检索结果-内蒙古大学图书馆

Enhancing Traffic Flow Prediction with Machine Learning Models: A Comparative Study

学校读者我要写书评

暂无评论

Enhancing Traffic Flow Prediction with Machine Learning Mode...

African Federation of Operational Research Societies (AFROS), International Conference of the

作者： Amina Bouhali Abdelhafid Zeroual Fouzi Harrou Laboratoire de Recherche d'Electronique de Skikda LRES Université 20 Août 1955 Skikda Algeria Computer Electrical and Mathematical Sciences and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia

ISBN: (数字)9798350386448

ISBN: (纸本)9798350386455

Precise traffic flow prediction is important for optimizing transportation management and developing urban strategies. This research study allows conducting a comparative analysis of various machine learning (ML) and deep learning (DL) algorithms to predict traffic flow patterns. The study examines five distinct models: Support Vector Regression (SVR), Extreme Gradient Boosting (XGBoost), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Networks (CNNs). SVR and XGBoost represent shallow and ensemble ML models, while the latter three exemplify DL architectures. The predictive quality of these models is evaluated utilizing four assessment metrics, Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination ( $\mathbf{R}^{\mathbf{2}}$ ). The analysis utilizes univariate traffic flow data sampled at 5 -minute intervals. The obtained results demonstrate the superiority prediction of the LSTM framework, achieving an $\mathbf{R}^{2}$ value of 0.97. This comprehensive comparison provides valuable insights into the effectiveness of various prediction frameworks compressing machine and deep learning architectures for traffic flow prediction, thereby enabling transportation authorities and urban planners to make evidence-based decisions for improved urban mobility.

关键词： Deep learning Measurement Analytical models Accuracy Transportation Predictive models Market research Data models Convolutional neural networks Long short term memory

Multi-dimensional wave steering with higher-order topological phononic crystal

学校读者我要写书评

暂无评论

science Bulletin 2021年第17期66卷 1740-1745,M0003页

作者： Changqing Xu Ze-Guo Chen Guanqing Zhang Guancong Ma Ying Wu Division of Computer Electrical and Mathematical Science and EngineeringKing Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Department of Physics Hong Kong Baptist UniversityHong KongChina

The recent discovery and realizations of higher-order topological insulators enrich the fundamental studies on topological ***,we report three-dimensional(3D)wave-steering capabilities enabled by topological boundary states at three different orders in a 3D phononic crystal with nontrivial bulk topology originated from the synergy of mirror symmetry of the unit cell and a non-symmorphic glide symmetry of the *** multitude of topological states brings diverse possibilities of wave *** judicious engineering of the boundary modes,we experimentally demonstrate two functionalities at different dimensions:2D negative refraction of sound wave enabled by a firstorder topological surface state with negative dispersion,and a 3D acoustic interferometer leveraging on second-order topological hinge *** work showcases that topological modes at different orders promise diverse wave steering applications across different dimensions.

关键词： Higher-order topological insulator Topological states Negative refraction 3D acoustic interferometer

Multilevel Monte Carlo for a class of Partially Observed Processes in Neuroscience

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Maama, Mohamed Jasra, Ajay Kamatani, Kengo Applied Mathematics and Computational Science Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia School of Data Science The Chinese University of Hong Kong CN Shenzhen China Institute of Statistical Mathematics Tokyo190-0014 Japan

In this paper we consider Bayesian parameter inference associated to a class of partially observed stochastic differential equations (SDE) driven by jump processes. Such type of models can be routinely found in applications, of which we focus upon the case of neuroscience. The data are assumed to be observed regularly in time and driven by the SDE model with unknown parameters. In practice the SDE may not have an analytically tractable solution and this leads naturally to a time-discretization. We adapt the multilevel Markov chain Monte Carlo method of [15], which works with a hierarchy of time discretizations and show empirically and theoretically that this is preferable to using one single time discretization. The improvement is in terms of the computational cost needed to obtain a pre-specified numerical error. Our approach is illustrated on models applied to examples of Bayesian inference problems using both simulated and real observed data from neuroscience. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems

Measure-based approach to mesoscopic modeling of optimal transportation networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Haskovec, Jan Markowich, Peter Portaro, Simone Mathematical and Computer Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Faculty of Mathematics University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria

