检索结果-内蒙古大学图书馆

Deep multistage multi-task learning for quality prediction of multistage manufacturing systems

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yan, Hao Sergin, Nurretin Dorukhan Brenneman, William A. Lange, Stephen Joseph Ba, Shan School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States The Procter & Gamble Company CincinnatiOH United States ProcessDev LLC CincinnatiOH United States LinkedIn Corporation

In multistage manufacturing systems, modeling multiple quality indices based on the process sensing variables is important. However, the classic modeling technique predicts each quality variable one at a time, which fails to consider the correlation within or between stages. We propose a deep multistage multi-task learning framework to jointly predict all output sensing variables in a unified end-to-end learning framework according to the sequential system architecture in the MMS. Our numerical studies and real case study have shown that the new model has a superior performance compared to many benchmark methods as well as great interpretability through developed variable selection techniques. © 2021, CC BY.

关键词： Deep neural networks

Transferable visual words: Exploiting the semantics of anatomical patterns for self-supervised learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Haghighi, Fatemeh Taher, Mohammad Reza Hosseinzadeh Zhou, Zongwei Gotway, Michael B. Liang, Jianming School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States Department of Biomedical Informatics Arizona State University ScottsdaleAZ85259 United States Radiology Department Mayo Clinic ScottsdaleAZ85259 United States

This paper introduces a new concept called "transferable visual words" (TransVW), aiming to achieve annotation efficiency for deep learning in medical image analysis. Medical imaging—focusing on particular parts of the body for defined clinical purposes—generates images of great similarity in anatomy across patients and yields sophisticated anatomical patterns across images, which are associated with rich semantics about human anatomy and which are natural visual words. We show that these visual words can be automatically harvested according to anatomical consistency via self-discovery, and that the self-discovered visual words can serve as strong yet free supervision signals for deep models to learn semantics-enriched generic image representation via self-supervision (self-classification and self-restoration). Our extensive experiments demonstrate the annotation efficiency of TransVW by offering higher performance and faster convergence with reduced annotation cost in several applications. Our TransVW has several important advantages, including (1) TransVW is a fully autodidactic scheme, which exploits the semantics of visual words for self-supervised learning, requiring no expert annotation;(2) visual word learning is an add-on strategy, which complements existing self-supervised methods, boosting their performance;and (3) the learned image representation is semantics-enriched models, which have proven to be more robust and generalizable, saving annotation efforts for a variety of applications through transfer learning. Our code, pre-trained models, and curated visual words are available at https://***/JLiangLab/TransVW. Copyright © 2021, The Authors. All rights reserved.

关键词： Semantics

Calibrating hypersonic turbulence flow models with the HIFiRE-1 experiment using data-driven machine-learned models

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chowdhary, Kenny Hoang, Chi Lee, Kookjin Ray, Jaideep Extreme-Scale Data Science and Analytics Department Sandia National Laboratories LivermoreCA94550 United States School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States

In this paper we study the efficacy of combining machine-learning methods with projection-based model reduction techniques for creating data-driven surrogate models of computationally expensive, high-fidelity physics models. Such surrogate models are essential for many-query applications e.g., engineering design optimization and parameter estimation, where it is necessary to invoke the high-fidelity model sequentially, many times. Surrogate models are usually constructed for individual scalar quantities. However there are scenarios where a spatially varying field needs to be modeled as a function of the model's input parameters. We develop a method to do so, using projections to represent spatial variability while a machine-learned model captures the dependence of the model's response on the inputs. The method is demonstrated on modeling the heat flux and pressure on the surface of the HIFiRE-1 geometry in a Mach 7.16 turbulent flow. The surrogate model is then used to perform Bayesian estimation of freestream conditions and parameters of the SST (Shear Stress Transport) turbulence model embedded in the high-fidelity (Reynolds-Averaged Navier-Stokes) flow simulator, using wind-tunnel data. The paper provides the first-ever Bayesian calibration of a turbulence model for complex hypersonic turbulent flows. We find that the primary issues in estimating the SST model parameters are the limited information content of the heat flux and pressure measurements and the large model-form error encountered in a certain part of the flow. Copyright © 2021, The Authors. All rights reserved.

