检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tassi, Stavroula C. Polyzos, Konstantinos D. Fotiadis, Dimitrios I. Sakellarios, Antonis I. Department of Material Science and Engineering Ioannina Greece University of Patras Department of Mechanical and Aeronautics Engineering Patras Greece University of Minnesota Department of Electrical and Computer Engineering MN United States Biomedical Reasearch Institute Ioannina Greece University of Patras Laboratory of Biomechanics and Biomedical Engineering Department of Mechanical and Aeronautics Engineering Patras Greece Ioannina Greece

ISBN: (纸本)9798350337488

Cardiovascular disease (CVD) poses a significant global health challenge, and accurate inference methods are vital for early detection and intervention. However, the quality of prediction relies heavily on the availability of labeled data, which are often limited in medical applications. To cope with the challenge of limited labeled data, we are the first to propose an active learning (AL) approach that leverages a weighted ensemble of Gaussian processes to effectively infer CVD by strategically selecting the few most informative data points to label. Through experiments conducted on the SMARTool dataset, we demonstrate the effectiveness of the advocated approach, achieving superior performance in CVD inference compared to baseline methods. Our findings highlight the potential impact of the proposed AL framework in CVD diagnosis and treatment clinical cases, particularly in scenarios where labeled data are scarce, due to data confidentiality concerns or high sampling costs. © 2023 IEEE.

关键词： CVD inference Ensemble of Gaussian Processes (EGPs) FFR index Gaussian Processes (GPs)

来源：评论

学校读者我要写书评

暂无评论

Hoist Control Stabilization with Real-Time Gyroscopic Data 14

Hoist Control Stabilization with Real-Time Gyroscopic Data

引用

14th IEEE Integrated STEM Education Conference, ISEC 2024

作者： Yu, Howard Peng, Rui Zheng, Meiyu Huang, Zhilin Tang, Luyi Lanzerotti, Mary Virginia Polytechnic Institute & State University Bradley Department of Electrical and Computer Engineering BlacksburgVA24060 United States Virginia Polytechnic Institute & State University Department of Biomedical Engineering and Mechanics BlacksburgVA24060 United States

ISBN: (纸本)9798350352801

A typical aerial medical evacuation (MEDEVAC) rescue retrieves a patient into the helicopter by shortening a 6-meter-long cable. This paper is dedicated to the design, construction, testing, and analysis of the swing stabilization of a gyroscope-equipped payload with variable length control of the cable. The stabilization algorithm uses real-time gyroscope data to control the hoist. Tracking software is employed to meticulously acquire experimental data from videos of the rescues. These data sets are subsequently analyzed using MATLAB. This paper aims to emphasize the necessity for enhancements in sensor platforms and to establish precise constraints for future rescue scenarios. Testing results for a rescue scenario show that the 6.0 m cable is shortened to approximately 0.2 m in about 75 s in two phases. In the first phase, the cable length decreases to 3.7 m in ≈72 s by shortening the cable at the ends of the swing. In the second phase, the cable is continuously shortened to ≈0.2 m in length from t ≈ 72 s to t ≈ 75 s. The results demonstrate that swing stabilization with reduced swing angle is achieved using variable length control hoisting. © 2024 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

NIR-Responsive Methotrexate-Modified Iron Selenide Nanorods for Synergistic Magnetic Hyperthermic, Photothermal, and Chemodynamic Therapy

引用

ACS Applied Materials and Interfaces 2024年第20期16卷 25622-25636页

作者： Thirumurugan, Senthilkumar Muthiah, Kayalvizhi Samuvel Lin, Yu-Chien Dhawan, Udesh Liu, Wai-Ching Wang, An-Ni Liu, Xinke Hsiao, Michael Tseng, Ching-Li Chung, Ren-Jei No. 1 Section 3 Zhongxiao East Road Taipei10608 Taiwan Centre for the Cellular Microenvironment Division of Biomedical Engineering James Watt School of Engineering Mazumdar-Shaw Advanced Research Centre University of Glasgow GlasgowG116EW United Kingdom Faculty of Science and Technology Technological and Higher Education Institute of Hong Kong Hong Kong New Territories999077 Hong Kong Scrona AG Grubenstrasse 9 Zürich8045 Switzerland College of Materials Science and Engineering Chinese Engineering and Research Institute of Microelectronics Shenzhen University Shenzhen518060 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Genomics Research Center Academia Sinica Taipei115 Taiwan Department and Graduate Institute of Veterinary Medicine School of Veterinary Medicine National Taiwan University Taipei10617 Taiwan Graduate Institute of Biomedical Materials and Tissue Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan International Ph.D. Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Research Center of Biomedical Device College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan International Ph.D. Program in Cell Therapy and Regenerative Medicine College of Medicine Taipei Medical University Taipei11031 Taiwan Taipei10608 Taiwan

