检索结果-内蒙古大学图书馆

11th International Conference on Information Technology in Medicine and Education, ITME 2021

作者： Yang, Xinquan Li, Xuechen Shen, Linlin Cao, Min Zhou, Changen College of Computer Science and Software Engineering Ai Research Center for Medical Image Analysis Diagnosis Shenzhen University Shenzhen China Guangzhou Panyu Sanatorium Radiology Department Guangzhou China School of Traditional Chinese Medicine Fujian University of Traditional Chinese Medicine Fuzhou China

ISBN: (纸本)9781665406796

Lung disease screening using Chest x-ray (CXR) radiographs can obviously decrease the incidence of lung cancer. Using computer-aided diagnosis system to assist doctors in lung disease screening can greatly improve the diagnosis efficiency. In this paper, a coarse feature reuse deep neural network for CXR lesion detection is proposed. Firstly, we design a coarse feature reuse (CFR) block that can reuse low-level semantic features and extract high-level semantic information, which is used to replace the max-pooling layer in the shallow part of the network to achieve better feature extraction. A novel backbone network - RRCNet, which combines RepVGG block and Resblock, is proposed. The RepVggblock is used for better feature extraction at shallow layers and the Resblock is used for better feature fusion at deep layers. Extensive experiments on VinDr-CXR dataset demonstrate that our RRCNet-based detection network outperformes other classic detectors on both mAP (17.67%) and inference speed (0.1426s). © 2021 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Noninherited Factors in Fetal Congenital Heart Diseases Based on Bayesian Network:A Large Multicenter Study

引用

Congenital Heart Disease 2021年第6期16卷 529-549页

作者： Yanping Ruan Xiangyu Liu Haogang Zhu Yijie Lu Xiaowei Liu Jiancheng Han Lin Sun Ye Zhang Xiaoyan Gu Ying Zhao Lei Li Suzhen Ran Jingli Chen Qiong Yu Yan Xu Hongmei Xia Yihua He Department of Echocardiography Maternal-Fetal Medicine Research Consultation CenterBeijing Anzhen HospitalCapital Medical UniversityBeijing100029China School of Biological Science and Medical Engineering Beihang UniversityBeijing100083China State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing100191China Department of Ultrasound Chongqing Health Center for Women and ChildrenChongqing400013China Department of Ultrasound Urumqi Maternal and Child Health HospitalUrumqi830001China Department of Ultrasound Pingxiang Maternal and Child CarePingxiang337055China Department of Ultrasound People’s Hospital of RizhaoRizhao276800China Department of Ultrasound Xinqiao Hospital Army Medical UniversityChongqing400038China

Background:Current studies have confirmed that fetal congenital heart diseases(CHDs)are caused by various ***,the quantitative risk of CHD is not clear given the combined effects of multiple ***:This cross-sectional study aimed to detect associated factors of fetal CHD using a Bayesian network in a large sample and quantitatively analyze relative risk ratios(RRs).Methods:Pregnant women who underwent fetal echocardiography(N=16,086 including 3,312 with CHD fetuses)were ***-six maternal and fetal factors were obtained.A Bayesian network is constructed based on all variables through structural learning and parameter learning methods to find the environmental factors that directly and indirectly associated with outcome,and the probability of fetal CHD in the two groups is predicted through a junction tree reasoning algorithm,so as to obtain RR for fetal CHD under different exposure factor *** into account the effect of gestational week on the accuracy of model prediction,we conducted sensitivity analysis on gestational week ***:The single-factor analysis showed that the RRs for the numbers of births,spontaneous abortions,and parental smoking were 1.50,1.38,and 1.11(P<0.001),*** risk gradually increased with the synergistic effect of ranging from one to more environmental factors *** risk was higher among subjects with five synergistic factors,including the number of births,upper respiratory tract infection during early pregnancy,anemia,and mental stress as well as a history of spontaneous abortions or parental smoking,than in those with less than 5 factors(RR=2.62 or 2.28,P<0.001).This result was consistent across the participants grouped by ***:We identified six factors that were directly associated with fetal CHD.A higher number of these factors led to a higher risk of *** findings suggest that it is important to strengthen healthcare and prenatal counseling for women

