检索结果-内蒙古大学图书馆

arXiv 2023年

作者： de Oliveira, Arthur Castello Branco Siami, Milad Sontag, Eduardo D. Department of Electrical & Computer Engineering Northeastern University BostonMA02115 United States Departments of Bioengineering Northeastern University BostonMA02115 United States

— Recent research in neural networks and machine learning suggests that using many more parameters than strictly required by the initial complexity of a regression problem can result in more accurate or faster-converging models – contrary to classical statistical belief. This phenomenon, sometimes known as "benign overfitting", raises questions regarding in what other ways might overparameterization affect the properties of a learning problem. In this work, we investigate the effects of overfitting on the robustness of gradient-descent training when subject to uncertainty on the gradient estimation. This uncertainty arises naturally if the gradient is estimated from noisy data or directly measured. Our object of study is a linear neural network with a single, arbitrarily wide, hidden layer and an arbitrary number of inputs and outputs. In this paper we solve the problem for the case where the input and output of our neural-network are one-dimensional, deriving sufficient conditions for robustness of our system based on necessary and sufficient conditions for convergence in the undisturbed case. We then show that the general overparametrized formulation introduces a set of spurious equilibria which lay outside the set where the loss function is minimized, and discuss directions of future work that might extend our current results for more general formulations. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Design Concept of a Wearable Device for Sleep Related Brain Wave Detection and Stimulation

Design Concept of a Wearable Device for Sleep Related Brain ...

引用

Data Science and computer Application (ICDSCA), IEEE International Conference on

作者： Ariel R. Yin David Z. Zhang David D. Mao Sichuang Li Haoliang Cheng Yangfan Deng Yifan Guo Helen X. Mao Jijun Yin Zhi-Hong Mao Canyon Crest Academy San Diego CA USA University High School Irvine CA USA North Allegheny Intermediate High School Pittsburgh PA USA Department of Electrical and Computer Engineering University of Pittsburgh Pittsburgh PA USA Department of Computer Science University of Pittsburgh Pittsburgh PA USA Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette IN USA Yale College Yale University New Haven CT USA Department of Electrical and Computer Engineering and Bioengineering University of Pittsburgh Pittsburgh PA USA

ISBN: (数字)9798350368239

ISBN: (纸本)9798350368246

This paper presents a design concept of an innovative wearable device for brain wave detection and stimulation to aid sleep. Sleep's importance for a healthy life emphasizes the value of studying the application of technology to improve sleep quality for individuals unable to receive a good night's rest. Utilizing electroencephalography (EEG) for accurate sleep tracking, the device aims to be portable and efficient. It includes the EEG sensing and processing module, adaptive control and machine learning module, and electronic stimulation module, working together to guide the brain toward relaxation. Preliminary results demonstrate promising performances or necessities of the subsystems of the proposed design.

关键词： Performance evaluation Machine learning algorithms Sleep Process control Machine learning Electroencephalography Sensors Wearable devices Adaptive control Testing

来源：评论

学校读者我要写书评

暂无评论

Compensating for the Spatial Impulse Response in 3D Photoacoustic Computed Tomography Using Learned Data Space Restoration Methods

Compensating for the Spatial Impulse Response in 3D Photoaco...

引用

Photons Plus Ultrasound: Imaging and Sensing 2025

作者： Yang, Kaiyi Park, Seonyeong Huang, Hsuan-Kai Villa, Umberto Anastasio, Mark A. Department of Electrical & Computer Engineering University of Illinois Urbana-Champaign IL United States Department of Bioengineering University of Illinois Urbana-Champaign IL United States Oden Institute The University of Texas at Austin AustinTX United States

ISBN: (纸本)9781510683860

Photoacoustic computed tomography (PACT) is a promising modality for biomedical imaging. Many existing reconstruction algorithms for PACT assume that the ultrasound transducers deployed to record the pressure measurements are point-like. However, using transducers with large detecting areas can be advantageous due to enhanced sensitivity and signal-to-noise ratio. Such transducers with finite detection surfaces have anisotropic detection sensitivity described by the spatial impulse response (SIR). When not accounted for, the reconstructed images may suffer from severe, spatially varying degradation in spatial resolution. This study proposes a learning-based method to compensate for SIR in the measurement domain, mapping the pressure data acquired by an array of large rectangular transducers to idealized data corresponding to point-like transducers. The model was trained with analytically computed pressure data from uniform spheres with stochastically determined locations, sizes, and initial pressure values. Subsequently, it was tested on pressure data simulated from realistic numerical breast phantoms. Importantly, although trained on simplified objects, the proposed method demonstrates robust performance on numerical breast phantoms that contain complex anatomical structures unseen in training. © 2025 SPIE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

DART: Deformable Anatomy-Aware Registration Toolkit for Lung CT Registration with Keypoints Supervision

DART: Deformable Anatomy-Aware Registration Toolkit for Lung...

