Gaussian processes (GPs) have attracted considerable attention in assisting evolutionary algorithms (EAs) to solve computationally expensive optimization problems (EOPs) because they can directly provide information about the uncertainty of their predictions. However, the computational complexity of GPs grows cubically as the amount of data increases, which severely limits their computational efficiency in high-dimensional expensive multiobjective optimization problems (EMOPs). To address this limitation, we propose a surrogate-assisted evolutionary algorithm (SAEA) that integrates multilayer perceptron (MLP) grouping with sparse GPs, referred to as MLPSGP-SAEA. First, the MLP grouping selects a subspace from the original space by evaluating the impact of each decision variable on the objective functions. Then, for each objective function, a sparse GP model is employed, and the locations of pseudo-input points are optimized to enhance computational efficiency while improving model accuracy. Moreover, an adaptive sparse and diverse (ASD) infill criterion is proposed, based on the characteristics of the sparse GP model predictive distribution, to better balance exploration and exploitation. Finally, extensive experiments are conducted on four benchmark suites and an aerodynamic design optimization problem. The experimental results demonstrate that MLPSGP-SAEA exhibits significant competitive advantages over the state-of-the-art SAEAs.

ABSTRACT Labanotation is a scientific method for documenting dance movements that has been widely adopted globally. Existing methods for Labanotation action recognition perform poorly in handling complex movements and integrating spatiotemporal information. To address this, we propose a multi‐branch spatiotemporal fusion network with attention mechanisms aimed at accurately recognizing Labanotation actions from motion capture data. Initially, we convert motion capture data into three‐dimensional coordinates and extract skeleton vector features. Subsequently, we enhance feature representation by extracting temporal difference features and skeleton angle features from the skeleton vectors. These features are processed using gated recurrent units and residual networks to effectively integrate spatiotemporal information. Finally, attention mechanisms are applied in the model to differentiate the importance of different positions in the features. This method effectively models spatiotemporal relationships, thereby improving the accuracy of Labanotation action recognition. We conducted experiments on two segmented motion capture datasets, demonstrating the effectiveness of each module. Compared to existing methods, our approach shows superior performance and strong generalization ability. Given the relative simplicity of upper limb action recognition, our focus primarily lies on lower limb action recognition. Notably, this marks the first application of skeleton angle features in the field of Labanotation action recognition.

To solve the delay during interest flooding and unbalanced energy consumption of nodes in the directed diffusion algorithm for Wireless Sensor Network (WSN), it proposes a Data Query Routing Algorithm with Cluster Bridge (DQCB) for WSN. In the clustering stage, it proposes the conception of cluster bridge and introduces triangular norm for an optimal strategy to select cluster bridge. In the query distribution phase, it establishes the network topology using the color conversion of nodes based on graph theory and passive clustering, as well as the advertisement routing table with key information to avoid in-cluster flooding. During data transmission phase, it designs the time level mechanism to prioritize tasks based on real-time requirements and the energy level mechanism to optimize the route. The simulation results prove that the proposed method effectively reduces the unbalanced energy consumption, improves query efficiency and prolongs the network life.

Coverage is an important indicator to measure the monitoring quality of Wireless Sensor Network (WSN).As a NP-hard problem, it is a mainstream method to introduce swarm intelligence algorithm to solve it.After analyzing the traditional Firefly Algorithm (FA), aiming at the defects of this algorithm, this paper proposes Modified Communication Parallel Firefly Algorithm (MCPFA) family algorithm, which improves the performance of the algorithm to a certain extent.On this basis, the compact optimization method is introduced and the Modified Communication Parallel Compact Firefly Algorithm (MCPCFA) family algorithm is proposed to further improve the overall function of traditional FA.The proposed algorithm is tested by several classical functions in CEC2013 test function set to verify the performance of the algorithm.Finally, a WSN node deployment scheme based on MCPCFA family algorithm is proposed to improve the network coverage.Through simulation experiments, compared with the traditional Partial Swarm Optimization (PSO), FA, Parallel FA (PFA) and Compact FA (CFA), MCPCFA family algorithm shows the best performance in WSN network layout.

The S-MAC protocol is a very classic competition-based MAC protocol [1]. Many MAC protocols proposed are modified on the basis of S-MAC protocol. However, most of the current improvements to traffic adaptation are for one or both of backoff mechanism [2], duty cycle mechanism [3] and power control mechanism [4]. The modified MAC protocols still have problems of single control factor. Therefore, this paper proposes a modified traffic self-adaptive MAC protocol called TSA-MAC1. In terms of backoff mechanism, a multi-factor cross-control backoff mechanism is proposed in this paper. Considering the duty cycle mechanism, the average flow factor is introduced for measuring network traffic, and the current value of duty cycle will vary around the initial duty cycle according to the range of that factor. Considering the power control mechanism, the formula of Friis is used to calculate the minimum transmission power. And an exponential function is chosen to multiply the minimum transmission power. Simulation results show that the proposed MAC protocol has significant advantages on energy consumption, throughput and transmission delay.