Deep neural networks have evolved significantly in the past decades and are now able to achieve better progression of sensor data. Nonetheless, most of the deep models verify the ruling maxim in deep learning—bigger is better—so they have very complex structures. As the models become more complex, the computational complexity and resource consumption of these deep models are increasing significantly, making them difficult to perform on resource-limited platforms, such as sensor platforms. In this paper, we observe that different layers often have different pruning requirements, and propose a differential evolutionary layer-wise weight pruning method. Firstly, the pruning sensitivity of each layer is analyzed, and then the network is compressed by iterating the weight pruning process. Unlike some other methods that deal with pruning ratio by greedy ways or statistical analysis, we establish an optimization model to find the optimal pruning sensitivity set for each layer. Differential evolution is an effective method based on population optimization which can be used to address this task. Furthermore, we adopt a strategy to recovery some of the removed connections to increase the capacity of the pruned model during the fine-tuning phase. The effectiveness of our method has been demonstrated in experimental studies. Our method compresses the number of weight parameters in LeNet-300-100, LeNet-5, AlexNet and VGG16 by $24\times$, $14\times$, $29\times$ and $12\times$, respectively.

The sensor-weapon–target assignment (S-WTA) problem is a crucial decision issue in C4ISR. The cooperative engagement capability (CEC) of sensors and weapons depends on the S-WTA schemes, which can greatly affect the operational effectiveness. In this paper, a mathematical model based on the synthetical framework of the S-WTA problem is established, combining the dependent and independent cooperative engagement modes of sensors and weapons. As this problem is a complex combinatorial optimization problem, a novel genetic algorithm is proposed to improve the solution of this formulated S-WTA model. Based on the prior knowledge of this problem, a problem-specific population initialization method and two novel repair operators are introduced. The performances of the proposed algorithm have been validated on the known benchmarks. Extensive experimental studies compared with three state-of-the-art approaches demonstrate that the proposed algorithm can generate better assignment schemes for the most of the benchmarks.

Dempster-Shafer evidence theory (DST) has shown its great advantages to tackle uncertainty in a wide variety of applications. However, how to quantify the information-based uncertainty of basic probability assignment (BPA) with belief entropy in DST framework is still an open issue. The main work of this study is to define a new belief entropy for measuring uncertainty of BPA. The proposed belief entropy has two components. The first component is based on the summation of the probability mass function (PMF) of single events contained in each BPA, which are obtained using plausibility transformation. The second component is the same as the weighted Hartley entropy. The two components could effectively measure the discord uncertainty and non-specificity uncertainty found in DST framework, respectively. The proposed belief entropy is proved to satisfy the majority of the desired properties for an uncertainty measure in DST framework. In addition, when BPA is probability distribution, the proposed method could degrade to Shannon entropy. The feasibility and superiority of the new belief entropy is verified according to the results of numerical experiments.

The weapon‐target assignment (WTA) problem is a key issue in Command & Control ( C ² ). Asset‐based multiobjective static WTA (MOSWTA) problem is known as one of the notable issues of WTA. Since this is an NP‐complete problem, multiobjective evolutionary algorithms (MOEAs) can be used to solve it effectively. The multiobjective evolutionary algorithm based on decomposition (MOEA/D) is a practical and promising multiobjective optimization technique. However, MOEA/D is originally designed for continuous multiobjective optimization which loses its efficiency to discrete contexts. In this study, an improved MOEA/D is proposed to solve the asset‐based MOSWTA problem. The defining characteristics of this problem are summarized and analyzed. According to these characteristics, an improved MOEA/D framework is introduced. A novel decomposition mechanism is designed. The mating restriction and selection operation are reformulated. Furthermore, a problem‐specific population initialization method is presented to improve the efficiency of the proposed algorithm, and a novel nondominated solution‐selection method is put forward to handle the constraints of Pareto front. Appropriate extensions of four MOEA variants are developed in comparison with the proposed algorithm on some generated scenarios. Extensive experiments demonstrate that the proposed method is effective and promising.

The Antagonistic Weapon-Target Assignment (AGWTA) problem is a crucial decision issue in Command & Control (C2). Since this is a minimax problem, co-evolutionary algorithms can be used to solve it effectively. However, the co-evolutionary algorithm is originally designed for continuous minimax problems which loses its efficiency to discrete contexts. In this paper, a novel elitism co-evolutionary algorithm is proposed to solve the AGWTA. Firstly, an improved AGWTA model for air combat based on the attack and evasion strategies is proposed. Secondly, an elite cooperative genetic algorithm based on the framework of the co-evolutionary algorithm is put forward. In this proposed algorithm, a problem-specific coding method and evolution operator are designed. Meanwhile, an elite individual update mechanism is presented. Finally, based on the analysis of the relationship between the feasible solutions under the air combat environment, an evaluation index is proposed. Experiments show that the proposed algorithm has higher accuracy than traditional co-evolutionary algorithms for solving AGWTA problems.

Domain adaptation aims to handle the distribution mismatch of training and testing data, which achieves dramatic progress in multi-sensor systems. Previous methods align the cross-domain distributions by some statistics, such as the means and variances. Despite their appeal, such methods often fail to model the discriminative structures existing within testing samples. In this paper, we present a sample-guided adaptive class prototype method, which consists of the no distribution matching strategy. Specifically, two adaptive measures are proposed. Firstly, the modified nearest class prototype is raised, which allows more diversity within same class, while keeping most of the class wise discrimination information. Secondly, we put forward an easy-to-hard testing scheme by taking into account the different difficulties in recognizing target samples. Easy samples are classified and selected to assist the prediction of hard samples. Extensive experiments verify the effectiveness of the proposed method.