检索结果-内蒙古大学图书馆

DeePKS: A comprehensive data-driven approach towards chemically accurate density functional theory

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Chen, Yixiao Zhang, Linfeng Wang, Han Weinan, E. Program in Applied and Computational Mathematics Princeton University PrincetonNJ United States Laboratory of Computational Physics Institute of Applied Physics and Computational Mathematics Huayuan Road 6 Beijing100088 China Department of Mathematics Princeton University PrincetonNJ United States

We propose a general machine learning-based framework for building an accurate and widely-applicable energy functional within the framework of generalized Kohn-Sham density functional theory. To this end, we develop a way of training self-consistent models that are capable of taking large datasets from different systems and different kinds of labels. We demonstrate that the functional that results from this training procedure gives chemically accurate predictions on energy, force, dipole, and electron density for a large class of molecules. It can be continuously improved when more and more data are available. Copyright © 2020, The Authors. All rights reserved.

关键词： Large dataset

DeePKS-kit: A package for developing machine learning-based chemically accurate energy and density functional models

学校读者我要写书评

暂无评论

arXiv 2020年

We introduce DeePKS-kit, an open-source software package for developing machine learning based energy and density functional models. DeePKS-kit is interfaced with PyTorch, an open-source machine learning library, and PySCF, an ab initio computational chemistry program that provides simple and customized tools for developing quantum chemistry codes. It supports the DeePHF and DeePKS methods. In addition to explaining the details in the methodology and the software, we also provide an example of developing a chemically accurate model for water clusters. Copyright © 2020, The Authors. All rights reserved.

关键词： Electronic structure

Convergence of deep fictitious play for stochastic differential games

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Han, Jiequn Hu, Ruimeng Long, Jihao Department of Mathematics Princeton University PrincetonNJ08544-1000 United States Department of Mathematics Department of Statistics and Applied Probability University of California Santa BarbaraCA93106-3080 United States Program in Applied and Computational Mathematics Princeton University PrincetonNJ08544-1000 United States

Stochastic differential games have been used extensively to model agents' competitions in Finance, for instance, in P2P lending platforms from the Fintech industry, the banking system for systemic risk, and insurance markets. The recently proposed machine learning algorithm, deep fictitious play, provides a novel efficient tool for finding Markovian Nash equilibrium of large N-player asymmetric stochastic differential games [J. Han and R. Hu, Mathematical and Scientific Machine Learning Conference, pages 221-245, PMLR, 2020]. By incorporating the idea of fictitious play, the algorithm decouples the game into N sub-optimization problems, and identifies each player's optimal strategy with the deep backward stochastic differential equation (BSDE) method parallelly and repeatedly. In this paper, we prove the convergence of deep fictitious play (DFP) to the true Nash equilibrium. We can also show that the strategy based on DFP forms an ϵ-Nash equilibrium. We generalize the algorithm by proposing a new approach to decouple the games, and present numerical results of large population games showing the empirical convergence of the algorithm beyond the technical assumptions in the theorems. Copyright © 2020, The Authors. All rights reserved.

关键词： Game theory

Prediction and Prevention of Pandemics via Graphical Model Inference and Convex programming

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Krechetov, Mikhail Sikaroudi, Amir Mohammad Esmaieeli Efrat, Alon Polishchuk, Valentin Chertkov, Michael Skolkovo Institute of Science and Technology Moscow121205 Russia University of Arizona Department of Computer Science TucsonAZ85721 United States University of Arizona Program in Applied Mathematics TucsonAZ85721 United States Linköping Univeristy Communications and Transport Systems Norrkoping60174 Sweden University of Arizona Department of Mathematics TucsonAZ85721 United States

Hard-to-predict bursts of COVID-19 pandemic revealed significance of statistical modeling which would resolve spatio-temporal correlations over geographical areas, for example spread of the infection over a city with census tract granularity. In this manuscript, we provide algorithmic answers to the following two inter-related public health challenges of immense social impact which have not been adequately addressed (1) Inference Challenge: assuming that there are N census blocks (nodes) in the city, and given an initial infection at any set of nodes, e.g. any N of possible single node infections, any N(N-1)=2 of possible two node infections, etc, what is the probability for a subset of census blocks to become infected by the time the spread of the infection burst is stabilized? (2) Prevention Challenge: What is the minimal control action one can take to minimize the infected part of the stabilized state footprint? To answer the challenges, we build a Graphical Model of pandemic of the attractive Ising (pair-wise, binary) type, where each node represents a census tract and each edge factor represents the strength of the pairwise interaction between a pair of nodes, e.g. representing the inter-node travel, road closure and related, and each local bias/field represents the community level of immunization, acceptance of the social distance and mask wearing practice, etc. Resolving the Inference Challenge requires finding the Maximum-A-Posteriory (MAP), i.e. most probable, state of the Ising Model constrained to the set of initially infected nodes. (An infected node is in the +1 state and a node which remained safe is in the-1 state.) We show that almost all attractive Ising Models on dense graphs result in either of the two possibilities (modes) for the MAP state: either all nodes which were not infected initially became infected, or all the initially uninfected nodes remain uninfected (susceptible). This bi-modal solution of the Inference Challenge allows us to re-sta

