检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Snyder, Christopher Vishwanath, Sriram Department of Biomedical Engineering University of Texas Austin United States Department of Electrical and Computer Engineering University of Texas Austin United States

Not only are Deep Neural Networks (DNNs) black box models, but also we frequently conceptualize them as such. We lack good interpretations of the mechanisms linking inputs to outputs. Therefore, we find it difficult to analyze in human-meaningful terms (1) what the network learned and (2) whether the network learned. We present a hierarchical decomposition of the DNN discrete classification map into logical (AND/OR) combinations of intermediate (True/False) classifiers of the input. Those classifiers that can not be further decomposed, called atoms, are (interpretable) linear classifiers. Taken together, we obtain a logical circuit with linear classifier inputs that computes the same label as the DNN. This circuit does not structurally resemble the network architecture, and it may require many fewer parameters, depending on the configuration of weights. In these cases, we obtain simultaneously an interpretation and generalization bound (for the original DNN), connecting two fronts which have historically been investigated separately. Unlike compression techniques, our representation is exact. We motivate the utility of this perspective by studying DNNs in simple, controlled settings, where we obtain superior generalization bounds despite using only combinatorial information (e.g. no margin information). We demonstrate how to "open the black box" on the MNIST dataset. We show that the learned, internal, logical computations correspond to semantically meaningful (unlabeled) categories that allow DNN descriptions in plain English. We improve the generalization of an already trained network by interpreting, diagnosing, and replacing components within the logical circuit that is the DNN. Copyright © 2020, 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

Prospectively accelerated dynamic speech MRI at 3 Tesla using a self-navigated spiral based manifold regularized scheme

arXiv

引用

arXiv 2022年

作者： Rusho, Rushdi Zahid Ahmed, Abdul Haseeb Kruger, Stanley Alam, Wahidul Meyer, David Howard, David Story, Brad Jacob, Mathews Lingala, Sajan Goud Roy J Carver Department of Biomedical Engineering University of Iowa Iowa city IA52242 United States Department of Electrical and Computer Engineering University of Iowa Iowa city IA52242 United States Department of Radiology University of Iowa Iowa city IA52242 United States Janette Ogg Voice Research Center Shenandoah University WinchesterVA22601 United States Department of Electronic Engineering Royal Holloway University of London United Kingdom Department of Speech Language and Hearing Sciences University of Arizona AZ85721 United States

This work develops and evaluates a self-navigated variable density spiral (VDS) based manifold regularization scheme to prospectively improve dynamic speech MRI at 3 Tesla. Short readout duration spirals (1.3 ms long) were used to minimize sensitivity to off-resonance. A custom 16-channel speech coil was used for improved parallel imaging of vocal tract structures. The manifold model leveraged similarities between frames sharing similar vocal tract postures without explicit motion binning. The self-navigating capability of VDS was leveraged to learn the Laplacian structure of the manifold. Reconstruction was posed as a SENSE-based non-local soft weighted temporal regularization scheme. Our approach was compared against view-sharing, low-rank, finite difference, extra-dimension-based sparsity reconstruction constraints. Under-sampling experiments were conducted on five volunteers performing repetitive and arbitrary speaking tasks at different speaking rates. Quantitative evaluation in terms of mean square error over moving edges were performed in a retrospective under-sampling experiment on one volunteer. For prospective under-sampling, blinded image quality evaluation in the categories of alias artifacts, spatial blurring, and temporal blurring were performed by three experts in voice research. Region of interest (ROI) analysis at articulator boundaries were performed in both the experiments to assess articulatory motion. Improved performance with manifold reconstruction constraints was observed over existing constraints. With prospective under-sampling, a spatial resolution of 2.4mm2/pixel and a temporal resolution of 17.4 ms/frame for single slice imaging, and 52.2 ms/frame for concurrent 3-slice imaging were achieved. We demonstrated implicit motion binning by analyzing the mechanics of the Laplacian matrix. Manifold regularization demonstrated superior image quality scores in reducing spatial and temporal blurring compared to all other reconstruction constraints

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Heart Position Uncertainty Quantification in the Inverse Problem of ECGI

Heart Position Uncertainty Quantification in the Inverse Pro...

