检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Rahman, Md Sadman Sakib 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

Point spread function (PSF) engineering has been pivotal in the remarkable progress made in high-resolution imaging in the last decades. However, the diversity in PSF structures attainable through existing engineering methods is limited. Here, we report universal PSF engineering, demonstrating a method to synthesize an arbitrary set of spatially varying 3D PSFs between the input and output volumes of a spatially incoherent diffractive processor composed of cascaded transmissive surfaces. We rigorously analyze the PSF engineering capabilities of such diffractive processors within the diffraction limit of light and provide numerical demonstrations of unique imaging capabilities, such as snapshot 3D multispectral imaging without involving any spectral filters, axial scanning or digital reconstruction steps, which is enabled by the spatial and spectral engineering of 3D PSFs. Our framework and analysis would be important for future advancements in computational imaging, sensing and diffractive processing of 3D optical information. Copyright © 2025, The Authors. All rights reserved.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Why should autoencoders work?

arXiv

引用

arXiv 2023年

作者： Kvalheim, Matthew D. Sontag, Eduardo D. Department of Mathematics and Statistics University of Maryland Baltimore CountyMD United States Departments of Electrical and Computer Engineering Bioengineering Northeastern University BostonMA United States

Deep neural network autoencoders are routinely used computationally for model reduction. They allow recognizing the intrinsic dimension of data that lie in a k-dimensional subset K of an input Euclidean space Rn. The underlying idea is to obtain both an encoding layer that maps Rn into Rk (called the bottleneck layer or the space of latent variables) and a decoding layer that maps Rk back into Rn, in such a way that the input data from the set K is recovered when composing the two maps. This is achieved by adjusting parameters (weights) in the network to minimize the discrepancy between the input and the reconstructed output. Since neural networks (with continuous activation functions) compute continuous maps, the existence of a network that achieves perfect reconstruction would imply that K is homeomorphic to a k-dimensional subset of Rk, so clearly there are topological obstructions to finding such a network. On the other hand, in practice the technique is found to "work" well, which leads one to ask if there is a way to explain this effectiveness. We show that, up to small errors, indeed the method is guaranteed to work. This is done by appealing to certain facts from differential topology. A computational example is also included to illustrate the ideas. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Intelligent upper-limb exoskeleton integrated with soft bioelectronics and deep learning for intention-driven augmentation

引用

npj Flexible Electronics 2024年第1期8卷 856-868页

作者： Jinwoo Lee Kangkyu Kwon Ira Soltis Jared Matthews Yoon Jae Lee Hojoong Kim Lissette Romero Nathan Zavanelli Youngjin Kwon Shinjae Kwon Jimin Lee Yewon Na Sung Hoon Lee Ki Jun Yu Minoru Shinohara Frank L.Hammond Woon-Hong Yeo Department of Mechanical Roboticsand Energy EngineeringDongguk UniversitySeoul 04620Republic of Korea IEN Center for Wearable Intelligent Systems and Healthcare Institute for Electronics and NanotechnologyGeorgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Computer Engineering Georgia Institute of TechnologyAtlantaGA 30332USA George W.Woodruff School of Mechanical Engineering Georgia Institute of TechnologyAtlantaGA 30332USA School of Industrial Design Georgia Institute of TechnologyAtlantaGA 30332USA School of Electrical and Electronic Engineering Yonsei UniversitySeoul 03722Republic of Korea School of Biological Sciences Georgia Institute of TechnologyAtlantaGA 30332USA Wallace H.Coulter Department of Biomedical Engineering Georgia Institute of Technology and Emory University School of MedicineAtlantaGA 30332USA Institute for Materials Parker H.Petit Institute for Bioengineering and BiosciencesInstitute for Robotics and Intelligent MachinesGeorgia Institute of TechnologyAtlantaGA 30332USA

The age and stroke-associated decline in musculoskeletal strength degrades the ability to perform daily human tasks using the upper ***,we introduce an intelligent upper-limb exoskeleton system that utilizes deep learning to predict human intention for strength *** embedded soft wearable sensors provide sensory feedback by collecting real-time muscle activities,which are simultaneously computed to determine the user’s intended *** deep learning predicts four upper-limb joint motions with an average accuracy of 96.2%at a 500–550 ms response rate,suggesting that the exoskeleton operates just by human *** addition,an array of soft pneumatics assists the intended movements by providing 897 newtons of force while generating a displacement of 87mm at *** intent-driven exoskeleton can reduce human muscle activities by 3.7 times on average compared to the unassisted exoskeleton.