We propose a mesoscopic modeling framework for optimal transportation networks with biological applications. The network is described in terms of a joint probability measure on the phase space of tensor-valued conductivity and position in physical space. The energy expenditure of the network is given by a functional consisting of a pumping (kinetic) and metabolic power-law term, constrained by a Poisson equation accounting for local mass conservation. We establish convexity and lower semicontinuity of the functional on approriate sets. We then derive its gradient flow with respect to the 2-Wasserstein topology on the space of probability measures, which leads to a transport equation, coupled to the Poisson equation. To lessen the mathematical complexity of the problem, we derive a reduced Wasserstein gradient flow, taken with respect to the tensor-valued conductivity variable only. We then construct equilibrium measures of the resulting PDE system. Finally, we derive the gradient flow of the constrained energy functional with respect to the Fisher-Rao (or Hellinger-Kakutani) metric, which gives a reaction-type PDE. We calculate its equilibrium states, represented by measures concentrated on a hypersurface in the phase space. © 2024, CC BY-NC-SA.

关键词： Poisson equation

Scaling the “Memory Wall” for Multi-Dimensional Seismic Processing with Algebraic Compression on Cerebras CS-2 Systems

学校读者我要写书评

暂无评论

Scaling the “Memory Wall” for Multi-Dimensional Seismic Pr...

Supercomputing Conference

作者： Hatem Ltaief Yuxi Hong Leighton Wilson Mathias Jacquelin Matteo Ravasi David Keyes Extreme Computing Research Center Computer Electrical and Mathematical Sciences & Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Cerebras Systems Inc. Sunnyvale California United States

We exploit the high memory bandwidth of AI-customized Cerebras CS-2 systems for seismic processing. By leveraging low-rank matrix approximation, we fit memory-hungry seismic applications onto memory-austere SRAM wafer-scale hardware, thus addressing a challenge arising in many wave-equation-based algorithms that rely on Multi-Dimensional Convolution (MDC) operators. Exploiting sparsity inherent in seismic data in the frequency domain, we implement embarrassingly parallel tile low-rank matrix-vector multiplications (TLR-MVM), which account for most of the elapsed time in MDC operations, to successfully solve the Multi-Dimensional Deconvolution (MDD) inverse problem. By reducing memory footprint along with arithmetic complexity, we fit a standard seismic benchmark dataset into the small local memories of Cerebras processing elements. Deploying TLR-MVM execution onto 48 CS-2 systems in support of MDD gives a sustained memory bandwidth of 92.58PB/s on 35,784,000 processing elements, a significant mile-stone that highlights the capabilities of AI-customized architectures to enable a new generation of seismic algorithms that will empower multiple technologies of our low-carbon future.

关键词：

Initial demonstration of AlGaAs-GaAsP-β-Ga2O3 n-p-n double heterojunctions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Jie Dheenan, Ashok Gong, Jiarui Adamo, Carolina Marshall, Patrick Sheikhi, Moheb Tsai, Tsung-Han Wriedt, Nathan Cheung, Clincy Qiu, Shuoyang Ng, Tien Khee Gan, Qiaoqiang Vincent, Gambin Ooi, Boon S. Rajan, Siddharth Ma, Zhenqiang Department of Electrical and Computer Engineering University of Wisconsin-Madison MadisonWI53706 United States Department of Electrical and Computer Engineering The Ohio State University ColumbusOH43210 United States Northrop Grumman Redondo BeachCA90278 United States Department of Electrical and Computer Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

β-Ga2O3, an ultrawide-bandgap semiconductor, has great potential for future power and RF electronics applications but faces challenges in bipolar device applications due to the lack of p-type dopants. In this work, we demonstrate monocrystalline AlGaAs/GaAsP/βGa2O3 n-p-n double-heterojunctions, synthesized using semiconductor grafting technology. By transfer printing an n-AlGaAs/p-GaAsP nanomembrane to the n-β-Ga2O3 epitaxial substrate, we simultaneously achieved AlGaAs/GaAsP epitaxial n-p junction diode with an ideality factor of 1.29 and a rectification ratio of 2.57×103 at +/-2 V, and grafted GaAsP/βGa2O3 p-n junction diode exhibiting an ideality factor of 1.36 and a rectification ratio of 4.85×102 at +/- 2 V. © 2023, CC BY.

