scholarly journals Deep learning or interpolation for inverse modelling of heat and fluid flow problems?

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Rainald Löhner ◽  
Harbir Antil ◽  
Hamid Tamaddon-Jahromi ◽  
Neeraj Kavan Chakshu ◽  
Perumal Nithiarasu
Keyword(s):  
Neural Networks ◽  
Heat Conduction ◽  
Deep Neural Networks ◽  
Nonlinear Behaviour ◽  
Content Type ◽  
Flow Problems ◽  
Interpolation Algorithms ◽  
Transfer Problems ◽  
First Time ◽  
Heat And Fluid Flow

Purpose The purpose of this study is to compare interpolation algorithms and deep neural networks for inverse transfer problems with linear and nonlinear behaviour. Design/methodology/approach A series of runs were conducted for a canonical test problem. These were used as databases or “learning sets” for both interpolation algorithms and deep neural networks. A second set of runs was conducted to test the prediction accuracy of both approaches. Findings The results indicate that interpolation algorithms outperform deep neural networks in accuracy for linear heat conduction, while the reverse is true for nonlinear heat conduction problems. For heat convection problems, both methods offer similar levels of accuracy. Originality/value This is the first time such a comparison has been made.

Convergent optimal variational iteration method and applications to heat and fluid flow problems

2016 ◽  
Vol 26 (3/4) ◽  
pp. 790-804 ◽  
Author(s):  
Mustafa Turkyilmazoglu
Keyword(s):  
Fluid Flow ◽  
Iteration Method ◽  
Sufficient Conditions ◽  
Variational Iteration Method ◽  
Content Type ◽  
Flow Problems ◽  
Variational Iteration ◽  
Physical Problems ◽  
Novel Approach ◽  
Heat And Fluid Flow

Purpose – In an earlier paper (Turkyilmazoglu, 2011a), the author introduced a new optimal variational iteration method. The idea was to insert a parameter into the classical variational iteration formula in an aim to prevent divergence or to accelerate the slow convergence property of the classical approach. The purpose of this paper is to approve the superiority of the proposed method over the traditional one on several physical problems treated before by the classical variational iteration method. Design/methodology/approach – A sufficient condition theorem with an upper bound for the error is also presented to further justify the convergence of the new variational iteration method. Findings – The optimal variational iteration method is found to be useful for heat and fluid flow problems. Originality/value – The optimal variational iteration method is shown to be convergent under sufficient conditions. A novel approach to obtain the optimal convergence parameter is introduced.

scholarly journals Technical note: AI-Track-tive: automated fission track recognition using computer vision (Artificial Intelligence)

2020 ◽  
Author(s):  
Simon Nachtergaele ◽  
Johan De Grave
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Computer Vision ◽  
Deep Neural Networks ◽  
Fission Track ◽  
Detection Algorithm ◽  
Technical Note ◽  
Success Rates ◽  
Automatic Counting ◽  
First Time

Abstract. Artificial intelligence techniques such as deep neural networks and computer vision are developed for fission track recognition and included in a computer program for the first time. These deep neural networks use the Yolov3 object detection algorithm, which is currently one of the most powerful and fastest object recognition algorithms. These deep neural networks can be used in new software called AI-Track-tive. The developed program successfully finds most of the fission tracks in the microscope images, however, the user still needs to supervise the automatic counting. The success rates of the automatic recognition range from 70 % to 100 % depending on the areal track densities in apatite and (muscovite) external detector. The success rate generally decreases for images with high areal track densities, because overlapping tracks are less easily recognizable for computer vision techniques.

scholarly journals Uncertainty estimation on road safety analysis using bayesian deep neural networks

2021 ◽  
Author(s):  
Guangyuan Pan ◽  
Chen Qili ◽  
Fu Liping ◽  
Yu Ming ◽  
Muresan Matthew
Keyword(s):  
Neural Networks ◽  
Traffic Engineering ◽  
Road Safety ◽  
Deep Neural Networks ◽  
Surface Condition ◽  
Uncertainty Estimation ◽  
Public Confidence ◽  
Accurate Information ◽  
Crash Prediction ◽  
First Time