关键词： Congenital heart diseases bayesian network risk ratio factor

来源：评论

学校读者我要写书评

暂无评论

Lasing from GaAs Nanowires on Fe Films

Lasing from GaAs Nanowires on Fe Films

引用

Laser Science, LS 2021 - Part of Frontiers in Optics, FiO 2021

作者： Aman, Gyanan Fränzl, Martin Lysevych, Mykhaylo Tan, Hark Hoe Jagadish, Chennupati Schmitzer, Heidrun Cahay, Marc Wagner, Hans Peter Department of Electrical Engineering and Computer Science University of Cincinnati OH45221 United States Department of Physics University of Cincinnati OH45221 United States Department of Physics University of Leipzig 04109 Germany ARC Center of Excellence for Transformative Meta-Optical Systems Department of Electronic Materials Engineering Research School of Physics The Australian National University ACT2601 Australia Department of Physics Xavier University CincinnatiOH45207 United States

We demonstrate optically pumped nearly photonic lasing from highly Zn-doped GaAs nanowires (NWs) on Fe films at 77 K. High Zn-doping enhances the radiative recombination rate and the material gain to overcome the plas... 详细信息

ISBN: (纸本)9781557528209

关键词： Metallic films

来源：评论

学校读者我要写书评

暂无评论

Advancing Metaverse-Based Healthcare With Multimodal Neuroimaging Fusion Via Multi-Task Adversarial Variational Autoencoder for Brain Age Estimation

引用

IEEE Journal of Biomedical and Health Informatics 2024年 PP卷 PP页

作者： Usman, Muhammad Rehman, Azka Shahid, Abdullah Rehman, Abd Ur Gho, Sung-Min Lee, Aleum Khan, Tariq M. Razzak, Imran Imaging Development Heuron Seoul07292 Korea Republic of Seoul National University Graduate School Department Of Biomedical Sciences Korea Republic of DeepChain Ai&it Technologies Islamabad Pakistan Dongguk University Division Of Electronics And Electrical Engineering Seoul04620 Korea Republic of Soonchunhyang University Bucheon Hospital Department Of Radiology Gyeonggi-do Bucheon-si14584 Korea Republic of Naif Arab University For Security Sciences Center Of Excellence In Cybercrimes And Digital Forensics Riyadh11452 Saudi Arabia University Of New South Wales School Of Computer Science And Engineering SydneyNSW Australia

The metaverse, which integrates physical and virtual realities through technologies such as high-speed internet, virtual and augmented reality, and artificial intelligence (AI), offers transformative prospects across various fields, particularly healthcare. This integration introduces a new paradigm in AI-driven medical imaging, particularly in assessing brain age'a crucial marker for detecting age-related neuropathologies such as Alzheimer's disease (AD) using magnetic resonance imaging (MRI). Despite advances in deep learning for estimating brain age from structural MRI (sMRI), incorporating functional MRI (fMRI) data presents significant challenges due to its complex data structure and the noisy nature of functional connectivity measurements. To address these challenges, we present the Multitask Adversarial Variational Autoencoder (M-AVAE), a bespoke deep learning framework designed to enhance brain age predictions through multimodal MRI data integration. The M-AVAE uniquely separates latent variables into generic and unique codes, effectively isolating shared and modality-specific features. Additionally, integrating multitask learning with sex classification as a supplementary task enables the model to account for sex-specific aging nuances. Evaluated on the OpenBHB dataset'a comprehensive multisite brain MRI aggregation-the M-AVAE demonstrates exceptional performance, achieving a mean absolute error of 2.77 years, surpassing conventional methodologies. This success positions M-AVAE as a powerful tool for metaverse-based healthcare applications in brain age estimation. The source code is made publicly available at: https://***/engrussman/MAVAE. © 2013 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Robust Voltage Control in DC Networks with Uncertain Nonlinear Load Dynamics

Robust Voltage Control in DC Networks with Uncertain Nonline...

引用

IEEE Conference on Decision and Control

作者： Amirreza Silani Giacomo Casadei Michele Cucuzzella Jan C. Wilems Center for Systems and Control ENTEG Faculty of Science and Engineering University of Groningen AG Groningen The Netherlands Control & Intelligent Processing Center of Excellence School of Electrical and Computer Engineering University of Tehran Tehran Iran Laboratoire Ampere Dpt. EEA of the Ecole Centrale de Lyon Université de Lyon Ecully France Department of Electrical Computer and Biomedical Engineering University of Pavia Pavia Italy

ISBN: (数字)9781665467612

ISBN: (纸本)9781665467629

In this letter, we propose a control scheme for regulating the voltage in Direct Current (DC) power networks. In contrast with other works in the literature where the loads are assumed to be constant, we consider uncertain time-varying loads described as the outputs of nonlinear dynamical exosystems with uncertain parameters. Based on the output regulation methodology, the proposed control scheme ensures the robust stability of the overall network and achieves voltage regulation in presence of impedance (Z), current (I), and power (P) loads. The simulation results illustrate excellent performance of the proposed control scheme.

