检索结果-内蒙古大学图书馆

International Conference on Edge computing and Applications (ICECAA)

作者： AR. Arunarani S. Selvanayaki Mohammed Saleh Al Ansari Md. Abul Ala Walid Nagamalleswari Devireddy Murugesan Mohana Keerthi Department of Computational Intelligence School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulatur Campus Chennai Tamilnadu India Artificial Intelligence and Data Science Saveetha Engineering College Chennai Tamilnadu India Department of Chemical Engineering College of Engineering University of Bahrain Bahrain Department of CSE Khulna University of Engineering & Technology (KUET) Khulna Bangladesh Department of Freshman Mohan Babu University Tirupathi Andhra Pradesh India School of Agriculture SR University Warangal Telangana India

Crop yield forecasting has been thoroughly studied recently and has become more important in preserving the safety of food. The majority of studies have concentrated on obtaining fixed spatial data from remote sensing images. Crop development, however, is a very complicated attribute influenced by a variety of factors. This work is intended to concurrently use spatial and temporal information from multimodal remotely sensed images in order to fully investigate these diverse characteristics. With the goal to make use of their supportive nature, Spatio temporal Convolutional Neural Networks (STCNN), is proposed as a revolutionary deep learning architecture for agricultural production prediction. To recognize the combined spatial-temporal representation, the STCNN specifically combines a spatial training segment and a temporal dependent segment into the convolutional network. The innovative spatial training segment begins by extracting enough spatial information from the multimodal spatial images. Then, in order to determine the temporal connection from the lengthy time-series images, the temporal dependent segment is concatenated on top of the spatial training segment. Both common machine learning techniques and cutting-edge deep learning techniques are compared to the outcomes of the proposed method. The experimental findings show that the STCNN can offer superior prediction performance of 0.64 RMSE and 12.03 MAPE values compared to the rival methods with minimized errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Microwave Absorption Characteristics of Porous Lamellar Hard Carbon Materials

SSRN

引用

SSRN 2023年

作者： Liu, Linlin Yibibulla, Tursunay Yang, Yang Hassan, Sibt ul Hou, Lizhen Kuang, Daitao Mead, James L. Deng, Lianwen Wang, Shiliang School of Physics and Electronics Central South University Changsha410083 China School of Physics and Electronic Nanning Normal University Nanning China School of Physics and Electronics Hunan Normal University Changsha410081 China School of Computational Science and Electronics Hunan Institute of Engineering Xiangtan411104 China Department of Computing Science University of Oldenburg Oldenburg26129 Germany

Porous lamellar hard carbon structures were synthesized using the direct hard template strategy with phenolic resin as the C source and ZnO as the template. The porosity of the hard carbon materials is adeptly fine-tuned by regulating the ZnO nanoparticle content. Notably, the introduction of porosity to lamellar hard carbon materials is shown to have a significant impact on their microwave absorption properties. A porous lamellar hard carbon material with impressive microwave absorption performance is synthesized, culminating in an optimal reflection loss of -45 dB and an effective absorption bandwidth of 4.08 GHz, even at a minimal absorber thickness of ~2.0 mm, with a mere 16.7% filling rate. These findings illustrate how the control of porosity provides a new design avenue for tailoring the absorption characteristics for microwave absorbers. This design approach will support the further development of versatile microwave absorption solutions, helping to address the prevalence of electromagnetic pollution. © 2023, The Authors. All rights reserved.

关键词： Porosity

来源：评论

学校读者我要写书评

暂无评论

Adaptive Wavelet Filters as Practical Texture Feature Amplifiers for Parkinson’s Disease Screening in OCT

arXiv

引用

arXiv 2025年

作者： Zhang, Xiaoqing Shi, Hanfeng Li, Xiangyu Ye, Haili Xu, Tao Li, Na Hu, Yan Lv, Fan Chen, Jiangfan Liu, Jiang Center for High Performance Computing and Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China State Key Laboratory of Ophthalmology Optometry and Vision Science Wenzhou Medical University Wenzhou China Centre for Computational Science and Mathematical Modelling Coventry University Coventry United Kingdom School of Computer Science University of Nottingham Ningbo China Ningbo315100 China School of Ophthalmology and Optometry Wenzhou Medical University Wenzhou325035 China Department of Electronic and Information Engineering Changchun University Changchun130022 China