Breast cancer is a malignant tumor with a high mortality rate among women. Therefore, it is necessary to develop novel therapies to effectively treat this disease. In this study, iron selenide nanorods (FeSe2 NRs) were designed for use in magnetic hyperthermic, photothermal, and chemodynamic therapy (MHT/PTT/CDT) for breast cancer. To illustrate their efficacy, FeSe2 NRs were modified with the chemotherapeutic agent methotrexate (MTX). MTX-modified FeSe2 (FeSe2-MTX) exhibited excellent controlled drug release properties. Fe2+ released from FeSe2 NRs induced the release of •OH from H2O2 via a Fenton/Fenton-like reaction, enhancing the efficacy of CDT. Under alternating magnetic field (AMF) stimulation and 808 nm laser irradiation, FeSe2-MTX exerted potent hyperthermic and photothermal effects by suppressing tumor growth in a breast cancer nude mouse model. In addition, FeSe2 NRs can be used for magnetic resonance imaging in vivo by incorporating their superparamagnetic characteristics into a single nanomaterial. Overall, we presented a novel technique for the precise delivery of functional nanosystems to tumors that can enhance the efficacy of breast cancer treatment. © 2024 The Authors. Published by American Chemical Society

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based ROI Segmentation using Convolution Neural Network 2

Deep Learning based ROI Segmentation using Convolution Neura...

引用

2nd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2023

作者： Arunadevi, R. Sudha, S. Karthi, V. Saranya, M.D. Raaj, Thurai V B Kumar K, Kavin Karpagam Academy of Higher Education Department of Biomedical Engineering Coimbatore India Velalar College of Engineering and Technology Department of Biomedical Engineering Erode India K S R Institute for Engineering and Technology Department of Computer Science and Engineering Tiruchengode India Kpr Institute of Engineering and Technology Department of Electronics and Communication Engineering Coimbatore India Madanapalle Institute of Technology & Science Department of Electrical and Electronics Engineering India Kongu Engineering College Department of Electronics and Communication Engineering Erode638060 India

ISBN: (纸本)9781665456302

Atherosclerosis is a chronic degenerative disease that results in cardiovascular diseases (CVDs) and is detected either by cardiac arrest or stroke. Early diagnosis of CVDs is made possible by identifying Intima Media Thickness (IMT) and elasticity. B-mode ultrasound imaging has on no account ionizing radiation and is economical and non-invasive to assess CVDs. This paper proposes an effective automatic image segmentation method using deep learning CNN for segmenting the region containing intima media of far wall carotid artery. The proposed approach is compared with SVM classifier and RBF neural network and is proven to be robust with improved accuracy and F1 score. © 2023 IEEE.

关键词： Ionizing radiation

来源：评论

学校读者我要写书评

暂无评论

Physics-Driven Deep Learning Reconstruction of Frequency-Modulated Rabi-Encoded Echoes for Faster Accessible MRI 46

Physics-Driven Deep Learning Reconstruction of Frequency-Mod...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Saberi, Mahdi Jenkins, Parker Garwood, Michael Akcakaya, Mehmet University of Minnesota Department of Electrical and Computer Engineering MinneapolisMN United States University of Minnesota Center for Magnetic Resonance Research MinneapolisMN United States University of Minnesota Department of Biomedical Engineering MinneapolisMN United States

