hybrid FS algorithm based on correlation-guided clustering and particle swarm optimization (PSO) (HFS-C-P) to tackle the above two problems at the same time. To this end, three kinds of FS methods are effectively integrated into the proposed algorithm based on their respective advantages. In the first and second phases, a filter FS method and a feature clustering-based method with low computational cost are designed to reduce the search space used by the third phase. After that, the third phase applies oneself to finding an optimal feature subset by using an evolutionary algorithm with the global searchability. Moreover, a symmetric uncertainty-based feature deletion method, a fast correlation-guided feature clustering strategy, and an improved integer PSO are developed to improve the performance of the three phases, respectively. Finally, the proposed algorithm is validated on 18 publicly available real-world datasets in comparison with nine FS algorithms. Experimental results show that the proposed algorithm can obtain a good feature subset with the lowest computational cost.
Identifying novel drug targets to overcome resistance to tyrosine kinase inhibitors (TKIs) and eradicating leukemia stem/progenitor cells are required for the treatment of chronic myelogenous ...leukemia (CML). Here, we show that ubiquitin-specific peptidase 47 (USP47) is a potential target to overcome TKI resistance. Functional analysis shows that USP47 knockdown represses proliferation of CML cells sensitive or resistant to imatinib in vitro and in vivo. The knockout of Usp47 significantly inhibits BCR-ABL and BCR-ABL
-induced CML in mice with the reduction of Lin
Sca1
c-Kit
CML stem/progenitor cells. Mechanistic studies show that stabilizing Y-box binding protein 1 contributes to USP47-mediated DNA damage repair in CML cells. Inhibiting USP47 by P22077 exerts cytotoxicity to CML cells with or without TKI resistance in vitro and in vivo. Moreover, P22077 eliminates leukemia stem/progenitor cells in CML mice. Together, targeting USP47 is a promising strategy to overcome TKI resistance and eradicate leukemia stem/progenitor cells in CML.
Display omitted
In this paper, a novel multi-population parallel co-evolutionary differential evolution, named MPPCEDE, is proposed to optimize parameters of photovoltaic (PV) models and enhance ...conversion efficiency of solar energy. In the MPPCEDE, the reverse learning mechanism is employed to generate the initial several subpopulations to enhance the convergence velocity and keep the population diversity. A new multi-population parallel control strategy is developed to maintain the search efficiency in subpopulations. The co-evolutionary mutation strategy with elite population and three mutation strategies is proposed to reduce computing resources and balance the exploration and exploration capability through the cooperative mechanism, improve the convergence speed, realize the information exchange. Then the MPPCEDE is employed to effectively optimize parameters of PV models under various conditions and environments to obtain a parameter values of PV models. Finally, the effectiveness of the proposed method is tested by different PV models and manufacturer's datasheet. The experimental and comparative results demonstrate that the MPPCEDE exhibits higher accuracy and reliability, and has fast convergence speed by comparing with several methods in extracting parameters of PV models.
•A multi-strategy-based co-evolutionary DE algorithm(MPPCEDE) is proposed.•A new multi-population parallel co-evolutionary mutation strategy is proposed.•The reverse learning mechanism is used to initialize the population to keep population diversity.•An adaptive adjustment strategy of parameters is designed to improve optimiztaion performance.•Comprehensive experiments are designed to evaluate the effectiveness of MPPCEDE.
Clustering is a typical and important method to discover new structures and knowledge from data sets. Most existing clustering methods need to know the number of clusters in advance, which is ...difficult. Some algorithms claim they do not need to know the number of clusters in advance. Among these algorithms, however, some need to manually determine the cluster centers in a decision graph, which is not easy; some assume that the number of initial cluster centers given is greater than the actual number of classes, but in fact the true number of clusters is not known. In order to tackle this issue, we propose a density-peak-based clustering algorithm of automatically determining the number of clusters. First, we design a density metric by using a continuous function which can well distinguish the densities of different data points. Then, we design a pre-clustering method which can get the initial cluster centers and the corresponding clusters. Furthermore, we propose an automatic clustering method which can automatically determine the final cluster centers and the corresponding clusters. Experiments are conducted on widely used data sets, and the results show the effectiveness of the proposed method.
As a promising source of clean energy in carbon neutrality, ocean wave energy generation depends heavily on forecasting significant wave height (SWH), whose evolution is too complex to accurately ...model due to multi-factor mixed effects. Additionally, most existing deep models present intelligent fitting via making some tricks and further have mining-extraction capabilities of hidden features, while they ignore the support of biologically-inspired ideas. An important and interesting open issue is how to utilize SWH data characteristics with advanced brain structures and functions to construct its high-performance forecasting network. Specifically, from SWH data analysis, the overall framework of the proposed network separately extracts autocorrelation and causality via two brain-interaction-inspired (BII) modules at first, and then integrates them via the attention fusion module, which coincides with the idea of “divide and conquer”. From a micro view, 1) through imitating both structures and functions in left-right brain interaction, the designed BII module stacks the one-dimensional convolutions and gate mechanisms to implement the gate, collaboration, and inhibition functions for capturing long short-term dependencies. 2) The attention mechanism with dynamic weights is designed to integrate captured information and real-timely grasp the main features for making high-accuracy forecasts. The proposed network not only has some interpretability in the design process but also effectively enhances the feature completeness. In six experiments of two real-world datasets, the proposed network improves the root mean squared error by averages of 26.3% and 23.7% compared with 11 baselines, respectively.
•A bionic deep network is proposed to forecast significant wave height.•Autocorrelation and causality are firstly extracted and then fused.•Both structure and function of the brain interaction are imitated.•Attention mechanism is designed to fuse features via real-time weights.•Six experiments show high accuracy of the proposed network.
Recent advances in artificial intelligence (AI) technologies have driven the dramatic developments in key consumer applications, e.g., smart manufacturing, equipment conditions and fault diagnosis, ...quality inspection, autonomous decision-making, etc. In the Industry 4.0 era, AI has become the core technology to promote the revolution and development of consumer electronics intelligence. In practice, AI-driven consumer electronics integrate AI technologies and the domain knowledge of standard process and operations to achieve smart systems incorporated with techniques of the Internet of Things (IoT), neural computing, machine learning, and deep learning. However, many challenges are remained to implement AI-powered modes for consumer electronics by directly applying advanced neural computing techniques. Moreover, complex application context in consumer electronics environments and prior domain knowledge further make it challengeable to fulfill emerging intelligent consumer applications. On the other hand, recent years have witnessed the rapid development of neural computing in various AI tasks. In particular, deep neural networks have been widely applied in real-world application scenarios in consumer electronics manufacturing. Moreover, advanced techniques and approaches in data modeling and prediction, learning strategies, optimization and control theories are also incorporated and developed under various consumer application scenarios.
Under mild conditions, the Pareto front (Pareto set) of a continuous m-objective optimization problem forms an (m - 1)-dimensional piecewise continuous manifold. Based on this property, this paper ...proposes a self-organizing multiobjective evolutionary algorithm. At each generation, a self-organizing mapping method with (m - 1) latent variables is applied to establish the neighborhood relationship among current solutions. A solution is only allowed to mate with its neighboring solutions to generate a new solution. To reduce the computational overhead, the self-organizing training step and the evolution step are conducted in an alternative manner. In other words, the self-organizing training is performed only one single step at each generation. The proposed algorithm has been applied to a number of test instances and compared with some state-of-the-art multiobjective evolutionary methods. The results have demonstrated its advantages over other approaches.