检索结果-内蒙古大学图书馆

17th International Conference on Signal Processing and Communication Systems, ICSPCS 2024

作者： Hammoud, Houssam Al Aref, Mohammad Yaman Al Jabouli, Mayar Hammoud, Mohamad Shehieb, Wessam Arshad, Kamran Ajman Univeristy College of Engineering and Information Technology Department of Biomedical Engineering Ajman United Arab Emirates Ajman Univeristy College of Engineering and Information Technology Department of Electrical and Computer Engineering Ajman United Arab Emirates Ajman University Artificial Intelligence Research Centre Ajman United Arab Emirates

ISBN: (纸本)9798350389630

Traditional diagnostic methods such as Fundus cameras and slit-lamps that are used for diagnosing various ocular diseases are often limited by their cost and accessibility which hinders timely intervention especially in rural areas and indigent societies with limited resources. While the current research is mostly focused on classification of single diseases or expensive setups, the proposed work aims to address these limitations by developing a cost-effective and user-friendly system for primary diagnosis of various ocular diseases, including Diabetic Retinopathy, Age-Related Macular Degeneration and Glaucoma. The proposed work utilizes a smartphone, cloud-based deep learning model, and a 3D printed multi-lens holder for fundus imaging. This research leverages open-source datasets for model training and testing, added to new sets of images that were collected throughout this work for validation. The new set tested the quality of the captured images in actual setup and verified accurate classification. Based on the results, the system has been successfully implemented and the overall classification accuracy of the multi-classification ResNet-50 model is 74%. Preliminary results demonstrate the potential of this approach for multi-classification of ocular diseases, marking a significant advancement in portable ocular health primary diagnostics. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Optically-generated focused ultrasound for noninvasive brain stimulation with ultrahigh precision

引用

Light(Science & Applications) 2022年第11期11卷 2817-2831页

作者： Yueming Li Ying Jiang Lu Lan Xiaowei Ge Ran Cheng Yuewei Zhan Guo Chen Linli Shi Runyu Wang Nan Zheng Chen Yang Ji-Xin Cheng Department of Mechanical Engineering Boston UniversityBostonMA 02215USA Graduate Program for Neuroscience Boston UniversityBostonMA 02215USA Department of Electrical and Computer Engineering Boston UniversityBostonMA 02215USA Department of Chemistry Boston UniversitBostonMA 02215USA Department of Biomedical Engineering Boston UniversityBostonMA 02215USA Division of Materials Science and Engineering Boston UniversityBostonMA 02215USA Department of Biological Engineering Massachusetts Institute of TechnologyCambridgeMA 02142USA

High precision neuromodulation is a powerful tool to decipher neurocircuits and treat neurological *** non-invasive neuromodulation methods offer limited precision at the milimeter ***,we report opticallygenerated focused ultrasound(OFUS)for non-invasive brain stimulation with ultrahigh *** is generated by a soft optoacoustic pad(SOAP)fabricated through embedding candle soot nanoparticles in a curved polydimethylsiloxane *** generates a transcranial ultrasound focus at 15 MHz with an ultrahigh lateral resolution of 83μm,which is two orders of magnitude smaller than that of conventional transcranial-focused ultrasound(tFUS).Here,we show effective OFUS neurostimulation in vitro with a single ultrasound *** demonstrate submillimeter transcranial stimulation of the mouse motor cortex in *** acoustic energy of 0.6 mJ/cm?,four orders of magnitude less than that of tFUS,is suffcient for successful OFUS *** offers new capabilities for neuroscience studies and disease treatments by delivering a focus with ultrahigh precision noninvasively.

关键词： SOAP stimulation precision

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

Gaussian Process-based Active Learning for Efficient Cardiovascular Disease Inference

Gaussian Process-based Active Learning for Efficient Cardiov...

引用

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

Using Sparse Autoencoders to Perform Blind Source Separation of High-Density Myoelectric Signal 33

Using Sparse Autoencoders to Perform Blind Source Separation...

引用

33rd IEEE International Workshop on Machine Learning for Signal Processing, MLSP 2023

作者： Romano, Marcelo Ramos Duarte, Leonardo Tomazeli Elias, Leonardo Abdala University of Campinas School of Applied Sciences SP Limeira Brazil University of Campinas Neural Engineering Research Laboratory Center for Biomedical Engineering SP Campinas Brazil University of Campinas Department of Electronics and Biomedical Engineering School of Electrical and Computer Engineering SP Campinas Brazil

ISBN: (纸本)9798350324112

A recent approach to address the blind source separation (BSS) problem relies on autoencoders with a discriminator as a generative adversarial network (GAN). However, this model is difficult to train due to the lack of metrics that ensure the convergence of a GAN. In this study, we try to provide an alternative solution by replacing the discriminator with appropriate regularization functions based on prior information on the sources. We tested this solution in the high-density electromyogram (HD-EMG) separation problem for a scenario with synthetic but realistic data and compared it with a classic algorithm from the literature. An interesting feature of the proposal is that it can be easily adapted for other source separation problems. Moreover, although the performance is slightly worse than the state-of the-art HD-EMG algorithm, which considers very detailed information on the problem, our proposal provides good results with a mean rate of agreement of 91.88% between the true and estimated spikes. © 2023 IEEE.

关键词： Generative adversarial networks

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

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：