检索结果-内蒙古大学图书馆

Comparing One-step and Two-step Scatter Correction and Density Reconstruction in X-ray CT

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sietsema, Alexander N. McCann, Michael T. Klasky, Marc L. Ravishankar, Saiprasad The Dept. of Mathematics Michigan State University East LansingMI48824 United States The Dept. of Computational Mathematics Science and Engineering The Dept. of Biomedical Engineering Michigan State University East LansingMI48824 United States The Theoretical Division Los Alamos National Laboratory Los AlamosNM87545 United States

In this work, we compare one-step and two-step approaches for X-ray computed tomography (CT) scatter correction and density reconstruction. X-ray CT is an important imaging technique in medical and industrial applications. In many cases, the presence of scattered X-rays leads to loss of contrast and undesirable artifacts in reconstructed images. Many approaches to computationally removing scatter treat scatter correction as a preprocessing step that is followed by a reconstruction step. Treating scatter correction and reconstruction jointly as a single, more complicated optimization problem is less studied. It is not clear from the existing literature how these two approaches compare in terms of reconstruction accuracy. In this paper, we compare idealized versions of these two approaches with synthetic experiments. Our results show that the one-step approach can offer improved reconstructions over the two-step approach, although the gap between them is highly object-dependent. Copyright © 2021, The Authors. All rights reserved.

关键词： Iterative methods

Advancements in Multiple Sclerosis Disease Classification Through Machine Learning

学校读者我要写书评

暂无评论

Advancements in Multiple Sclerosis Disease Classification Th...

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Darshanaben D. Pandya Sheshang Degadwala Dhairya Vyas Vishal Narendrakumar Solanki Sharma Vishalkumar Sureshbhai Hiteshkumar Gunvantbhai Patel Dept. of Comp. Sci. SCJCCS (BCA) Sankalchand Patel University Visnagar Gujarat India Dept. of Comm. Engg. Sigma University Gujarat India The Maharaja Sayajirao University of Baroda Vadodara Gujarat India D L Patel Institute of Mgt. & Technology (MCA College) Himatnagar Gujarat India Department of Computer Science (MCA) Sankalchand Patel University Visnagar Gujrat Quality Engineering - Data Tiger Analytics Chennai Tamil Nadu

In recent years, the field of medical diagnosis has witnessed significant advancements due to the application of machine learning algorithms, especially in complex neurological diseases like Multiple Sclerosis (MS). This study delves into the progress made in MS disease classification using various machine learning techniques, including SVM, KNN, DT, RF, NB, and Extra Trees. Through a diverse dataset of clinical and neuroimaging data, this study has systematically compared the performance of these algorithms in identifying different MS subtypes. SVM and Random Forest exhibited the highest accuracy, while KNN and Decision Trees showed competitive performance. Naive Bayes and Extra Trees also demonstrated promising results in specific scenarios. The study discusses the strengths and weaknesses of each approach and explores the interpretability of the models to understand the key features influencing the classification process. These findings contribute to the growing knowledge base of machine learning in MS disease classification and open avenues for more efficient and accurate diagnostic tools, ultimately leading to personalized patient care and improved treatment planning.

关键词：

De Novo Drug Property Prediction using Graph Convolutional Neural Networks

学校读者我要写书评

暂无评论

De Novo Drug Property Prediction using Graph Convolutional N...

IEEE Region 10 Humanitarian Technology Conference (R10-HTC)

作者： Fairuz Shadmani Shishir Khan Md. Hasib Shadman Sakib Shithi Maitra Faisal Muhammad Shah BJIT Group Dhaka Sylhet Bangladesh Dept. of Computer Science and Engineering DhakaSylhetBangladesh Ahsanullah University of Science and Technology Leading University Dhaka Sylhet Bangladesh Data and BI | Engineering SureCash Dhaka Sylhet Bangladesh

Drug property prediction poses a complex task in the healthcare domain, because the drug-like molecules greatly vary in chemical structures. Inhibitory concentration (IC 50 ) prediction is essential to reduce the cost and labor of a drug's preclinical and clinical trials, because a lot of drug evaluations (cellular, animal, and clinical) can be spared due to the predicted IC 50 . In the era of Artificial Intelligence, Drug Discovery processes can benefit from deep learning, which has been widely used in computational chemistry and bioinformatics with state-of-the-art performance. In this paper, we propose a novel (in other words, de novo) graph convolutional network approach, cross-validated by traditional methods like Lipinski's rule of five and PaDEL-described one-hot encoding. The experiment has been carried out on the ChEMBL bioactivity dataset of Acetylcholinesterase protein, achieving an R2 score of 0.52.