Deep neural networks have been successfully used in many different areas of traffic engineering, such as crash prediction, intelligent signal optimization and real-time road surface condition monitoring. The benefits of deep neural networks are often uniquely suited to solve certain problems and can offer improvements in performance when compared to traditional methods. In collision prediction, uncertainty estimation is a critical area that can benefit from their application, and accurate information on the reliability of a model’s predictions can increase public confidence in those models. Applications of deep neural networks to this problem that consider these effects have not been studied previously. This paper develops a Bayesian deep neural network for crash prediction and examines the reliability of the model based on three key methods: layer-wise greedy unsupervised learning, Bayesian regularization and adapted marginalization. An uncertainty equation for the model is also proposed for this domain for the first time. To test the performance, eight years of car collision data collected from Highway 401, Canada, is used, and three experiments are designed.

scholarly journals Intelligent control of quad-rotor aircrafts with a STM32 microcontroller using deep neural networks

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Xiaochun Guan ◽  
Sheng Lou ◽  
Han Li ◽  
Tinglong Tang
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Data Communication ◽  
Efficient Design ◽  
Embedded Devices ◽  
Content Type ◽  
Design Scheme ◽  
Communication Module ◽  
Aerial Vehicle ◽  
Optical Flow Sensor

Purpose Deployment of deep neural networks on embedded devices is becoming increasingly popular because it can reduce latency and energy consumption for data communication. This paper aims to give out a method for deployment the deep neural networks on a quad-rotor aircraft for further expanding its application scope. Design/methodology/approach In this paper, a design scheme is proposed to implement the flight mission of the quad-rotor aircraft based on multi-sensor fusion. It integrates attitude acquisition module, global positioning system position acquisition module, optical flow sensor, ultrasonic sensor and Bluetooth communication module, etc. A 32-bit microcontroller is adopted as the main controller for the quad-rotor aircraft. To make the quad-rotor aircraft be more intelligent, the study also proposes a method to deploy the pre-trained deep neural networks model on the microcontroller based on the software packages of the RT-Thread internet of things operating system. Findings This design provides a simple and efficient design scheme to further integrate artificial intelligence (AI) algorithm for the control system design of quad-rotor aircraft. Originality/value This method provides an application example and a design reference for the implementation of AI algorithms on unmanned aerial vehicle or terminal robots.

Obtaining depth map from 2D non stereo images using deep neural networks

2018 ◽  
Vol 6 (3) ◽  
pp. 134-146
Author(s):  
Daniil Igorevich Mikhalchenko ◽  
Arseniy Ivin ◽  
Dmitrii Malov
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Depth Map ◽  
Depth Information ◽  
Data Sets ◽  
Data Set ◽  
Content Type ◽  
Laser Sensors ◽  
Depth Images ◽  
Depth Prediction

Purpose Single image depth prediction allows to extract depth information from a usual 2D image without usage of special sensors such as laser sensors, stereo cameras, etc. The purpose of this paper is to solve the problem of obtaining depth information from 2D image by applying deep neural networks (DNNs). Design/methodology/approach Several experiments and topologies are presented: DNN that uses three inputs—sequence of 2D images from videostream and DNN that uses only one input. However, there is no data set, that contains videostream and corresponding depth maps for every frame. So technique of creating data sets using the Blender software is presented in this work. Findings Despite the problem of an insufficient amount of available data sets, the problem of overfitting was encountered. Although created models work on the data sets, they are still overfitted and cannot predict correct depth map for the random images, that were included into the data sets. Originality/value Existing techniques of depth images creation are tested, using DNN.

scholarly journals Physics‐Informed Deep Neural Networks for Learning Parameters and Constitutive Relationships in Subsurface Flow Problems