关键词： Robust stability Simulation Regulation Impedance Voltage control

来源：评论

学校读者我要写书评

暂无评论

Sex-specific differences in the efficacy of traditional low frequency versus high frequency spinal cord stimulation for chronic pain

引用

Bioelectronic Medicine 2022年第1期8卷 1-14页

作者： Conic, Rosalynn R. Z. Caylor, Jacob Cui, Christina L. Reyes, Zabrina Nelson, Eric Yin, Sopyda Lerman, Imanuel Department of Family Medicine and Public Health University of California San Diego La JollaCA United States Department of Anesthesiology Center for Pain Medicine University of California San Diego School of Medicine La JollaCA United States Northwest Pain Care PS SpokaneWA United States Division of Vascular and Endovascular Surgery Department of Surgery Duke University Medical Center DurhamNC United States School of Medicine University of California San Diego San DiegoCA United States College of Osteopathic Medicine of the Pacific Western University of Health Sciences PomonaCA United States Department of Electrical and Computer Engineering University of California San Diego La JollaCA United States VA Center of Excellence for Stress and Mental Health VA San Diego Healthcare System La JollaCA United States San DiegoCA92161 United States

Introduction: Spinal cord stimulation (SCS), an FDA-approved therapy for chronic pain, uses paresthesia (low frequency SCS (LF-SCS)) or paresthesia-free (such as high-frequency SCS (HF-SCS)) systems, providing analgesia through partially-elucidated mechanisms, with recent studies indicating a sexual dimorphism in pain pathogenesis (Bretherton et al., Neuromodulation, 2021;Paller et al., Pain Med 10:289–299, 2009;Slyer et al., Neuromodulation, 2019;Van Buyten et al., Neuromodulation 20:642–649, 2017;Mekhail et al., Pain Pract, 2021). We aim to evaluate SCS therapy sex effects based on paradigm, utilizing visual analog scores (VAS), perceived pain reduction (PPR), and opioid use. Methods: A retrospective cohort study of SCS patients implanted between 2004 and 2020 (n = 237) was conducted. Descriptive statistics and linear mixed methods analyses were used. Results: HF-SCS (10 kHz) was implanted in 94 patients (40 females, 54 males), and LF-SCS in 143 (70 females, 73 males). At 3 months and 6 months, HF-SCS (p © 2022, The Author(s).

关键词： Spinal cord stimulator Outcomes HF-SCS LF-SCS VAS Opioid Sex

来源：评论

学校读者我要写书评

暂无评论

SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks

arXiv

引用

arXiv 2025年

作者： Malialis, Kleanthis Filippou, Stylianos Panayiotou, Christos G. Polycarpou, Marios M. KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus

Data stream mining, also known as stream learning, is a growing area which deals with learning from high-speed arriving data. Its relevance has surged recently due to its wide range of applicability, such as, critical infrastructure monitoring, social media analysis, and recommender systems. The design of stream learning methods faces significant research challenges;from the nonstationary nature of the data (referred to as concept drift) and the fact that data streams are typically not annotated with the ground truth, to the requirement that such methods should process large amounts of data in real-time with limited memory. This work proposes the SiameseDuo++ method, which uses active learning to automatically select instances for a human expert to label according to a budget. Specifically, it incrementally trains two siamese neural networks which operate in synergy, augmented by generated examples. Both the proposed active learning strategy and augmentation operate in the latent space. SiameseDuo++ addresses the aforementioned challenges by operating with limited memory and limited labelling budget. Simulation experiments show that the proposed method outperforms strong baselines and state-of-the-art methods in terms of learning speed and/or performance. To promote open science we publicly release our code and datasets. © 2025, CC BY.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

On Quantized Sampled–Data Event–Triggered Consensus Tracking of Nonlinear Multi–Agent Time–Delay Systems

引用

IFAC-PapersOnLine 2022年第36期55卷 276-281页

作者： M. Di Ferdinando P. Pepe S. Di Gennaro Department of Information Engineering Computer Science and Mathematics University of L'Aquila Via Vetoio Loc. Coppito 67100 L'Aquila Italy Center of Excellence for Research DEWS University of L'Aquila Via Vetoio Loc. Coppito 67100 L'Aquila Italy