引用

computers in Cardiology (CinC)

作者： Jake A Bergquist Lindsay C Rupp Anna Busatto Ben Orkild Brian Zenger Wilson Good Jaume Coll-Font Akil Narayan Jess Tate Dana Brooks Rob S MacLeod Scientific Computing and Imaging Institute University of Utah SLC UT USA Nora Eccles Treadwell CVRTI University of Utah SLC UT USA Department of Biomedical Engineering University of Utah SLC UT USA School of Medicine University of Utah SLC UT USA Acutus Medical Carlsbad CA USA Department of Mathematics University of Utah SLC UT USA Department of Electrical and Computer Engineering Northeastern University Boston MA USA

Electrocardiographic imaging (ECGI) is a clinical and research tool for noninvasive diagnosis of cardiac electrical dysfunction. The position of the heart within the torso is both an input and common source of error in ECGI. Many studies have sought to improve cardiac localization accuracy, however, few have examined quantitatively the effects of uncertainty in the position of the heart within the torso. Recently developed uncertainty quantification (UQ) tools enable the robust application of UQ to ECGI reconstructions. In this study, we developed an ECGI formulation, which for the first time, directly incorporated uncertainty in the heart position. The result is an ECGI solution that is robust to variation in heart position. Using data from two Langendorff experimental preparations, each with 120 heartbeats distributed across three activation sequences, we found that as heart position uncertainty increased above ±10 mm, the solution quality of the ECGI degraded. However, even at large heart position uncertainty (±40 mm) our novel UQ-ECGI formulation produced reasonable solutions (root mean squared error < 1 mV, spatial correlation >0.6, temporal correlation >0.75).

关键词： Heart Torso Location awareness Uncertainty Correlation Inverse problems Heart beat

来源：评论

学校读者我要写书评

暂无评论

Scientometric Analysis of Artificial Intelligence Research in Agriculture

Scientometric Analysis of Artificial Intelligence Research i...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Fairuz Iqbal Maulana Andi Pramono Miftahul Hamim Sukeipah Yuli Prihatin Rahman Arifuddin Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Interior Design Department School of Design Bina Nusantara University Jakarta Indonesia Entrepreneurship Business Creation BINUS Business School Bina Nusantara University Jakarta Indonesia Informatics Study Program Politeknik Kota Malang Malang Indonesia Department of Electrical Engineering University of Merdeka Malang Malang Indonesia

ISBN: (纸本)9781665473286

Artificial Intelligence Research in Agriculture has grown so common, and the potential they provide is so revolutionary that it is considered essential for competitive growth. Until we conducted this research, only 1064 academic documents on Trends of Artificial Intelligence Research in Agriculture that we found from 2012 to 2021 were obtained by searching the Scopus database. This study uses bibliometric analysis methods to map scientific publications worldwide. We use an article selection process, the year limitation, then the database is exported to RIS and CSV format files. Researchers in the United States had the most published articles and were indexed by Scopus among the most prolific authors ( $\mathrm{N}=287$ ), followed by the United Kingdom at second ( $\mathrm{N}=139$ ) and Italy with 66 academic publications. Data analysis reveals an increasing trend in the number of Trends of Artificial Intelligence Research in Agriculture publications worldwide, as measured by the Scopus index.

