检索结果-南通市图书馆

SEFormer:A lightweight CNN-Transformer Based on Separable Multiscale Depthwise Convolution and Efficient Self-Attention for Rotating Machinery Fault Diagnosis

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 1417-1437页

作者： Hongxing Wang Xilai ju Hua Zhu Huafeng li State Key Laboratory of Mechanics and Control for Aerospace Structures Nanjing University of Aeronautics and AstronauticsNanjing210016China School of Computer Science and Engineering Nanyang Technological UniversitySingapore639798Singapore

Traditional data-driven fault diagnosis methods depend on expert experience to manually extract effective fault features of signals,which has certain ***,deep learning techniques have gained prominence as a central focus of research in the field of fault diagnosis by strong fault feature extraction ability and end-to-end fault diagnosis ***,utilizing the respective advantages of convolution neural network(CNN)and Transformer in local and global feature extraction,research on cooperating the two have demonstrated promise in the field of fault ***,the cross-channel convolution mechanism in CNN and the self-attention calculations in Transformer contribute to excessive complexity in the cooperative *** complexity results in high computational costs and limited industrial *** tackle the above challenges,this paper proposes a lightweight CNN-Transformer named as SEFormer for rotating machinery fault ***,a separable multiscale depthwise convolution block is designed to extract and integrate multiscale feature information from different channel dimensions of vibration ***,an efficient self-attention block is developed to capture critical fine-grained features of the signal from a global ***,experimental results on the planetary gearbox dataset and themotor roller bearing dataset prove that the proposed framework can balance the advantages of robustness,generalization and lightweight compared to recent state-of-the-art fault diagnosis models based on CNN and *** study presents a feasible strategy for developing a lightweight rotating machinery fault diagnosis framework aimed at economical deployment.

关键词： CNN-Transformer separable multiscale depthwise convolution efficient self-attention fault diagnosis

Optimizing Fine-Tuning in Quantized Language Models:An In-Depth Analysis of Key Variables

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2025年第1期82卷 307-325页

作者： Ao shen Zhiquan Lai Dongsheng li Xiaoyu Hu National Key Laboratory of Parallel and Distributed Computing National University of Defense TechnologyChangsha410073China Strategic Assessments and Consultation Institute Academy of Military ScienceBeijing100091China

Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning *** this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader ***-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational *** these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA *** these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains *** study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM *** investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do *** insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized ***,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller *** study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM

关键词： Large-scale Language Model Parameter-Efficient Fine-Tuning parameter quantization key variable trainable parameters experimental analysis

A Rapid Adaptation Approach for Dynamic Air‑Writing Recognition Using Wearable Wristbands with Self‑Supervised Contrastive Learning

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第2期17卷 417-431页

作者： Yunjian Guo Kunpeng li Wei Yue Nam‑Young Kim Yang li Guozhen shen Jong‑Chul Lee Department of Electronic Convergence Engineering Kwangwoon UniversitySeoul 01897South Korea Radio Frequency Integrated Circuit(RFIC)Bio Centre Kwangwoon UniversitySeoul 01897South Korea Department of Electronic Engineering Kwangwoon UniversitySeoul 01897South Korea School of Microelectronics Shandong UniversityJinan 250101People’s Republic of China State Key Laboratory of Integrated Chips and Systems Fudan UniversityShanghai 200433People’s Republic of China School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081People’s Republic of China

Wearable wristband systems leverage deep learning to revolutionize hand gesture recognition in daily *** existing approaches that often focus on static gestures and require extensive labeled data,the proposed wearable wristband with selfsupervised contrastive learning excels at dynamic motion tracking and adapts rapidly across multiple *** features a four-channel sensing array composed of an ionic hydrogel with hierarchical microcone structures and ultrathin flexible electrodes,resulting in high-sensitivity capacitance *** wireless transmission from a Wi-Fi module,the proposed algorithm learns latent features from the unlabeled signals of random wrist ***,only few-shot labeled data are sufficient for fine-tuning the model,enabling rapid adaptation to various *** system achieves a high accuracy of 94.9%in different scenarios,including the prediction of eight-direction commands,and air-writing of all numbers and *** proposed method facilitates smooth transitions between multiple tasks without the need for modifying the structure or undergoing extensive task-specific *** utility has been further extended to enhance human–machine interaction over digital platforms,such as game controls,calculators,and three-language login systems,offering users a natural and intuitive way of communication.

