检索结果-内蒙古大学图书馆

Artificial intelligence for modelling infectious disease epidemics

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. © Springer Nature Limited 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Electrocardiograms Insights: A Comparative Study of Network Architectures Predicting Sex and Left Ventricular Dysfunction

引用

Heliyon 2025年

作者： Michal Cohen-Shelly David Hochstein Noam Barda Amit Bleiweiss Estelle Aflalo Nitzan Bar Eyal Zimlichman Eyal Klang Nisim Rahman Talia Sela Robert Klempfner Elad Maor Roy Beinart Amit Segev Ehud Raanani Avi Sabbag The Olga and Lev Leviev Heart Center Sheba Medical Center Sheba ARC Sagol Big data & AI Hub Sheba Medical Center Tel Hashomer Israel Sheba ARC and Hospital Management Sheba Medical Center Tel Hashomer Israel Tel Aviv University Tel Aviv Israel Software and Information Systems Engineering Ben-Gurion University of the Negev Be'er Sheva Israel Epidemiology Biostatistics and Community Health Sciences Ben-Gurion University of the Negev Be’er Sheva Israel Datacenter & AI group Intel Corporation The Division of Data Driven and Digital Medicine (D3M) Icahn School of Medicine at Mount Sinai New York NY USA

Objective To compare the effectiveness of Vision Transformers (ViTs) and Convolutional Neural Networks (CNNs) in developing AI-driven electrocardiogram (ECG) algorithms for predicting sex and left ventricular dysfunction (LVD). Patients and Methods In this retrospective study, we utilized 12-lead ECG data collected from January 1, 2005, through December 31, 2022, from a tertiary healthcare center. The data comprised 150,691 patients for the sex model and 29,422 patients for the LVD model (defined as Left Ventricular Ejection Fraction [LVEF] below 35%). We developed binary classification models using complete ECGs, single leads, and truncated recordings of 1 to 10 seconds, employing CNNs (PyTorch) and ViTs (HuggingFace) for comparison. Results For the sex prediction model, AUROCs were 0.915 (95% CI: 0.912-0.918) for CNNs and 0.898 (95% CI: 0.894-0.901) for ViTs, with the difference statistically significant (P-Value < 0.001). LVD prediction yielded comparable AUROCs of 0.895 (95% CI: 0.884-0.906) for CNNs and 0.866 (95% CI: 0.853-0.879) for ViTs (P = 0.023). Furthermore, we found that 99% for the maximal predictive power of the models was achieved within a 2 second time frame of a 12 lead ECG. Similarly, a single lead based model achieved a relatively high AUC for the prediction of LVD. Conclusion AI-ECG models developed with ViT architecture did not demonstrate superiority over CNN-based models in predicting sex and LVD. The study underscores the potential of lean models allowing for rapid prediction within 2-second tracings or using a single lead, demonstrates the potential for streamlined AI-ECG applications in clinical practice.

关键词： Deep Learning Cardiology ECG

来源：评论

学校读者我要写书评

暂无评论

Batch Mode Deep Active Learning for Regression on Graph data

Batch Mode Deep Active Learning for Regression on Graph Data

引用

IEEE International Conference on Big data

作者： Peter Samoaa Linus Aronsson Philipp Leitner Morteza Haghir Chehreghani Data Science and AI Division Chalmers University of technology Gothenburg Sweden Interaction Design and Software Engineering Chalmers University of technology Gothenburg Sweden

Acquiring labelled data for machine learning tasks, for example, for software performance prediction, remains a resource-intensive task. This study extends our previous work by introducing a batch-mode deep active learning approach tailored for regression in graph-structured data. Our framework leverages the source code conversion into Flow Augmented-AST graphs (FA-AST), subsequently utilizing both supervised and unsupervised graph embeddings. In contrast to single-instance querying, the batch-mode paradigm adaptively selects clusters of unlabeled data for labelling. We deploy an array of base kernels, kernel transformations, and selection methods, informed by both Bayesian and non-Bayesian strategies, to enhance the sample efficiency of neural network regression. Our experimental evaluation, conducted on multiple real-world software performance datasets, demonstrates the efficacy of the batch mode deep active learning approach in achieving robust performance with a reduced labelling budget. The methodology scales effectively to larger datasets and requires minimal alterations to existing neural network architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of physics simulation in serious game