关键词： Data analysis Databases Multimedia systems Bibliometrics Market research Agriculture Indexes

来源：评论

学校读者我要写书评

暂无评论

Statistical testing-based framework for differentiating anomalous diffusion models with constant and random parameters

引用

Journal of Computational and Applied Mathematics 2026年 472卷

作者： Katarzyna Maraj-Zygmąt Aleksandra Grzesiek Diego Krapf Agnieszka Wyłomańska Faculty of Pure and Applied Mathematics Hugo Steinhaus Center Wroclaw University of Science and Technology 50-370 Wroclaw Poland Department of Electrical and Computer Engineering and School of Biomedical Engineering Colorado State University Fort Collins CO 80523 USA

Anomalous diffusion describes processes where the mean squared displacement scales non-linearly with time, E ( X 2 ( t ) ) ∼ t β , where β is termed the anomalous exponent. This behavior, seen in complex systems like biological cells, often defies standard diffusion models. Classical models such as fractional Brownian motion (FBM) and scaled Brownian motion (SBM) assume constant exponents, failing to capture dynamics with varying anomalous parameters. To address this limitations, models like FBM with random exponents (FBMRE) and SBM with random exponents (SBMRE) were introduced. This work proposes an universal procedure based on statistical testing framework that distinguishes between anomalous diffusion models with constant and random anomalous exponents using time-averaged statistics and their ratio-based counterparts. A novel procedure for optimizing time lag selection via divergence measure (here the Hellinger distance) is also proposed. The introduced methodology applies broadly to constant vs. random anomalous diffusion scenarios, with effectiveness depending on statistic selection, time lags, and process properties, as shown in simulations (with the two-point distribution of anomalous exponent) and real-world data analysis.

关键词： Anomalous diffusion Fractional Brownian Motion Scaled Brownian motion Statistical testing Monte Carlo simulations Real data analysis

来源：评论

学校读者我要写书评

暂无评论

Phased Array Beamforming Methods for Powering biomedical Ultrasonic Implants

arXiv

引用

arXiv 2022年

作者： Benedict, Braeden C. Ghanbari, Mohammad Meraj Muller, Rikky UC Berkeley UC San Francisco Joint Program in Bioengineering BerkeleyCA94720 United States The Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States The Chan Zuckerberg Biohub San FranciscoCA94158 United States

Millimeter-scale implants using ultrasound for power and communication have been proposed for a range of deep-tissue applications, including neural recording and stimulation. However, published implementations have shown high sensitivity to misalignment with the external ultrasound transducer. Ultrasonic beamforming using a phased array to these implants can improve tolerance to misalignment, reduce implant volume, and allow multiple implants to be operated simultaneously in different locations. This paper details the design of a custom planar phased array ultrasound system, which is capable of steering and focusing ultrasound power within a 3D volume. Analysis and simulation is performed to determine the choice of array element pitch, with special attention given to maximizing the power available at the implant while meeting FDA limits for diagnostic ultrasound. Time reversal is proposed as a computationally simple approach to beamforming that is robust despite scattering and inhomogeneity of the acoustic medium. This technique is demonstrated both in active drive and pulse-echo modes, and it is experimentally compared with other beamforming techniques by measuring energy transfer efficiency. Simultaneous power delivery to multiple implants is also demonstrated. Copyright © 2022, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

UAV communications for sustainable federated learning

arXiv

引用

arXiv 2021年

作者： Pham, Quoc-Viet Zeng, Ming Ruby, Rukhsana Huynh-The, Thien Hwang, Won-Joo Korean Southeast Center for The 4th Industrial Revolution Leader Education Pusan National University Korea Republic of Department of Electrical Engineering and Computer Engineering Laval University Canada College of Computer Science and Software Engineering Shenzhen University China ICT Convergence Research Center Kumoh National Institute of Technology Korea Republic of Department of Biomedical Convergence Engineering Pusan National University Korea Republic of

