检索结果-内蒙古大学图书馆

Incorporating Lasso Regression to Physics-Informed Neural Network for Inverse PDE Problem

computer Modeling in engineering & sciences 2024年第10期141卷 385-399页

作者： Meng Ma Liu Fu Xu Guo Zhi Zhai National Key Lab of Aerospace Power System and Plasma Technology Xi’an Jiaotong UniversityXi’an710049China School of Mechanical Engineering Xi’an Jiaotong UniversityXi’an710049China Department of Electrical and Computer Engineering University of Massachusetts LowellLowellMA 01854USA

Partial Differential Equation(PDE)is among the most fundamental tools employed to model dynamic *** PDE modeling methods are typically derived from established knowledge and known phenomena,which are time-consuming and ***,discovering governing PDEs from collected actual data via Physics Informed Neural Networks(PINNs)provides a more efficient way to analyze fresh dynamic systems and establish *** study proposes Sequentially Threshold Least Squares-Lasso(STLasso),a module constructed by incorporating Lasso regression into the Sequentially Threshold Least Squares(STLS)algorithm,which can complete sparse regression of PDE coefficients with the constraints of l0 *** further introduces PINN-STLasso,a physics informed neural network combined with Lasso sparse regression,able to find underlying PDEs from data with reduced data requirements and better *** addition,this research conducts experiments on canonical inverse PDE problems and compares the results to several recent *** results demonstrated that the proposed PINN-STLasso outperforms other methods,achieving lower error rates even with less data.

关键词： Physics-informed neural network inverse partial differential equation Lasso regression scientific machine learning

来源：评论

学校读者我要写书评

暂无评论

Game Theory Based Approach for Massive Route Planning in Dynamic Road Networks

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 1-1页

作者： Zhang, Detian Zhou, Yunjun Wang, Jin School of Computer Science and Technology Soochow University Suzhou China School of Future Science and Engineering Soochow University Suzhou China

With the widely use of mobile consumer electronics devices, location-based services becomes more and more popular in our lives, e.g., mapping services and ride-hailing services. Most of location-based services rely on the support of efficient and accurate route planning. However, existing route planning algorithms mainly aim to plan for a single query in dynamic road networks, while ignoring the internal flows caused by massive planned route themselves, i.e., many vehicles may take the same road segments and thus cause traffic congestion and increase the global travel time. Therefore, in this paper, we focus on massive route planning in dynamic road networks to avoid such traffic congestion caused by the internal traffic flows. We first formally define the massive route planning with minimizing the global travel time (MRP-GTT) problem. Then, we prove that the MRP-GTT problem is NP-hard. To effectively solve it, we first design a novel game theory based algorithm (GTA) to reduce the global travel time for massive route queries. Because of the low efficiency of the global gaming for all queries, we then devise a game theory with query clustering algorithm (GTA-QC) in the paper, which first clusters queries based on the source and destination locations of queries, so that only queries in the same cluster can participate in a game to improve gaming efficiency. Extensive experiments on both synthetic and real datasets demonstrate the efficiency and effectiveness of our algorithms. IEEE

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Application of a 3D Sensor as a Vehicle Detector

引用

IEEJ Transactions on Industry Applications 2023年第6期143卷 464-472页

作者： Teng, Lin Watanabe, Nobuhiro Matsuzaki, Hiroaki Izumi, Takashi Lu, xiaofeng Izumi & Teng Lab. Department of Computer Engineering College of Science and Technology Nihon University 7-24-1 Narashinodai Funabashi Chiba274-8501 Japan School of Computer Science and Engineering Xi’an University of Technology Shaanxi Xi’an710048 China

Vehicle detectors are required to operate in various environments. Current detectors employ various types of sensors including ultrasonic, loop coil, and image sensors. However, there exist some problems such as temperature and wind effects, maintenance problems, and accuracy degradation during nighttime. To solve these problems, we propose a vehicle detector that utilizes a 3D sensor based on near infrared laser and Time-of-Flight. This sensor can acquire a three-dimensional image that includes the distance data, unaffected by the external factors mentioned earlier. Therefore, our proposed vehicle detector design can be applied to traffic volume measurement, vehicle classification, multiple lane detection, etc. This paper discusses the application of the proposed vehicle detector in several scenarios. © 2023 The Institute of Electrical Engineers of Japan.