引用

IEEE International Symposium on Biomedical Imaging

作者： Yunzheng Zhu Luoting Zhuang Yannan Lin Tengyue Zhang Hossein Tabatabaei Denise R Aberle Ashley E Prosper Aichi Chien William Hsu Department of Radiological Sciences Medical & Imaging Informatics David Geffen School of Medicine at UCLA Department of Electrical & Computer Engineering UCLA Samueli School of Engineering Medical Informatics Home Area UCLA Graduate Programs in Bioscience Department of Computer Science UCLA Samueli School of Engineering Department of Radiological Sciences David Geffen School of Medicine at UCLA Department of Bioengineering UCLA Samueli School of Engineering

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

Spatially aligning two computed tomography (CT) scans of the lung using automated image registration techniques is a challenging task due to the deformable nature of the lung. However, existing deep-learning-based lung CT registration models are not trained with explicit anatomical knowledge. We propose the deformable anatomy-aware registration toolkit (DART), a masked autoencoder (MAE)-based approach, to improve the keypoint-supervised registration of lung CTs. Our method incorporates features from multiple decoders of networks trained to segment anatomical structures, including the lung, ribs, vertebrae, lobes, vessels, and airways, to ensure that the MAE learns relevant features corresponding to the anatomy of the lung. The pretrained weights of the transformer encoder and patch embeddings are then used as the initialization for the training of downstream registration. We compare DART to existing state-of-the-art registration models. Our experiments show that DART outperforms the baseline models (Voxelmorph, ViT-V-Net, and MAE-TransRNet) in terms of target registration error of both corrField-generated keypoints with 17%, 13%, and 9% relative improvement, respectively, and bounding box centers of nodules with 27%, 10%, and 4% relative improvement, respectively. Our implementation is available at https://***/yunzhengzhu/DART.

关键词： Training Image registration Computed tomography Computational modeling Lung Brain modeling Transformers

来源：评论

学校读者我要写书评

暂无评论

An exact active sensing strategy for a class of bio-inspired systems

arXiv

引用

arXiv 2024年

作者： Biswas, Debojyoti Sontag, Eduardo D. Cowan, Noah J. Laboratory for Computational Sensing and Robotics Johns Hopkins University BaltimoreMD United States Department of Electrical and Computer Engineering Department of Bioengineering Northeastern University BostonMA United States Department of Mechanical Engineering Johns Hopkins University BaltimoreMD United States

We consider a general class of translation-invariant systems with a specific category of output nonlinearities motivated by biological sensing. We show that no dynamic output feedback can stabilize this class of systems to an isolated equilibrium point. To overcome this fundamental limitation, we propose a simple control scheme that includes a low-amplitude periodic forcing function akin to so-called "active sensing" in biology, together with nonlinear output feedback. Our analysis shows that this approach leads to the emergence of an exponentially stable limit cycle. These findings offer a provably stable active sensing strategy and may thus help to rationalize the active sensing movements made by animals as they perform certain motor behaviors. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Self-supervised neural network for holographic microscopy

Self-supervised neural network for holographic microscopy

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Huang, Luzhe Chen, Hanlong Liu, Tairan Ozcan, Aydogan Electrical and Computer Engineering Department University of California Los AngelesCA90095 United States Bioengineering Department University of California Los AngelesCA90095 United States University of California Los AngelesCA90095 United States David Geffen School of Medicine University of California Los Angeles Los AngelesCA90095 United States

ISBN: (纸本)9781957171258

We present a self-supervised hologram reconstruction neural network trained using a physics-consistency loss, which achieves superior generalization to reconstruct holograms of various samples, without previously having/seeing any experimental data or prior knowledge regarding the samples. © Optica Publishing Group 2023 © 2023 The Author(s)

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Radar Based Fall Detection with Imbalance Data Handling and Data Augmentation

Radar Based Fall Detection with Imbalance Data Handling and ...

引用

IEEE Sensors Applications Symposium, SAS

作者： Hamidreza Sadreazami Abhishek Khoyani Marzieh Amini Sreeraman Rajan Miodrag Bolic Bioengineering Department McGill University Montreal Canada System and Computer Engineering Department Carleton University Ottawa Canada School of Information Technology Carleton University Ottawa Canada School of Electrical Engineering and Computer Science University of Ottawa Ottawa Canada

Radar-based fall detection is helping seniors to live independently. In this paper, a new method for fall detection from human activities is proposed using data augmentation and class imbalance handling. Data collected from a radar signal is processed and a time series is obtained by aggregating the individual time series in the fast-time of the radar returns. This time series is used as input to several classifiers to distinguish fall from non-fall activities. To this end, we augment the radar time series data using a Mu-Sigma method. To handle the imbalanced data, we apply the synthetic minority over-sampling technique and class weighting strategy. A comprehensive study is performed to build a supervised learning method with or without data augmentation and imbalanced data handling. The performance of the proposed method is compared with some of the other existing methods using different classifiers including k-nearest neighbors, decision trees, naive Bayes, support vector machine and multi-layer perceptron. The results demonstrate that the proposed fall detection method outperforms the other methods in terms of providing higher accuracy, precision, sensitivity and specificity values.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A retracing free-space optical connection for reliable underwater optical communications 7

A retracing free-space optical connection for reliable under...

