Search

To solve the problems of empiricism, subjectivity and randomness in the manual layout of human machine interface in wheelhouse, an optimization layout design method of human machine interface that combines virtual simulation and optimization algorithm is proposed. First, the optimal operating point and the operating comfort of each area of the human machine interface are obtained through virtual simulation. Then, the layout criteria and ergonomics criteria of human machine interface are quantified as objective functions and constraints, a layout optimization mathematical model of human machine interface is established, and a large number of initial positions of the particles in the particle swarm optimization (PSO) algorithm are obtained through the differential evolution algorithm. Finally, the optimal layout scheme is obtained, and virtual simulation evaluation is conducted. Taking a control panel as an example for layout optimization and virtual simulation, the optimal layout scheme obtained is proved to satisfy ergonomic criteria, and the performance of the human machine interface has been improved. This paper can provide references for the layout design of the high performance human machine interface in wheelhouse.

Detecting wildfires presents significant challenges due to the presence of various potential targets in fire imagery, such as smoke, vehicles, and people. To address these challenges, we propose a novel multi-label classification model based on BiFormer's feature extraction method, which constructs sparse region-indexing relations and performs feature extraction only in key regions, thereby facilitating more effective capture of flame characteristics. Additionally, we introduce a feature screening method based on a domain-adversarial neural network (DANN) to minimize misclassification by accurately determining feature domains. Furthermore, a feature discrimination method utilizing a Graph Convolutional Network (GCN) is proposed, enabling the model to capture label correlations more effectively and improve performance by constructing a label correlation matrix. This model enhances cross-domain generalization capability and improves recognition performance in fire scenarios. In the experimental phase, we developed a comprehensive dataset by integrating multiple fire-related public datasets, and conducted detailed comparison and ablation experiments. Results from the tenfold cross-validation demonstrate that the proposed model significantly improves recognition of multi-labeled images in fire scenarios. Compared with the baseline model, the mAP increased by 4.426%, CP by 4.14% and CF1 by 7.04%. [ABSTRACT FROM AUTHOR]

The composition of microtubules involving several steps, including the polymerization and depolymerization of α-tubulin and β-tubulin heterodimers. Microtubule-targeting agents can increase or inhibit microtubule polymerization, thereby disrupting the dynamic process and stalling cells in G2/M phase. Microtubule-targeting agents are generally cytotoxic, which neurological toxicity being one of the significant adverse events associated. We recently reported a novel 5-arylalkynyl-2-benzoyl thiophene (PST-3) that exhibited broad-spectrum cellular cytotoxicity and in vivo potency with high safety. PST-3 was a substrate of p-gp, which could not cross the blood-brain barrier and lead to less neurotoxicity. The antitumor activities in vitro demonstrated that PST-3 combined with the colchicine-binding site on microtubule, induces morphological changes, disrupts microtubule networks, inhibits polymerization of tubulin, arrests breast cancer cells in the G2/M phase of the cell cycle and induces apoptosis. Evaluation of the antitumor effect in vivo demonstrated that PST-3 elicited MDA-MB-468 tumor %T/C of 11.75%, whereas elicited MCF7 tumor %T/C of 44.38% in breast cancer xenograft models. Besides, in vivo experiments of a higher dose (60 mg/kg) of PST-3 treatment for 21 days did not produce any significant neurotoxicity. These results provide evidence that PST-3 might possess the potential to be developed into a new microtubule inhibitor without neurological toxicity., Competing Interests: None., (AJCR Copyright © 2022.)