Search

Maritime objects frequently exhibit low-quality and insufficient feature information, particularly in complex maritime environments characterized by challenges such as small objects, waves, and reflections. This situation poses significant challenges to the development of reliable object detection including the strategies of loss function and the feature understanding capabilities in common YOLOv8 (You Only Look Once) detectors. Furthermore, the widespread adoption and unmanned operation of intelligent ships have generated increasing demands on the computational efficiency and cost of object detection hardware, necessitating the development of more lightweight network architectures. This study proposes the EL-YOLO (Efficient Lightweight You Only Look Once) algorithm based on YOLOv8, designed specifically for intelligent ship object detection. EL-YOLO incorporates novel features, including adequate wise IoU (AWIoU) for improved bounding box regression, shortcut multi-fuse neck (SMFN) for a comprehensive analysis of features, and greedy-driven filter pruning (GDFP) to achieve a streamlined and lightweight network design. The findings of this study demonstrate notable advancements in both detection accuracy and lightweight characteristics across diverse maritime scenarios. EL-YOLO exhibits superior performance in intelligent ship object detection using RGB cameras, showcasing a significant improvement compared to standard YOLOv8 models. [ABSTRACT FROM AUTHOR]

Various amplification mechanisms have been developed to extend the travel range of compliant mechanisms. For the serial design of these mechanisms and the neglection of the deflection of the link lever, the modeling errors are accumulated and contribute to a large deviation in the design performance. A stiffness-adjustable micro-motion is proposed in this work to offset the gaps between the design values and actual performance by utilizing the nonlinearity of corner-fillet leaf spring (CFLS). Simplified stiffness formulas of the right circular flexure hinge (RCFH) and fixed-guided CFLS are provided for easy design. The accurate model is built for the calculation of the amplification ratio by taking the deflection of the link lever and adjustment mechanism into account. The adjustment performance of the proposed mechanism is modeled by utilizing the nonlinear deflection. The design models are verified using finite element analysis (FEA) which presents a good agreement. Experimental investigations are carried out to illustrate the adjustment performance of the proposed micro-motion stage. [ABSTRACT FROM AUTHOR]

A precise motion control for compliant mechanisms hinges on an accurate kinematics model, particularly when dealing with intricate nonlinear coupled mechanisms. The motivation driving this research lies in leveraging existing knowledge to direct traditional neural networks (NN) in acquiring a nonlinear kinematics model (grey box), even with a limited dataset. Within this study, the 3-RRR (Revolute-Revolute-Revolute) flexure mechanism was selected due to its inherent nonlinear multi-input multi-output (MIMO) configuration. In relation to this type of flexure mechanism, the convolutional modeling approach based on compliance matrix theory aptly captures the relationship between inputs and outputs. Nonetheless, its linearity poses challenges in achieving utmost precision. In contrast, the NN modeling technique (black box) excels in accurately fitting kinematics models, yet its reliance on extensive data samples hinders practical engineering applications. To achieve a finely-tuned nonlinear kinematic model with a minimal dataset, theoretical prior knowledge serves as a guiding force for the NN to discern the intricate kinematic correlations within the 3-RRR nanopositioner. In-depth, the grey-box network’s training process is steered by a refined learning rate, tailored through convolutional modeling theory (adaptive learning rate). Ultimately, the validation outcomes underscore a substantial enhancement in modeling accuracy. [ABSTRACT FROM AUTHOR]

Ferroptosis is a newly defined form of regulated cell death characterized by the iron-dependent accumulation of lipid hydroperoxides. Erastin, the ferroptosis activator, binds to voltage-dependent anion channels VDAC2 and VDCA3, but treatment with erastin can result in the degradation of the channels. Here, the authors show that Nedd4 is induced following erastin treatment, which leads to the ubiquitination and subsequent degradation of the channels. Depletion of Nedd4 limits the protein degradation of VDAC2/3, which increases the sensitivity of cancer cells to erastin. By understanding the molecular mechanism of erastin-induced cellular resistance, we can discover how cells adapt to new molecules to maintain homeostasis. Furthermore, erastin-induced resistance mediated by FOXM1-Nedd4-VDAC2/3 negative feedback loop provides an initial framework for creating avenues to overcome the drug resistance of ferroptosis activators. Erastin, the ferroptosis activator, binds to voltage gated ion channels CDAC2 and VDCA3 but treatment with erastin can result in the degradation of the channels. Here, the authors show that Nedd4 is induced following erastin treatment, which leads to the ubiquitination and subsequent degradation of the channels. [ABSTRACT FROM AUTHOR]