Federated learning (FL), invented by Google in 2016, has become a hot research trend. However, enabling FL in wireless networks has to overcome the limited battery challenge of mobile users. In this regard, we propose to apply unmanned aerial vehicle (UAV)-empowered wireless power transfer to enable sustainable FL-based wireless networks. The objective is to maximize the UAV transmit power efficiency, via a joint optimization of transmission time and bandwidth allocation, power control, and the UAV placement. Directly solving the formulated problem is challenging, due to the coupling of variables. Hence, we leverage the decomposition technique and a successive convex approximation approach to develop an efficient algorithm, namely UAV for sustainable FL (UAV-SFL). Finally, simulations illustrate the potential of our proposed UAV-SFL approach in providing a sustainable solution for FL-based wireless networks, and in reducing the UAV transmit power by 32.95%, 63.18%, and 78.81% compared with the benchmarks. Copyright © 2021, The Authors. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

A Generative Modeling Approach for Interpreting Population-Level Variability in Brain Structure 23rd

A Generative Modeling Approach for Interpreting Population-L...

引用

23rd International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2020

作者： Liu, Ran Subakan, Cem Balwani, Aishwarya H. Whitesell, Jennifer Harris, Julie Koyejo, Sanmi Dyer, Eva L. School of Electrical and Computer Engineering Georgia Institute of Technology Atlanta United States Mila - Quebec Artificial Intelligence Institute Montreal Canada Neuroanatomy Division Allen Institute for Brain Science Seattle United States Department of Computer Science University of Illinois at Urbana Champaign Urbana United States Department of Biomedical Engineering Georgia Institute of Technology Atlanta United States

ISBN: (纸本)9783030597214

Understanding how neural structure varies across individuals is critical for characterizing the effects of disease, learning, and aging on the brain. However, disentangling the different factors that give rise to individual variability is still an outstanding challenge. In this paper, we introduce a deep generative modeling approach to find different modes of variation across many individuals. Our approach starts with training a variational autoencoder on a collection of auto-fluorescence images from a little over 1,700 mouse brains at 25μ m resolution. We then tap into the learned factors and validate the models expressiveness, via a novel bi-directional technique that makes structured perturbations to both, the high-dimensional inputs of the network, as well as the low-dimensional latent variables in its bottleneck. Our results demonstrate that through coupling generative modeling frameworks with structured perturbations, it is possible to probe the latent space of the generative model to provide insights into the representations of brain structure formed in deep networks. © 2020, Springer Nature Switzerland AG.

关键词： Taps

来源：评论

学校读者我要写书评

暂无评论

AI-Derived Left Ventricular Mass From Noncontrast Cardiac CT: Correlation With Contrast CT Angiography and CMR

JACC: Advances

引用

JACC: Advances 2024年第10期3卷 101249-101249页

作者： Han, Donghee Shanbhag, Aakash Miller, Robert JH. Kwok, Nicholas Waechter, Parker Builoff, Valerie Newby, David E. Dey, Damini Berman, Daniel S. Slomka, Piotr Departments of Medicine (Division of Artificial Intelligence in Medicine) Imaging and Biomedical Sciences Cedars-Sinai Medical Center Los Angeles CA United States Signal and Image Processing Institute Ming Hsieh Department of Electrical and Computer Engineering University of Southern California Los Angeles CA United States Department of Cardiac Sciences University of Calgary Calgary AB Canada British Heart Foundation Centre for Cardiovascular Science University of Edinburgh Edinburgh United Kingdom