Implementation of physics simulation in serious game

引用

International Conference on ICT For Smart Society (ICISS)

作者： Rizal Broer Bahaweres Angga Pratama Benhard Sitohang Data & Software Engineering Research Division-School of Electrical Engineering & Informatics Institute of Technology Bandung Faculty of Science and Technology State Islamic University Syarif Hidayatullah Jakarta Indonesia

Three dimension computer graphics has become important to present virtual objects to be more realistic and physically correct. One way to enhancing realism is by representing the physics simulation. We tried to implement physics simulation into a serious game. It is because of ability to increase realism in synthesis on virtual object motion. We design a serious game called “Traffic Drive”. Traffic Drive is a vehicle simulation game that has a goal to drive a vehicle, especially cars, with emphasis on safety and presented in a fun way. In physics simulation and game that are vehicle's physics a physics of gear and physics of rollover. It was expected that physics simulation can make the behavior of vehicles in the game resembles the behavior of the vehicle in terms of more realistics. And it is used as the object of research to compare the results of the data simulation with data from manual calculations. Comparison of results from the simulation output data and manual calculations were analyzed using T test hypotheses. From that T test was concluded that the output of data simulation with formula calculation almost the same.

关键词： Physics Games Gears Solid modeling Manuals Mathematical model Vehicles

来源：评论

学校读者我要写书评

暂无评论

ADAPTIVE GRAPH DIFFUSION NETWORKS

arXiv

引用

arXiv 2020年

作者： Sun, Chuxiong Hu, Jie Gu, Hongming Chen, Jinpeng Yang, Mingchuan Big Data and AI Division China Telecom Research Institute Beijing China School of Software Engineering Beijing University of Posts and Telecommunications Beijing China

Graph Neural Networks (GNNs) have received much attention in the graph deep learning domain. However, recent research empirically and theoretically shows that deep GNNs suffer from overfitting and over-smoothing problems. The usual solutions either cannot solve extensive runtime of deep GNNs or restrict graph convolution in the same feature space. We propose the Adaptive Graph Diffusion Networks (AGDNs) which perform multi-layer generalized graph diffusion in different feature spaces with moderate complexity and runtime. Standard graph diffusion methods combine large and dense powers of the transition matrix with predefined weighting coefficients. Instead, AGDNs combine smaller multi-hop node representations with learnable and generalized weighting coefficients. We propose two scalable mechanisms of weighting coefficients to capture multi-hop information: Hop-wise Attention (HA) and Hop-wise Convolution (HC). We evaluate AGDNs on diverse, challenging Open Graph Benchmark (OGB) datasets with semi-supervised node classification and link prediction tasks. Until the date of submission (Aug 26, 2022), AGDNs achieve top-1 performance on the ogbn-arxiv, ogbn-proteins and ogbl-ddi datasets and top-3 performance on the ogbl-citation2 dataset. On the similar Tesla V100 GPU cards, AGDNs outperform Reversible GNNs (RevGNNs) with 13% complexity and 1% training runtime of RevGNNs on the ogbn-proteins dataset. AGDNs also achieve comparable performance to SEAL with 36% training and 0.2% inference runtime of SEAL on the ogbl-citation2 dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification of Real and Deepfakes Visual Samples with Pre-trained Deep Learning Models 7th

Classification of Real and Deepfakes Visual Samples with Pre...