关键词： Wearable wristband Self-supervised contrastive learning Dynamic gesture Air-writing Human-machine interaction

Investigation of bubbles escape behavior from low basicity mold flux for high-Mn high-Al steels using 3D X-ray microscope

在线全文

学校读者我要写书评

暂无评论

International Journal of Minerals,Metallurgy and Materials 2025年第1期32卷 102-110页

作者： Qiang liu Xiang li shen Du Ming Gao Yanbin Yin Jiongming Zhang State Key Laboratory of Advanced Metallurgy University of Science and Technology BeijingBeijing 100083China

During the continuous casting process of high-Mn high-Al steels,various types of gases such as Ar need to escape through the top of the *** which,the behavior of bubbles traversing the liquid slag serves as a restrictive link,closely associated with viscosity and the thickness of liquid *** contrast to two-dimensional surface observation,three-dimensional(3D)analysis method can offer a more intuitive,accurate,and comprehensive ***,this study employs a 3D X-ray microscope(3D-XRM)to obtained spatial distribution and 3D morphological characteristics of residual bubbles in mold flux under different basicity of liquid slag,different temperatures,and different holding *** results indicate that as basicity of slag increases from 0.52 to 1.03,temperature increases from 1423 to 1573 K,the viscosity of slag decreases,the floating rate of bubbles *** addition,when holding time increases from 10 to 30 s,the bubbles floating distance increases,and the volume fraction and average equivalent sphere diameter of the bubbles solidified in the mold flux gradually *** one word,increasing the basicity,temperature,and holding time leading to an increase in the removal rate of bubbles especially for the *** findings of bubbles escape behavior provide valuable insights into optimizing low basicity mold flux for high-Mn high-Al steels.

关键词： mold flux low basicity bubbles three-dimensional X-ray microscope viscosity

Potential role and therapeutic implications of glutathione peroxidase 4 in the treatment of Alzheimer's disease

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 613-631页

作者： Yanxin shen Guimei Zhang Chunxiao Wei Panpan Zhao Yongchun Wang Mingxi li li Sun Department of Neurology and Neuroscience Center The First Hospital of Jilin UniversityJilin UniversityChangchunJilin ProvinceChina Cognitive Impairment Center Department of NeurologyThe First Hospital of Jilin UniversityJilin UniversityChangchunJilin ProvinceChina

Alzheimer's disease is an age-related neurodegenerative disorder with a complex and incompletely understood pathogenesis. Despite extensive research, a cure for Alzheimer's disease has not yet been found. Oxidative stress mediates excessive oxidative responses, and its involvement in Alzheimer's disease pathogenesis as a primary or secondary pathological event is widely accepted. As a member of the selenium-containing antioxidant enzyme family, glutathione peroxidase 4 reduces esterified phospholipid hydroperoxides to maintain cellular redox homeostasis. With the discovery of ferroptosis, the central role of glutathione peroxidase 4 in anti-lipid peroxidation in several diseases, including Alzheimer's disease, has received widespread attention. Increasing evidence suggests that glutathione peroxidase 4 expression is inhibited in the Alzheimer's disease brain, resulting in oxidative stress, inflammation, ferroptosis, and apoptosis, which are closely associated with pathological damage in Alzheimer's disease. Several therapeutic approaches, such as small molecule drugs, natural plant products, and non-pharmacological treatments, ameliorate pathological damage and cognitive function in Alzheimer's disease by promoting glutathione peroxidase 4 expression and enhancing glutathione peroxidase 4 activity. Therefore, glutathione peroxidase 4 upregulation may be a promising strategy for the treatment of Alzheimer's disease. This review provides an overview of the gene structure, biological functions, and regulatory mechanisms of glutathione peroxidase 4, a discussion on the important role of glutathione peroxidase 4 in pathological events closely related to Alzheimer's disease, and a summary of the advances in small-molecule drugs, natural plant products, and non-pharmacological therapies targeting glutathione peroxidase 4 for the treatment of Alzheimer's disease. Most prior studies on this subject used animal models, and relevant clinical studies are lacking. Future clinica

