检索结果-内蒙古大学图书馆

Enhancing Multilabel ECG Classification via Task-Guided Lead Correlations in Internet of Medical Things

IEEE Internet of Things Journal 2025年第12期12卷 20544-20555页

作者： Yuan, Xiaoyan Wang, Wei Chen, Junxin Fang, Kai Kashif Bashir, Ali Mondal, Tapas Hu, Xiping Jamal Deen, M. Beijing Institute of Technology School of Medical Technology Beijing100081 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Guangdong Shenzhen518172 China Dalian University of Technology School of Software Dalian116621 China Zhejiang A&F University College of Mathematics and Computer Science Hangzhou311300 China Manchester Metropolitan University Department of Computing and Mathematics ManchesterM15 6BH United Kingdom Chitkara University Institute of Engineering and Technology Chitkara University Centre for Research Impact and Outcome Rajpura140401 India McMaster University Faculty of Health Science Department of Pediatrics ON HamiltonL8S 4L8 Canada McMaster University McMaster School of Biomedical Engineering Electrical and Computer Engineering Department ON HamiltonL8S 4L8 Canada

With the rise of the Internet of Things, wearable devices have enabled real-time health monitoring, particularly through physiological signals like electrocardiograms (ECG). The standard 12-lead ECG records the electrical activity of the heart from multiple perspectives, providing valuable insights into cardiac health. However, existing 12-lead ECG analysis methods often treat leads as channel-level arrangements or rely on spatial adjacency to predefine lead connections, limiting their ability to capture the complex spatial and functional relationships between leads fully. To address this limitation, we propose TGLLNet, a task-driven model that automatically learns interlead relationships to improve multilabel ECG classification. TGLLNet adaptively learns lead connectivity patterns and relational strengths, enhancing ECG representation and improving model generalizability across tasks. Specifically, TGLLNet employs a temporal graph construction module to convert ecg signals into temporal graphs and uses a residual pyramid graph convolution module for multilevel graph embeddings, utilizing a graph convolutional network with independently learnable adjacency matrices. Combined with a temporal context convolution module, TGLLNet captures spatio-temporal dependencies, significantly improving ECG representation. Experimental results on seven tasks from PTB-XL and CPSC2018 datasets demonstrate that TGLLNet outperforms existing methods, showing superior generalizability across different tasks. Our code is available at https://***/rosemary333/TGLLnet. © 2014 IEEE.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

A heterogeneous graph cross-omics attention model for single-cell representation learning

A heterogeneous graph cross-omics attention model for single...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Liu, Yue Zhang, Junfeng Wang, Shulin Zhang, Wei Zeng, Xiangxiang Kwoh, Chee Keong Hunan University College of Computer Science and Electronic Engineering Hunan Changsha China Hangzhou Machine Learning Research and Development Center Sina Weibo Zhejiang Hangzhou China Changsha University College of Computer Engineering & Applied Mathematics Hunan Changsha China Nanyang Technological University School of Computer Science and Engineering Singapore

ISBN: (纸本)9781665468190

Single-cell multi-omics sequencing technologies allow simultaneous measurement of transcriptome and epigenome profiles in the same cell, providing unprecedented opportunities to dissect cell heterogeneity. Despite great efforts, conjoint analysis of single-cell multi-omics data still suffers from sparsity, high dimensionality and binary. In this study, we present a heterogeneous graph cross-omics attention model (scHGA), a computational tool based on a heterogeneous graph neural network combining two attention mechanisms to jointly analyze single-cell multi-omics data based on different protocols data, including SNARE-seq, scMT-seq and sci-CAR. To avoid the cell heterogeneity of single-omics data, scHGA automatically learns a cell association graph to capture neighbor information. The latent representation of aggregated cells generated by hierarchical attention can fuse knowledge across different omics to dissect cellular heterogeneity, providing a better scheme to characterize the features of cells. scHGA is an effective exploration of graph neural networks in single-cell multi-omics analysis, providing new insights into the understanding of single-cell sequencing data. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