关键词： skeleton learning utilize

来源：评论

学校读者我要写书评

暂无评论

Unpacking the terminology used in human cochlear dimension methodologies

引用

Translational Research in Anatomy 2024年 35卷 100290-100290页

作者： Human-Baron, Rene Hanekom, Tania Department of Anatomy School of Medicine Faculty of Health Sciences University of Pretoria Pretoria 0002 South Africa Bioengineering Department of Electrical Electronic and Computer Engineering Faculty of Engineering University of Pretoria Pretoria 0002 South Africa

Many definitions of the dimensions of cochlear measurements are described in the literature. However, these terminologies are typically not standardised or vary among disciplines. Confusion of the defined parameters may lead to ambiguity in the derived dimensions. Inconsistent terminology may, therefore, contribute to the variations reported in cochlear morphology. This article proposes using a standard set of terminology, including its associated landmarks and measurements, to describe the shape and dimensions of the human cochlea. To provide a basis for comparison for the dimensional description of ambiguous terms in the literature and to supplement existing data where terms are unique, micro-CT (μCT) scans of thirty temporal bones were subjected to landmarking and measuring according to the terminology standard. The results confirm that methodological techniques and definitions of cochlear measurements may affect the quantification of dimensions that describe cochlear morphology and may, therefore, introduce variations when reporting these measurements. Histology and μCT images, for example, could provide a more accurate and comprehensive measure of cochlear dimensions than measurements on casts. © 2024

关键词： cochlea cochlear variation Dimension Terminology μCT

来源：评论

学校读者我要写书评

暂无评论

ESTIMATING AND ANALYZING NEURAL INFORMATION FLOW USING SIGNAL PROCESSING ON GRAPHS

arXiv

引用

arXiv 2022年

作者： Schwock, Felix Bloch, Julien Atlas, Les Abadi, Shima Yazdan-Shahmorad, Azadeh Department of Electrical and Computer Engineering University of Washington Seattle United States Department of Bioengineering University of Washington Seattle United States

Correlating neural communication in brain networks with behavior and cognition can provide fundamental insights into the functionality of both healthy and diseased brains. We demonstrate how communication in the brain can be estimated from recorded neural activity using concepts from graph signal processing. The communication is modeled as a flow signals on the edges of a graph and naturally arises from a graph diffusion process. We apply the diffusion model to micro-electrocorticography (ECoG) recordings from sensorimotor cortex of two non-human primates to estimate the neural communication flow during excitatory optogenetics. Comparisons with a baseline model demonstrate that adding the neural flow can improve ECoG predictions. Finally, we demonstrate how the neural flow can be decomposed into a gradient and rotational component and show that the gradient component depends on the location of stimulation. This technique, for the first time, offers the opportunity to study neural communication on an unprecedented spatiotemporal scale. Copyright © 2022, The Authors. All rights reserved.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Utilizing Shape-features and GAN-Based Model for Renal Segmentation in DW-MRI

Utilizing Shape-features and GAN-Based Model for Renal Segme...

