Aiming at high network energy consumption and data delay induced by mobile sink in wireless sensor networks (WSNs), this paper proposes a cluster-based energy optimization algorithm called Cluster-Based Energy Optimization with Mobile Sink (CEOMS). CEOMS algorithm constructs the energy density function of network nodes firstly and then assigns sensor nodes with higher remaining energy as cluster heads according to energy density function. Meanwhile, the directivity motion performance function of mobile sink is constructed to enhance the probability of remote sensor nodes being assigned as cluster heads. Secondly, based on Low Energy Adaptive Clustering Hierarchy Protocol (LEACH) architecture, the energy density function and the motion performance function are introduced into the cluster head selection process to avoid random assignment of cluster head. Finally, an adaptive adjustment function is designed to improve the adaptability of cluster head selection by percentage of network nodes death and the density of all surviving nodes of the entire network. The simulation results show that the proposed CEOMS algorithm improves the cluster head selection self-adaptability, extends the network life, reduces the data delay, and balances the network load.

In the Dempster-Shafer evidence theory, how to effectively measure the degree of conflict between two bodies of evidence is still an open question. To solve this problem, we propose a weighted conflict evidence combination method based on Hellinger distance and the belief entropy. This method uses the probability transformation function to deal with the multi-subset focal elements firstly. Next, the Hellinger distance is introduced to measure the degree of conflict among the evidence. Moreover, improved belief entropy is also employed to quantify the uncertainty of the basic belief assignments. Further, Hellinger distance and the improved belief entropy are combined to construct the weight coefficient concerning evidence, and finally, the Dempster combination rule is used for fusion. The final fusion results of proposed method on fault diagnosis experiment and target recognition experiment are 0.9018 and 0.9895 respectively, apparently higher than that of other methods, revealing the advantages of the proposed method.

Deep-learning (DL)-based change detection (CD) techniques have recently become increasingly complex to produce more accurate detection results. However, the increase in complexity leads to reduced efficiency and limits the application of DL-based CD techniques in domains that require real-time performance. To this end, a lightweight CD network (LCDNet) is proposed to accurately recognize changes in remote-sensing (RS) image pairs while maintaining high efficiency. First, a focus module is utilized at the beginning of the encoding layer for the downsampling operation, which reduces the computation of the model and the loss of information. Then, a depthwise (DW) convolution-based efficient extraction block (EEB) is designed by stacking different sizes of convolution kernels for the effective extraction of change features under different receptive fields. Next, a dual-attention guidance module (DAGM) is designed to guide the encoder in processing and selectively aggregating information related to changes. Lastly, a multiscale feature fusion module (MFFM) with low parameters is proposed that combines feature maps of different scales to exploit their complementary information. Compared with other state-of-the-art (SOTA) methods, the proposed LCDNet only requires approximately 0.83 M Params, 2.03 G FLOPs, and 3.03 ms inference time (It) to remarkably surpass them in terms of accuracy. Moreover, compared with other dual-attention and multiscale fusion modules, the proposed DAGM and MFFM are more effective and efficient. The source code will be made available at https://github.com/sjl2023/LCDNet .

Change detection (CD) is a major topic in remote sensing research. Deep learning (DL) based CD methods have made great progress. However, existing CD methods have difficulty in exploiting the different semantic and detailed information in deep and shallow features, which often leads to blurred target boundaries of identified changes. In addition, most CD methods based on the NestedUNet structure focus on improving accuracy, ignoring the importance of efficiency. Therefore, in this paper, an adaptive fusion NestedUNet for CD (AFNUNet) is proposed. AFNUNet compresses the model parameters and computational cost by using the encoder based on the inverted bottleneck structure and the decoder based on the depthwise convolution. The correlation between the final multi-level feature maps extracted by NestedUNet is difficult to model by summation or concatenation. Therefore, an attention mechanism-based adaptive fusion module (AFM) is proposed. The AFM allows the network to adaptively select feature information from the final different layers of features extracted from NestedUNet in both channel and spatial dimensions so that the fused features capture deep rich semantic information while retaining detailed information at shallow boundaries. Finally, a loss function based on the Bray-Curtis distance is introduced for suppressing the sample imbalance problem. Extensive experiments on the WHU-CD, LEVIR-CD, and SYSU-CD datasets demonstrate that AFNUNet surpasses several state-of-the-art (SOTA) CD methods in terms of effectiveness. Moreover, the proposed AFNUNet remarkably reduces Params and FLOPs by 63% and 70% compared to other NestedUNet-based CD models.

Multi-resolution feature fusion DCF (Discriminative Correlation Filter) methods have significantly advanced the object tracking performance. However, careless choice and fusion of sample features make the algorithm susceptible to interference, leading to tracking failure. Some trackers embed the re-detection module to remedy tracking failures, yet distinguishing ability and stability of the sample features are scarcely considered when training the detector, resulting in low effectiveness detection. Firstly, this paper proposes a criterion of feature tracking reliability and conduct a novel feature adaptive fusion framework. The feature tracking reliability criterion is proposed to evaluate the robustness and distinguishing ability of the sample features. Secondly, a re-detection module is proposed to further avoid tracking failures and increase the accuracy of target re-detection. The re-detection module consists of multiple SVM detectors trained by different sample features. When the tracking fails, the SVM detector trained by the most reliable sample feature will be activated to recover the target and adjust the target position. Finally, comparison experiments on OTB2015 and UAV123 databases demonstrate the accuracy and robustness of the proposed method.