Internet of Things (IoT) task offloading involves conflicting objectives of energy consumption and delay. We formulate a bi-objective optimization model for a multi-UAV-assisted mobile edge computing (MEC) system, jointly optimizing resource allocation, task offloading decisions, and UAV deployment to minimize both energy consumption and delay. As the number of offloaded tasks increases, finding feasible solutions becomes more challenging. To address this, we develop an Information Feedback Evolutionary Algorithm (IFEA) that leverages feedback driven guidance to enhance the diversity and convergence of the Pareto front (PF). Simulation results show that IFEA achieves better trade offs than the other four multi-objective algorithms.

To tackle the challenge of maintaining population diversity in the decision space for multimodal multiohjective optimization prohlems (MMOPs), this paper introduces a novel mating selection strategy based on kernel K-means clustering. By leveraging the ability of kernel K-means to identify solution clusters within complex decision spaces, the proposed method enhances the exploration of promising parent solutions during the mating selection process. This method, combined with the environmental selection approach used in MMOEA/DC, led to the development of a novel algorithm called Multimodal Multiobjective Evolutionary Algorithm with Three Clustering mechanisms, termed as MMEATC. To evaluate the effectiveness of MMEATC, we compare MMEATC against five state-of-the-art multimodal multiobjective evolutionary algorithms: MMOEA/DC, MO_Ring_PSO_SCD, TriMOEA-TA&R, MMEA-WI, and CoMMEA. Extensive experimental results show that MMEATC achieves competitive performance, highlighting its potential as an effective approach to solving MMOPs.

Electroencephalography (EEG)-based applications in Brain-Computer Interfaces (BCIs), neurological disease diagnosis, rehabilitation, and other areas rely on the utilization of extensive data for model development. Nevertheless, this raises concerns regarding storage and privacy, since model development needs a significant amount of data, and EEG sharing discloses sensitive information such as identity and health. To address this challenging problem, we provide the paradigm of EEG condensation, aiming to generate a synthetic sample set that is highly information-concentrated yet not visually similar. Correspondingly, we propose a novel dataset condensation framework where the knowledge of the original EEG dataset is condensed into diffusion models, named EEGCiD. Specifically, EEGCiD first utilizes a deterministic denoising diffusion implicit model (DDIM) to store the information of the original dataset and optimizes the condensation latent codes z to obtain the EEG condensation dataset. Further, to enhance the modeling of EEG knowledge in DDIM, we design a transformer architecture incorporating the spatial and temporal self-attention block (STSA) to replace the traditional U-Net backbone. In the condensation phase, EEGCiD randomly initializes a subset of samples from the original dataset to obtain the condensation latent codes z through the forward process in DDIM. Then, it optimizes z by matching the feature distributions in multiple EEG decoding models between the synthetic samples and the original dataset. Extensive experiments across three EEG datasets demonstrate that the condensation dataset from the proposed model not only achieves superior classification performance with limited sample sizes, but also effectively prevents membership inference attacks (MIA). Note to Practitioners—This paper aims to investigate a novel EEG generation paradigm that extracts representative synthetic samples from large-scale datasets. Existing studies in EEG generation primarily concentrate on generating real-like signals, and some work claims that the generated EEG can serve as a substitute for the original dataset to achieve privacy preservation. In the EEGCiD framework, the deterministic DDIM is pre-trained with the original dataset to store the knowledge. Besides, an ensemble feature matching strategy is proposed to condense the information from the original dataset into a small latent code set. Experiments on three datasets demonstrate that EEGCiD addresses two fundamental challenges: 1) obtaining superior classification performance within a small dataset (limited storage capacity); 2) avoiding potential privacy issues during EEG sharing and transmission.