引用

Proceedings of the 7th International Conference on Advances in Computing and data Sciences, ICACDS 2023

作者： Nawaz, Marriam Javed, Ali Nazir, Tahira Khan, Muhammad Attique Rajinikanth, Venkatesan Kadry, Seifedine Department of Software Engineering UET Taxila Taxila47050 Pakistan Department of Computing Riphah International University Islamabad Pakistan Department of Computer Science HITEC University Taxila Pakistan Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India Department of Applied Data Science Noroff University College Kristiansand4612 Norway Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon

ISBN: (纸本)9783031379390

Serious security and privacy problems have arisen as a result of significant advancements in the creation of deepfakes. Attackers can easily replace a person’s face with the target person’s face in an image using sophisticated Deep learning (DL) algorithms to spoof their identity. Deepfakes detection algorithms have been proposed in response to the growing concerns about the potential harm caused by deepfakes. However, a reliable deepfakes detector that can keep up with contemporary deepfakes creation techniques is required. In this work, we have proposed an end-to-end methodology for detecting manipulated visual content. We used multiple CNN models i.e., ResNet18, ResNet50, DenseNet65, DenseNet77, and DenseNet100 along with the SVM classifier to compute effective cues from the input facial faces to distinguish between actual and altered content. We have also applied the concept of transfer learning to solve the issue of model over-fitting and improve generalizability against different manipulation algorithms. A comparison study is carried out to evaluate the performance of several feature extractors. Through thorough experiments performed using the Deepfakes Detection Challenge dataset, our results demonstrated that DenseNet100 surpasses the other CNN models by better recognizing deepfakes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Evaluation of OSA Patient Sleep Stage Classification Performance Using a Multi-Channel PSG dataset

Evaluation of OSA Patient Sleep Stage Classification Perform...

引用

2022 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2022

作者： Na, Younghoon Kim, Dongyoung Kim, Dong-Kyu Lee, Jeong-Gun Division of Software Hallym University Chuncheon Korea Republic of Dept. of Computer Engineering Hallym University Chuncheon Korea Republic of Department of Otorhinolaryngology-Head and Neck Surgery Chuncheon Sacred Heart Hospital Hallym University College of Medicine Chuncheon Korea Republic of Institute of New Frontier Research Division of Big Data and Artificial Intelligence Chuncheon Sacred Heart Hospital Chuncheon Korea Republic of

ISBN: (数字)9781665464345

ISBN: (纸本)9781665464345

In this paper, we conduct a comparative analysis of sleep stage classification for patients having different levels of obstructive sleep apnea (OSA). For the analysis, we use 10 bio-signal channels: 4 EEG (Electroencephalogram) channels (F3-M2, F4-M1, C3-M2, and C4-M1), 2 EOG (Electrooculogram) channels (E1-M2 and E2-M1), and 4 other bio-channels (EMG, ECG, Flow, and Abdomen). In this work, in particular, we consider OSA severity for training and testing. Then, we investigated the detailed impacts of the OSA severity on the accuracy performance of a modern deep learning model with single channel and multiple channels. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Behaviour of Tree-Based Neural Networks in Regression Tasks

arXiv

引用

arXiv 2024年

作者： Samoaa, Peter Farahani, Mehrdad Longa, Antonio Leitner, Philipp Chehreghani, Morteza Haghir Data Science and AI Division Chalmers University of Technology Gothenburg Sweden Interaction Design and Software Engineering Division Chalmers University of Technology Gothenburg Sweden Department of Information Engineering and Computer Science University of Trento Trento Italy

The landscape of deep learning has vastly expanded the frontiers of source code analysis, particularly through the utilization of structural representations such as Abstract Syntax Trees (ASTs). While these methodologies have demonstrated effectiveness in classification tasks, their efficacy in regression applications, such as execution time prediction from source code, remains underexplored. This paper endeavours to decode the behaviour of tree-based neural network models in the context of such regression challenges. We extend the application of established models—tree-based Convolutional Neural Networks (CNNs), Code2Vec, and Transformer-based methods—to predict the execution time of source code by parsing it to an AST. Our comparative analysis reveals that while these models are benchmarks in code representation, they exhibit limitations when tasked with regression. To address these deficiencies, we propose a novel dual-transformer approach that operates on both source code tokens and AST representations, employing cross-attention mechanisms to enhance interpretability between the two domains. Furthermore, we explore the adaptation of Graph Neural Networks (GNNs) to this tree-based problem, theorizing the inherent compatibility due to the graphical nature of ASTs. Empirical evaluations on real-world datasets showcase that our dual-transformer model outperforms all other tree-based neural networks and the GNN-based models. Moreover, our proposed dual transformer demonstrates remarkable adaptability and robust performance across diverse datasets. © 2024, CC BY-NC-SA.

