Echo state network (ESN) has recently attracted increasing interests because of its superior capability in modeling nonlinear dynamic systems. In the conventional echo state network model, its dynamic reservoir (DR) has a random and sparse topology, which is far from the real biological neural networks from both structural and functional perspectives. We hereby propose three novel types of echo state networks with new dynamic reservoir topologies based on complex network theory, i.e., with a small-world topology, a scale-free topology, and a mixture of small-world and scale-free topologies, respectively. We then analyze the relationship between the dynamic reservoir structure and its prediction capability. We utilize two commonly used time series to evaluate the prediction performance of the three proposed echo state networks and compare them to the conventional model. We also use independent and identically distributed time series to analyze the short-term memory and prediction precision of these echo state networks. Furthermore, we study the ratio of scale-free topology and the small-world topology in the mixed-topology network, and examine its influence on the performance of the echo state networks. Our simulation results show that the proposed echo state network models have better prediction capabilities, a wider spectral radius, but retain almost the same short-term memory capacity as compared to the conventional echo state network model. We also find that the smaller the ratio of the scale-free topology over the small-world topology, the better the memory capacities.

As a technique to buffer the conflict between computation-intensive tasks and capability-limited devices, unmanned aerial vehicle-enabled mobile-edge computing (UAV-MEC) has been witnessed as a promising approach, especially in the post-disaster scenario where the infrastructure is limited or unavailable. In this article, we consider a joint optimization of topology reconstruction and subtask scheduling to minimize the average completion time of the subtask. To address this problem, we propose a hierarchical hybrid subtask scheduling algorithm (H-HSS). First, a topology reconstruction game algorithm for energy-efficient control (TRGE) is investigated to get optimal power and node-to-node connection decision, in which the interaction between the node with its neighbors is modeled as a single-leader–multifollowers Stackelberg game. Second, by analyzing the dependency between subtasks, a hierarchical-dependent subgraph extraction scheme (HDSE) is proposed, which transforms the subtask call graph into a hierarchical tree diagram to obtain a hierarchical scheduling list. Finally, a hybrid subtask scheduling scheme is presented to make optimal task scheduling decisions. Numerical results show that H-HSS can significantly outperform the other representative benchmarks with low complexity, in subtask completion time, energy consumption, or weighted sum. In addition, the tolerance capability of our proposed TRGE algorithm is increased by 66%.

Cloud computing enables service sharing in a massive scale via network access to a pool of configurable computing resources. It has to allocate resources adaptively for tasks and applications to be executed effectively and reliably in a large scale, highly heterogeneous environment. Resource allocation in cloud computing is an NP‐hard problem. In this study, the authors conduct a reliability analysis of cloud services by applying a Markov‐based method. They formulate the cloud scheduling problem as a multi‐objective optimisation problem with constraints in terms of reliability, makespan, and flowtime. Furthermore, they propose a genetic algorithm‐based chaotic ant swarm (GA‐CAS) algorithm, in which four operators and natural selection are applied, to solve this constrained multi‐objective optimisation problem. Simulation results have demonstrated that GA‐CAS generally speeds up convergence and outperforms other meta‐heuristic approaches.

In recent years, the number of frauds in credit card-based online payments has grown dramatically, pushing the banks and e-commerce organizations to develop fraud detection models based on substantial transaction logs. However, the transaction datasets available for training are extremely imbalanced, with fraudulent transaction logs considerably less represented. Meanwhile, the feature information of the fraud samples with better classification capabilities cannot be mined directly by feature learning methods due to too few fraud samples. These significantly reduce the effectiveness of fraud detection models. In this paper, we proposed a Dual Autoencoders Generative Adversarial Network, which can balance the majority and minority classes and learn feature representations of normal and fraudulent transactions to improve the accuracy of the fraud detection. The new model firstly trains a Generative Adversarial Networks to output sufficient mimicked fraudulent transactions for autoencoder training. Then, two Autoencoders are trained on the normal and fraud dataset, respectively. The samples are encoded by two Autoencoders to obtain two sets of features, which are combined to form the Dual Autoencoding features. Finally, the model detects fraudulent transactions by a Neural Network trained on the augmented training set. Experimental results show that the model outperforms a set of well-known classification methods in experiments, especially the sensitivity and precision, which are effectively improved.

As promising privacy-preserving machine learning technology, federated learning enables multiple clients to train the joint global model via sharing model parameters. However, inefficiency and vulnerability to poisoning attacks significantly reduce federated learning performance. To solve the aforementioned issues, we propose a dynamic asynchronous anti poisoning federated deep learning framework to pursue both efficiency and security. This paper proposes a lightweight dynamic asynchronous algorithm considering the averaging frequency control and parameter selection for federated learning to speed up model averaging and improve efficiency, which enables federated learning to adaptively remove the stragglers with low computing power, bad channel conditions, or anomalous parameters. In addition, a novel local reliability mutual evaluation mechanism is presented to enhance the security of poisoning attacks, which enables federated learning to detect the anomalous parameter of poisoning attacks and adjust the weight proportion of in model aggregation based on evaluation score. The experiment results on three datasets illustrate that our design can reduce the training time by 30% and is robust to the representative poisoning attacks significantly, confirming the applicability of our scheme.