引用

IEEE International Symposium on Biomedical Imaging

作者： Israa Sharaby Ahmed Alksas Hossam Magdy Balaha Ali Mahmoud Mohammed Badawy Mohamed Abou EI–Ghar Mohammed Ghazal Sohail Contractor Ayman El–Baz Department of Bioengineering University of Louisville Louisville KY USA Radiology Department Urology and Nephrology Center Mansoura University Mansoura Egypt Electrical Computer and Biomedical Engineering Department Abu Dhabi University Abu Dhabi UAE Department of Radiology University of Louisville Louisville KY USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Medical image segmentation plays a crucial role in diagnosing several health conditions. This is particularly significant for kidney transplantation, where identifying those at risk of renal rejection is a major challenge. This paper proposes a novel framework for renal segmentation for binary masks generation from diffusion-weighted magnetic resonance imaging (DW-MRI) scans of kidney-transplant patients. The introduced framework improves the segmentation performance by applying fusion between the shape features and Generative Adversarial Networks (GANs), thus reducing the dependency on image alignment and data augmentation techniques. The approach is as follows: (i) enhancing the images' contrast by calculating the Cumulative Distribution Function, (ii) extracting the region of interest (ROI) to delineate kidney structure, (iii) generating contour-based probability maps to differentiate between kidney and non-kidney tissues, and (iv) averaging the ground truth dataset to highlight shared kidney features. Afterward, these shape features represent the RGB format of the GAN input image: the first channel is the ROI, the second channel is the probability map of the kidney region, and the last channel is the shared layer from the ground truth dataset. Finally, we employed a residual Pix2Pix GAN model to transform the RGB images into accurate binary masks. This approach was tested on a cohort of 37 patients suspected of renal rejection through performance metrics, reporting a Dice Score of 88% and an accuracy of 94%. These results underscore the effectiveness of our framework to advance the medical imaging segmentation field and offer promising solutions for both clinical applications and future research.

关键词： Image segmentation Accuracy Shape Magnetic resonance imaging Transforms Probability Generative adversarial networks Feature extraction Kidney Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Experimental Assessment of Reversibility-Aware Deep Reinforcement Learning for Optical Data Center Network Reconfiguration

Experimental Assessment of Reversibility-Aware Deep Reinforc...

引用

International Conference on Optical Network Design and Modeling, ONDM

作者： Massimiliano Sica Sandeep Kumar Singh Roberto Proietti Massimo Tornatore S. J. Ben Yoo Department of Electrical and Computer Engineering University of California Davis CA USA Department of Electronics Information and Bioengineering Politecnico di Milano Milano Italy Department of Electronics and Telecommunication Politecnico di Torino Italy

The performance of communication-intensive distributed machine learning (DML) workloads and other emerging applications can suffer from a traffic-topology mismatch in traditional data-center networks. This degradation can be alleviated by performing a logical network topology reconfiguration. However, how to dynamically reconfigure the logical topology and steer the bandwidth efficiently with a control plane capable of efficiently adapting to the current data center traffic patterns without considerable overhead is still an open question. This paper presents a reversibility-aware deep reinforcement learning algorithm (RA-DRL) for optical switch reconfiguration in data center networks and validates it in an experimental testbed. Using our testbed, we show that appropriate optical-switch reconfiguration, driven both by a baseline DRL and an RA-DRL method, can improve the training performance of DML workloads under network congestion. More importantly, by incorporating the concept of reversibility in the training of the DRL agent, we demonstrate a 5x training-time decrease for a distributed computer-vision application and an improvement in convergence time by up to 64%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Task-oriented design of a multi-degree of freedom upper limb prosthesis with integrated myocontrol and sensory feedback

TechRxiv

引用

TechRxiv 2023年

作者： Kashiwakura, Jumpei Alva, Patrick Gabriel Sagategui Guerra, Irene Mendez Bona, Conrad Atashzar, S. Farokh Farina, Dario The Department of Bioengineering Imperial College London London United Kingdom The Department of Electrical and Computer Engineering Mechanical and Aerospace Engineering New York University New York United States The Wetherby Growth London United Kingdom

Despite the progresses in upper limb prosthetic technologies of the past decades, there is still a large gap between the user needs and the available devices. Here, we describe the design and validation of a fully integrated, multi-degree of freedom upper limb prosthetic system designed on the basis of user survey studies. The system has five degrees of freedom, sufficient grasping/pinching force achieved by a combination of direct and underactuated activation to perform activities of daily living, an active wrist, a closed-loop tactile biofeedback system, and simultaneous/proportional myoelectric control. The aforementioned components have been successfully integrated into a standalone prosthetic system. The system has been tested for its capacity to reproduce the human grasp when applied to objects common in daily living. Moreover, we tested the system in standardized clinical tests that showed a reduction of shoulder and trunk compensatory movements with respect to a state-of-the-art commercial prosthesis. © 2023, CC BY-NC-SA.