关键词： Aluminum gallium arsenide

Memristors Threshold Based Physical Unclonable Function

学校读者我要写书评

暂无评论

Memristors Threshold Based Physical Unclonable Function

International Conference on Microelectronics, ICM

作者： Aref Al-Tamimi Shawkat Ali Yuan Cao Amine Bermak College of Science and Engineering Hamad Bin Khalifa Univesty Qatar Department of Electrical and Computer Engineering King Abdullah University of Science and Technology Saudi Arabia College of IoT Hohai University

ISBN: (纸本)9781665493253

This paper presents a novel physical unclonable function (PUF) design that extracts entropy of random threshold voltage variations of a memristor-based cell. Each cell consists of two equivalent memristors in series. Applying an increasing voltage within the threshold range across the cell causes the memristor with a lower threshold to change state before the other. This uncertainty is then digitized to produce a random output. The design has no area/power hungry CMOS comparator overhead. Instead, only an output memristor holds the PUF response bit. The PUF signature is extracted during the set process. The proposed PUF cell which consists of two filament memristor sub-models connected in series is modeled, designed, implemented, and simulated using SystemC-AMS. Simulation results show that the effect of the sneak path does not alter the PUF response.

关键词： Semiconductor device modeling Uncertainty Manufacturing processes Simulation Memristors Physical unclonable function Threshold voltage

PDE MODELS FOR DEEP NEURAL NETWORKS: LEARNING THEORY, CALCULUS OF VARIATIONS AND OPTIMAL CONTROL

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Markowich, Peter Portaro, Simone Mathematical and Computer Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia Faculty of Mathematics University of Vienna Oskar-Morgenstern-Platz 1 Vienna1090 Austria

We propose a partial differential-integral equation (PDE) framework for deep neural networks (DNNs) and their associated learning problem by taking the continuum limits of both network width and depth. The proposed model captures the complex interactions among hidden nodes, overcoming limitations of traditional discrete and ordinary differential equation (ODE)-based models. We explore the well-posedness of the forward propagation problem, analyze the existence and properties of minimizers for the learning task, and provide a detailed examination of necessary and sufficient conditions for the existence of critical points. Controllability and optimality conditions for the learning task with its associated PDE forward problem are established using variational calculus, the Pontryagin Maximum Principle, and the Hamilton-Jacobi-Bellman equation, framing the deep learning process as a PDE-constrained optimization problem. In this context, we prove the existence of viscosity solutions for the latter and we establish optimal feedback controls based on the value functional. This approach facilitates the development of new network architectures and numerical methods that improve upon traditional layer-by-layer gradient descent techniques by introducing forward-backward PDE discretization. The paper provides a mathematical foundation for connecting neural networks, PDE theory, variational analysis, and optimal control, partly building on and extending the results of [28], where the main focus was the analysis of the forward evolution. By integrating these fields, we offer a robust framework that enhances deep learning models’ stability, efficiency, and interpretability. © 2024, CC0.

关键词： Constrained optimization

Demonstration of a monocrystalline GaAs-β-Ga2O3 p-n heterojunction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Jie Sheikhi, Moheb Dheenan, Ashok Abbasi, Haris Gong, Jiarui Liu, Yang Adamo, Carolina Marshall, Patrick Wriedt, Nathan Cheung, Clincy Qiu, Shuoyang Ng, Tien Khee Gan, Qiaoqiang Gambin, Vincent Ooi, Boon S. Rajan, Siddharth Ma, Zhenqiang Department of Electrical and Computer Engineering University of Wisconsin-Madison MadisonWI53706 United States Department of Electrical and Computer Engineering The Ohio State University ColumbusOH43210 United States Northrop Grumman Corporation Redondo BeachCA90278 United States Department of Electrical and Computer Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

In this work, we report the fabrication and characterizations of a monocrystalline GaAs/βGa2O3 p-n heterojunction by employing semiconductor grafting technology. The heterojunction was created by lifting off and transfer printing a p-type GaAs single crystal nanomembrane to an Al2O3 -coated n-type β-Ga2O3 epitaxial substrate. The resultant heterojunction diodes exhibit remarkable performance metrics, including an ideality factor of 1.23, a high rectification ratio of 8.04 × 109 at +/- 4V, and a turn on voltage at 2.35 V. Furthermore, at +5V, the diode displays a large current density of 2500 A/cm2 along with a low ON resistance of 2 mΩ∙cm2 Copyright © 2023, The Authors. All rights reserved.

关键词： Heterojunctions