关键词： apoptosis ferroptosis inflammation lipid peroxidation natural plant products neurodegenerative disorder neuroprotection oxidative stress small-molecule drugs

Photo‑Energized MoS_(2)/CNT Cathode for High‑Performance li–CO_(2)Batteries in a Wide‑Temperature Range

在线全文

学校读者我要写书评

暂无评论

Nano-Micro Letters 2025年第1期17卷 160-175页

作者： Tingsong Hu Wenyi lian Kang Hu Qiuju li Xueliang Cui Tengyu Yao Laifa shen Jiangsu Key Laboratory of Materials and Technologies for Energy Storage College of Materials Science and TechnologyNanjing University of Aeronautics and AstronauticsNanjing 210016People’s Republic of China

li–CO_(2) batteries are considered promising energy storage systems in extreme environments such as Mars;however,severe performance degradation will occur at a subzero temperature owning to the sluggish reaction ***,a photo-energized strategy adopting sustainable solar energy in wide working temperature range li–CO_(2) battery was achieved with a binder-free MoS_(2)/carbon nanotube(CNT)photo-electrode as *** unique layered structure and excellent photoelectric properties of MoS_(2) facilitate the abundant generation and rapid transfer of photo-excited carriers,which accelerate the CO_(2) reduction and li_(2)CO_(3) decomposition upon *** illuminated battery at room temperature exhibited high discharge voltage of 2.95 V and mitigated charge voltage of 3.27 V,attaining superior energy efficiency of 90.2%and excellent cycling stability of over 120 *** at an extremely low temperature of−30℃,the battery with same electrolyte can still deliver a small polarization of 0.45 V by the photoelectric and photothermal synergistic mechanism of MoS_(2)/CNT *** work demonstrates the promising potential of the photo-energized wide working temperature range li–CO_(2) battery in addressing the obstacle of charge overpotential and energy efficiency.

关键词： li-CO_(2)batteries Photo-energized Wide operation-temperature Kinetics MoS_(2)

Maintaining moderate levels of hypochlorous acid promotes neural stem cell proliferation and differentiation in the recovery phase of stroke

在线全文

学校读者我要写书评

暂无评论

Neural Regeneration Research 2025年第3期20卷 845-857页

作者： lin-Yan Huang Yi-De Zhang Jie Chen Hai-Di Fan Wan Wang Bin Wang ju-Yun Ma Peng-Peng li Hai-Wei Pu Xin-Yian Guo Jian-Gang shen Su-Hua Qi School of Medical Technology Xuzhou Key Laboratory of Laboratory DiagnosticsXuzhou Medical UniversityXuzhouJiangsu ProvinceChina School of Pharmacy Xuzhou Medical UniversityXuzhouJiangsu ProvinceChina Department of Laboratory Medicine Branch Hospital of Huai’an First People’s HospitalHuai’anJiangsu ProvinceChina Department of Laboratory Medicine the Affiliated Hospital of Xuzhou Medical UniversityXuzhouJiangsu ProvinceChina School of Chinese Medicine The University of Hong KongHong Kong Special Administrative RegionChina

It has been shown clinically that continuous removal of ischemia/reperfusion-induced reactive oxygen species is not conducive to the recovery of late ***,previous studies have shown that excessive increases in hypochlorous acid after stroke can cause severe damage to brain *** previous studies have found that a small amount of hypochlorous acid still exists in the later stage of stroke,but its specific role and mechanism are currently *** simulate stroke in vivo,a middle cerebral artery occlusion rat model was established,with an oxygen-glucose deprivation/reoxygenation model established in vitro to mimic *** found that in the early stage(within 24 hours)of ischemic stroke,neutrophils produced a large amount of hypochlorous acid,while in the recovery phase(10 days after stroke),microglia were activated and produced a small amount of hypochlorous ***,in acute stroke in rats,hypochlorous acid production was prevented using a hypochlorous acid scavenger,taurine,or myeloperoxidase inhibitor,4-aminobenzoic acid *** results showed that high levels of hypochlorous acid(200μM)induced neuronal apoptosis after oxygen/glucose deprivation/***,in the recovery phase of the middle cerebral artery occlusion model,a moderate level of hypochlorous acid promoted the proliferation and differentiation of neural stem cells into neurons and *** suggests that hypochlorous acid plays different roles at different phases of cerebral ischemia/reperfusion *** levels of hypochlorous acid(5 and 100μM)promoted nuclear translocation ofβ-*** transfection of single-site mutation plasmids,we found that hypochlorous acid induced chlorination of theβ-catenin tyrosine 30 residue,which promoted nuclear ***,our study indicates that maintaining low levels of hypochlorous acid plays a key role in the recovery of neurological function.