ISBN: (纸本)9798350371499

Magnetic resonance imaging (MRI) is a powerful imaging modality with exceptional soft tissue contrast capabilities, but it is estimated to only serve 10% of the world's population reliably. This lack of access is largely due to the multi-million cost of initial investment, as well as recurring expenses. Radiofrequency (RF) imaging methods present an opportunity to reduce MRI costs by replacing expensive B0 gradients with less expensive RF B1+ field gradients for spatial encoding. Frequency-modulated Rabi encoded echoes (FREE) is one such technique that has demonstrated robust phase-encoded imaging capabilities over large inhomogeneities. However, conventional reconstruction of such acquisitions lead to distortions due to nonlinear phase accrual, and imaging speed is slow when B1+ phase encoding is employed in two spatial dimensions. In this work, we propose a physics-driven deep learning (PD-DL) reconstruction approach to resolve distortion artifacts of FREE acquisitions, while enabling higher acceleration rates. We map out the forward operator for FREE encoding, and devise an unrolled network that utilizes this operator. Results on sequential gradient superposition (SGS) FREE sequence indicates feasibility of up to 4-fold acceleration with a single receive-coil. © 2024 IEEE.

关键词： Frequency modulation

来源：评论

学校读者我要写书评

暂无评论

Characterization of a Remote Fiber Optic Strain Sensing System

Characterization of a Remote Fiber Optic Strain Sensing Syst...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

作者： Daxini, Swapnil Aydin, Deniz Giron-Santos, Arthur Barnes, Jack Gu, Xijia Loock, Hans-Peter University of Victoria Department of Physics VictoriaBC Canada Queen's University Department of Chemistry KingstonON Canada Toronto Metropolitan University Department of Electrical Computer and Biomedical Engineering TorontoON Canada

We present a passive, all-fiber strain sensing system capable of measuring strain over 75 km using a diode laser locked to a π-shifted grating, with potential applications to develop a fiber optic hydrophone. © ... 详细信息

关键词： Fiber optics

来源：评论

学校读者我要写书评

暂无评论

Aerodynamic Effects Compensation on Multi-Rotor UAVs Based on a Neural Network Control Allocation Approach

引用

IEEE/CAA Journal of Automatica Sinica 2022年第2期9卷 295-312页

作者： Sarah P.Madruga Augusto H.B.M.Tavares Saulo O.D.Luiz Tiago P.do Nascimento Antonio Marcus N.Lima Graduate Program of Electrical Engineering Universidade Federal de Campina GrandeCampina Grande-PBBrazil Department of Electrical Engineering Universidade Federal de Campina GrandeCampina Grande-PBBrazil IEEE Department of Computer Systems Universidade Federal da ParaibaJoao Pessoa-PBBrazil

This paper shows that the aerodynamic effects can be compensated in a quadrotor system by means of a control allocation approach using neural ***,the system performance can be improved by replacing the classic allocation matrix,without using the aerodynamic inflow equations *** network training is performed offline,which requires low computational *** target system is a Parrot MAMBO drone whose flight control is composed of PD-PID controllers followed by the proposed neural network control allocation *** a quadrotor is particularly susceptible to the aerodynamics effects of interest to this work,because of its small *** compared the mechanical torques commanded by the flight controller,i.e.,the control input,to those actually generated by the actuators and established at the *** was observed that the proposed neural network was able to closely match them,while the classic allocation matrix could not achieve *** allocation error was also determined in both ***,the closed-loop performance also improved with the use of the proposed neural network control allocation,as well as the quality of the thrust and torque signals,in which we perceived a much less noisy behavior.

关键词： Aerodynamics effects control allocation minidrone multi-rotor UAV neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Multiclass Brain Tumor Detection in MRI Using Similarity-Navigated Graph Neural Networks with Banyan Tree Growth Optimization 4

Enhanced Multiclass Brain Tumor Detection in MRI Using Simil...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Babu Rao, K. Singh, Pallavi Verma, Gargi Shankar Kannan, L. Mohana Kadam, Swaraj Mangalore Institute of Technology & Engineering Department of Computer Science and Engineering Karnataka Mijar India Saraswati Dental College & Hospital Department of Public Health Dentistry Uttar Pradesh Lucknow India Krishna's Vikash Institute of Technology Department of Computer Science and Engineering Chhattisgarh Raipur India Erode Sengunthar Engineering College Department of Biomedical Engineering Tamil Nadu Perundurai India Dr. D Y Patil Institute of Technology Department of Electrical Engineering Maharashtra Pune India