ON THE MAXIMUM SIZE OF VARIABLE-LENGTH NON-OVERLAPPING CODES

arXiv

引用

arXiv 2024年

作者： Wang, Geyang Wang, Qi Department of Electrical and Computer Engineering Institute for Systems Research University of Maryland College ParkMD20742 United States Department of Computer Science and Engineering National Center for Applied Mathematics Shenzhen Southern University of Science and Technology Nanshan District Guangdong Shenzhen518055 China

Non-overlapping codes are a set of codewords such that the prefix of each codeword is not a suffix of any codeword in the set, including itself. If the lengths of the codewords are variable, it is additionally required that every codeword is not contained in any other codeword as a subword. Let C(n, q) be the maximum size of q-ary fixed-length non-overlapping codes of length n. The upper bound on C(n, q) has been well studied. However, the nontrivial upper bound on the maximum size of variable-length non-overlapping codes of length at most n remains open. In this paper, by establishing a link between variable-length non-overlapping codes and fixed-length ones, we are able to show that the size of a q-ary variable-length non-overlapping code is upper bounded by C(n, q). Furthermore, we prove that the average length of the codewords in a q-ary variable-length non-overlapping codes is lower bounded by ⌈logq C˜⌉, and is asymptotically no shorter than n−2 as q approaches ∞, where C˜ denotes the cardinality of q-ary variable-length non-overlapping codes of length up to *** Codes 94A45, 94B25 © 2024, CC BY.

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Study of fuzzy expert system for the diagnosis of various types of cancer

引用

Materials Today: Proceedings 2022年 56卷 298-307页

作者： Boadh, Rahul Grover, Reena Dahiya, Mamta Kumar, Ajay Rathee, Rakesh Rajoria, Yogendra Kumar Rawat, Meena Rani, Sangeeta Department of the Mathematics School of Basic and Applied Science K.R. Mangalam University Sohna Road Gurugram Haryana 122103 India Department of Mathematics Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi-NCR Campus U.P. Ghaziabad India Department of Computer Science and Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122505 India Department of Mechanical Engineering Faculty of Engineering and Technology Shree Guru Govind Singh Tricentenary University Haryana Gurugram122505 India University Institute of Engineering and Technology Maharshi Dayanand University Haryana Rohtak124001 India Department of Computer Science and Engineering World College of Technology and Management Gurgaon122506 India

Early exposure of critical diseases is the main necessity for the patients and a difficult errand for the oncologist. In the event that it is distinguished early, it makes the patient bound to live. Lately, the fuzzy rationale has shown up as a dynamical strategy in the acknowledgment of illnesses like various sorts of malignant growths. For the most part, the identification of malignant growths illnesses is taken care of with vagary, mistake, and unclearness yet very much worked by utilizing fuzzy rationale-based models. This paper surveys a few techniques for the early identification of diseases to sum things up. By using fuzzy artificial intelligent Programme, created calculation;patient information alongside master specialist's recommendation, any quiet's infections can be analyzed early which lessen mortality and grimness. This review gives a proposal that a fuzzy approach running smoothly in multiple regions to the diagnosis of cancers. © 2022

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Fractional order modeling of dengue transmission dynamics in Bangladesh

引用

Partial Differential Equations in applied mathematics 2025年 14卷

作者： Sikder, Arun Kumar Islam, Md Hamidul Department of Computer Science and Engineering Varendra University Rajshahi 6204 Bangladesh Department of Applied Mathematics University of Rajshahi Rajshahi 6205 Bangladesh

Over the past three decades, the epidemiological characteristics of dengue fever in Bangladesh have raised significant public health concerns, with the disease progressively spreading across the country's subtropical and tropical regions since 2004. This study introduces a fractional-order mathematical model that incorporates both human and mosquito populations using Caputo derivatives to account for memory and hereditary effects in disease transmission. Analytical solutions are approximated using the Laplace–Adomian decomposition method, while the Adams–Bashforth-Moulton predictor–corrector (PECE) scheme is applied for numerical solutions. Model parameters are estimated via the maximum likelihood method, using dengue case data from Bangladesh (June 1, 2022–September 30, 2022). Our findings indicate that the fractional-order model effectively captures a range of transmission scenarios, with lower derivative orders correlating with reduced outbreak severity. Moreover, numerical solutions exhibit higher accuracy compared to analytical approximations, particularly for complex nonlinear systems. Additionally, the results suggest that controlling mosquito populations, reducing transmission rates, and improving treatment measures are critical strategies for dengue mitigation. © 2025 The Authors