引用

Environmental Effects on Light Propagation and Adaptive Systems VII 2024

作者： Paglierani, P. Di Giancamillo, M. Martinelli, M. Gladysz, S. Stipanov, M. Zappa, G. Panipinto, M. Alves, J. NATO STO Centre for Maritime Research and Experimentation Viale S. Bartolomeo 400 La Spezia19126 Italy Politecnico di Milano Department of Electronics Information and Bioengineering Milano20133 Italy Fraunhofer IOSB Ettlingen Fraunhofer Institute of Optronics System Technologies and Image Exploitation Gutleuthausstr. 1 Ettlingen76275 Germany Holcombe Department of Computer and Electrical Engineering Clemson University ClemsonSC29634 United States

ISBN: (纸本)9781510680968

To establish a free-space underwater optical connection between a transmitter and a receiver suitable for operation in the single photon regime, techniques must be developed to compensate for: a) rotational and translational motions of both the transmitter and the receiver, b) their vibrations, and c) turbulence-induced deformations of the wavefront leading to beam wander, scintillation and beam spreading. The purpose of this work is to present and discuss experimental results obtained using a pseudo phase-conjugated mirror placed at the end of an underwater optical path disturbed by artificially induced turbulence. This configuration emulates a scenario whereby a modulated retroreflector is used to transmit the data back to the laser transmitter. The measurements obtained with the proposed retracing optical connection are found to be promising and pave the way for the use of this technique for quantum communications. © 2024 SPIE.

关键词： Quantum communication

来源：评论

学校读者我要写书评

暂无评论

Entirely 3D Printed Spectrometer: Application of Consumer-grade Printing Technologies for Fabrication of Optical and Opto-mechanical Components

Entirely 3D Printed Spectrometer: Application of Consumer-gr...

引用

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

作者： Berglund, Gregory Tkaczyk, Tomasz Department of Bioengineering Rice University HoustonTX77005 United States Electrical and Computer Engineering Rice University HoustonTX77005 United States

This paper presents a successful demonstration of a spectrometer device fully printed on consumer-grade 3D printers. Optical components were made with SLA technology while FDM printing was applied to fabricate opto-me... 详细信息

ISBN: (纸本)9781557528209

关键词： Spectrometers

来源：评论

学校读者我要写书评

暂无评论

A microwell-based impedance sensor on an insertable microneedle for real-time in vivo cytokine detection

引用

Microsystems & Nanoengineering 2021年第6期7卷 139-150页

作者： Naixin Song Pengfei Xie Wen Shen Hanju Oh Yejia Zhang Flavia Vitale Mehdi Javanmard Mark G.Allen Department of Electrical and Systems Engineering University of PennsylvaniaPhiladelphiaPAUSA Department of Electrical and Computer Engineering Rutgers UniversityPiscatawayNJUSA Department of Physical Medicine and Rehabilitation University of PennsylvaniaPhiladelphiaPAUSA Department of Orthopedic Surgery University of PennsylvaniaPhiladelphiaPAUSA Corporal Michael J.Crescenz Veterans Affairs Medical Center PhiladelphiaPAUSA Department of Bioengineering School of Engineering and Applied ScienceUniversity of PennsylvaniaPhiladelphiaPAUSA Department of Neurology Perelman School of MedicineUniversity of PennsylvaniaPhiladelphiaPAUSA

Impedance-based protein detection sensors for point-of-care diagnostics require quantitative specificity,as well as rapid or real-time ***,microfabrication of these sensors can lead to the formation of factors suitable for in vivo ***,we present microfabricated needle-shaped microwell impedance sensors for rapid-sample-to-answer,label-free detection of cytokines,and other *** microneedle form factor allows sensors to be utilized in transcutaneous or transvascular sensing *** vitro,experimental characterization confirmed sensor specificity and sensitivity to multiple proteins of *** characterization demonstrated sufficient microneedle robustness for transcutaneous insertion,as well as preserved sensor function *** further utilized these sensors to carry out real-time in vivo quantification of human interleukin 8(hIL8)concentration levels in the blood of transgenic mice that endogenously express *** assess sensor functionality,hIL8 concentration levels in serum samples from the same mice were quantified by *** agreement between real-time in vivo sensor readings in blood and subsequent ELISA serum assays was observed over multiple transgenic mice expressing hIL8 concentrations from 62 pg/mL to 539 ng/mL.

关键词： needle utilized insertion

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：