Self-supervised zero-shot dehazing network based on dark channel prior.

Most learning-based methods previously used in image dehazing employ a supervised learning strategy, which is time-consuming and requires a large-scale dataset. However, large-scale datasets are difficult to obtain. Here, we propose a self-supervised zero-shot dehazing network (SZDNet) based on dark channel prior, which uses a hazy image generated from the output dehazed image as a pseudo-label to supervise the optimization process of the network.

A method to improve multi-node power transmission efficiency of inductively coupled mooring cable.

The inductively coupled mooring cable is an important tool for monitoring the ocean hydrological data. The mooring cable is an open-loop structure that uses a section of seawater as the transmission medium. The power transmission efficiency of this structure is very low due to the large power loss of the seawater medium, and it is rarely studied.

Prescribed-Time Consensus Tracking of Multiagent Systems With Nonlinear Dynamics Satisfying Time-Varying Lipschitz Growth Rates.

Prescribed-time consensus tracking for second-order nonlinear multiagent systems (MASs) with the unknown nonlinear dynamics satisfying a time-varying Lipschitz growth rate is investigated in this article. A time-varying function is introduced as a part of the controller gains, and it plays an important role in overcoming the rapid growth of nonlinear terms and in ensuring that the consensus can be achieved in a preassigned time. An integral sliding-mode control protocol, which forces the system trajectory to move on to the defined sliding manifold at the initial moment, is proposed for solving the prescribed-time consensus tracking problem of leader-following MASs with disturbances.

Prescribed-time cluster lag consensus control for second-order non-linear leader-following multiagent systems.

Prescribed-time Lag consensus, as a special case of prescribed-time cluster lag consensus, is first investigated. The task is to design a control protocol for each follower so that the multiagent system (MAS) achieves lag consensus in any specified time. To achieve this goal, we propose a new distributed controller, in which the control gains are designed as time-varying functions related to the pre-specified time.