Integrating data security with resource management enhances security, efficiency, and reliability of blockchain-enabled mobile edge computing (MEC) systems. However, challenges such as secure data storage, timely task execution, and limited parallelism introduce complexities in task offloading decisions and resource allocation strategies. To address these challenges, the task latency minimization problem in blockchain-enabled MEC networks is formulated as an NP-hard optimization problem. The model incorporates constraints on parallelism, partial task offloading, bandwidth and computation resource allocation among mobile users (MUs) and edge servers (ESs). To enhance the reliability and transparency of data storage, a dual-blockchain framework is proposed, consisting of multiple MU blockchains and a dedicated ES blockchain. To tackle the NP-hard problem, the original optimization problem is decomposed into multiple sub-problems, facilitating parameter decoupling. An alternating optimization algorithm is employed to refine task offloading decisions and resource allocation of MUs and ESs with limited parallelism. The ESs update their strategies iteratively based on feedback mechanisms. Additionally, a task prioritization formulation is developed to enhance scalability, considering sub-level task importance, urgency, and first-level task classification. Extensive simulation experiments demonstrate that the proposed algorithm achieves lower task latency compared to existing methods across varying network sizes, offloading schemes, and parallelism constraints. By optimizing the parallel processing of tasks, the waiting latency of this algorithm is reduced on average by 35. 35%, 57. 16% and 35. 35% compared to other methods, respectively.

In the vehicular edge networks (VEN), task migration is complicated by issues like vehicle movement, diverse resource allocation, and integrating sensing with communication technologies. This paper presents a task migration strategy to optimize task flow under limited resources in PMN-assisted VEN. Vehicles can send public and private tasks to roadside units (RSUs), constrained by bandwidth, computational power, and storage space. Public tasks aim at data collection for road transportation management, while private tasks cover a spectrum of services from work to entertainment. To address the limitations imposed by resource scarcity and meet the demands of task migration, we have developed a dual-layer graph neural network (GNN) that leverages vehicle mobility patterns. In particular, the first layer of GNN acquires vehicle information and the latest surrounding information, and sends it to the nearby RSU. Considering the variety of tasks and multi-dimensional resource constraints, the second GNN layer forecasts RSU resource availability and vehicular trajectories. Subsequently, a task-based maximum flow algorithm (T-MFA) is proposed to refine task migration paths and resource allocation strategies to maximize task flow. Simulation experiments validate the efficacy of the proposed algorithm, demonstrating its capability to achieve optimal task migration by accommodating differences in tasks, resources, and capacities.

This article presents a neural network model based on edge intelligence for seismic event detection. We implemented the model in hardware using a field-programmable gate array (FPGA) to achieve in-situ detection of seismic events at acquisition nodes or edge nodes. We designed and implemented the model, focusing on its suitability for hardware implementation on FPGA, employing an encoder—decoder structure. The encoder incorporates reparameterization and depthwise separable convolutions. During training, a multibranch structure was employed, which was then converted to an equivalent single-branch structure during inference to reduce model complexity and parameters. The features extracted by the encoder were further learned by the bi-directional long short-term memory (Bi-LSTM) network and then fed into the decoder for classification. We evaluated the model using the stanford earthquake data set (STEAD) and observed a 70% reduction in parameters while achieving comparable detection performance to EQTransformer. Furthermore, the model structure is well-suited for hardware implementation on FPGA. Applying this model to edge devices for seismic event detection can effectively minimize redundant data transmission and enable in-situ quality control.

The identification and determination of seismic phase arrival times is a critical task in seismic data processing. In recent years, methods based on convolutional neural networks (CNN) and Transformer models have been widely applied in this field. While CNNs offer potential in seismic feature extraction, modeling limitations restrict their efficiency for detailed waveform analysis. Conversely, Transformer models, though powerful, are constrained by their quadratic computational complexity. Recent research has shown that the state space model (SSM) represented by Mamba can effectively simulate long-range interactions while maintaining linear computational complexity. Inspired by this, we propose the seismic phase picking mamba (SPPMamba) model. We have designed a novel Conv-SSM module that combines CNN layers’ local feature extraction capabilities with SSM’s long-range dependency-modeling abilities. This enables the model to effectively identify and utilize the temporal variations of seismic signals, enhancing the model’s analytical capabilities for dynamic seismic feature characteristics. To validate the performance of SPPMamba, we conducted experiments on public seismic datasets. Experimental results show that SPPMamba demonstrates superior performance in seismic phase picking. This study aims to lay a research foundation for developing seismic data processing algorithms based on SSM.

Detecting cracks is a crucial task to ensure the safety of engineering. However, the complexity of the crack background and the highly uneven pixel ratio between the crack and the background significantly limit the effectiveness of detection algorithms. Therefore, an efficient and innovative algorithm for crack detection is proposed, which utilizes a transformer and a multilevel cross-scale weighted feature fusion module, as well as a progressive transfer learning (TL) strategy. Firstly, in terms of existing algorithms, there are limitations in terms of high leakage and false detection rates, as well as a lack of generalization ability, therefore, a F2N-CrackNet model is proposed, which consists of two efficient feature fusion modules and a Nested Multi-level Attention with Atrous Spatial Pyramid Pooling (NMA-ASPP). Secondly, to tackle sparse and unevenly distributed bridge crack data, enhance model detection capabilities, and expedite convergence, a progressive three-stage hybrid TL strategy incorporating across-domain, inter-domain, and inner-domain transferring is proposed, by migrating knowledge from related domains. Finally, to enrich experimental data supporting and validating the proposed model and the transfer learning approach, a new group of experimental data set is offered, comprising hundreds of high-resolution bridge crack images collecting in Shanghai by using a digital camera. Additionally, an efficient human-computer interactive labeling approach combined with morphological processing is devised. Experiments conducted on both open-source and private datasets reveal substantial performance improvements in crack detection achieved by the proposed model and TL strategy. On private data, the model achieves an 81.28% MIoU, exceeding or approaching the performance of state-of-the-art (SOTA) methods, while simultaneously reducing training time by 5–8 seconds per round compared to SOTA. Meanwhile, the performance on multiple sets of open-source data is similarly elevated.