Background: Noncontrast computed tomography (CT) scans are not used for evaluating left ventricle myocardial mass (LV mass), which is typically evaluated with contrast CT or cardiovascular magnetic resonance imaging (CMR). Objectives: The purpose of the study was to assess the feasibility of LV mass estimation from standard, ECG-gated, noncontrast CT using an artificial intelligence (AI) approach and compare it with coronary CT angiography (CTA) and CMR. Methods: We enrolled consecutive patients who underwent coronary CTA, which included noncontrast CT calcium scanning and contrast CTA, and CMR. The median interval between coronary CTA and CMR was 22 days (interquartile range: 3-76). We utilized a no new UNet AI model that automatically segmented noncontrast CT structures. AI measurement of LV mass was compared to contrast CTA and CMR. Results: A total of 316 patients (age: 57.1 ± 16.7 years, 56% male) were included. The AI segmentation took on average 22 seconds per case. An excellent correlation was observed between AI and contrast CTA LV mass measures (r = 0.84, P < 0.001), with no significant differences (136.5 ± 55.3 g vs 139.6 ± 56.9 g, P = 0.133). Bland-Altman analysis showed minimal bias of 2.9. When compared to CMR, measured LV mass was higher with AI (136.5 ± 55.3 g vs 127.1 ± 53.1 g, P < 0.001). There was an excellent correlation between AI and CMR (r = 0.85, P < 0.001), with a small bias (−9.4). There were no statistical differences between the correlations of LV mass between contrast CTA and CMR or AI and CMR. Conclusions: The AI-based automated estimation of LV mass from noncontrast CT demonstrated excellent correlations and minimal biases when compared to contrast CTA and CMR. © 2024 The Authors

关键词： artificial intelligence cardiac magnetic resonance imaging computed tomography myocardial mass

来源：评论

学校读者我要写书评

暂无评论

Volumetric and Functional Changes in Patients with Benign and Low-Grade Tumors Receiving Partial Brain Radiotherapy

SSRN

引用

SSRN 2023年

作者： Finkelstein, Alan J. Tivarus, Madalina E. Venkataraman, Arun Culakova, Eva Uddin, Md Nasir Usuki, Kenneth Zhong, Jianhui Schifitto, Giovanni Milano, Michael T. Janelsins, Michelle Hardy, Sara J. Department of Biomedical Engineering University of Rochester RochesterNY United States Department of Imaging Sciences University of Rochester Medical Center RochesterNY United States Department of Neuroscience University of Rochester Medical Center RochesterNY United States Department of Neurology University of Rochester Medical Center RochesterNY United States Department of Physics and Astronomy University of Rochester RochesterNY United States Department of Radiation Oncology University of Rochester Medical Center RochesterNY United States Department of Surgery Supportive Care in Cancer Division University of Rochester Medical Center RochesterNY United States Department of Electrical and Computer Engineering University of Rochester RochesterNY United States

Background: Patients receiving partial cranial radiation therapy (RT) often experience cognitive impairment. RT is associated with dose-dependent atrophy of the cortex, hippocampus, and amygdala. However, volumetric changes may present as late as 6-12 months post-RT. Sensitive MRI biomarkers are needed to identify early RT damage to intracranial structures. We aimed to determine whether partial brain RT impacted functional network topology using resting-state functional MRI and quantifying subcortical atrophy. We hypothesized that changes in functional connectivity precedes volumetric changes. Methods: Functional connectivity and subcortical volumes were evaluated in 19 patients with low-grade or benign brain tumors receiving partial brain RT. Patients underwent baseline and six-months post-RT assessments, including 3D volumetric MRI and resting-state fMRI (rs-fMRI). The effect of RT dose on volumetric and graph theory measurements of subcortical gray matter, was analyzed. Local graph theory metrics (clustering coefficient, local efficiency) and global metrics (global efficiency, transitivity) were evaluated. Results Multivariate analysis revealed mean RT dose was significantly correlated with volumetric loss in the hippocampus, amygdala, and thalamus. Mean RT dose also significantly predicted decreases in local efficiency and clustering coefficient in the amygdala, thalamus, and putamen. Total brain RT dose significantly predicted a reduction in global efficiency and transitivity. Conclusions: Measures of functional connectivity and subcortical volume are sensitive to RT dose. Functional connectivity analysis using graph theory is a complementary method to structural MRI, capable of elucidating changes in brain network topology in the setting of partial brain radiation therapy that are not apparent with conventional structural MRI analyses. © 2023, The Authors. All rights reserved.

关键词： Radiotherapy

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：