Value function approximation, such as Q-learning, is widely used in the discrete control rather than the continuous one because the optimal action in the discrete setting is more easily selected. Optimizing the action is a non-convex optimization problem with respect to the complex value function. Some notable studies simplify the non-convex optimization problem by assuming the value function as quadratic in the actions or by discretizing the action space. However, the performance of the output policy will decline if these studies’ premises do not hold. In order to address the problem, we propose a framework that combines swarm intelligence algorithms with value-based Reinforcement Learning, where the swarm intelligence algorithms are employed to search for the optimal action with respect to the state and the value function. To ensure the correctness of this framework, we conditionally claim the convergence rate of swarm intelligence algorithms with high probability. We then implement it by searching the batch optimal actions to various states on the GPU platform for the batch training. Furthermore, we employ the population-based atomic actions for the compatibility with the existing related work about solving discrete control problems. Four classical control models and four robot simulation environments are utilized in the comparisons. According to empirical results, our framework outputs a policy comparable with that of the policy-based algorithms by 10% timesteps in the continuous control. Note to Practitioners—This paper is motivated by the exploration-exploitation dilemma of Reinforcement Learning to solve continuous control tasks. To balance the exploration and exploitation, the stochastic exploration and the prioritized exploration are roughly two feasible ways, where the prioritized one is a better choice due to the higher data efficiency than the stochastic one, e.g.$\varepsilon $-greedy. Normally, the prioritized exploration works well in the value-based Reinforcement Learning algorithms rather than the policy-based ones; meanwhile, the policy-based algorithms are more suitable to continuous control tasks than the value-based ones. To tackle this conflict, we especially design a particle swarm optimization to maximize the Q-value of action in Q-learning. Our design can be hybridized by various swarm intelligence and value-based Reinforcement Learning algorithms. Also, it can be embedded in most intelligent control systems easily. The aim of this study is to solve the continuous control tasks by value-based algorithms as the first step of applying the prioritized exploration. The simulative results verify the effectiveness and efficiency of our design.

Graph neural networks (GNNs) have shown significant performance in various practical applications due to their strong learning capabilities. Backdoor attacks are a type of attack that can produce hidden attacks on machine learning models. GNNs take backdoor datasets as input to produce an adversary‐specified output on poisoned data but perform normally on clean data, which can have grave implications for applications. Backdoor attacks are under‐researched in the graph domain, and almost existing graph backdoor attacks focus on the graph‐level classification task. To close this gap, we propose a novel graph backdoor attack that uses node features as triggers and does not need knowledge of the GNNs parameters. In the experiments, we find that feature triggers can destroy the feature spaces of the original datasets, resulting in GNNs inability to identify poisoned data and clean data well. An adaptive method is proposed to improve the performance of the backdoor model by adjusting the graph structure. We conducted extensive experiments to validate the effectiveness of our model on three benchmark datasets.

Uncertainty is a practical issue in system design optimization because some characteristics of components, such as reliability and cost, cannot be determined precisely in many situations. Considering the imprecise characteristics of components, few works have focused on the multi-objective optimization for the redundancy allocation due to the challenges of comparing multi intervals. To tackle the issue, a novel angle-based bi- objective redundancy allocation algorithm is proposed in this study, introducing three original contributions: 1) An angle-based interval crowding distance (ICA) is especially designed for effective performance and reduced computational time; 2) Two techniques are applied to tackle the problem: An elite selection for mutation is presented for generating better offsprings; A penalty-guided constraint handling technique is introduced for converting the problem into an unconstrained one. 3) Since a set of optimal solutions is obtained by the proposed method and no preference on uncertainties is provided, this paper proposes a novel knee interval method to help DMs make a decision. To be specific, the proposed ICA can describe the distribution of the whole population intuitively and effectively, considering not only the angle between two compared individuals but also the angle range of the interval values. The computational results from two typical experiments demonstrate that the proposed algorithm is more efficient than other state-of-the-art algorithms, generating Pareto sets with less repeating individuals, stronger convergence, wider distribution, less imprecision, and reduced computational time. Note to Practitioners—This article is motivated by two practical problems in multi-objective redundancy allocation in presence of interval uncertainty: First, this paper tries to solve the multi-objective redundancy allocation problem with the imprecise characteristics of components, which is rarely considered in the field of reliability optimization design. Second, the calculation of the crowding distance needs extra time cost and is less efficient. To tackle this issue, an interval crowding angle is especially designed, considering not only the angle between two compared individuals, but also the angle range of the interval values. The proposed method can be embedded in most multi-objective interval evolutionary algorithms to compute the diversity of the individuals. The goal of this study is to allocate the economy and high-reliable components for practitioners. The computational results verify its effectiveness and efficiency. Besides, in many cases the practitioners know only few or no preferences, this paper proposes a knee point analysis of interval values that allows practitioners to select the optimal solution with large hypervolume and less imprecision among a set of solutions.