关键词： Dengue fever Fractional order modeling LADM Mathematical modeling MLE fitting Monte Carlo method PECE method

来源：评论

学校读者我要写书评

暂无评论

Global scale solar energy harnessing: An advanced intra-hourly diffuse solar irradiance predicting framework for solar energy projects

引用

Neural Computing and Applications 2024年第18期36卷 10585-10598页

作者： El-kenawy, El-Sayed M. Bailek, Nadjem Bouchouicha, Kada Zerouali, Bilel Hassan, Muhammed A. Kuriqi, Alban Jamil, Basharat Colak, Ilhami Khalil, Adel Ibrahim, Abdelhameed Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Mansoura35111 Egypt Laboratory of Mathematics Modeling and Applications Department of Mathematics and Computer Science Faculty of Sciences and Technology Ahmed Draia University of Adrar Adrar01000 Algeria Energies and Materials Research Laboratory Faculty of Sciences and Technology University of Tamanghasset Tamanrasset10034 Algeria MEU Research Unit Middle East University Amman Jordan Adrar01000 Algeria Vegetal Chemistry-Water-Energy Laboratory Faculty of Civil Engineering and Architecture Department of Hydraulic Hassiba Benbouali University of Chlef Ouled Fares Chlef02180 Algeria Mechanical Power Engineering Department Faculty of Engineering Cairo University Giza12613 Egypt School of Architecture University of Waterloo 7 Melville St S CambridgeONN1S 2H4 Canada CERIS Instituto Superior Tecnico Universidade de Lisboa Lisbon Portugal Civil Engineering Department University for Business and Technology PristinaKosovo10000 High Temperature Processes Unit IMDEA Energy Institute Av. Ramón de La Sagra 3 Móstoles Madrid28935 Spain Faculty of Engineering and Architectures Nisantasi University Istanbul Turkey Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

Diffuse horizontal irradiance (DHI) forecasts are critical for adopting solar photovoltaic technology. Yet, they can lack reliability given the limited and uncertain meteorological data available for desert areas. This research develops a new sine cosine dipper throated optimization (SCDTO) technique, targeting DHI prediction even given such data constraints. SCDTO uniquely hybridizes sine cosine metaheuristics, adept at exploration, with dipper throat optimization, providing focused exploitation. This hybridization aims to create a robust ensemble model capable of delivering reliable DHI predictions despite climatic uncertainty. The ensemble model, employing various input combinations, was rigorously evaluated across multiple meteorological stations. The SCDTO algorithm exhibited remarkable performance improvements, yielding substantial reductions exceeding 93% in root mean squared error and 98% in mean absolute error at key stations in Morocco, including Tan-Tan, Zagora, Erfoud, and Oujda. Comparative analyses against established optimization algorithms consistently underscored the superior predictive capabilities of SCDTO. Visualizations, including box plots and histograms, demonstrated SCDTO’s efficacy in minimizing prediction errors, particularly for Tan-Tan, Zagora, and Erfoud stations. Also, statistical validation through one-way analysis of variance (ANOVA) further affirmed the significance of the proposed SCDTO method. Therefore, this hybrid metaheuristic optimization enables more accurate DHI predictions from limited meteorological data. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Experimental Design and Maintenance, Towards a Decision-Making Approach Driven by Degradation Models, with Application to Lithium-Ion Batteries 2

Experimental Design and Maintenance, Towards a Decision-Maki...