关键词： Drugs Proteins Molecular biophysics Medical services Predictive models Real-time systems Encoding

Prompt-guided Scene Generation for 3D Zero-Shot Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Nasiri, Majid Cheraghian, Ali Chowdhury, Townim Faisal Ahmadi, Sahar Saberi, Morteza Rahman, Shafin Business school The University of New South Wales Australia School of Engineering Australian National University Australia Dept. of Electrical and Computer Engineering North South University Bangladesh School of Computer Science and DSI University of Technology Sydney Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia

Zero-shot learning on 3D point cloud data is a related underexplored problem compared to its 2D image counterpart. 3D data brings new challenges for ZSL due to the unavailability of robust pre-trained feature extraction models. To address this problem, we propose a prompt-guided 3D scene generation and supervision method that augments 3D data to learn the network better, exploring the complex interplay of seen and unseen objects. First, we merge point clouds of two 3D models in certain ways described by a prompt. The prompt acts like the annotation describing each 3D scene. Later, we perform contrastive learning to train our proposed architecture in an end-to-end manner. We argue that 3D scenes can relate objects more efficiently than single objects because popular language models (like BERT) can achieve high performance when objects appear in a context. Our proposed prompt-guided scene generation method encapsulates data augmentation and prompt-based annotation/captioning to improve 3D ZSL performance. We have achieved state-of-the-art ZSL and generalized ZSL performance on synthetic (ModelNet40, ModelNet10) and real-scanned (ScanOjbectNN) 3D object datasets. © 2022, CC BY.

关键词： Zero-shot learning

SkyNetPredictor: Network Performance Prediction in Avionic Communication using AI

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Mukhtar, Hind Schaub, Raymond Erol-Kantarci, Melike Satcom Direct Inc. Melbourne Florida University of Ottawa OttawaON Canada Dept. of Data Science Satcom Direct Inc. MelbourneFL United States Dept. of Electrical & Computer Engineering University of Ottawa OttawaON Canada

Satellite-based communication systems are integral to delivering high-speed data services in aviation, particularly for business aviation operations requiring global connectivity. These systems, however, are challenged by a multitude of interdependent factors such as satellite handovers, congestion, flight maneuvers and seasonal trends, making network performance prediction a complex task. No established methodologies currently exist for network performance prediction in avionic communication systems. This paper addresses the gap by proposing machine learning (ML)-based approaches for pre-flight network performance predictions. The proposed models predict performance along a given flight path, taking as input positional and network-related information and outputting the predicted performance for each position. In business aviation, flight crews typically have multiple flight plans to choose from for each city pair, allowing them to select the most optimal option. This approach enables proactive decision-making, such as selecting optimal flight paths prior to departure. © 2025, CC BY-NC-ND.

关键词： Satellite communication systems

AMG Preconditioners based on Parallel Hybrid Coarsening and Multi-objective Graph Matching

学校读者我要写书评

暂无评论

AMG Preconditioners based on Parallel Hybrid Coarsening and ...

Euromicro Conference on Parallel, Distributed and Network-Based Processing

作者： Pasqua D'Ambra Fabio Durastante S M Ferdous Salvatore Filippone Mahantesh Halappanavar Alex Pothen National Research Council (CNR) Institute for Applied Computing “M. Picone” (IAC) Napoli Italy Department of Mathematics University of Pisa Pisa Italy Pacific Northwest National Laboratory Physical and Computational Sciences Richland WA USA Dept. of Civil and Computer Engineering University of Rome Tor-Vergata Rome Italy Computer Science Department Purdue University West Lafayette IN USA

We describe preliminary results from a multi-objective graph matching algorithm, in the coarsening step of an aggregation-based Algebraic MultiGrid (AMG) preconditioner, for solving large and sparse linear systems of equations on high-end parallel computers. We have two objectives. First, we wish to improve the convergence behavior of the AMG method when applied to highly anisotropic problems. Second, we wish to extend the parallel package PSCToolkit to exploit multi-threaded parallelism at the node level on multi-core processors. Our matching proposal balances the need to simultaneously compute high weights and large cardinalities by a new formulation of the weighted matching problem combining both these objectives using a parameter $\lambda$ . We compute the matching by a parallel $2/3-\varepsilon$ -approximation algorithm for maximum weight matchings. Results with the new matching algorithm show that for a suitable choice of the parameter $\lambda$ we compute effective preconditioners in the presence of anisotropy, i.e., smaller solve times, setup times, iterations counts, and operator complexity.