关键词： Turbulence models

Machine learning structure preserving brackets for forecasting irreversible processes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lee, Kookjin Trask, Nathaniel A. Stinis, Panos School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ85281 United States Center for Computing Research Sandia National Laboratories AlbuquerqueNM87123 United States Pacific Northwest National Laboratory RichlandWA99354 United States

Forecasting of time-series data requires imposition of inductive biases to obtain predictive extrapolation, and recent works have imposed Hamiltonian/Lagrangian form to preserve structure for systems with reversible dynamics. In this work we present a novel parameterization of dissipative brackets from metriplectic dynamical systems appropriate for learning irreversible dynamics with unknown a priori model form. The process learns generalized Casimirs for energy and entropy guaranteed to be conserved and nondecreasing, respectively. Furthermore, for the case of added thermal noise, we guarantee exact preservation of a fluctuation-dissipation theorem, ensuring thermodynamic consistency. We provide benchmarks for dissipative systems demonstrating learned dynamics are more robust and generalize better than either "black-box" or penalty-based approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Dynamics

Worst-case Satisfaction of STL Specifications Using Feedforward Neural Network Controllers: A Lagrange Multipliers Approach

学校读者我要写书评

暂无评论

Worst-case Satisfaction of STL Specifications Using Feedforw...

Information Theory and Applications Workshop, ITA

作者： SHAKIBA YAGHOUBI GEORGIOS FAINEKOS CIDSE Arizona State University School of Computing Informatics and Decision Systems Engineering Arizona State University Tempe Arizona

ISBN: (数字)9781728141909

ISBN: (纸本)9781728188256

In this paper, a reinforcement learning approach for designing feedback neural network controllers for nonlinear systems is proposed. Given a Signal Temporal Logic (STL) specification which needs to be satisfied by the system over a set of initial conditions, the neural network parameters are tuned in order to maximize the satisfaction of the STL formula. The framework is based on a max-min formulation of the robustness of the STL formula. The maximization is solved through a Lagrange multipliers method, while the minimization corresponds to a falsification problem. We present our results on a vehicle and a quadrotor model and demonstrate that our approach reduces the training time more than 50 percent compared to the baseline approach.

关键词： Training State feedback Systematics Artificial neural networks Reinforcement learning Robustness Robots

Using Novel Statistical Techniques to Accurately Determine the Predictive Dose Range in a Study of Overall Survival after Definitive Radiotherapy for Stage III Non-Small Cell Lung Cancer in Association with Heart Dose

学校读者我要写书评

暂无评论

Journal of Cancer Therapy 2021年第9期12卷 505-529页

作者： Joshua R. Niska Jiuyun Hu Jing Li Michael G. Herman Cameron S. Thorpe Steven E. Schild Mirek Fatyga Department of Radiation Oncology Banner MD Anderson Cancer Center Phoenix Arizona USA School of Computing Informatics and Decision Systems Engineering Tempe Arizona USA School of Industrial and Systems Engineering Georgia Institute of Technology Atlanta Georgia USA Department of Radiation Oncology Mayo Clinic Rochester Minnesota USA Department of Radiation Oncology Mayo Clinic Phoenix Arizona USA

Purpose: Recent studies of radiotherapy (RT) for stage III non-small-cell lung cancer (NSCLC) have associated high dose to the heart with cardiac toxicity and decreased overall survival (OS). We used advanced statisti... 详细信息

Purpose: Recent studies of radiotherapy (RT) for stage III non-small-cell lung cancer (NSCLC) have associated high dose to the heart with cardiac toxicity and decreased overall survival (OS). We used advanced statistical techniques to account for correlations between dosimetric variables and more accurately determine the range of heart doses which are associated with reduced OS in patients receiving RT for stage III NSCLC. Methods: From 2006 to 2013, 119 patients with stage III NSCLC received definitive RT at our institution. OS data was obtained from institutional tumor registry. We used multivariate Cox model to determine patient specific covariates predictive for reduced overall survival. We examined age, prescription dose, mean lung dose, lung V20, RT technique, stage, chemotherapy, tumor laterality, tumor volume, and tumor site as candidate covariates. We subsequently used novel statistical techniques within multivariate Cox model to systematically search the whole heart dose-volume histogram (DVH) for dose parameters associated with OS. Results: Patients were followed until death or 2.5 to 81.2 months (median 30.4 months) in those alive at last follow up. On multivariate analysis of whole heart DVH, the dose of 51 Gy was identified as a threshold dose above which the dose volume relationship becomes predictive for OS. We identified

关键词： Lung Cancer Cardiac Toxicity Lung Radiation Therapy Non-Small Cell Lung Cancer Radiation Toxicity

Predictive Modeling of Periodic Behavior for Human-Robot Symbiotic Walking

学校读者我要写书评

暂无评论

Predictive Modeling of Periodic Behavior for Human-Robot Sym...