引用

2nd Edition IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural engineering, MetroXRAINE 2023

作者： Pievatolo, Antonio Magrini, Alessandro Meccariello, Giovanni Cristaldi, Loredana Patrizi, Gabriele Nikiforova, Nedka D. Institute for Applied Mathematics and Information Technologies 'E. Magenes' National Research Council Milan Italy University of Florence Department of Statistics Computer Science Applications 'G. Parenti' Florence Italy Institute of Sciences and Technologies for Energy and Sustainable Mobility National Research Council Naples Italy Polytechnic of Milan Department of Electronics Information and Bioengineering Milan Italy University of Florence Department of Information Engineering Florence Italy

ISBN: (纸本)9798350300802

We discuss an innovative decision-making frame-work for accelerated degradation tests and predictive maintenance, when information about the state of the system, represented by prior knowledge and experimental data, is encapsulated in a degradation model. We consider dynamic programming and reinforcement learning as the framework for sequential decision making in these areas, also including the degradation model learning when necessary. The application of these methods to the design of life testing experiments and to the maintenance of lithium-ion batteries is proposed. © 2023 IEEE.

关键词： accelerated degradation tests degradation modeling predictive maintenance reinforcement learning remaining useful life

来源：评论

学校读者我要写书评

暂无评论

Mixed Contact Problem for the Lamé System with Piecewise Constant Main Coefficients

引用

Journal of Mathematical Sciences (United States) 2023年第1期276卷 168-190页

作者： Vuong, Tran Quang Soldatov, A.P. Dalat University Lam Dong Da Lat Viet Nam Federal Research Center “Computer Science and Control” RAS 40 Vavilova St. Moscow 119333 Russian Federation Moscow Center for Fundamental and Applied Mathematics National Research University “Moscow Power Engineering Institute” 14 Krasnokazarmennaya St. Moscow 111250 Russian Federation

We construct the fundamental matrix of solutions to the Lamé system with constant main coefficients in the general anisotropic case. Using the fundamental matrix, we obtain an integral representation of functions of a Hölder class in a closed domain with Lyapunov boundary. In the case of an infinite domain, the representation is described within the framework of weighted Hölder spaces (of functions with power behavior at infinity). Based on this representation, we can reduce the mixed contact boundary value problem for the Lamé system with piecewise constant main coefficients to a system of integral equations that are Fredholm in the domain and are singular on the boundary. As a result, we establish a Fredholm criterion and indicate the index for this problem. © 2023, Springer Nature Switzerland AG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toddler Activity Analysis Using Machine Learning

Toddler Activity Analysis Using Machine Learning

引用

Intelligent Systems for Communication, IoT and Security (ICISCoIS), International Conference on

作者： I. Kala Bhuvaneswari P Dharun R Dharshini S Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

Toddler activity recognition aims in finding out the activities of toddler and also toddlers based on the video captured by camera. The purpose of activity recognition is to monitor a new employee of the company (maybe a software or even a restaurant) whether employees are working properly or do we need to give more training. This system can also be used by the parents to monitor the activity of the kids who are alone at home. This system can also be implemented in hospitals to monitor the patients and to check their improvement. Toddler activity recognition system is developed using CNN and LSTM. To predict the activity the path of the video file is given as input. The predicted result by the model is checked for accuracy. To make the result available for the end user (who needs to monitor the activity) and can access the result through two ways. In the First method user can directly view on the system where the model is predicting the result. In the second method user is out of station, so the predicted result will be updated on the cloud on fixed time intervals and user can view the result from the working place itself.

关键词： Training Pediatrics Surveillance Machine learning Activity recognition Predictive models Cameras

来源：评论

学校读者我要写书评

暂无评论

Home Automation with Webserver Deployment with Raspberry Pi Pico

Home Automation with Webserver Deployment with Raspberry Pi ...

引用

Automation, Computing and Renewable Systems (ICACRS), International Conference on

作者： C P Shabariram M Venkateshwaran R Abinesh R Manoranjith Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

Home Automation system with web server deployment is developed using Raspberry Pi Pico and micropython, which turns ON the lights based on the count of persons inside that particular room. The system uses Infrared Red (IR) sensor, which detects the heat radiation in the environment. This heat radiation is not constant as it changes due to the movement of people in the sensing environment. This change is used as a measure to detect the changes in the environment which allows us to perform a particular action for the event. The data is sent to node which sends the data to the webserver running in the Raspberry pi pico. Based on the result, the light is turned ON or OFF.

关键词：

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：