In this paper, the quantized sampled-data leaderless consensus tracking problem of nonlinear time–delay multi–agent systems (MASs) is studied. In particular, a new methodology for the design of quantized sampled–data event–triggered controllers achieving the leaderless consensus tracking of nonlinear MASs affected by state–delays is proposed. Firstly, the notion of steepest descent consensus feedback (SDCF), induced by a general class of Lyapunov–Krasovskii functionals, is introduced. Then, it is proved that there exist a suitably accurate quantization of the input channels and a suitably small maximum inter–sampling time such that: the digital implementation of SDCFs (continuous or not), with an event-triggered mechanism to update the control law only when necessary, achieves the leaderless consensus tracking in a semi–global practical sense of the related closed–loop MAS. The stabilization in the sample-and-hold sense theory is used as a tool for proving the results. The possible non–uniform quantization of the input channels is considered. Moreover, the case of time–varying sampling intervals as well as the stability analysis of the inter–sampling system behaviour is included in the theory here developed. An example is studied in order to validate the results.

关键词： Nonlinear Multi–Agent Time–Delay Systems Leaderless Consensus Tracking Quantized Sampled–Data Event–Triggered Control Control Lyapunov–Krasovskii Functionals

来源：评论

学校读者我要写书评

暂无评论

Towards Mutual Trust-Based Matching For Federated Learning Client Selection

Towards Mutual Trust-Based Matching For Federated Learning C...

引用

International Wireless Communications and Mobile Computing Conference, IWCMC

作者： Osama Wehbi Omar Abdel Wahab Azzam Mourad Hadi Otrok Hoda Alkhzaimi Mohsen Guizani Mohammad Bin Zayed University of Artificial Intelligence Abu Dhabi UAE Department of CSM Cyber Security Systems and Applied AI Research Center Lebanese American University Lebanon Department of Computer and Software Engineering Polytechnique Montréal Montreal Quebec Canada Division of Science New York University Abu Dhabi UAE Department of EECS Center of Cyber-Physical Systems (C2PS) Khalifa University Abu Dhabi UAE Division of Engineering New York University Abu Dhabi UAE

Federated Learning (FL) is a revolutionary privacy-preserving distributed learning framework that allows a small group of users to cooperatively build a machine-learning model using their own data locally. Smart cities are areas that can generate high volume and critical data, which has the potential to revolutionize federated learning. Nevertheless, it is highly challenging to select a trustworthy group of clients to collaborate in model training. The utilization of a random selection technique would pose many threats due to malicious clients’ targeted and untargeted attacks. Such vulnerability may cause attacks and poisoning in the produced model. To address this problem, we present a mutual trust client-server selection approach based on matching game theory and bootstrapping mechanisms for federated learning in smart cities. Our solution entails the creation of: (1) preference functions for federated servers and smart devices (i.e., IoT/IoV) that enables them to sort each other based on trust score, (2) light feedback-base technique that leverages the cooperation of multiple client devices to assign trust value to the newly connected federated server, and (3) intelligent matching algorithms consider trust preferences of both parties in their design. According to our simulation results, our technique outperforms the baseline selection approach VanillaFL in terms of increasing the trust level and hence the global accuracy of the federated learning model and optimizing the number of untrusted selected clients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio-Based Deep Learning Frameworks for Detecting COVID-19

arXiv

引用

arXiv 2022年

作者： Ngo, Dat Pham, Lam Hoang, Truong Kolozali, Şefki Jarchi, Delaram School of Computer Science and Electronic Engineering University of Essex United Kingdom Center for Digital Safety & Security Austrian Institute of Technology Austria Solution Technology Unit Department FPT Software Company Limited Viet Nam

This paper evaluates a wide range of audio-based deep learning frameworks applied to the breathing, cough, and speech sounds for detecting COVID-19. In general, the audio recording inputs are transformed into low-level spectrogram features, then they are fed into pre-trained deep learning models to extract high-level embedding features. Next, the dimension of these high-level embedding features are reduced before fine-tuning using Light Gradient Boosting Machine (LightGBM) as a back-end classification. Our experiments on the Second DiCOVA Challenge achieved the highest Area Under the Curve (AUC), F1 score, sensitivity score, and specificity score of 89.03%, 64.41%, 63.33%, and 95.13%, respectively. Based on these scores, our method outperforms the state-of-the-art systems, and improves the challenge baseline by 4.33%, 6.00% and 8.33% in terms of AUC, F1 score and sensitivity score, respectively. Copyright © 2022, The Authors. All rights reserved.

关键词： Spectrographs

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：