关键词： cell differentiation cerebral ischemia/reperfusion injury chlorination hypochlorous acid microglia neural stem cell neurogenesis nuclear translocation stroke β-catenin

Unraveling post-growth mechanisms of monolayer CsPbBr3 nanocubes:Laser-enhanced transformations and cathodoluminescence-electron microscopy correlations

在线全文

学校读者我要写书评

暂无评论

Journal of Energy Chemistry 2025年第1期100卷 146-156页

作者： Mingxing li Xiaoge Wang Xiaofan Cao Zhiqun He Chunjun liang Mingxing Chen Jing ju Fangtian You Key Laboratory of Luminescence and Optical Information Ministry of Education Institute of Optoelectronic Technology Beijing Jiaotong University Beijing National Laboratory for Molecular Sciences (BNLMS) College of Chemistry and Molecular Engineering Peking University

Lead-halide perovskite nanoparticles（LHP NPs） are highly promising materials for next-generation displays and solid-state lighting due to their exceptional optical properties. However, their inherent instability presents a significant challenge. Recent advances have demonstrated that optoelectronic devices based on monolayer nanoparticle films exhibit both high luminescence efficiency and long-term *** research demonstrates that mobility limitations and anisotropic alignments in CsPbBr3nanocube monolayer films are key to their stabilization, hindering spontaneous growth through face-to-face fusion and resulting in the formation of connecting necks in a diagonal direction. Introducing laser irradiation confirmed this by significantly accelerating nanocubes growth, increasing mobility, and enhancing local structural ordering, leading to larger and more regularly shaped nanosheets. Fourier transform infrared spectroscopy and energy dispersive spectroscopy line-scan analyses indicated that laser irradiation did not disrupt the ligand structure. Transmission electron microscopy and correlative cathodoluminescence electron microscopy revealed the effects of post-growth and heterogeneous structures, including enhanced luminescence and inhomogeneous intensity in the nanosheets. These findings deepen the understanding of the post-growth mechanism of monolayer nanoparticles and the structure-emission correlation and highlight the unique role of laser irradiation in directing the formation of well-defined and regular nanostructures.

关键词： Energy dispersive spectroscopy

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

破碎岩体巷道变形破坏特征的数值模拟研究

采矿与安全工程学报 2011年第1期28卷 39-44页

作者：李慎举王连国陆银龙霍州煤电集团公司山西霍州031400 中国矿业大学深部岩土力学与地下工程国家重点实验室江苏徐州221008

为了研究岩体节理裂隙分布规律对巷道围岩稳定性的影响,依据概率与统计理论建立了破碎岩体结构面产状、规模和密度的概率模型,并运用Monte-Carlo随机模拟方法生成了可以描述和表征破碎岩体及其裂隙结构信息的二维结构面网络模型.在此基... 详细信息

为了研究岩体节理裂隙分布规律对巷道围岩稳定性的影响,依据概率与统计理论建立了破碎岩体结构面产状、规模和密度的概率模型,并运用Monte-Carlo随机模拟方法生成了可以描述和表征破碎岩体及其裂隙结构信息的二维结构面网络模型.在此基础上,建立了破碎岩体条件下巷道围岩结构的离散元数值计算模型,分析了块状型和破碎型围岩的应力状态、塑性区分布以及变形特征.研究结果表明:岩体结构面分布的尺度和规模对巷道围岩的应力状态有较大影响,破碎型围岩的承载能力明显低于块状型围岩;破碎岩体变形不再是岩体材料的本质属性,而是破裂块体之间的镶嵌组合的一种结构效应.

关键词：破碎岩体二维结构面网络离散元巷道变形破坏特征