关键词： Volume measurement

来源：评论

学校读者我要写书评

暂无评论

AtomGAN:unsupervised deep learning for fast and accurate defect detection of 2D materials at the atomic scale

引用

science China(Information sciences) 2023年第6期66卷 102-114页

作者： Danpeng CHENG Wuxin SHA Zuo XU Shide LI Zhigao YIN Yuling LANG Shun TANG Yuan-Cheng CAO State Key Laboratory of Advanced Electromagnetic Engineering and Technology School of Electrical and Electronic EngineeringHuazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology CITIC Dicastal Co. Ltd.

The extraction of atomic-level material features from electron microscope images is crucial for studying structure-property relationships and discovering new materials. However, traditional electron microscope analyses rely on time-consuming and complex human operations; thus, they are only applicable to images with a small number of atoms. In addition, the analysis results vary due to observers' individual deviations. Although efforts to introduce automated methods have been performed previously, many of these methods lack sufficient labeled data or require various conditions in the detection process that can only be applied to the target material. Thus, in this study, we developed AtomGAN, which is a robust, unsupervised learning method, that segments defects in classical 2D material systems and the heterostructures of MoS2/WS2automatically. To solve the data scarcity problem, the proposed model is trained on unpaired simulated data that contain point and line defects for MoS2/WS2. The proposed AtomGAN was evaluated on both simulated and real electron microscope images. The results demonstrate that the segmented point defects and line defects are presented perfectly in the resulting figures, with a measurement precision of 96.9%. In addition, the cycled structure of AtomGAN can quickly generate a large number of simulated electron microscope images.

关键词： deep learning generative adversarial network defect detection atomic resolution 2D materials

来源：评论

学校读者我要写书评

暂无评论

A two-stage sign language recognition method focusing on the semantic features of label text 20

A two-stage sign language recognition method focusing on the...

引用

20th CSI International Symposium on Artificial Intelligence and Signal Processing, AISP 2024

作者： Xu, Xuebin Fu, Jun Xi'An University of Posts & Telecommunications School of Computer Science and Technology Xi'an China

ISBN: (纸本)9798350383942

The ability to recognize sign language is an indispensable technology that plays a crucial role in facilitating communication between individuals who are deaf or hard of hearing. It is of utmost importance to comprehensively understand the nonverbal expressions employed by the hearing impaired. In order to enhance the efficacy of sign language recognition technology, it is imperative to focus on language modeling and improve the utilization of linguistic elements. At present, much attention in sign language recognition techniques that integrate language modeling is directed toward the translation of GLOSS to text in research related to Sign Language Translation (SLT). Our paper, however, proposes a creative approach that involves the linguistic modeling of the corresponding text of sign language during the process of converting signs to GLOSS. Specifically, we have implemented a text correction module that uses a front-mounted sign language recognition module to make preliminary predictions. The corrected GLOSS sequence is then used to obtain the final recognition result with higher accuracy. Our framework was tested on the RWTHPHOENIX-Weather-2014-T dataset and CSL dataset to evaluate its effectiveness in recognizing sign language on a large scale. The experimental results demonstrate that the proposed method significantly enhances the accuracy of the sign language recognition model. © 2024 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Acoustofluidics at Audible Frequencies—A Review

引用

工程（英文） 2025年第1期44卷 51-72页

作者： Chuanyu Zhang Philippe Brunet Shuo Liu xiaofeng Guo Laurent Royon xianming Qin Xueyong Wei School of Instrument Science and Technology Xi'an Jiaotong UniversityXi'an 710049China State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong UniversityXi'an 710049China Laboratoire Matière et Systèmes Complexes Université Paris CitéParis 75013France State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong UniversityXi'an 710049China School of Mechanical Engineering Xi'an Jiaotong UniversityXi'an 710049China Laboratoire Interdisciplinaire des Energies de Demain Université Paris CitéParis 75013France School of Mechano-Electronic Engineering Xidian UniversityXi'an 710071China