关键词： Ising model

Enhanced Gaussian Process Regression for Diagnosing Wind Energy Conversion Systems

学校读者我要写书评

暂无评论

IFAC-PapersOnLine 2022年第6期55卷 673-678页

作者： Majdi Mansouri Radhia Fezai Mohamed Trabelsi Hajji Mansour Hazem Nounou Mohamed Nounou Department of Mathematics and Sciences Prince Sultan University Riyadh 11586 Saudi Arabia Research Laboratory of Automation Signal Processing and Image National Engineering School of Monastir 5019 Tunisia Electronic and Communications Engineering Department Kuwait College of Science and Technology P. O. Box 27235 Kuwait Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Tunisia Chemical Engineering Program Texas A&M University at Qatar Doha Qatar

Fault detection and diagnosis techniques are increasingly important to ensure robust and resource efficient operation of Wind Energy Conversion (WEC) systems. In this context, this paper presents a Reduced Enhanced Gaussian Process Regression (REGPR)-based Random Forest (RF) technique (REGPR-RF) to identify and diagnose faults occurring in a nonlinear WEC systems. The proposed technique uses REGPR technique for features extraction and selection from raw sensor data. Then, these selected features are fed to RF classifier to reliably detect and classify faults. The use of REGPR to learn features avoid the dimension problems and improves the classification performance significantly with a small number of training data. The results obtained by REGPR-RF are compared to those obtained with other conventional classifiers (Support Vector Machines (SVM), Naive Bayes (NB), ...). The results show that the developed REGPR-RF technique achieve higher accuracy (99.99%) with small data sets.

关键词： Gaussian Process Regression (GPR) Noise-Signal-Dependence Random Forest (RF) Feature Extraction Selection Fault Detection Diagnosis (FDD) Wind Energy Conversion (WEC) Systems

Cosmology with Galaxy Photometry Alone

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Hahn, ChangHoon Villaescusa-Navarro, Francisco Melchior, Peter Teyssier, Romain Department of Astrophysical Sciences Princeton University Peyton Hall PrincetonNJ08544 United States Center for Computational Astrophysics Flatiron Institute 162 5th Avenue New YorkNY10010 United States Center for Statistics & Machine Learning Princeton University PrincetonNJ08544 United States Program in Applied and Computational Mathematics Princeton University Fine Hall Washington Road PrincetonNJ08544-1000 United States

We present the first cosmological constraints using only the observed photometry of galaxies. Villaescusa-Navarro et al. (2022b) recently demonstrated that the internal physical properties of a single simulated galaxy contain a significant amount of cosmological information. These physical properties, however, cannot be directly measured from observations. In this work, we present how we can go beyond theoretical demonstrations to infer cosmological constraints from actual galaxy observables (e.g. optical photometry) using neural density estimation and the CAMELS suite of hydrodynamical simulations. We find that the cosmological information in the photometry of a single galaxy is limited. However, we combine the constraining power of photometry from many galaxies using hierarchical population inference and place significant cosmological constraints. With the observed photometry of ∼20,000 NASA-Sloan Atlas galaxies, we constrain (formula presented) and (formula presented). © 2023, CC BY.

关键词： Galaxies

Trends in bimetallic nanomaterials and methods for fourth-generation glucose sensors

学校读者我要写书评

暂无评论

TrAC - Trends in Analytical Chemistry 2023年第1期162卷

作者： Naikoo, Gowhar A. Arshad, Fareeha Hassan, Israr U. Omar, Fatima Ba Tambuwala, Murtaza M. Mustaqeem, Mujahid Saleh, Tawfik A. Department of Mathematics and Sciences College of Arts and Applied Sciences Dhofar University SalalahPC 211 Oman College of Engineering Dhofar University SalalahPC 211 Oman Lincoln Medical School University of Lincoln Brayford Pool Campus LincolnLN6 7TS United Kingdom Department of Chemistry National Taiwan University No. 1 Section 4 Roosevelt Road Taipei10617 Taiwan Nano-Science and Technology Program Taiwan International Graduate Program Institute of Physic Academia Sinica Taipei106 Taiwan Department of Chemistry King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia

