Computationally efficient CFD prediction of bubbly flow using physics-guided deep learning

Crowd management has attracted serious attention under the prevailing pandemic conditions of COVID-19, emphasizing that sick persons do not become a source of virus transmission. World Health Organization (WHO) guidelines include maintaining a safe distance and wearing a mask in gatherings as part of standard operating procedures (SOP), considered thus far the most effective preventive measures to protect against COVID-19. Several methods and strategies have been used to construct various face detection and social distance detection models. In this paper, a deep learning model is presented to detect people without masks and those not keeping a safe distance to contain the virus. It also counts individuals who violate the SOP. The proposed model employs the Single Shot Multi-box Detector as a feature extractor, followed by Spatial Pyramid Pooling (SPP) to integrate the extracted features to improve the model's detecting capabilities. The MobilenetV2 architecture as a framework for the classifier makes the model highly light, fast, and computationally efficient, allowing it to be employed in embedded devices to do real-time mask and social distance detection, which is the sole objective of this research. This paper's technique yields an accuracy score of 99% and reduces the loss to 0.04%. Doi: 10.28991/esj-2021-SPER-14 Full Text: PDF

Download Full-text

Deep learning for Chinese NOx emission inversion and the integration of in situ observations: a case study on the COVID-19 pandemic

10.5194/ems2021-391 ◽

2021 ◽

Author(s):

Tai-Long He ◽

Dylan Jones ◽

Kazuyuki Miyazaki ◽

Kevin Bowman ◽

Zhe Jiang ◽

...

Keyword(s):

Deep Learning ◽

Reanalysis Data ◽

Data Sets ◽

Computationally Efficient ◽

Transport Models ◽

The Neural Network ◽

In Situ Observations ◽

Typical Variation

The COVID-19 pandemic led to the lockdown of over one-third of Chinese cities in early 2020. Observations have shown significant reductions of atmospheric abundances of NO2 over China during this period. This change in atmospheric NO2 implies a dramatic change in emission of NOx, which provides a unique opportunity to study the response of the chemistry of the atmospheric to large reductions in anthropogenic emissions. We use a deep learning (DL) model to quantify the change in surface emissions of NOx in China that are associated with the observed changes in atmospheric NO2 during the lockdown period. Compared to conventional data assimilation systems, deep neural networks are free of the potential errors associated with parameterized subgrid-scale processes. Furthermore, they are not susceptible to the chemical errors typically found in atmospheric chemical transport models. The neural-network-based approach also offers a more computationally efficient means of inverse modeling of NOx emissions at high spatial resolutions. Our DL model is trained using meteorological predictors and reanalysis data of surface NO2 from 2005 to 2017. The evaluation is conducted using in-situ measurements of NO2 in 2019 and 2020. The Baidu 'Qianxi' migration data sets are used to evaluate the model's performance in capturing the typical variation in Chinese NOx emissions during the Chinese New Year holidays. The TROPOMI-derived TCR-2 chemical reanalysis is used to evaluate the DL analysis in 2020. We show that the DL-based approach is able to better reproduce the variation in anthropogenic NOx emissions and capture the reduction in Chinese NOx emissions during the period of the COVID-19 pandemic.

Download Full-text

Anatomical Modeling of Brain Vasculature in Two-Photon Microscopy by Generalizable Deep Learning

BME Frontiers ◽

10.34133/2021/8620932 ◽

2021 ◽

Vol 2021 ◽

pp. 1-12

Author(s):

Waleed Tahir ◽

Sreekanth Kura ◽

Jiabei Zhu ◽

Xiaojun Cheng ◽

Rafat Damseh ◽

...

Keyword(s):

Deep Learning ◽

Large Scale ◽

Imaging Systems ◽

Total Variation Regularization ◽

Computationally Efficient ◽

Two Photon Microscopy ◽

Two Photon ◽

Brain Vasculature ◽

Vascular Segmentation ◽

Anatomical Modeling

Objective and Impact Statement. Segmentation of blood vessels from two-photon microscopy (2PM) angiograms of brains has important applications in hemodynamic analysis and disease diagnosis. Here, we develop a generalizable deep learning technique for accurate 2PM vascular segmentation of sizable regions in mouse brains acquired from multiple 2PM setups. The technique is computationally efficient, thus ideal for large-scale neurovascular analysis. Introduction. Vascular segmentation from 2PM angiograms is an important first step in hemodynamic modeling of brain vasculature. Existing segmentation methods based on deep learning either lack the ability to generalize to data from different imaging systems or are computationally infeasible for large-scale angiograms. In this work, we overcome both these limitations by a method that is generalizable to various imaging systems and is able to segment large-scale angiograms. Methods. We employ a computationally efficient deep learning framework with a loss function that incorporates a balanced binary-cross-entropy loss and total variation regularization on the network’s output. Its effectiveness is demonstrated on experimentally acquired in vivo angiograms from mouse brains of dimensions up to 808×808×702 μm. Results. To demonstrate the superior generalizability of our framework, we train on data from only one 2PM microscope and demonstrate high-quality segmentation on data from a different microscope without any network tuning. Overall, our method demonstrates 10× faster computation in terms of voxels-segmented-per-second and 3× larger depth compared to the state-of-the-art. Conclusion. Our work provides a generalizable and computationally efficient anatomical modeling framework for brain vasculature, which consists of deep learning-based vascular segmentation followed by graphing. It paves the way for future modeling and analysis of hemodynamic response at much greater scales that were inaccessible before.

Download Full-text

Diagnosis of Melanoma Lesion Using Neutrosophic and Deep Learning

Traitement du signal ◽

10.18280/ts.380507 ◽

2021 ◽

Vol 38 (5) ◽

pp. 1327-1338

Author(s):

Shubhendu Banerjee ◽

Sumit Kumar Singh ◽

Avishek Chakraborty ◽

Sharmistha Basu ◽

Atanu Das ◽

...

Keyword(s):

Deep Learning ◽

Accurate Result ◽

Recent Past ◽

Computationally Efficient ◽

Deep Convolutional Neural Networks ◽

Skin Imaging ◽

Melanocytic Lesions ◽

Skin Cancers ◽

Straight Line ◽

Efficient Mechanisms

Melanoma is a kind of skin cancer which occurs due to too much exposure of melanocyte cells to the dangerous UV radiations, that gets damaged and multiplies uncontrollably. This is popularly known as malignant melanoma and is comparatively less heard of than certain other types of skin cancers; however it can be more detrimental as it swiftly spreads if not detected and attended at a primary stage. The differentiation between benign and melanocytic lesions sometimes may be confusing, but the symptoms of the disease can reasonably be discriminated by a profound investigation of its histopathological and clinical characteristics. In the recent past, Deep Convolutional Neural Networks (DCNNs) have advanced in accomplishing far better results. The necessity of the present day is to have faster and computationally efficient mechanisms for diagnosis of the deadly disease. This paper makes an effort to showcase a deep learning-based ‘Keras’ algorithm, which is established on the implementation of DCNNs to investigate melanoma from dermoscopic and digital pictures and provide swifter and more accurate result as contrasted to standard CNNs. The main highlight of this paper, basically stands in its incorporation of certain ambitious notions like the segmentation performed by a culmination of a moving straight line with a sequence of points and the application of the concept of triangular neutrosophic number based on uncertain parameters. The experiment was done on a total of 40,676 images obtained from four commonly available datasets— International Symposium on Biomedical Imaging (ISBI) 2017, International Skin Imaging Collaboration (ISIC) 2018, ISIC 2019 and ISIC 2020 and the end result received was indeed motivating. It attained a Jac score of 86.81% on ISIC 2020 dataset and 95.98%, 95.66% and 94.42% on ISBI 2017, ISIC 2018 and ISIC 2019 datasets, respectively. The present research yielded phenomenal output in most instances in comparison to the pre-defined parameters with the similar types of works in this field.

