Abstracts:Current noninvasive electroencephalography (EEG)-based brain–computer interface (BCI) systems face a fundamental scalability barrier: they either suffer catastrophic forgetting (CF) when learning from new users or require centralized management and use of sensitive neural data from previous users-making real-world deployment impractical. To address this, we introduce subject-incremental continual adaptation (SI-CA), a novel paradigm that models cross-subject continual learning (CL), where knowledge transfer and limited replay sustain stable performance as new subjects are introduced, enabling continual decoding without forgetting. Building on this paradigm, we propose a novel CL framework that achieves memory-efficient adaptation by integrating an extendable architecture with prototype-based consistency regularization and limited replay to mitigate CF. The effectiveness of our proposed method has been validated on three benchmark EEG-BCI datasets. Experimental results demonstrate that the proposed method can effectively reduce reliance on historical samples during CL, while maintaining stable decoding performance for previously learned individuals and ensuring reliable motor decoding for newly encountered ones. This holds significant importance for the development of scalable, privacy-preserving, and stable neural interface systems.

Abstracts:This study investigates a scheduling problem involving dual-arm cluster tools (CTs) that simultaneously handle two types of wafers, considering both wafer priority and residency time constraints. The two types of wafers have their own processing routes and processing times at each step. To fully utilize the resources of the CTs, we use the fewest processing modules (PMs) to produce one type of wafers with maximum productivity, and use the available PMs to produce the other type of wafers. Based on this, we introduce a swap sequence for scheduling a dual-arm robot, which is simple to implement and supports periodic operations. Without affecting the priority wafer production, we provide the necessary and sufficient conditions for scheduling a CT that processes two types of wafers, and present the optimal PM configuration. A high-performance algorithm is developed to determine an optimal periodic schedule, with its practicality and feasibility illustrated through several examples.

Abstracts:Recently, machine learning-embedded large-scale multiobjective evolutionary algorithms (LMOEAs) have shown great promise in solving large-scale multiobjective optimization problems (LMOPs). However, the fast convergence of the population to the true Pareto-optimal front (POF) and even distribution of the obtained Pareto-optimal solutions (POSs) on the POF are not adequately considered when tackling an LMOP. Besides, existing LMOEAs typically pair solutions with a matching rule and employ a network to learn the evolution pattern among the obtained solution pairs. It is difficult to learn various evolution patterns through a simple network, which hinders the collaboration of different patterns for enhancing the search capability. Facing such difficulties, this article proposes an LMOEA with multipattern learning and collaboration (LMOEA-MLC), where a single-hidden-layer multioutput network (SMN) is established to learn inductive and hybrid evolution patterns. Specifically, two inductive ones can be learned with the solution pairs built by two matching rules toward fast convergence and even distribution, respectively. Moreover, the solution pairs considering the fusion of the two inductive ones are collected, enabling SMN to learn a hybrid one and thus making a tradeoff between fast convergence and even distribution. Besides, the learned evolution patterns collaborate to enhance the search capability due to the distinct patterns. To enhance learning speed, SMN’s parameters are updated by an incremental random vector functional link (IRVFL). In our experiments, comprehensive comparisons with eight state-of-the-art LMOEAs demonstrate the significant performance improvement of LMOEA-MLC in handling LMOPs.

Abstracts:This study tackles the challenge of robust fault diagnosis in discrete event systems (DESs) that experience permanent observation losses using labeled Petri nets (LPNs). We consider the scenario that the initially observable transitions may become unobservable before their firings. Especially, the case that some, instead of all, of the transitions with a shared label may become unobservable is also taken into account. In such a scenario, the diagnosers in the existing methods may not report correct diagnostic results. This article presents a novel notion to ensure robust diagnosability for LPNs, aimed at overcoming the issue of permanent observation loss. To avert enumerating all the reachable markings, a structure called a tagged basis reachability graph (t-BRG) is developed, based on which all subsets of observable transitions, called diagnosis transition sets (DTSs), that ensure the diagnosability of the plant independently are calculated. Then, a special class of verifiers to assess the robust diagnosability of a system experiencing permanent observation loss is developed. Finally, an online diagnosis method performed by a set of diagnosers is presented and demonstrated by examples.

Abstracts:Due to its exceptional feature representation capabilities and high computational efficiency, the broad learning system (BLS) has been widely employed in various classification tasks. Nevertheless, BLS encounters considerable challenges in semi-supervised classification tasks involving complex heterogeneous data, given the data’s high-dimensional and noisy nature, coupled with a limited number of available labeled samples. To tackle these challenges, this article introduces a semi-supervised BLS based on distance constraint regularization (DRBLS) and a semi-supervised broad ensemble method (E-DRBLS) for high-dimensional data. Specifically, we present a distance constraint regularization (DR) that utilizes both labeled and unlabeled data to derive an optimal projection matrix, which maximizes the preservation of the original data’s intrinsic distribution structure. DR is designed to minimize intraclass distance, maximize interclass distance, and minimize the distance between neighboring samples. To boost the performance of BLS in semi-supervised classification, we integrate DR and BLS to construct the semi-supervised classifier DRBLS. Finally, we propose a mixed dimensionality reduction space generation (MDRSG) method that generates multiple high-quality and diverse mixed dimensionality reduction spaces (MDRSs). Based on MDRS, an ensemble framework, E-DRBLS, is developed for semi-supervised classification tasks targeting high-dimensional data. Comprehensive experiments confirm the superiority of the proposed methods.

