In order to improve the recognition accuracy of partial discharge (PD) by making full use of the time-frequency characteristics of PD signals and employing deep learning theory, a kind of PD pattern recognition method based on variational mode decompositon (VMD)-Choi-Williams distribution (CWD) spectrum and optimized convolutional neural network (CNN) with cross-layer feature fusion is proposed in this paper. Firstly, a PD signal is decomposed into several components by VMD algorithm, and the CWD analysis of the obtained components is carried out to obtain the VMD-CWD time-frequency spectrum. Secondly, the cross-layer feature fusion and optimization CNN (CFFO-CNN) is constructed by introducing cross-layer connection and optimization algorithm. Thirdly, the VMD-CWD is regarded as the input vector to train CFFO-CNN to learn and extract the intrinsic features of the spectrum. Finally, the trained network is used to recognize the PD types of the test samples. The proposed method is compared with traditional recognition methods such as BP neural network (BPNN) and support vector machine (SVM), as well as some commonly used deep learning algorithms. The experimental results indicate that the recognition performance of the proposed method is significantly better than that of existing recognition methods with accuracy up to 99.5%. It is proved that CFFO-CNN has superior feature extraction ability, which can extract the internal features of the VMD-CWD spectrum independently with higher recognition accuracy and wider application prospect. INDEX TERMS Variational mode decomposition (VMD), Choi-Williams distribution (CWD), feature fusion, convolutional neural network (CNN), partial discharge, pattern recognition.
Face masks, which serve as personal protection equipment, have become ubiquitous for combating the ongoing COVID-19. However, conventional electrostatic-based mask filters are disposable and short-term effective with high breathing resistance, causing respiratory ailments and massive consumption (129 billion monthly), intensifying global environmental pollution. In an effort to address these challenges, the introduction of a piezoelectric polymer was adopted to realize the charge-laden melt-blown via the melt-blowing method. The charge-laden melt-blown could be applied to manufacture face masks and to generate charges triggered by mechanical and acoustic energy originated from daily speaking. Through an efficient and scalable industrial melt-blown process, our charge-laden mask is capable of overcoming the inevitable electrostatic attenuation, even in a high-humidity atmosphere by long-wearing (prolonging from 4 to 72 h) and three-cycle common decontamination methods. Combined with outstanding protective properties (PM 2.5 filtration efficiency >99.9%), breathability (differential pressure <17 Pa/cm 2 ), and mechanical strength, the resultant charge-laden mask could enable the decreased replacement of masks, thereby lowering to 94.4% of output masks worldwide (∼122 billion monthly) without substituting the existing structure or assembling process.
Herein, we report a remotely controlled soft robot employing a photoresponsive nanocomposite synthesized from liquid crystal elastomers (LCEs), high elastic form-stable phase change polymer (HEPCP), and multiwalled carbon nanotubes (MWCNTs). Possessing a two-stage deformation upon exposure to near-infrared (NIR) light, the LCE/HEPCP/MWCNT (LHM) nanocomposite allows the soft robot to exhibit an obvious, fast, and reversible shape change with low detection limitations. In addition to the deformation and bending of the LCE molecular chains itself, the HEPCP in the composite material can also be triggered by a reversible solid–liquid transition due to the temperature rise caused by MWCNTs, which further promotes the change of the LCE. In particular, the proposed photodriven LHM soft robot can bend up to 180° in 2 s upon NIR stimulation (320 mW, distance of 5 cm) and generate recoverable, dramatic, and sensitive deformation to execute various tasks including walking, twisting, and bending. With the capacity of imitating biological behaviors through remote control, the disruptive innovation developed here offers a promising path toward miniaturized untethered robotic systems.
Published data on the association between three polymorphisms (Lys939Gln, Ala499Val, and PAT±) of Xeroderma Pigmentosum group C (XPC) and breast cancer risk are inconclusive. To derive a more precise estimation of the relationship, a meta-analysis was performed. Crude ORs with 95% CIs were used to assess the strength of association between them. A total of 11 studies including 5,090 cases and 5,214 controls were involved in this meta-analysis. For XPC Lys939Gln polymorphism, no obvious associations were found for all genetic models when all studies were pooled into the meta-analysis (Lys/Gln vs. Lys/Lys: OR = 1.00, 95% CI 0.92-1.10; Gln/Gln vs. Lys/Lys: OR = 0.96, 95% CI 0.84-1.09; dominant model: OR = 0.99, 95% CI 0.91-1.08; and recessive model: OR = 0.97, 95% CI 0.86-1.09). In the subgroup analysis by ethnicity or study design, still no obvious associations were found. For XPC Ala499Val polymorphism, also no obvious associations were found for all genetic models when all studies were pooled into the meta-analysis (Val/Ala vs. Ala/Ala: OR = 0.91, 95% CI 0.79-1.05; Val/Val vs. Ala/Ala: OR = 1.07, 95% CI 0.80-1.44; dominant model: OR = 0.93, 95% CI 0.81-1.06; and recessive model: OR = 1.11, 95% CI 0.84-1.48). For XPC PAT± polymorphism, obvious associations were found for recessive model when all studies were pooled into the meta-analysis (OR = 1.41, 95% CI 1.05-1.89). In conclusion, this meta-analysis suggests that the XPC PAT± polymorphism allele may be a low-penetrant risk factor for developing breast cancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.