The resource allocation problem in Multi-access Edge Computing (MEC) has been widely studied to maximize its operation efficiency under limited resource constraint. However, the existing literatures overlooked the setup cost and the associated dynamic operations. In this work, we consider server configuration and overload in the multi-server scenario where servers are switched on/off depending on the network environment. A novel pricing mechanism maximizing the utility of base station (BS) monitoring multiple servers is proposed, which jointly optimizes the setup cost and server load. We aim to maximize the BS utility under one-day task requests, and divide the time into off-peak and peak periods based on task requests. In the off-peak period, we flexibly switch on/off servers for BS to reduce setup costs. In the peak period, to avoid overloading, we introduce crowdsourcing where servers as agents purchase idle resources from private users (PUs) for mobile users (MUs) and minimize MUs’ cost by a contract-based knapsack algorithm. Lastly, a pricing mechanism is proposed to solve the BS utility maximization problem with an exploratory Upper Confidence Bound (UCB)-based algorithm adjusting server prices dynamically. Simulation results show that the proposed algorithm is superior to others in minimizing MUs cost and maximizing BS utility.

Prior hashing works typically learn a projection function from high-dimensional visual feature space to low-dimensional latent space. However, such a projection function remains several crucial bottlenecks: 1) information loss and coding redundancy are inevitable; 2) the available information of semantic labels is not well-explored; 3) the learned latent embedding lacks explicit semantic meaning. To overcome these limitations, we propose a novel supervised Discrete Auto-Encoder Hashing (DAEH) framework, in which a linear auto-encoder can effectively project the semantic labels of images into a latent representation space. Instead of using the visual feature projection, the proposed DAEH framework skillfully explores the semantic information of supervised labels to refine the latent feature embedding and further optimizes hashing function. Meanwhile, we reformulate the objective and relax the discrete constraints for the binary optimization problem. Extensive experiments on Caltech-256, CIFAR-10, and MNIST datasets demonstrate that our method can outperform the state-of-the-art hashing baselines.

This paper proposes an effective method to elevate the performance of saliency detection via iterative bootstrap learning, which consists of two tasks including saliency optimization and saliency integration. Specifically, first, multiscale segmentation and feature extraction are performed on the input image successively. Second, prior saliency maps are generated using existing saliency models, which are used to generate the initial saliency map. Third, prior maps are fed into the saliency regressor together, where training samples are collected from the prior maps at multiple scales and the random forest regressor is learned from such training data. An integration of the initial saliency map and the output of saliency regressor is deployed to generate the coarse saliency map. Finally, in order to improve the quality of saliency map further, both initial and coarse saliency maps are fed into the saliency regressor together, and then the output of the saliency regressor, the initial saliency map as well as the coarse saliency map are integrated into the final saliency map. Experimental results on three public data sets demonstrate that the proposed method consistently achieves the best performance and significant improvement can be obtained when applying our method to existing saliency models.

In this paper, a multi-objective evolutionary algorithm based on adaptive discrete differential evolution is proposed for multi-objective optimization problems, especially in discrete domain. By introducing differential evolution to multi-objective optimization field, a novel adaptive discrete differential evolution strategy is presented firstly to enhance the ability of global exploration, so that the proposed multi-objective evolutionary algorithm can achieve the better approximate Pareto-optimal solutions. Furthermore, the proposed multi-objective evolutionary algorithm integrates the adaptive discrete differential evolution strategy with a fast Pareto ranking strategy and a truncating operation based on crowding density and Pareto rank to maintain the good diversity of evolutionary population. The simulations are conducted for a set of standard Multi-objective 0/1 knapsack problems which are the typical NP-hard problems. The performance of the proposed multi-objective evolutionary algorithm is compared with that of SPEA and NSGA-II which are state-of-the-art. Experimental results indicate that the proposed multi-objective evolutionary algorithm is more effective and efficient.

Global optimization problems with numerous local and global optima are difficult to solve, which can trap traditional genetic algorithms. To solve the problems, a hybrid self-adaptive genetic algorithm based on sexual reproduction and Baldwin effect is presented for global optimization in this paper. By simulating sexual reproduction in nature, the proposed algorithm utilizes a gender determination method to determine the gender of individuals in population. Then, it adopts the different initial genetic parameters for female and male subgroups, and self-adaptively adjusts the sexual genetic operation based on the competition and cooperation between different gender subgroups. Furthermore, the fitness information transmission between parents and offspring is implemented to guide the evolution of individuals- acquired fitness. Moreover, on the basis of the Darwinian evolution theory, the proposed algorithm guides individuals to forward or reverse acquired reinforcement learning based on Baldwin effect in niche. Numerical simulations are conducted for a set of benchmark functions with different dimensional decision variables. The results show that the proposed algorithm can find optimal or closer-to-optimal solution, and has faster search speed and higher convergence rate.

This paper presents a diversity enhanced particle swarm optimizer (DivEnh-PSO) which uses an external memory to enhance the diversity of the swarm and to discourage premature convergence. The external memory holds selected past solutions with good diversity. Selected past solutions are periodically injected into the swarm. This approach does not require additional function evaluations as past solutions are used to enhance diversity. Experiments were conducted on multimodal and composition test problems with and without coordinate rotations. The test results indicate improved performance of the DivEnh-PSO in solving multimodal problems when compared with the same PSO implementation without diversity enhancement.