IEEE International Conference on Robotics and Automation (ICRA)

作者： Geoffrey Clark Joseph Campbell Seyed Mostafa Rezayat Sorkhabadi Wenlong Zhang Heni Ben Amor School of Computing Informatics and Decision Systems Engineering Arizona State University The Polytechnic School Arizona State University Mesa AZ USA

ISBN: (数字)9781728173955

ISBN: (纸本)9781728173962

We propose in this paper Periodic Interaction Primitives - a probabilistic framework that can be used to learn compact models of periodic behavior. Our approach extends existing formulations of Interaction Primitives to periodic movement regimes, i.e., walking. We show that this model is particularly well-suited for learning data-driven, customized models of human walking, which can then be used for generating predictions over future states or for inferring latent, biomechanical variables. We also demonstrate how the same framework can be used to learn controllers for a robotic prosthesis using an imitation learning approach. Results in experiments with human participants indicate that Periodic Interaction Primitives efficiently generate predictions and ankle angle control signals for a robotic prosthetic ankle, with MAE of 2.21° in 0.0008s per inference. Performance degrades gracefully in the presence of noise or sensor fall outs. Compared to alternatives, this algorithm functions 20 times faster and performed 4.5 times more accurately on test subjects.

关键词： Legged locomotion Robot sensing systems Biomechanics Predictive models Prosthetics Probabilistic logic

Inverse learning of black-box aggregator for robust Nash equilibrium

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Guanpu Xu, Gehui He, Fengxiang Tao, Dacheng Parisini, Thomas Johansson, Karl Henrik Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden Digital Futures Stockholm100 44 Sweden Artificial Intelligence and its Applications Institute School of Informatics University of Edinburgh EdinburghEH8 9AB United Kingdom College of Computing & Data Science Nanyang Technological University Singapore639798 Singapore Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom Department of Engineering and Architecture University of Trieste Trieste34127 Italy

In this note, we investigate the robustness of Nash equilibria (NE) in multi-player aggregative games with coupling constraints. There are many algorithms for computing an NE of an aggregative game given a known aggregator. When the coupling parameters are affected by uncertainty, robust NE need to be computed. We consider a scenario where players' weight in the aggregator is unknown, making the aggregator kind of "a black box". We pursue a suitable learning approach to estimate the unknown aggregator by proposing an inverse variational inequality-based relationship. We then utilize the counterpart to reconstruct the game and obtain first-order conditions for robust NE in the worst case. Furthermore, we characterize the generalization property of the learning methodology via an upper bound on the violation probability. Simulation experiments show the effectiveness of the proposed inverse learning approach. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

Deep Representation Learning for Multimodal Brain Networks 23rd

学校读者我要写书评

暂无评论

Deep Representation Learning for Multimodal Brain Networks

23rd International Conference on Medical Image computing and Computer-Assisted Intervention, MICCAI 2020

作者： Zhang, Wen Zhan, Liang Thompson, Paul Wang, Yalin School of Computing Informatics and Decision Systems Engineering Arizona State University TempeAZ United States Electrical and Computer Engineering University of Pittsburgh PittsburghPA United States Imaging Genetics Center University of Southern California Los AngelesCA United States

ISBN: (纸本)9783030597276

Applying network science approaches to investigate the functions and anatomy of the human brain is prevalent in modern medical imaging analysis. Due to the complex network topology, for an individual brain, mining a discriminative network representation from the multimodal brain networks is non-trivial. The recent success of deep learning techniques on graph-structured data suggests a new way to model the non-linear cross-modality relationship. However, current deep brain network methods either ignore the intrinsic graph topology or require a network basis shared within a group. To address these challenges, we propose a novel end-to-end deep graph representation learning (Deep Multimodal Brain Networks - DMBN) to fuse multimodal brain networks. Specifically, we decipher the cross-modality relationship through a graph encoding and decoding process. The higher-order network mappings from brain structural networks to functional networks are learned in the node domain. The learned network representation is a set of node features that are informative to induce brain saliency maps in a supervised manner. We test our framework in both synthetic and real image data. The experimental results show the superiority of the proposed method over some other state-of-the-art deep brain network models. © 2020, Springer Nature Switzerland AG.

关键词： Complex networks