Abstracts:For unknown continuous-time heterogeneous linear multiagent systems (MASs) under mixed denial-of-service (DoS) attacks, a novel reinforcement learning (RL) algorithm named hybrid iterative (HI) is proposed in this article to solve the secure output tracking problem based on a prescribed-time observer. Considering the scenario that MASs are subjected to mixed DoS attacks that can cause the connectivity maintained or broken of the network communication topology, a distributed resilient prescribed-time observer is designed to accurately estimate the leader’s state and output within a prescribed time. Then, the secure output tracking problem of heterogeneous MASs is converted into the optimal linear quadratic tracking (LQT) problem by introducing a discounted performance function, and inhomogeneous algebraic Riccati equations (AREs) are further derived to solve it. Meanwhile, an HI-based data-driven RL algorithm independent of the initial admissible control policy and the system dynamics knowledge is proposed to learn the optimal solution of inhomogeneous AREs. Compared with the traditional RL algorithms, that is, policy iteration (PI) and value iteration (VI), HI can not only remove the restrictions of the initial admissible policy in PI but also converge to the optimal solution faster than the VI. Finally, comparative simulation verifies the effectiveness of the theoretical results.

Abstracts:Surrogate-assisted evolutionary algorithms are frequently applied to solve time-consuming, resource-intensive, and black-box multiobjective optimization problems. Multiple approximation effectively identifies an approximate optimal solution set within finite exact function evaluations, which may need significant training time for the surrogate models. This article offers a model training method guided by estimation errors to assist the evolutionary algorithm in the search for optimal solutions. In model training, we dynamically use the Gaussian process (GP) and radial basis function (RBF) models following the adjacent generation discrepancy of estimation errors to reduce computational time. They are updated if only the current estimation error exceeds the previous, where the estimation error combines the minimum distance in the decision space and the prediction error of all test samples. In the model-assisted search, an autonomous function estimation method is proposed based on the preference for approximate model errors. The selection of the updated GP or RBF approximation is via a lower model estimation error; in contrast, the average is considered the function value of an individual. In infill sampling, the solution is selected based on the nondominated sorting of function estimation with the maximum angle. The uncertainty-based sampling method is to replenish when these models are not updated. The experiment investigates the effectiveness of the error preference-guided approximation method. The results of two classic benchmark problems and one practice problem show the superiority of the proposed algorithm compared to even well-performed optimization algorithms.

Abstracts:The graph coloring problem (GCP) is a classic combinatorial optimization problem that aims to find the minimum number of colors assigned to the vertices of a graph such that no two adjacent vertices receive the same color. GCP has been extensively studied by researchers from various fields, including mathematics, computer science, and biological science. Due to the $\mathcal {NP}$ -hard nature, many heuristic algorithms have been proposed to solve GCP. However, existing GCP algorithms focus on either small hard graphs or large-scale sparse graphs (with up to $10^{7}$ vertices). This article presents an efficient hybrid heuristic algorithm for GCP, named HyColor, which excels in handling large-scale sparse graphs while achieving impressive results on small dense graphs. The efficiency of HyColor comes from the following three aspects: 1) a local decision strategy to improve the lower bound on the chromatic number; 2) a graph-reduction strategy to reduce the working graph; and 3) a $k$ -core and mixed degree-based greedy heuristic for efficiently coloring graphs. HyColor is evaluated against three state-of-the-art GCP algorithms across four benchmarks, comprising three large-scale sparse graph benchmarks and one small dense graph benchmark, totaling 209 instances. The results demonstrate that HyColor consistently outperforms existing heuristic algorithms in both solution accuracy and computational efficiency for the majority of instances. Notably, HyColor achieved the best solutions in 194 instances (over 93%), with 34 of these solutions significantly surpassing those of other algorithms. Furthermore, HyColor successfully determined the chromatic number and achieved optimal coloring in 128 instances.

Abstracts:This article addresses the adaptive optimal tracking control problem of nonlinear switched systems with unstable unmodeled dynamics. One challenge is how to find the optimal control strategy for a modeled x-dynamic system containing the unmodeled dynamics. Another challenge is how to achieve both optimality and stability of the closed-loop system with unstable dynamics. To this end, a novel solution combines adaptive dynamic programming and the small-gain approach, integrating integral penalties on control, states, and unstable dynamics via actor–critic learning and nonzero game mechanisms. The small-gain approach links closed-loop optimality and stability. For unstable dynamics, stability analysis employs a combined fast-slow switching strategy with gain allocation satisfying the small-gain theorem conditions; optimality analysis compensates unstable dynamics via adaptive parameter estimation and derives the optimal controller via a two-player game. Under small-gain conditions, the designed optimal controller ensures closed-loop output tracks reference signals with ultimately bounded errors. Finally, simulation results validate the proposed approach.

Abstracts:This study presents a novel reinforcement learning (RL)-based, predefined-time tracking fault-tolerant control (FTC) scheme with prescribed performance for handling unknown stochastic nonlinear systems (SNSs) operating in various environments with actuator faults. The scheme addresses multiple actuator fault types, including loss-in-effectiveness (LIE) and lock-in-place (LIP), within a unified theoretical framework in which some actuators may become partially or completely disabled. This framework learns the stochastic nonlinear dynamics and control behaviors of the system using fuzzy logic systems (FLSs) within an RL-based identifier-critic-actor (ICA) structure. By combining prescribed performance control with predefined-time control, the proposed controller achieves fault-tolerant tracking performance, guarantees that all signals are probabilistically bounded, and preserves the output within a specified range. Unlike traditional FTC methods, which depend on knowing the system model to handle LIP faults and bias, this method addresses LIP faults without requiring prior knowledge of the system and achieves different performance levels by utilizing an RL-based ICA to adjust the FLS weights. A practical example using a single-link robot arm driven by a brushed dc (BDC) motor demonstrates the effectiveness and improved performance of the developed FTC scheme.