关键词：

Bilevel learning of 1regularizers with closed-form gradients (BLORC)

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ghosh, Avrajit McCann, Michael T. Ravishankar, Saiprasad Dept. of Computational Mathematics Science and Engineering Michigan State University East LansingMI United States Theoretical Division Los Alamos National Laboratory Los AlamosNM United States Dept. of Biomedical Engineering Michigan State University East LansingMI United States

We present a method for supervised learning of sparsitypromoting regularizers, a key ingredient in many modern signal reconstruction problems. The parameters of the regularizer are learned to minimize the mean squared error of reconstruction on a training set of ground truth signal and measurement pairs. Training involves solving a challenging bilevel optimization problem with a nonsmooth lower-level objective. We derive an expression for the gradient of the training loss using the implicit closed-form solution of the lower-level variational problem given by its dual problem, and provide an accompanying gradient descent algorithm (dubbed BLORC) to minimize the loss. Our experiments on simple natural images and for denoising 1D signals show that the proposed method can learn meaningful operators and the analytical gradients calculated are faster than standard automatic differentiation methods. While the approach we present is applied to denoising, we believe that it can be adapted to a wide-variety of inverse problems with linear measurement models, thus giving it applicability in a wide range of scenarios. © 2021, CC BY.

关键词： Gradient methods

Normal Variation in Brain Volumetrics, CSF Dynamics, and Ocular Structures from Magnetic Resonance Images of Healthy Participants Over Two Years

学校读者我要写书评

暂无评论

Journal of applied physiology (Bethesda, Md. : 1985) 2025年第1期139卷 2025 May 21页

作者： Katrina J Carter Steven S Laurie Katherine G Warthen Stuart H Sater Bryn A Martin Ching Mei Feng Millennia Young Khader M Hasan Larry A Kramer Brandon R Macias Cardiovascular and Vision Laboratory Kellogg Brown and Root Houston TX United States. Alcyone Therapeutics Inc. Lowell MA United States. Dept. of Chemical and Biological Engineering University of Idaho Moscow ID USA. Department of Diagnostic Imaging and Intervention McGovern Medical School UTHealth Houston Houston TX United States. Statistics and Data Science NASA Johnson Space Center Houston TX United States. Cardiovascular and Vision Laboratory NASA Johnson Space Center Houston TX United States.

Changes in ocular and brain structure and cerebral spinal fluid (CSF) dynamics from magnetic resonance imaging (MRI) data have been reported in astronauts following long-duration spaceflight. The purpose of this study was to quantify normal variation in these outcomes over a 2-year period in a healthy cohort similar in age to astronauts, but without spaceflight experience. Variation in MRI acquisition, observer measurement, or normal aging over a 2-year period was used to determine thresholds for interpreting measures following long duration spaceflight. Ten healthy participants (5 male) age 38 ± 8 years (mean ± SD) underwent five MRI sessions at baseline, 2, 6, 12, and 24 months to quantify intracranial volumetry, CSF dynamics, pituitary morphology, and ocular structures. Total within-person variation (σ), modeled as the sum of the variance components for each outcome measure, was used to define a sensitivity threshold of 2.00 x σ. Changes greater than these thresholds can be interpreted as a result of an intervention and have <5% probability of occurring due to expected variability. Thresholds for change due to all sources of variability were: 27 mL for gray matter volume, 16 mL for white matter volume, 0.9 mL for lateral ventricular volume, 26.0 µL for CSF aqueductal stroke volume, 3.2 cm/s for peak-to-peak aqueductal CSF velocity, 0.5 mm for pituitary height, 0.50 mm for optic nerve sheath diameter, and 10.2 mm for posterior optic globe volume displacement. Changes on brain MR images after an intervention need to exceed these thresholds to be attributable to that intervention.

关键词： Brain Healthy Magnetic resonance imaging Spaceflight Variability

A family of metrics from the truncated smoothing of Reeb graphs

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chambers, Erin Wolf Munch, Elizabeth Ophelders, Tim Dept. of Computer Science St. Louis University Dept. of Computational Mathematics Science and Engineering Michigan State University Dept. of Mathematics Michigan State University

In this paper, we introduce an extension of smoothing on Reeb graphs, which we call truncated smoothing;this in turn allows us to define a new family of metrics which generalize the interleaving distance for Reeb graphs. Intuitively, we "chop off" parts near local minima and maxima during the course of smoothing, where the amount cut is controlled by a parameter τ. After formalizing truncation as a functor, we show that when applied after the smoothing functor, this prevents extensive expansion of the range of the function, and yields particularly nice properties (such as maintaining connectivity) when combined with smoothing for 0 ≤ τ ≤ 2Ε, where Ε is the smoothing parameter. Then, for the restriction of τ ∈ [0, Ε], we have additional structure which we can take advantage of to construct a categorical flow for any choice of slope m ∈ [0, 1]. Using the infrastructure built for a category with a flow, this then gives an interleaving distance for every m ∈ [0, 1], which is a generalization of the original interleaving distance, which is the case m = 0. While the resulting metrics are not stable, we show that any pair of these for m, m0 ∈ [0, 1) are strongly equivalent metrics, which in turn gives stability of each metric up to a multiplicative constant. We conclude by discussing implications of this metric within the broader family of metrics for Reeb graphs. Copyright © 2020, The Authors. All rights reserved.

关键词： Algebra