Parkinson’s disease (PD) is a prevalent neurodegenerative disorder globally. The eye’s retina is an extension of the brain and has great potential in PD screening. Recent studies have suggested that texture features extracted from retinal layers can be adopted as biomarkers for PD diagnosis under optical coherence tomography (OCT) images. Frequency domain learning techniques can enhance the feature representations of deep neural networks (DNNs) by decomposing frequency components involving rich texture features. Additionally, previous works have not exploited texture features for automated PD screening in OCT. Motivated by the above analysis, we propose a novel Adaptive Wavelet Filter (AWF) that serves as the Practical Texture Feature Amplifier to fully leverage the merits of texture features to boost the PD screening performance of DNNs with the aid of frequency domain learning. Specifically, AWF first enhances texture feature representation diversities via channel mixer, then emphasizes informative texture feature representations with the well-designed adaptive wavelet filtering token mixer. By combining the AWFs with the DNN stem, AWFNet is constructed for automated PD screening. Additionally, we introduce a novel Balanced Confidence (BC) Loss by mining the potential of sample-wise predicted probabilities of all classes and class frequency prior, to further boost the PD screening performance and trustworthiness of AWFNet. The extensive experiments manifest the superiority of our AWFNet and BC over state-of-the-art methods in terms of PD screening performance and trustworthiness. © 2025, CC BY-NC-SA.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

A scalable domain decomposition method for FEM discretizations of nonlocal equations of integrable and fractional type

arXiv

引用

arXiv 2023年

作者： Klar, Manuel Capodaglio, Giacomo D’Elia, Marta Glusa, Christian Gunzburger, Max Vollmann, Christian Department of Mathematics Universität Trier Trier54296 Germany Center for Computing Research Sandia National Laboratories AlbuquerqueNM87321 United States Computational Physics and Methods Group Los Alamos National Laboratory Los AlamosNM87545 United States Pasteur Labs BrooklynNY11205 United States Oden Institute for Computational Science and Engineering University of Texas Austin78712 United States

Nonlocal models allow for the description of phenomena which cannot be captured by classical partial differential equations. The availability of efficient solvers is one of the main concerns for the use of nonlocal models in real world engineering applications. We present a domain decomposition solver that is inspired by substructuring methods for classical local equations. In numerical experiments involving finite element discretizations of scalar and vectorial nonlocal equations of integrable and fractional type, we observe improvements in solution time of up to 14.6x compared to commonly used solver *** Codes 34B10, 65M60, 45P05, 45A99, 65R99 Copyright © 2023, The Authors. All rights reserved.

关键词： Domain decomposition methods

来源：评论

学校读者我要写书评

暂无评论

Characterizing Faculty Online Learning Community Interactions Using Social Network Analysis

arXiv

引用

arXiv 2024年

作者： Bolger, Emily Nwobi, Marius Caballero, Marcos D. Department of Computational Mathematics Science and Engineering Michigan State University East LansingMI48824 United States Department of Biochemistry and Molecular Biology Michigan State University East LansingMI48824 United States Department of Physics and Astronomy CREATE for STEM Institute Michigan State University East LansingMI48824 United States Department of Physics Center for Computing in Science Education University of Oslo Oslo0315 Norway

Expanding on other work in the Physics Education Community, we apply Social Network Analysis to a Faculty Online Learning Community focused on facilitating the integration of computation into physics courses. The Partnership for Integration of Computation into Undergraduate Physics (PICUP) uses Slack as a mechanism for continued communication beyond face-to-face meetings. Through our analysis, we use networks to represent the Slack channels, identify lurkers, and use metrics to quantify pariticipation. Additionally, we use randomization techniques to understand how similar our metric values are to networks of similar size and distribution. We highlight the need for using the appropriate randomization model and assumption checking. We characterize participation amongst users in the network and provide potential reasonings for their actions. Copyright © 2024, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Monte Carlo PINNs: deep learning approach for forward and inverse problems involving high dimensional fractional partial differential equations

arXiv

引用

arXiv 2022年

作者： Guo, Ling Wu, Hao Yu, Xiaochen Zhou, Tao Department of Mathematics Shanghai Normal University Shanghai China School of Mathematical sciences Tongji University Shanghai China Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

