5,057 publications found
Sort by
Transferable Adaptive Differential Evolution for Many-Task Optimization.

The evolutionary multitask optimization (EMTO) algorithm is a promising approach to solve many-task optimization problems (MaTOPs), in which similarity measurement and knowledge transfer (KT) are two key issues. Many existing EMTO algorithms estimate the similarity of population distribution to select a set of similar tasks and then perform KT by simply mixing individuals among the selected tasks. However, these methods may be less effective when the global optima of the tasks greatly differ from each other. Therefore, this article proposes to consider a new kind of similarity, namely, shift invariance, between tasks. The shift invariance is defined that the two tasks are similar after linear shift transformation on both the search space and the objective space. To identify and utilize the shift invariance between tasks, a two-stage transferable adaptive differential evolution (TRADE) algorithm is proposed. In the first evolution stage, a task representation strategy is proposed to represent each task by a vector that embeds the evolution information. Then, a task grouping strategy is proposed to group the similar (i.e., shift invariant) tasks into the same group while the dissimilar tasks into different groups. In the second evolution stage, a novel successful evolution experience transfer method is proposed to adaptively utilize the suitable parameters by transferring successful parameters among similar tasks within the same group. Comprehensive experiments are carried out on two representative MaTOP benchmarks with a total of 16 instances and a real-world application. The comparative results show that the proposed TRADE is superior to some state-of-the-art EMTO algorithms and single-task optimization algorithms.

Open Access
Active Human-Following Control of an Exoskeleton Robot With Body Weight Support.

This article presents an active human-following control of the lower limb exoskeleton for gait training. First, to improve safety, considering the human balance, the OpenPose-based visual feedback is used to estimate the individual's pose, then, the active human-following algorithm is proposed for the exoskeleton robot to achieve the body weight support and active human-following. Second, taking the human's intention and voluntary efforts into account, we develop a long short-term memory (LSTM) network to extract surface electromyography (sEMG) to build the estimation model of joints' angles, that is, the multichannel sEMG signals can be correlated with flexion/extension (FE) joints' angles of the human lower limb. Finally, to make the robot motion adapt to the locomotion of subjects under uncertain nonlinear dynamics, an adaptive control strategy is designed to drive the exoskeleton robot to track the desired locomotion trajectories stably. To verify the effectiveness of the proposed control framework, several recruited subjects participated in the experiments. Experimental results show that the proposed joints' angles estimation model based on the LSTM network has a higher estimation accuracy and predicted performance compared with the existing deep neural network, and good simultaneous locomotion tracking performance is achieved by the designed control strategy, which indicates that the proposed control can assist subjects to perform gait training effectively.

PSDC: A Prototype-Based Shared-Dummy Classifier Model for Open-Set Domain Adaptation.

Open-set domain adaptation (OSDA) aims to achieve knowledge transfer in the presence of both domain shift and label shift, which assumes that there exist additional unknown target classes not presented in the source domain. To solve the OSDA problem, most existing methods introduce an additional unknown class to the source classifier and represent the unknown target instances as a whole. However, it is unreasonable to treat all unknown target instances as a group since these unknown instances typically consist of distinct categories and distributions. It is challenging to identify all unknown instances with only one additional class. In addition, most existing methods directly introduce marginal distribution alignment to alleviate distribution shift between the source and target domains, failing to learn discriminative class boundaries in the target domain since they ignore categorical discriminative information in the adaptation. To address these problems, in this article, we propose a novel prototype-based shared-dummy classifier (PSDC) model for the OSDA. Specifically, our PSDC introduces an auxiliary dummy classifier to calibrate the source classifier and simultaneously develops a weighted adaptation procedure to align class-wise prototypes for adaptation. We further design a pseudo-unknown learning algorithm to reduce the open-set risk. Extensive experiments on Office-31, Office-Home, and VisDA datasets show that the proposed PSDC can outperform existing methods and achieve the new state-of-the-art performance. The code will be made public.

PriMPSO: A Privacy-Preserving Multiagent Particle Swarm Optimization Algorithm.

Centralized particle swarm optimization (PSO) does not fully exploit the potential of distributed or parallel computing and suffers from single-point-of-failure. Particularly, each particle in PSO comprises a potential solution (e.g., traveling route and neural network model parameters) which is essentially viewed as private data. Unfortunately, previously neither centralized nor distributed PSO algorithms fail to protect privacy effectively. Inspired by secure multiparty computation and multiagent system, this article proposes a privacy-preserving multiagent PSO algorithm (called PriMPSO) to protect each particle's data and enable private data sharing in a privacy-preserving manner. The goal of PriMPSO is to protect each particle's data in a distributed computing paradigm via existing PSO algorithms with competitive performance. Specifically, each particle is executed by an independent agent with its own data, and all agents jointly perform global optimization without sacrificing any particle's data. Thorough investigations show that selecting an exemplar from all particles and updating particles through the exemplar are critical operations for PSO algorithms. To this end, this article designs a privacy-preserving exemplar selection algorithm and a privacy-preserving triple computation protocol to select exemplars and update particles, respectively. Strict privacy analyses and extensive experiments on a benchmark and a realistic task confirm that PriMPSO not only protects particles' privacy but also has uniform convergence performance with the existing PSO algorithm in approximating an optimal solution.

An Augmented Game Approach for Design and Analysis of Distributed Learning Dynamics in Multiagent Games.

In this article, an augmented game approach is proposed for the formulation and analysis of distributed learning dynamics in multiagent games. Through the design of the augmented game, the coupling structure of utility functions among all the players can be reformulated into an arbitrary undirected connected network while the Nash equilibria are preserved. In this case, any full-information game learning dynamics can be recast into a distributed form, and its convergence can be determined from the structure of the augmented game. We apply the proposed approach to generate both deterministic and stochastic distributed gradient play and obtain several negative convergent results about the distributed gradient play: 1) a Nash equilibrium is convergent under the classic gradient play, yet its corresponding augmented Nash equilibrium may be not convergent under the distributed gradient play and, on the other side, 2) a Nash equilibrium is not convergent under the classic gradient play, yet its corresponding augmented Nash equilibrium may be convergent under the distributed gradient play. In particular, we show that the variational stability structure (including monotonicity as a special case) of a game is not guaranteed to be preserved in its augmented game. These results provide a systematic methodology about how to formulate and then analyze the feasibility of distributed game learning dynamics.