With the development of cloud computing, multi-cloud systems have become common platforms for hosting and executing workflow applications in recent years. However, the complexity of workflow scheduling increases exponentially because of the diversified billing mechanisms, heterogeneous virtual machines, and reliability of multi-cloud systems. This article focuses on a multi-objective workflow scheduling problem in multi-cloud systems (MOWSP-MCS). The makespan, cost, and reliability are considered the optimization objectives from the perspective of users. Compared with the classical multi-objective workflow scheduling in the cloud environment, MOWSP-MCS allows users to apply the backup technique to improve reliability. To solve the MOWSP-MCS, this article proposes a reliability-aware multi-objective memetic algorithm (RA-MOMA) containing a diversification strategy and intensification strategy. In the diversification strategy, several problem-specific genetic operators are introduced to construct the diversified offspring individuals. In the intensification strategy, four problem-specific neighborhood operators are designed based on the critical path and resource utilization rate to improve the quality of the individuals in the archive set. A comprehensive numerical experiment is conducted to evaluate the effectiveness of RA-MOMA. The comparisons with several related algorithms demonstrate the superiority of RA-MOMA for solving the MOWSP-MCS.

Mobile edge computing (MEC) is an emerging computing paradigm that decreases the computing time and extends the lifespan of user equipments (UEs). In MEC, the computational tasks are offloaded from UEs to the base station (BS) at the edge of the network for processing. However, MEC cannot cope with environments where there are no BS or where communication facilities have been destroyed. In this paper, we study the problem of minimizing the energy consumption of UAV equipped with MEC servers as a mobile base station to serve users. The problem involves user offloading decision, UAV location and allocation with computational resources, and is a hybrid optimization problem with continuous and discrete variables. To address this problem, we propose a hybrid nature-inspired optimization algorithm (HNIO) and its version for discrete optimization, where HNIO incorporates mutation and population diversity detection mechanisms to boost its global optimization capability, and we design a probabilistic selection-based coding strategy for the discrete optimization version. The experimental study is conducted based on ten cases with different numbers of UEs. Comparing HNIO with several other state-of-the-art optimization algorithms, it is concluded from the Friedman and Wilcoxon’s test of the experimental results that HNIO shows better precision and stability in nine out of the ten cases with higher number of UEs.

This letter focuses on the problem of lifelong classification in the open world, the goal of which is to achieve an endless process of learning. However, incremental data sets (like the streaming data) in the open world, where the new classes may be emerging, are unsuited for classical classification methods. For addressing this problem, existing methods usually retrain the whole observed data sets with the complex computation and the expensive storage cost. This letter attempts to improve the performance of classification in the open world and decomposes the problem into three subproblems: (1) to reject unknown instances, (2) to classify accepted instances, and (3) to cut the cost of learning. Rejecting unknown instances refers to recognize those instances whose classes are unknown according to the learner, which could reduce the computation of the retraining process and eliminate the storage of historical data sets. We employ outlier detection for rejecting instances and a variant artificial neural network for classifying with fewer weights. Results on several experiments show that the work is effective. Source code can be found at https://github.com/wangbi1988/Lifelong-learning-in-Open-World-Classification.

Fruit fly optimisation algorithm is a new swarm intelligence algorithm, which is simple and efficient. However, it is easy to get premature convergence in solving high-dimensional complex continuous functions. In order to overcome the shortcoming and improve the precision of solution, we propose a new fruit fly optimisation algorithm (SEDMFOA) based on spatial expansion and dynamic mutation. It is featured with changing the original constant step size to a focused search method, and embedding the dynamic mutation strategy in the evolution of the algorithm. Furthermore, we employed gauss mapping operation on the best individual to generate new individuals to substitute for those trans-boundary individuals. Finally, the inverse solution to expand the space was designed to develop the durative search ability in the later stage of the algorithm. According to the experimental results of eighteen well-known benchmark functions, the SEDMFOA is efficient and effective. The precision and stability of the approximate solution of SEDMFOA are superior the algorithms proposed in some related literatures. In wind energy research, the new algorithm is applied to optimise extreme learning machines for short-term wind forecasting. Simulation results show that SEDMFOA has better prediction effect than traditional algorithms.