INDEEDopt: a deep learning-based ReaxFF parameterization framework

<div><div><div><p>ReaxFF is an empirical interatomic potential capable of simulating reactions in complex chemical processes and thus determine the dynamical evolution of the molecular systems. A drawback of this method is the necessity of a significant preprocessing to adapt it to a chemical system of nterest. One of the preprocessing steps is the optimization of force field parameters that are used to tune interatomic interactions to mimic ones obtained by quantum chemistry-based methods. The optimization of these parameters is a very complex high dimensional problem. Here, we propose an INitial-DEsign Enhanced Deep learning-based OPTimization (INDEEDopt) framework to be used in ReaxFF parameterization. The procedure starts with a Latin Hypercube Design (LHD) algorithm that is used to explore the parameter landscape extensively. The LHD passes the information about explored regions to a deep learning model for training. The deep learning model finds the minimum discrepancy regions and eliminates unfeasible regions, which originate from the unphysical atomistic interactions, and constructs a more comprehensive understanding of a physically meaningful parameter space. The procedure was successfully used to parametrize a nickel-chromium binary force field and a tungsten-sulfide-carbon-hydrogen quaternary force field and produced improved accuracies in shorter periods time compared to conventional optimization method.</p></div></div></div>

Download Full-text

An Initial Design-enhanced Deep Learning-based Optimization Framework to Parameterize Multicomponent ReaxFF Force Fields

10.26434/chemrxiv.12323909.v1 ◽

2020 ◽

Author(s):

Mert Sengul ◽

Nadire Nayir ◽

Yawei Gao ◽

Ying Hung ◽

Tirthankar Dasgupta ◽

...

Keyword(s):

Deep Learning ◽

Force Field ◽

Interatomic Potential ◽

Dynamical Evolution ◽

Optimization Method ◽

Learning Model ◽

Chemical System ◽

Latin Hypercube Design ◽

Initial Design ◽

Deep Learning Model

<div><div><div><p>ReaxFF is an empirical interatomic potential capable of simulating reactions in complex chemical processes and thus determine the dynamical evolution of the molecular systems. A drawback of this method is the necessity of a significant preprocessing to adapt it to a chemical system of nterest. One of the preprocessing steps is the optimization of force field parameters that are used to tune interatomic interactions to mimic ones obtained by quantum chemistry-based methods. The optimization of these parameters is a very complex high dimensional problem. Here, we propose an INitial-DEsign Enhanced Deep learning-based OPTimization (INDEEDopt) framework to be used in ReaxFF parameterization. The procedure starts with a Latin Hypercube Design (LHD) algorithm that is used to explore the parameter landscape extensively. The LHD passes the information about explored regions to a deep learning model for training. The deep learning model finds the minimum discrepancy regions and eliminates unfeasible regions, which originate from the unphysical atomistic interactions, and constructs a more comprehensive understanding of a physically meaningful parameter space. The procedure was successfully used to parametrize a nickel-chromium binary force field and a tungsten-sulfide-carbon-hydrogen quaternary force field and produced improved accuracies in shorter periods time compared to conventional optimization method.</p></div></div></div>

Download Full-text

An Initial Design-enhanced Deep Learning-based Optimization Framework to Parameterize Multicomponent ReaxFF Force Fields

10.26434/chemrxiv.12323909 ◽

2020 ◽

Author(s):

Mert Sengul ◽

Yao Song ◽

Nadire Nayir ◽

Yawei Gao ◽

Ying Hung ◽

...

Keyword(s):

Deep Learning ◽

Force Field ◽

Interatomic Potential ◽

Dynamical Evolution ◽

Optimization Method ◽

Learning Model ◽

Chemical System ◽

Latin Hypercube Design ◽

Initial Design ◽

Deep Learning Model

<div><div><div><p>ReaxFF is an empirical interatomic potential capable of simulating reactions in complex chemical processes and thus determine the dynamical evolution of the molecular systems. A drawback of this method is the necessity of a significant preprocessing to adapt it to a chemical system of nterest. One of the preprocessing steps is the optimization of force field parameters that are used to tune interatomic interactions to mimic ones obtained by quantum chemistry-based methods. The optimization of these parameters is a very complex high dimensional problem. Here, we propose an INitial-DEsign Enhanced Deep learning-based OPTimization (INDEEDopt) framework to be used in ReaxFF parameterization. The procedure starts with a Latin Hypercube Design (LHD) algorithm that is used to explore the parameter landscape extensively. The LHD passes the information about explored regions to a deep learning model for training. The deep learning model finds the minimum discrepancy regions and eliminates unfeasible regions, which originate from the unphysical atomistic interactions, and constructs a more comprehensive understanding of a physically meaningful parameter space. The procedure was successfully used to parametrize a nickel-chromium binary force field and a tungsten-sulfide-carbon-hydrogen quaternary force field and produced improved accuracies in shorter periods time compared to conventional optimization method.</p></div></div></div>

Download Full-text

Ground-truth uncertainty-aware metrics for machine learning applications on seismic image interpretation: Application to faults and horizon extraction

The Leading Edge ◽

10.1190/tle39100734.1 ◽

2020 ◽

Vol 39 (10) ◽

pp. 734-741

Author(s):

Sébastien Guillon ◽

Frédéric Joncour ◽

Pierre-Emmanuel Barrallon ◽

Laurent Castanié

Keyword(s):

Deep Learning ◽

Image Interpretation ◽

Ground Truth ◽

Learning Model ◽

Seismic Interpretation ◽

Data Set ◽

Seismic Image ◽

Machine Learning Applications ◽

Deep Learning Model

We propose new metrics to measure the performance of a deep learning model applied to seismic interpretation tasks such as fault and horizon extraction. Faults and horizons are thin geologic boundaries (1 pixel thick on the image) for which a small prediction error could lead to inappropriately large variations in common metrics (precision, recall, and intersection over union). Through two examples, we show how classical metrics could fail to indicate the true quality of fault or horizon extraction. Measuring the accuracy of reconstruction of thin objects or boundaries requires introducing a tolerance distance between ground truth and prediction images to manage the uncertainties inherent in their delineation. We therefore adapt our metrics by introducing a tolerance function and illustrate their ability to manage uncertainties in seismic interpretation. We compare classical and new metrics through different examples and demonstrate the robustness of our metrics. Finally, we show on a 3D West African data set how our metrics are used to tune an optimal deep learning model.

Download Full-text

Analysis of COVID-19 Infections on a CT Image Using DeepSense Model

Frontiers in Public Health ