This paper proposes an evolutionary-group-based particle-swarm-optimization (EGPSO) algorithm for fuzzy-controller (FC) design. The EGPSO uses a group-based framework to incorporate crossover and mutation operations into particle-swarm optimization. The EGPSO dynamically forms different groups to select parents in crossover operations, particle updates, and replacements. An adaptive velocity-mutated operation (AVMO) is incorporated to improve search ability. The EGPSO is applied to design all of the free parameters in a zero-order Takagi-Sugeno-Kang (TSK)-type FC. The objective of EGPSO is to improve fuzzy-control accuracy and design efficiency. Comparisons with different population-based optimizations of fuzzy-control problems demonstrate the superiority of EGPSO performance. In particular, the EGPSO-designed FC is applied to mobile-robot navigation in unknown environments. In this application, the robot learns to follow object boundaries through an EGPSO-designed FC. A simple learning environment is created to build this behavior without an exhaustive collection of input-output training pairs in advance. A behavior supervisor is proposed to combine the boundary-following behavior and the target-seeking behavior for navigation, and the problem of dead cycles is considered. Successful mobile-robot navigation in simulation and real environments verifies the EGPSO-designed FC-navigation approach.

This paper proposes a new multiobjective optimization approach to designing a fuzzy logic system (FLS) using process data and applies it to the wall-following control of a mobile robot. The objectives considered include both the interpretability and control performance of the FLS. It is assumed that no off-line training data are available in advance, and the rule base is initially empty. All rules are generated through an online clustering and fuzzy set merging (OCFM) algorithm using data generated online during the FLS evaluation process. The OCFM builds a reference rule base that flexibly partitions the input space with distinguishable fuzzy sets (FSs). Based on the reference rule base, a new multiobjective front-guided continuous ant-colony optimization (MO-FCACO) algorithm is proposed to optimize the FLS structure and parameters. In addition to the objective functions defined to evaluate the FLS control performance, a transparency-oriented objective function is defined with constraints imposed on the FS parameters to obtain an interpretable FLS with transparent FSs. The MO-FCACO solves the constrained multiobjective optimization problem by optimizing all of the free parameters in an FLS through ant-path selection, sampling operation, and front-guided optimization processes. The multiobjective FLS design approach is applied to control the orientation and moving speed of a mobile robot in performing the wall-following task. Optimization performance of the MO-FCACO is verified through comparisons with various multiobjective population-based optimization algorithms. Experimental results verify the effectiveness of the designed FLSs in controlling a real robot.

Brain-computer interface technologies, such as steady-state visually evoked potential, P300, and motor imagery are methods of communication between the human brain and the external devices. Motor imagery-based brain-computer interfaces are popular because they avoid unnecessary external stimuli. Although feature extraction methods have been illustrated in several machine intelligent systems in motor imagery-based brain-computer interface studies, the performance remains unsatisfactory. There is increasing interest in the use of the fuzzy integrals, the Choquet and Sugeno integrals, that are appropriate for use in applications in which fusion of data must consider possible data interactions. To enhance the classification accuracy of brain-computer interfaces, we adopted fuzzy integrals, after employing the classification method of traditional brain-computer interfaces, to consider possible links between the data. Subsequently, we proposed a novel classification framework called the multimodal fuzzy fusion-based brain-computer interface system. Ten volunteers performed a motor imagery-based brain-computer interface experiment, and we acquired electroencephalography signals simultaneously. The multimodal fuzzy fusion-based brain-computer interface system enhanced performance compared with traditional brain-computer interface systems. Furthermore, when using the motor imagery-relevant electroencephalography frequency alpha and beta bands for the input features, the system achieved the highest accuracy, up to 78.81% and 78.45% with the Choquet and Sugeno integrals, respectively. Herein, we present a novel concept for enhancing brain-computer interface systems that adopts fuzzy integrals, especially in the fusion for classifying brain-computer interface commands.

This paper proposes a new learning approach for evolving dynamic gaits of a hexapod robot. The controller that coordinates the leg movements consists of fully connected recurrent neural networks (FCRNNs). To automate the FCRNN parameter design, a symbiotic species-based particle swarm optimization (SSPSO) algorithm is proposed. There are multiple swarms in the SSPSO, where a swarm only optimizes the relevant parameters to a single node. The number of swarms is equal to the number of nodes in an FCRNN. The symbiotic behavior of particles from different swarms corresponds to the symbiotic structure of different nodes in an FCRNN. For a particle update, particles in different swarms update independently using a local version of particle swarm optimization (PSO) based on speciation. In each swarm, species are formed adaptively in each iteration according to both particle distance and performance. The design of FCRNNs using the SSPSO for temporal sequence generation and hexapod robot dynamic gait evolution for forward movement is conducted. For the latter, a multiple-FCRNN controller is first designed using a simulated hexapod robot. The designed controller is then successfully applied to a real hexapod robot gait control. The SSPSO is compared with the genetic algorithm and different PSO algorithms to verify its efficiency and effectiveness.

Fuzzy neural networks (FNNs) have been very successful at handling uncertainty in data using fuzzy mappings and if-then rules. However, they suffer from generalization and dimensionality issues. Although deep neural networks (DNNs) represent a step toward processing high-dimensional data, their capacity to address data uncertainty is limited. Furthermore, deep learning algorithms designed to improve robustness are either time consuming or yield unsatisfactory performance. In this article, we propose a robust fuzzy neural network (RFNN) to overcome these problems. The network contains an adaptive inference engine that is capable of handling samples with high-level uncertainty and high dimensions. Unlike traditional FNNs that use a fuzzy AND operation to calculate the firing strength for each rule, our inference engine is able to learn the firing strength adaptively. It also further processes the uncertainty in membership function values. Taking advantage of the learning ability of neural networks, the acquired fuzzy sets can be learned from training inputs automatically to cover the input space well. Furthermore, the consequent layer uses neural network structures to enhance the reasoning ability of the fuzzy rules when dealing with complex inputs. Experiments on a range of datasets show that RFNN delivers state-of-the-art accuracy even at very high levels of uncertainty. Our code is available online. https://github.com/leijiezhang/RFNN

Heterogeneous big data poses many challenges in machine learning. Its enormous scale, high dimensionality, and inherent uncertainty make almost every aspect of machine learning difficult, from providing enough processing power to maintaining model accuracy to protecting privacy. However, perhaps the most imposing problem is that big data is often interspersed with sensitive personal data. Hence, we propose a privacy-preserving hierarchical fuzzy neural network (PP-HFNN) to address these technical challenges while also alleviating privacy concerns. The network is trained with a two-stage optimization algorithm, and the parameters at low levels of the hierarchy are learned with a scheme based on the well-known alternating direction method of multipliers, which does not reveal local data to other agents. Coordination at high levels of the hierarchy is handled by the alternating optimization method, which converges very quickly. The entire training procedure is scalable, fast and does not suffer from gradient vanishing problems like the methods based on back-propagation. Comprehensive simulations conducted on both regression and classification tasks demonstrate the effectiveness of the proposed model. Our code is available online at https://github.com/leijiezhang/PP_HFNN.