Acoustofluidics is a term describing the class of phenomena in which mechanical or acoustic vibrations induce a deformation or a flow in a *** deficiencies in our understanding of these phenomena remain to be addressed,with respect to the fundamental theoretical framework as well as in numerous *** this regard,the frequency of external forcing is a key *** to the low cost,substantial magnitude,and versatility associated with acoustofluidic phenomena at audible frequencies,studies of these phenomena in the audible range have emerged with increasing amount in recent years and have attracted considerable ***,compared with studies focusing on the ultrasonic frequency domain,critical features and information specific to audible acoustofluidics remain dispersed across many independent publications,and a systematic integration of the literature on this topic is ***,this review summarizes the basic theory and methods for generating vibrations in the audible range,presents various applications thereof in biology,chemistry,and other fields,and pro-vides a high-level overview of the current status of the topic to motivate developing interesting proposals for further research in this field of study.

关键词： Acoustofluidics Audible frequency Vibration generation Biological detection Particle manipulation Mixing Chemical reaction Micropumping Heat transfer

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Based Volumetric Parameterizations for Lattice Structures

引用

computer Modeling in engineering & sciences 2023年第4期135卷 687-709页

作者： Long Chen Shuxun Liang Nan Yan xiangqian Yang Baotong Li School of Mechanical Engineering University of Shanghai for Science and TechnologyShanghai200093China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and TechnologyShanghai200093China Key Laboratory of EducationMinistry for Modern Design&Rotor-Bearing System Xi’an Jiaotong UniversityXi’an710049China

Lattice structures with excellent physical properties have attracted great research *** this paper,a novel volume parametric modeling method based on the skeleton model is proposed for the construction of threedimensional lattice *** skeleton model is divided into three types of *** the corresponding algorithms are utilized to construct diverse types of volume parametric *** unit-cell is assembled with distinct nodes according to the geometric *** final lattice structure is created by the periodic arrangement of *** different types of volume parametric lattice structures are constructed to prove the stability and applicability of the proposed *** quality is assessed in terms of the value of the Jacobian ***,the volume parametric lattice structures are tested with the isogeometric analysis to verify the feasibility of integration of modeling and simulation.

关键词： Lattice structure volumetric parameterization skeleton model node modeling

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Multiscale Feature Fusion Network for Solar Cell Defect Detection

引用

computers, Materials & Continua 2025年第1期82卷 521-542页

作者： xiaoyun Chen Lanyao Zhang xiaoling Chen Yigang Cen Linna Zhang Fugui Zhang School of Mechanical Engineering Guizhou UniversityGuiyang550025China School of Computer Science and Technology Beijing Jiaotong UniversityBeijing100044China

Solar cell defect detection is crucial for quality inspection in photovoltaic power generation *** the production process,defect samples occur infrequently and exhibit random shapes and sizes,which makes it challenging to collect defective ***,the complex surface background of polysilicon cell wafers complicates the accurate identification and localization of defective *** paper proposes a novel Lightweight Multiscale Feature Fusion network(LMFF)to address these *** network comprises a feature extraction network,a multi-scale feature fusion module(MFF),and a segmentation ***,a feature extraction network is proposed to obtain multi-scale feature outputs,and a multi-scale feature fusion module(MFF)is used to fuse multi-scale feature information *** order to capture finer-grained multi-scale information from the fusion features,we propose a multi-scale attention module(MSA)in the segmentation network to enhance the network’s ability for small target ***,depthwise separable convolutions are introduced to construct depthwise separable residual blocks(DSR)to reduce the model’s parameter ***,to validate the proposed method’s defect segmentation and localization performance,we constructed three solar cell defect detection datasets:SolarCells,SolarCells-S,and *** and SolarCells-S are monocrystalline silicon datasets,and PVEL-S is a polycrystalline silicon *** results show that the IOU of our method on these three datasets can reach 68.5%,51.0%,and 92.7%,respectively,and the F1-Score can reach 81.3%,67.5%,and 96.2%,respectively,which surpasses other commonly usedmethods and verifies the effectiveness of our LMFF network.