We introduce a sampling based machine learning approach, Monte Carlo physics informed neural networks (MC-PINNs), for solving forward and inverse fractional partial differential equations (FPDEs). As a generalization of physics informed neural networks (PINNs), our method relies on deep neural network surrogates in addition to a stochastic approximation strategy for computing the fractional derivatives of the DNN outputs. A key ingredient in our MC-PINNs is to construct an unbiased estimation of the physical soft constraints in the loss function. Our directly sampling approach can yield less overall computational cost compared to fPINNs proposed in [1] and thus provide an opportunity for solving high dimensional fractional PDEs. We validate the performance of MC-PINNs method via several examples that include high dimensional integral fractional Laplacian equations, parametric identification of time-space fractional PDEs, and fractional diffusion equation with random inputs. The results show that MC-PINNs is flexible and promising to tackle high-dimensional FPDEs. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Cross-Platform Multimodal Frogeye Leaf Spot Recognition and Classification: Advancing with Cutting-Edge CNN Technologies and Transfer Learning in Diverse Plant Species

Cross-Platform Multimodal Frogeye Leaf Spot Recognition and ...

引用

International Conference on Circuit, Power and computing Technologies (ICCPCT)

作者： G. Mohan R Usharani Vatsala Tomar Arthi A Suniti Kumar Kuriyal K.P. Yuvaraj Department of Mathematics K.S.Rangasamy College of Technology Tamil Nadu India Department of Computational Intelligence School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Department of Botany School of Life Science & Technology IIMT University Meerut UP India Department of Information Technology Karpagam College of Engineering Coimbatore India Department of Botany Pt.L.M.S.Sridev Suman Uttarakhand University Campus Rishikesh India Department of Mechanical Engineering Sri Krishna College of Engineering and Technology Coimbatore India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

Frogeye Leaf Spot, a common agricultural disease, poses a significant threat to crop yields. Using multimodal data from different platforms successfully has been a hurdle for existing research in leaf spot detection. Using cutting-edge convolutional neural network (CNN) and transfer learning techniques, this research presents a Cross-Platform Multimodal Recognition system to solve this issue. With a recall of 0.88, F1-score of 0.90, accuracy of 0.91, and precision of 0.92, the suggested method demonstrates exceptional performance. Our accuracy is 6% higher, F1-score is 8% higher, and recall is 9% higher than the preceding state-of-the-art, according to comparisons with previous studies. Improved Frogeye Leaf Spot detection on many platforms is a direct result of our method's success in combining picture and sensor data. This study improves farmers' ability to identify diseases and provides a solid answer for precision agriculture. Our Cross-Platform Multimodal Recognition system has shown to be effective in enhancing agricultural disease recognition, and the shown advances highlight its potential influence on crop management tactics.

关键词： Precision agriculture Accuracy Plants (biology) Transfer learning Neural networks Solids Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Optimization of web-based application to donate blood-on-demand: A machine learning approach

引用

AIP Conference Proceedings 2024年第1期3075卷

作者： S. Sasikumar R. Pradeep P. V. Gopirajan M. Kanchana N. Velmurugeshkumar Department of Computer Science and Engineering Saveetha Engineering College Chennai 602105 India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur Chennai 603203 India Department of Computing Technologies School of Computing SRM Institute of Science and Technology Kattankulathur Chennai 603203 India Department of Computer Science and Engineering RMK Engineering College Kavaraipettai Tamil Nadu India