ISBN: (纸本)9798331529635

The diagnosis of brain tumors is admittedly difficult because of their varied and complicated nature. Therefore, one has to get the right diagnosis and categorization for it to be treated well. This is a situation where identification of multiple classes such as;meningioma, pituitary, glioma and no tumor is crucial in taking the right course of action. Therefore, a new deep learning architecture is suggested in this work to increase the specificity between different types of tumors by detecting brain tumors with high accuracy in MRI scans. The proposed methodology starts with the Cumulative Curve Fitting Approximation (CCFA) preprocessing algorithm to improve the quality of MRI images. Preprocessed images are used as inputs for feature extraction based on geometric algebra transformers. These transformers include geometric relationships within the data, ensuring more distinctive selection. The categorization is further carried out with assistance of a Similarity-Navigated Graph Neural Network (SNGNN) incorporating the Banyan Tree Growth Optimizer (BTGO) model, which is constructed for efficient detection of the subtlest patterns and their connection between classes of brain tumors. It integrates very well in terms of the accuracy shown by its performance metrics. It shows effectiveness in a multiclass scenario of detecting brain tumors, which helps in the precise and early diagnosis and even tailors proper treatment plans. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

The good, the bad and the ugly sides of data augmentation: an implicit spectral regularization perspective

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 4470-4554页

作者： Chi-Heng Lin Chiraag Kaushik Eva L. Dyer Vidya Muthukumar School of Electrical & Computer Engineering Georgia Institute of Technology Atlanta GA Coulter Department of Biomedical Engineering School of Electrical & Computer Engineering Georgia Institute of Technology Atlanta GA School of Electrical & Computer Engineering School of Industrial & Systems Engineering Georgia Institute of Technology Atlanta GA

Data augmentation (DA) is a powerful workhorse for bolstering performance in modern machine learning. Specific augmentations like translations and scaling in computer vision are traditionally believed to improve generalization by generating new (artificial) data from the same distribution. However, this traditional viewpoint does not explain the success of prevalent augmentations in modern machine learning (e.g. randomized masking, cutout, mixup), that greatly alter the training data distribution. In this work, we develop a new theoretical framework to characterize the impact of a general class of DA on underparameterized and overparameterized linear model generalization. Our framework reveals that DA induces implicit spectral regularization through a combination of two distinct effects: a) manipulating the relative proportion of eigenvalues of the data covariance matrix in a training-data-dependent manner, and b) uniformly boosting the entire spectrum of the data covariance matrix through ridge regression. These effects, when applied to popular augmentations, give rise to a wide variety of phenomena, including discrepancies in generalization between over-parameterized and under-parameterized regimes and differences between regression and classification tasks. Our framework highlights the nuanced and sometimes surprising impacts of DA on generalization, and serves as a testbed for novel augmentation design.

关键词： data augmentation generalization analysis overparameterized models spectral analysis regression classification

来源：评论

学校读者我要写书评

暂无评论

Safety Comparison of Vehicular Platoons Under Different Bidirectional Communication Topologies: A Signal Analysis Method 27

Safety Comparison of Vehicular Platoons Under Different Bidi...

引用

27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024

作者： Zakerimanesh, Amir Qiu, Tony Z. Tavakoli, Mahdi University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 1H9 Canada University of Alberta Department of Civil and Environmental Engineering EdmontonABT6G 1H9 Canada University of Alberta Department of Electrical and Computer Engineering The Department of Biomedical Engineering EdmontonABT6G 1H9 Canada

ISBN: (纸本)9798331505929

This paper conducts a comparative analysis of bidirectional communication topologies in vehicular platooning, emphasizing their impact on safety during travel. Introducing two novel metrics, the Accumulative Average Penalty of Minimum Time to Collision (AAPMTTC) and Accumulative Average Deceleration Rate to Avoid Collision (AADRAC), the study evaluates collision susceptibility between neighboring vehicles, taking into consideration their relative velocities and accelerations. Utilizing platoon dynamics based on intervehicle distances and their derivatives, the analysis captures the evolving vehicle behaviors over travel time. Results highlight the safety benefits of communication topologies where follower vehicles receive information from more preceding vehicles, particularly when incorporating the leader vehicle's state. This research underscores the significance of information exchange within vehicular platoons and offers insights for providing more safety through design of communication structure in automated driving scenarios in vehicular platooning. © 2024 IEEE.

关键词： Vehicle safety

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：