查看更多>>摘要：The current study has systematically presented a strategy of designing the fixed-time high -order sliding mode (HOSM) controller with asymmetric output constraints. This construc-tive method is accomplished by three crucial mechanisms. First of all, some nonlinear terms satisfying homogeneous growth conditions are implanted into the mismatched channels of the traditional HOSM system. Based on this, a HOSM system with mismatched terms is built to weaken the uncertainties in control input channels. Secondly, a barrier Lyapunov function (BLF) is developed to resolve the constraints. Thirdly, by integrating the BLF with a backstepping-like method, a fixed-time HOSM controller is explicitly pro-posed to handle the HOSM dynamics with mismatched terms and asymmetric output con-straints. It is shown via the strict Lyapunov analysis that under the constructed controller, the closed-loop system is fixed-time stabilized and the realization of prescribed constraints is insured. The investigations of two cases are provided to validate the established theoret-ical results. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：With the growing use of multi-core processors in the market, efficient and effective task parallelization strategies are on huge demand, so are the task scheduling algorithms. The scalability and efficiency of the existing algorithms on multi-core task scheduling need to be improved. To schedule real-time tasks on a multi-core processor, any pair of inter-dependent tasks must be executed following their original execution order. The directed acyclic graph (DAG) is commonly used to study the internal structure of a program. In this work, we investigated the property of the data dependency to eliminate the unnecessary execution constraints, and improved the DAG model by incorporating the temporal prop-erty of these dependencies. Based on such a model, we proposed a dynamic decomposed scheduling (DDS) strategy. With DDS, the dependent tasks could be released and executed earlier before the completion of their precedent tasks without producing any data hazards. The experiments were conducted on both synthesized tasks and real industrial embedded applications, the results show that DDS has a good performance in multi-core task schedul-ing, and it outperforms the state-of-the-art scheduling algorithms including the decom-posed scheduling, the global scheduling, and the federated scheduling.(c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Biometrics has nowadays become a preferred solution for systems requiring secure authentication. However, the usage of biometric characteristics raises significant concerns regarding personal data protection and privacy. Several template protection schemes have been therefore proposed to conceal the employed identifiers, while still ensuring the ability to efficiently recognise users. In this paper, we propose and analyse three different approaches generating cancelable templates from finger vein features. A thorough analysis of the considered methods is conducted to investigate their impact on the achievable recognition performance, as well as their security in terms of renewability and unlinkability. Furthermore, a specific attack is designed to evaluate the irreversibility of the protection scheme providing the best recognition performance.(c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Since multimodal imaging technology is able to provide multiple perspectives on the lesion, it has become increasingly important in clinical diagnosis and treatment planning. In this paper, a novel medical image fusion using gradient domain-guided filter random walk (GDGFRW) and side window filtering (SWF) in the framelet transform (FT) domain is presented. Firstly, FT is performed on the original multimodal source images to obtain the corresponding approximate and residual representations. Secondly, a novel model- GDGFRW, which combines the superiorities of both gradient domain guided filtering and random walks-is constructed to interpret the approximate sub-bands, while the residual sub-bands are fused by SWF. Finally, the fused approximate sub-bands and residual sub bands undergo inverse FT to generate the final fused image. To verify its effectiveness, the proposed method was tested on different categories of multimodal medical image fusion issues, in more than 40 pairs of source images. The proposed method outperforms the current representative ones in terms of both subjective visual performance and objective assessment.(c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Multi-modal multi-objective optimization problem (MMOPs) has attracted more and more attention in evolutionary computing recently. It is not easy to solve these problems using the existing evolutionary algorithms. The non-dominated solution sorting genetic algorithm (NSGA-II) has poor PS distribution and convergence. In this paper, an enhanced fast NSGA-II based on a special congestion strategy and adaptive crossover strategy, namely ASDNSGA-II is proposed. In the ASDNSGA-II, the strategy with a special congestion degree is used to improve the selection strategy. Then a new adaptive crossover strategy is designed by evaluating the advantages and disadvantages of the SBX crossover strategy with the ability to solve high dimensions and the BLX-alpha with the ability of Pareto solution to produce offspring solutions. These can ensure the generation of offspring solutions around individuals with large crowding degrees and balance the convergence and diversity of decision space and object space. It can improve PS distribution and convergence and maintain PF precision. Eight functions of MMF1-MMF8 from the CEC2020 are selected to prove the effectiveness of the ASDNSGA-II. By comparing several latest multi-modal multi-objective evolutionary algorithms, the results show that the ASDNSGA-II can effectively find the global Pareto solution set and improve the distribution and convergence of PS. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：Cooperative problems under continuous control have always been the focus of multi-agent reinforcement learning. Existing algorithms suffer from the problem of uneven learning degree with the increase of the number of agents. In this paper, a new structure for a multi-agent actor critic is proposed, and the self-attention mechanism is applied in the critic network and the value decomposition method used to solve the uneven problem. The proposed algorithm makes full use of the samples in the replay memory buffer to learn the behavior of a class of agents. First, a new update method is proposed for policy networks that promotes learning efficiency. Second, the utilization of samples is improved, at the same time reflecting the ability of perspective-taking among groups. Finally, the "deceptive signal" in training is eliminated and the learning degree among agents is more uniform than in the existing methods. Multiple experiments were conducted in two typical scenarios of a multi-agent particle environment. Experimental results show that the proposed algorithm can perform better than the state-of-the-art ones, and that it exhibits higher learning efficiency with an increasing number of agents.(c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：In this paper, we extend the concept of Dempster-Shafer Belief Structures to the case of Linguistic Belief Structures, whose focal elements and probability mass assignments are linguistic, i.e. words modeled by Interval Type-2 Fuzzy Sets. We show that Linguistic Weighted Averages are pertinent tools for derivation of lower and upper probabilities from such Belief Structures, especially when words describing probability masses and focal ele-ments are modeled by Interval Type-2 Fuzzy Sets synthesized by collecting data from sub-jects. We moreover introduce methods for performing operations on Linguistic Belief Structures as well as combining them. We demonstrate how Linguistic Belief Structures can be used to represent uncertainties in natural languages and present methods for infer-ence from them. (c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：In recent years, many applications are using various forms of deep learning models. Such methods are usually based on traditional learning paradigms requiring the consistency of properties among the feature spaces of the training and test data and also the availability of large amounts of training data, e.g., for performing supervised learning tasks. However, many real-world data do not adhere to such assumptions. In such situations transfer learning can provide feasible solutions, e.g., by simultaneously learning from data-rich source data and data-sparse target data to transfer information for learning a target task. In this paper, we survey deep transfer learning models with a focus on applications to text data. First, we review the terminology used in the literature and introduce a new nomenclature allowing the unequivocal description of a transfer learning model. Second, we introduce a visual taxonomy of deep learning approaches that provides a systematic structure to the many diverse models introduced until now. Furthermore, we provide comprehensive information about text data that have been used for studying such models because only by the application of methods to data, performance measures can be estimated and models assessed. (c) 2021 The Author(s). Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
查看更多>>摘要：In the age of connectivity, every person is constantly producing large amounts of data every minute: social networks, information about trips, work connections, etc. These data will only become useful information if we are able to analyze and extract the most relevant features from it, which depends on the field of analysis. This task is usually performed by clustering data into similar groups with the aim of finding similarities and differences among them. However, the vast amount of data available makes traditional analysis obsolete for real-life datasets. This paper addresses the problem of dividing a set of elements into a predefined number of equally-sized clusters. In order to do so, we propose a Strategic Oscillation approach combined with a Greedy Randomized Adaptive Search Procedure. The computational experiments section firstly tunes the parameters of the algorithm and studies the influence of the proposed strategies. Then, the best variant is compared with the current state-of-the-art method over the same set of instances. The obtained results show the superiority of the proposal using two different clustering metrics: MSE (Mean Square Error) and Davies-Bouldin index.(c) 2021 Elsevier Inc. All rights reserved.
查看更多>>摘要：The pattern recognition of surface electromyography (sEMG) signal is an important application in the realization of human-machine interface. However, due to the disturbance of human body, sensors and environment, sEMG signal usually contains lots of noise, which brings great challenges to the high-accuracy sEMG pattern recognition. In addition, embedded human wearable devices are becoming more and more popular nowadays. How to realize the sEMG recognition method with low power consumption and high noise immunity has also become a difficult and very meaningful research topic. In this paper, a spiking neural network (SNN) classification method based on second-order information bottleneck training is proposed. Firstly, the training loss function for classification neural networks is constructed based on the proposed second-order information bottleneck. The method is used to train the conventional continuous-valued neural network and convert it into an SNN model with equivalent structure and connection weights. Then, the converted SNN is used to classify the sEMG signal patterns. Through a series of theoretical analysis and experimental results, it is proved that this method has significant advantages in terms of generalization of network determination and computational efficiency. The experimental code can be accessed from https://github.com/anvien/2OIB-for-sEMG-Recognition. (c) 2021 Published by Elsevier Inc.
NSTL
Elsevier