Salp swarm algorithm (SSA) is a newly developed meta-heuristic algorithm, which is mainly developed based on the swarming behavior of salps sailing and foraging in the ocean. An improved salp swarm-based optimizer is proposed in this paper to overcome the potential shortcomings of original SSA, including being easily trapped in local or deceptive optima and its slow convergence rates in dealing with some high-dimensional and multimodal landscapes. The designed variant is called CMSSA that combines two strategies simultaneously. First, a chaotic exploitative mechanism with ''shrinking'' mode is introduced into the basic SSA to improve the exploitative tendencies of the algorithm. Then, a combined mutation scheme is adapted to make full use of the strong intensification capabilities of Gaussian mutation and the strong exploratory leanings of Cauchy mutation. In addition, the embedded strategies can achieve a more stable equilibrium between the core searching patterns of the SSA, which are diversification and intensification. We thoroughly studied the optimization advantages of the improved CMSSA using several representative benchmark cases, including unimodal, multimodal, and fixed-dimension multimodal functions, and three well-regarded engineering cases. The obtained experimental results, statistical tests, and comparative simulations indicate that the exploratory and exploitative proclivities of the SSA and its convergence patterns are vividly improved. The results indicate that the proposed CMSSA is a promising algorithm and shows superior efficacy compared with other algorithms.

No abstract

No abstract

As 4-sensor line scan camera technology has matured, red (R), green (G), blue (B), and near-infrared (RGB-NIR) datasets have begun to appear in large numbers. The RGB-NIR data contain the rich color features of the RGB image and the sharp edge features of the NIR image. At present, in many studies, the RGB-NIR data are input directly into the processing algorithms for calculation of the 4D data; in these cases, redundant information is included, and the high correlation between the bands results in an inability to fully exploit the characteristics of the RGB-NIR data. In this paper, we propose a double-channel convolutional neural network (CNN) algorithm that takes into account the strong correlation between the R, G, and B bands in aerial images and the weaker correlation between the NIR band and the R, G, and B bands. First, the features of the RGB and NIR bands are calculated in two different CNN networks, and subsequently, feature fusion is performed in the fully connected layer. This is followed by the classification. By combining the two neural networks of RGB-CNN and NIR-CNN, the respective characteristics of the RGB-NIR data are fully exploited. INDEX TERMS Multi-spectral, CNN, RGB-NIR, double-channel CNN.

This paper presents three open-source reinforcement learning environments developed on the MuJoCo physics engine with the Franka Emika Panda arm in MuJoCo Menagerie. Three representative tasks, push, slide, and pick-and-place, are implemented through the Gymnasium Robotics API, which inherits from the core of Gymnasium. Both the sparse binary and dense rewards are supported, and the observation space contains the keys of desired and achieved goals to follow the Multi-Goal Reinforcement Learning framework. Three different offpolicy algorithms are used to validate the simulation attributes to ensure the fidelity of all tasks, and benchmark results are also given. Each environment and task are defined in a clean way, and the main parameters for modifying the environment are preserved to reflect the main difference. The repository, including all environments, is available at https://github.com/ zichunxx/panda mujoco gym.