Automated waterway environment perception is crucial for enabling unmanned surface vessels (USVs) to understand their surroundings and make informed decisions. Most existing waterway perception models primarily focus on instance-level object perception paradigms (e.g., detection, segmentation). However, due to the complexity of waterway environments, current perception datasets and models fail to achieve global semantic understanding of waterways, limiting large-scale monitoring and structured log generation. With the advancement of vision-language models (VLMs), we leverage image captioning to introduce WaterCaption, the first captioning dataset specifically designed for waterway environments. WaterCaption focuses on fine-grained, multi-region long-text descriptions, providing a new research direction for visual geo-understanding and spatial scene cognition. Exactly, it includes 20.2k image-text pair data with 1.8 million vocabulary size. Additionally, we propose Da Yu, an edge-deployable multi-modal large language model for USVs, where we propose a novel vision-to-language projector called Nano Transformer Adaptor (NTA). NTA effectively balances computational efficiency with the capacity for both global and fine-grained local modeling of visual features, thereby significantly enhancing the model’s ability to generate long-form textual outputs. Da Yu achieves an optimal balance between performance and efficiency, surpassing state-of-the-art models on WaterCaption and several other captioning benchmarks. The project is available at https://github.com/GuanRunwei/WaterCaption.

Reconfigurable Intelligent Surfaces (RISs) and Non-Orthogonal Multiple Access (NOMA) can enhance Visible Light Communication (VLC) systems by mitigating signal blockage and improving spectrum utilization. While boosting communication efficiency is crucial, maintaining high illumination quality is equally important. This paper investigates a novel approach to simultaneously improving the sum rate (SR) and illumination uniformity (IU) in a RIS-assisted NOMA-based VLC system. Communication and illumination optimization problems are formulated as a non-convex mixed-integer non-linear programming problem, considering RIS placement, LED-user association, and power allocation. To the best of our knowledge, this is the first work to jointly optimize SR and IU with explicit consideration of RIS placement. We propose a joint optimization approach that leverages a differential evolution algorithm to optimize RIS placement. During each iteration, the obtained solutions are further refined using a block coordinate descent algorithm, which iteratively solves the decomposed sub-problems of LED-user association and power allocation. Simulation results show that the approach outperforms existing methods in both SR and IU. Moreover, RIS placement optimization is shown to be crucial, as neglecting it significantly degrades performance. Finally, the impacts of noise power and total LED power are analyzed, offering practical insights for parameter selection in VLC systems.

Federated learning (FL) is a decentralized learning paradigm wherein a central server iteratively trains a global model by utilizing clients who possess a certain amount of private datasets. The main challenge of FL lies in the fact that the client-side private data may not be identically and independently distributed (Non-IID), significantly impacting the accuracy of the global model. Existing methods tend to overlook analysis and utilize the characteristics of data complementary among clients due to privacy constraints. Intuitively, utilizing statistical distinctions among private data on the client side can help mitigate the Non-IID degree. Besides, the recent advancements in dataset condensation technology have inspired us to investigate its potential applicability in addressing Non-IID issues while maintaining privacy. Motivated by this, we propose DCFL which divides clients into groups by using weight similarity measurement method, like Centered Kernel Alignment (CKA), to approximate and represent data similarity. The private data from clients within the same group be complementary and then can use dataset condensation methods with Non-IID awareness to complement clients. Additionally, filtering mechanism, data enhancement techniques are incorporated to efficiently utilize condensed data, enhance model performance, and minimize communication time. Experimental results demonstrate that DCFL achieves competitive performance on popular federated learning benchmarks including MNIST, Fashion-MNIST, SVHN, and CIFAR-10 with existing FL algorithms.

To further enhance the convergence performance and accuracy of SHADE, a SHADE with tolerance-based multiple topology selection framework (MTT_SHADE) is proposed in this paper. In MTT_SHADE, three population topologies are established employing the k-nearest neighbor network, small-world network, and random network, respectively, and the evolution of individuals depends on the neighborhoods derived from different topologies. The tolerance-based composite framework is proposed to select the appropriate topology for an individual at the same time. Specifically, local tolerance and global tolerance are predetermined, corresponding to the tolerance for individuals and the population, respectively. The topology involved in the evolution of the individual is replaced when the individual does not progress after successive iterations. The population that does not improve in effect after successive iterations are considered to have exceeded the global tolerance and the three population topologies are reconstructed. The CEC2022 competition on single objective bound-constrained numerical optimization and four state-of-the-art DE variants are employed to investigate the effectiveness of the proposed algorithm. Experimental results show that MTT_SHADE is competitive in terms of accuracy and convergence.

Differential evolution (DE), as an extremely powerful evolutionary algorithm, has recently been widely employed within complex reality optimisation problems. However, the DE algorithm mainly focuses on strengthening the adaptability of exploitation, which allows the sensitivity of the DE algorithm to be solved in cases where the effects of solving various types of problems are quite different. Moreover, the local search ability and population diversity have not been solved properly. Therefore, an adaptive DE algorithm using fitness distance correlation and a neighbourhood-based strategy (FNADE) is proposed. FNADE introduces the fitness distance correlation (FDC) as the basis for judging the difficulty of the problem, utilises a Voronoi diagram to increase the population diversity for complex multimodal problems and adopts the neighbourhood-based mutation strategy to strengthen the local search capability. FNADE is committed to solving unconstrained single-objective optimisation problems. The proposed algorithm is compared with six advanced DE algorithms in terms of CEC2017 benchmark functions. The experimental results show that the adaptive DE algorithm using FNADE is superior to other DE algorithms with regard to the accuracy and population diversity of the solution.