Blood is a necessary element of all human beings. The number of persons who require blood is increasing in significant number day by day. Donors across the globe are three types: Voluntary donors, Professional donors, and Replacement donors. The safe, deliberate blood givers who are non-compensated from hazard populaces. The web structure for fussbudgets with cutoff times empowers quick turn of events and a clean, down-to-earth plan through Django. The current framework is restricted to manual processes. This has a constraint on controlling the processes safely, for announcing the outcomes on schedule, and has an intense usage on assets. Advanced software tools/applications are essential in providing easy access to get/donate blood in this pandemic. ‘Web-based blood donation’ is a machine language-based online portal to facilitate the coordination between the supply and demand of blood. The whole purpose of the project is to bring an online approach for blood givers and blood seekers and to create an interactive way of getting the donors and seekers of blood. The model proposed gives a lot of information about blood groups, blood availability, and blood donation details to create awareness among the people. In addition, extra features in the system, like security protection through a password, generating reports, chat applications, and stock shortage, can enhance management activities even more effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Smartphone Recommendation System Using Ensemble Machine Learning

A Novel Smartphone Recommendation System Using Ensemble Mach...

引用

2023 IEEE Asia-Pacific Conference on Computer science and Data engineering, CSDE 2023

作者： Almadhor, Ahmad Abbas, Sidra Sampedro, Gabriel Avelino Abisado, Mideth Gadekallu, Thippa Reddy College of Computer and Information Sciences Jouf University Sakaka72388 Saudi Arabia Comsats University Islamabad Department of Computer Science Islamabad Pakistan University of the Philippines Open University Faculty of Information and Communication Studies Los Baños4031 Philippines De la Salle University Center for Computational Imaging and Visual Innovations 2401 Taft Ave. Manila1004 Philippines College of Computing and Information Technologies National University Manila Philippines Zhongda Group Jiaxing City Zhejiang Province Haiyan County314312 China Lebanese American University Department of Electrical and Computer Engineering Byblos Lebanon School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu India College of Information Science and Engineering Jiaxing University Jiaxing314001 China Lovely Professional University Division of Research and Development Phagwara India

ISBN: (纸本)9798350341072

Due to the proliferation of internet evaluations brought on by the rising demand for smartphones, consumers find it challenging to make accurate selections when purchasing. In this paper, we offer ensemble voting methods based on TF-IDF (Term Frequency-Inverse Document Frequency) features for clas-sifying mobile phone ratings. We use a recently assembled dataset comprising over 13,000 smartphone reviews from the Flipkart website. The suggested approach includes feature extraction using the TF-IDF, data cleaning, balancing, and voting-based model prediction. To identify the recently created Flipkart dataset, the suggested method created an ensemble voting mechanism based on machine learning techniques. According to the experimental findings, the suggested method performs more accurately and efficiently than conventional machine learning techniques. At 98.0 %, the model achieved the greatest accuracy. The suggested method can be expanded to additional e-commerce platforms with sizable datasets of online evaluations and assist customers in making updated purchase preferences. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

QUASI-LINEAR FRACTIONAL-ORDER OPERATORS IN LIPSCHITZ DOMAINS

arXiv

引用

arXiv 2023年

作者： Borthagaray, Juan Pablo Li, Wenbo Nochetto, Ricardo H. Instituto de Matemática y Estadística "Rafael Laguardia" Facultad de Ingeniería Universidad de la República Montevideo Uruguay Institute of Computational Mathematics and Scientific/Engineering Computing The Chinese Academy of Sciences Beijing100190 China Department of Mathematics Institute for Physical Science and Technology University of Maryland College ParkMD20742 United States

We prove Besov boundary regularity for solutions of the homogeneous Dirichlet problem for fractional-order quasi-linear operators with variable coefficients on Lipschitz domains Ω of Rd. Our estimates are consistent with the boundary behavior of solutions on smooth domains and apply to fractional p-Laplacians and operators with finite horizon. The proof exploits the underlying variational structure and uses a new and flexible local translation operator. We further apply these regularity estimates to derive novel error estimates for finite element approximations of fractional p-Laplacians and present several simulations that reveal the boundary behavior of solutions. © 2023, CC BY.

关键词： Mathematical operators

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：