关键词： Regression analysis

来源：评论

学校读者我要写书评

暂无评论

Entropy-Based Model Generalization for Sleep Stage Classification 13

Entropy-Based Model Generalization for Sleep Stage Classific...

引用

13th International Conference on Information and Communication Technology Convergence, ICTC 2022

作者： Kim, Dongyoung Na, Younghoon Woo, Yunhee Kim, Dong-Kyu Lee, Jeong-Gun Hallym University Dept. of Computer Engineering Chuncheon Korea Republic of Hallym University Division of Software Chuncheon Korea Republic of Chuncheon Sacred Heart Hospital Hallym University College of Medicine Department of Otorhinolaryngology-Head and Neck Surgery Chuncheon Korea Republic of Institute of New Frontier Research and Division of Big Data and Artificial Intelligence Chuncheon Sacred Heart Hospital Chuncheon Korea Republic of

ISBN: (数字)9781665499392

ISBN: (纸本)9781665499392

The most recent researches on sleep stage classification have been focused on a model architecture to attain high classification accuracy. Sleep stage classification is performed by human sleep experts and consequently there are some inconsistencies of labels among the scoring experts. To improve robustness of the sleep stage classification model, it is essential to consider those noisy labels which have been commonly mentioned in typical image classification problems as well. To partly solve the problem, we employ 'entropy minimization' in a loss function. By including the entropy, we can make a generalized model with regard to the label noises. To validate the effectiveness of the use of entropy on model generalization, we use two different datasets gathered from two institutions. We train a model only using a dataset obtained from one institution. Then we test the model using the dataset of another institution to investigate the accuracy improvement by the generalization. © 2022 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

CAN-D: A modular four-step pipeline for comprehensively decoding controller area network data

arXiv

引用

arXiv 2020年

作者： Verma, Miki E. Bridges, Robert A. Sosnowski, Jordan J. Hollifield, Samuel C. Iannacone, Michael D. Cyber & Applied Data Analytics Division Oak Ridge National Laboratory Oak RidgeTN United States Department of Computer Science & Software Engineering Auburn University

Controller area networks (CANs) are a broadcast protocol for real-time communication of critical vehicle subsystems. Original equipment manufacturers of passenger vehicles hold secret their mappings of CAN data to vehicle signals, and these definitions vary according to make, model, and year. Without these mappings, the wealth of real-time vehicle information hidden in the CAN packets is uninterpretable, severely impeding vehicle-related research, including CAN cybersecurity and privacy studies, aftermarket tuning, efficiency and performance monitoring, and fault diagnosis to name a few. Guided by the four-part CAN signal definition, we present CAN-D (CAN-Decoder), a modular, four-step pipeline for identifying each signal's boundaries (start bit and length), endianness (byte ordering), signedness (bit-to-integer encoding), and by leveraging diagnostic standards, augmenting a subset of the extracted signals with meaningful, physical interpretation. En route to CAN-D, we provide a comprehensive review of the CAN signal reverse engineering research. All previous methods ignore endianness and signedness, rendering them incapable of decoding many standard CAN signal definitions. Incorporating endianness grows the search space from 128 to 4.72E21 signal tokenizations and introduces a web of changing dependencies. In response, we formulate, formally analyze, and provide an efficient solution to an optimization problem, allowing identification of the optimal set of signal boundaries and byte orderings. In addition, we provide two novel, state-of-the-art signal boundary classifiers-both of which are superior to previous approaches in precision and recall in three different test scenarios-and the first signedness classification algorithm, which exhibits a > 97% F-score. Overall, CAN-D is the only solution with the potential to extract any CAN signal that is also the state of the art. In evaluation on 10 vehicles of different makes, CAN-D's average l1 error is five times bette

关键词： Control system synthesis

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：