Download Full-text

PDE-NetGen 1.0: from symbolic partial differential equation (PDE) representations of physical processes to trainable neural network representations

Geoscientific Model Development ◽

10.5194/gmd-13-3373-2020 ◽

2020 ◽

Vol 13 (7) ◽

pp. 3373-3382 ◽

Cited By ~ 1

Author(s):

Olivier Pannekoucke ◽

Ronan Fablet

Keyword(s):

Neural Network ◽

Deep Learning ◽

Network Architectures ◽

Computationally Efficient ◽

Partial Differential ◽

Compact Representations ◽

Network Generator ◽

Open Issue ◽

Neural Network Architectures ◽

Pde Solvers

Abstract. Bridging physics and deep learning is a topical challenge. While deep learning frameworks open avenues in physical science, the design of physically consistent deep neural network architectures is an open issue. In the spirit of physics-informed neural networks (NNs), the PDE-NetGen package provides new means to automatically translate physical equations, given as partial differential equations (PDEs), into neural network architectures. PDE-NetGen combines symbolic calculus and a neural network generator. The latter exploits NN-based implementations of PDE solvers using Keras. With some knowledge of a problem, PDE-NetGen is a plug-and-play tool to generate physics-informed NN architectures. They provide computationally efficient yet compact representations to address a variety of issues, including, among others, adjoint derivation, model calibration, forecasting and data assimilation as well as uncertainty quantification. As an illustration, the workflow is first presented for the 2D diffusion equation, then applied to the data-driven and physics-informed identification of uncertainty dynamics for the Burgers equation.

Download Full-text

A computationally efficient approach to segmentation of the aorta and coronary arteries using deep learning

IEEE Access ◽

10.1109/access.2021.3099030 ◽

2021 ◽

pp. 1-1

Author(s):

Wing Keung Cheung ◽

Robert Bell ◽

Arjun Nair ◽

Leon J. Menezes ◽

Riyaz Patel ◽

...

Keyword(s):

Deep Learning ◽

Coronary Arteries ◽

Computationally Efficient ◽

Efficient Approach

Download Full-text

Advanced Deep Learning-Based Bubbly Flow Image Generator under Different Superficial Gas Velocities

Industrial & Engineering Chemistry Research ◽

10.1021/acs.iecr.1c03883 ◽

2022 ◽

Author(s):

Zhong Xiang ◽

Binbin Xie ◽

Rui Fu ◽

Miao Qian

Keyword(s):

Deep Learning ◽

Bubbly Flow ◽

Flow Image ◽

Image Generator

Download Full-text

Deep learning for 3D seismic compressive-sensing technique: A novel approach

The Leading Edge ◽

10.1190/tle38090698.1 ◽

2019 ◽

Vol 38 (9) ◽

pp. 698-705

Author(s):

Ping Lu ◽

Yuan Xiao ◽

Yanyan Zhang ◽

Nikolaos Mitsakos

Keyword(s):

Deep Learning ◽

Compressive Sensing ◽

Field Data ◽

Original Data ◽

Generative Adversarial Networks ◽

Sampled Data ◽

Computationally Efficient ◽

Efficient Manner ◽

Adversarial Networks ◽

Novel Approach

A deep-learning-based compressive-sensing technique for reconstruction of missing seismic traces is introduced. The agility of the proposed approach lies in its ability to perfectly resolve the optimization limitation of conventional algorithms that solve inversion problems. It demonstrates how deep generative adversarial networks, equipped with an appropriate loss function that essentially leverages the distribution of the entire survey, can serve as an alternative approach for tackling compressive-sensing problems with high precision and in a computationally efficient manner. The method can be applied on both prestack and poststack seismic data, allowing for superior imaging quality with well-preconditioned and well-sampled field data, during the processing stage. To validate the robustness of the proposed approach on field data, the extent to which amplitudes and phase variations in original data are faithfully preserved is established, while subsurface consistency is also achieved. Several applications to acquisition and processing, such as decreasing bin size, increasing offset and azimuth sampling, or increasing the fold, can directly and immediately benefit from adopting the proposed technique. Furthermore, interpolation based on generative adversarial networks has been found to produce better-sampled data sets, with stronger regularization and attenuated aliasing phenomenon, while providing greater fidelity on steep-dip events and amplitude-variation-with-offset analysis with migration.

Download Full-text