2020 ◽  
Vol 56 (5) ◽  
Author(s):  
A. M. Tartakovsky ◽  
C. Ortiz Marrero ◽  
Paris Perdikaris ◽  
G. D. Tartakovsky ◽  
D. Barajas‐Solano
Keyword(s):  
Neural Networks ◽  
Deep Neural Networks ◽  
Subsurface Flow ◽  
Flow Problems ◽  
Constitutive Relationships

scholarly journals CryoDRGN: Reconstruction of heterogeneous structures from cryo-electron micrographs using neural networks

2020 ◽  
Author(s):  
Ellen D. Zhong ◽  
Tristan Bepler ◽  
Bonnie Berger ◽  
Joseph H. Davis
Keyword(s):  
Neural Networks ◽  
Conformational Changes ◽  
Deep Neural Networks ◽  
Protein Complexes ◽  
Structural Heterogeneity ◽  
Particle Analysis ◽  
Single Particle Analysis ◽  
Current Analysis ◽  
Heterogeneous Structures ◽  
First Time

AbstractCryo-EM single-particle analysis has proven powerful in determining the structures of rigid macromolecules. However, many protein complexes are flexible and can change conformation and composition as a result of functionally-associated dynamics. Such dynamics are poorly captured by current analysis methods. Here, we present cryoDRGN, an algorithm that for the first time leverages the representation power of deep neural networks to efficiently reconstruct highly heterogeneous complexes and continuous trajectories of protein motion. We apply this tool to two synthetic and three publicly available cryo-EM datasets, and we show that cryoDRGN provides an interpretable representation of structural heterogeneity that can be used to identify discrete states as well as continuous conformational changes. This ability enables cryoDRGN to discover previously overlooked structural states and to visualize molecules in motion.

scholarly journals Raspberry PI for Kill Mosquitoes by Laser

2021 ◽  
Author(s):  
Ildar Rakhmatulin
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Raspberry Pi ◽  
Classification Problems ◽  
Power Laser ◽  
The World ◽  
Aerial Vehicle ◽  
First Time ◽  
Laser Installation

More than 700 thousand human deaths from mosquito bites are observed annually in the world. It is more than 2 times the number of annual murders in the world. In this regard, the invention of new more effective methods of protection against mosquitoes is necessary. In this article for the first time, comprehensive studies of mosquito neutralization using machine vision and a 1 W power laser are considered. Developed laser installation with Raspberry Pi that changing the direction of the laser with a galvanometer. We developed a program for mosquito tracking in real. The possibility of using deep neural networks, Haar cascades, machine learning for mosquito recognition was considered. We considered in detail the classification problems of mosquitoes in images. A recommendation is given for the implementation of this device based on a microcontroller for subsequent use as part of an unmanned aerial vehicle. Any harmful insects in the fields can be used as objects for control.

A numerical method for two-dimensional inverse heat conduction problems

2015 ◽  
Vol 25 (1) ◽  
pp. 190-198 ◽  
Author(s):  
Xiuying Li
Keyword(s):  
Heat Conduction ◽  
Iteration Method ◽  
Present Method ◽  
Design Methodology ◽  
Variational Iteration Method ◽  
Two Dimensional ◽  
Inverse Heat Conduction ◽  
Content Type ◽  
Inverse Heat Conduction Problems ◽  
First Time

Purpose – The purpose of this paper is to introduce an effective method for two-dimensional inverse heat conduction problems. Design/methodology/approach – The variational iteration method (VIM) is used to solve two-dimensional inverse heat conduction problems and restore boundary conditions in heat conduction. Findings – Numerical results compared with other methods show that the present method is remarkably effective for solving two-dimensional inverse heat conduction problems. This method is a very promoting method, which will be certainly found wide applications. Originality/value – The VIM is applied to two-dimensional inverse heat conduction problems for the first time.

Sign in / Sign up

Export Citation Format

Share Document