关键词： Closed loop systems

来源：评论

学校读者我要写书评

暂无评论

Filament-Free Bulk RRAM with High Endurance and Long Retention for Neuromorphic Few-Shot Learning On-Chip

Filament-Free Bulk RRAM with High Endurance and Long Retenti...

引用

International Electron Devices Meeting (IEDM)

作者： Ashwani Kumar Yucheng Zhou Sai Praneeth Potladurthy Jeong-Hoon Kim Weihong Xu Flavio Ponzina Seonghyun Kim Ertugrul Cubukcu Tajana Rosing Gert Cauwenberghs Duygu Kuzum Department of Electrical and Computer Engineering University of California San Diego CA USA Department of Bioengineering University of California San Diego CA USA Department of Computer Science University of California San Diego CA USA SK Hynix Korea Department of NanoEngineering University of California San Diego CA USA

ISBN: (数字)9798350365429

ISBN: (纸本)9798350365436

Bulk switching RRAM devices have emerged to address nonidealities of filamentary RRAM for AI at the edge. However, long retention and high endurance needed for continual on-chip learning have yet to be demonstrated. Here, we report a filament-free and multilevel bulk RRAM (b-RRAM) technology with long retention and high endurance. The oxygen vacancy gradient across the $\text{TiO}_{\mathrm{x}}$ switching layer and $\text{Al}_{2}\mathrm{O}_{3}$ tunnel barrier are designed to suppress filament formation and achieve multilevel switching through modulation of oxygen vacancy distribution. AI-Ti-O oxygen barrier enables reliable switching with high uniformity, retention and endurance. We develop a compact model that captures both DC and pulse switching. $\mathrm{M}\Omega$ -level resistance and switching current nonlinearity allow highly accurate read/write operations and matrix vector multiplications (MVM) in selectorless b-RRAM crossbars. A neuro-inspired few-shot learning (FSL) algorithm based on dendritic computation and behavioral time plasticity (BTSP) is mapped onto b-RRAM crossbar arrays. Weights are continuously updated on-chip to learn shortest navigation to reward within a few trials in a 2D maze. We also present FSL of large-size images with hyperdimensional (HD) computing using our b-RRAM model. System-level simulations with 64-level b-RRAM arrays show an increase in accuracy by 5.9 % and 5.4 % for a 5-way 10-shot learning of CIFAR-100 and CUB-200 datasets as compared to the state-of-the-art FSL-HD.

关键词： Resistance Accuracy Navigation Neuromorphics Computational modeling Switches Vectors System-on-chip Reliability Few shot learning

来源：评论

学校读者我要写书评

暂无评论

Wearable Impedance Sensor for Wireless Measurements of Protein Biomarkers in Dermal Interstitial Fluid

Wearable Impedance Sensor for Wireless Measurements of Prote...

引用

IEEE International Conference on Micro Electro Mechanical Systems

作者： Elizabeth C. Wilkirson Yan Gong Wen Li Peter B. Lillehoj Department of Mechanical Engineering Rice University Houston TX USA Department of Electrical and Computer Engineering Michigan State University East Lansing MI USA Institute for Quantitative Health Science & Engineering Michigan State University East Lansing MI USA Department of Bioengineering Rice University Houston TX USA

This paper presents a wearable skin patch for wireless measurements of protein biomarkers in dermal interstitial fluid (ISF). ISF is extracted from the skin using a microneedle (MN)-based, vacuum-assisted technique and autonomously transported through the patch via vacuum pressure. This device was used for quantitative measurements of C-X-C motif chemokine ligand 9 (CXCL9), a biomarker for autoimmune diseases and inflammation, which could be detected from 10 pg/mL to 1,000 pg/mL in phosphate-buffered saline (PBS) with a lower limit of detection of 1.33 pg/mL. Proof-of-concept was demonstrated by performing measurements on cadaver porcine skin dermally injected with ISF simulant spiked with CXCL9, which could be detected at 100 and 1,000 pg/mL, thus validating the functionality of this wearable sensor.

关键词：

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：