关键词： Defect segmentation multi-scale feature fusion multi-scale attention depthwise separable residual block

来源：评论

学校读者我要写书评

暂无评论

Tailoring the geometry of silicon nitride nanofillers to simultaneously strengthen and toughen carbon/carbon composites

引用

Journal of Materials science & technology 2024年第35期202卷 183-191页

作者： Lei Feng Liyuan Guo Qiang Chen Rui Tian Jiaxu Zhang Qiang Song Peng Wei Caixiang xiao Qiangang Fu School of Materials Science and Engineering Shaanxi University of Science and TechnologyXi’an 710021China State Key Laboratory of Solidification Processing Northwestern Polytechnical UniversityXi’an 710072China Shandong Shengshida Technology Co. Ltd.Jinan 250013China

Incorporating one-dimensional(1D)nanofillers into carbon/carbon composites(C/Cs)can increase their mechanical ***,this method is ineffective in improving the fracture toughness of C/Cs be-cause cracks can easily pass over the 1D nanofillers,resulting in a flat fracture ***,we propose a new technique to significantly improve both the strength and toughness of C/Cs by incorporating 2D ribbon-shaped *** nitride nanoribbons(SiNNRs)are assembled into a film-like structure and inserted into each layer of a carbon fiber laminate,which is then densified with a pyrocarbon *** to the large interfacial contact area between the nanoribbon and matrix,ribbon-shaped SiNNRs can efficiently arrest and deflect cracks in both two and three dimensions,exhibiting a higher reinforcement efficiency than that of slender silicon nitride nanowires(SiNNWs).Mechanical tests show that the per-centage increases in fracture toughness,flexural strength,and compressive strength of C/Cs produced by SiNNRs are approximately 9.8,1.8,and 1.25 times higher than those produced by SiNNWs at the same volume fraction of nanofillers,*** study suggests that 2D ribbon-shaped nanofillers are more effective than 1D fibrous nanofillers in enhancing the strength and toughness of C/Cs.

关键词： Carbon/carbon composites Nanoribbons Nanowires Fracture toughness Strength

来源：评论

学校读者我要写书评

暂无评论

Graphene quantum dots as sulfiphilic and lithiophilic mediator toward high stability and durable life lithium-sulfur batteries

引用

Journal of Energy Chemistry 2023年第10期85卷 254-266,I0008页

作者： Chaojiang Fan Rong Yang Yong Huang Lei Mao Yuanyuan Yang Le Gong xin Dong Yinglin Yan Yiming Zou Lisheng Zhong Yunhua Xu International Research Center for Composite and Intelligent Manufacturing Technology Institute of Chemical Power SourcesXi'an University of TechnologyXi'an 710048ShaanxiChina School of Materials Science and Engineering Xi'an University of TechnologyXi'an 710048ShaanxiChina School of Chemistry&Chemical Engineering Yulin UniversityYulin 719000ShaanxiChina

The development of lithium-sulfur(Li-S) battery as one of the most attractive energy storage systems among lithium metal batteries is seriously hindered by low sulfur utilization, poor cycle stability and uneven redeposition of Li anode. It is necessary to propose strategies to address the problems as well as improve the electrochemical performance. One of the effective solutions is to improve the sulfiphilicity of sulfur cathode and the lithiophilicity of the Li anode. Herein, we reported that a synergistic functional separator(graphene quantum dots(GQDs)-polyacrylonitrile(PAN) @polypropylene(PP) separator)improved the electrochemical activity of sulfur cathode as well as the stability of Li anode. GQDs induced uniform Li^(+)nucleation and deposition, which slowed down the passivation of Li anode and avoided shortcircuit. Further, three-dimensional network constructed by electrospinning nanofibers and the polar functional groups of GQDs could both effectively inhibit the shuttle of LiPSs and improve the sulfur utilization. The stability of Li-S battery was improved by the synergistic effect. In addition, GQDs and electrospinning nanofibers protector increased lifetime of separators. Benefiting from the unique design strategy, Li//Li symmetric battery with GQDs-PAN@PP separators exhibited stably cycling for over 600 h. More importantly, the Li-S full batteries based GQDs-PAN@PP separators enabled high stability and desirable sulfur electrochemistry, including high reversibility of 558.09 mA h g^(-1)for 200 cycles and durable life with a low fading rate of 0.075% per cycle after 500 cycles at 0.5 C. Moreover, an impressive areal capacity of 3.23 mA h cm^(-2)was maintained under high sulfur loading of 5.10 mg cm^(-2). This work provides a new insight for modification separator to improve the electrochemical performance of Li-S/Li metal batteries.

关键词： Lithium-sulfur batteries Separator Graphene quantum dots Cycle stability Durable life

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：