Diabetes mellitus is one of the most rapidly rising chronic diseases around the globe. To combat these rising numbers, active research has been done in recent years to enhance the sensitivity, selectivity, and specificity of glucose biosensors. Despite the easy availability of these enzymatic glucose sensors, these have demonstrated limitations like low stability, short shelf-life, and being easily altered by physical and chemical environmental factors. To overcome these limitations, non-enzymatic sensors, also called fourth-generation glucose sensors, have been developed. These sensors use nanomaterials and do not employ any enzymes therefore exhibit better shelf life, improved sensitivity, and allow for quick detection of glucose without needing additional steps. In recent years, bimetallic nanocomposite-based fourth-generation glucose sensors have gained widespread attention from the scientific community. Owing to the synergistic effect of two distinct metal nanomaterials, these sensors show enhanced reproducibility and excellent stability as compared to monometallic nanomaterials. In this review, we aim to represent a comprehensive overview of the recent developments in the development of bimetallic nanocomposite-based glucose sensors for rapid and accurate glucose detection. After a brief introduction, we discussed the various bimetallic nanomaterials developed in recent years, followed by a discussion on the mechanism of action of such sensors. We then briefly discussed the industrial challenges of developing such sensors and discussed the advantages and disadvantages of bimetallic nanomaterial-based sensors. We finally concluded the review by highlighting the future perspectives of this new and upcoming field. © 2023 Elsevier B.V.

关键词： Glucose sensors

Assessment of Gamma and Neutron Dose of Optimizing the Radiation Protection in TRIGA 2000 BATAN Bandung. 6

学校读者我要写书评

暂无评论

Assessment of Gamma and Neutron Dose of Optimizing the Radia...

6th International Conference on Advances in Nuclear Science and Engineering, ICANSE 2018

作者： Oméga, Rakotovao Lovanantenaina Permana, Sidik Oetami, Rini Heroe Rasito Master Program of Physics Department Faculty of Mathematics and Natural Science Bandung Institute of Technology Jalan Ganesha 10 Bandung40132 Indonesia Nuclear Physics Laboratory Physics Department Faculty of Mathematics and Natural Science Bandung Institute of Technology Jalan Ganesha 10 Bandung40132 Indonesia Center for Science and Applied Nuclear Technology National Nuclear Energy Agency Jl. Tamansari 71 Bandung Indonesia

The TRIGA 2000 reactor is a nuclear installation which is operated at 1000 kW. Gamma and neutron radiation exposure will contribute to occupational doses that will be received by operators and other radiation workers. To maintain the safety of radiation workers, assessment of gamma and neutron radiation is needed in the TRIGA 2000 reactor. survey in the hall reactor using the RTD 30 and RadEye NL detectors. In addition to the direct measurement, calculations are also carried out with simulation data dose using Monte Carlo MCNPX for the calculation and followed by PHITS to get the graphical dose distribution of gamma and neutron. The study will focus on the assessment of the diffusion Gamma and neutron doses by doing the measurement and simulation data collect for the aim of the optimization of the Radiation protection policy in the reactor TRIGA 2000 Bandung. The result of the measurement is shown with graph in different power taken during the measurement and the simulation is the graphical distribution dose of gamma and neutron using PHITS code. A preventive dose reduction technique, worker and publics protection elaborate to optimise the Radiation protection program. © 2020 Published under licence by IOP Publishing Ltd.

关键词： Monte Carlo methods

Exploring the business aspects of digital pathology, deep learning in cancers

学校读者我要写书评

暂无评论

Intelligence-Based Medicine 2024年 10卷 100172-100172页

作者： Reddy, Arjun Adrian Williams, Darnell K. Graifman, Gillian Hussain, Nowair Amiel, Maytal Priscilla, Tran Haider, Ali Kavitesh, Bali Kumar Li, Austin Alishahian, Leael Perera, Nichelle Efros, Corey Babu, Myoungmee Tharakan, Mathew Etienne, Mill Babu, Benson A. Applied Mathematics & Statistics Stony Brook University LabelMD New York United States Medical Scientist Training Program Albert Einstein College of Medicine Bronx New York United States New York Medical College Valhalla New York United States Department of Internal Medicine Overlook Medical Center NJ United States Artificial Intelligence Yeshiva University New York United States Centre for Frontier AI Research (CFAR) Agency for Science Technology and Research (A∗STAR) Singapore Artificial Intelligence and Mathematics New York City Department of Education New York United States Stonybrook Medical Center New York United States Department of Neurology New York Medical College Valhalla NY United States Department of Hospital Medicine Wyckoff Medical Center Brooklyn NY United States

Introduction: Cancer remains one of the leading causes of morbidity and mortality worldwide. Deep learning in digital pathology has the potential to improve operational efficiency, costs, and care. Methods: We searched Web of Science, Arxiv, MedRxiv, Embase, PubMed, DBLP, Google Scholar, IEEE Xplore, and Cochrane databases for whole slide imaging and deep learning articles published between 2019 and 2023. The final six articles were selected from 776 articles identified through an inclusion criterion. Conclusion: Digital pathology services that utilize deep learning have the potential to enhance clinical workflow efficiencies and can have a positive impact on business activities. We anticipate cost reductions as deep learning technology advances and more companies enter the digital pathology ecosystem. However, the limited availability of business use cases, primarily due to publication bias, poses a challenge in medicine without clear examples to learn from. © 2024

关键词： Artificial intelligence Business development Cancer Computational pathology Deep learning Digital pathology Whole slide image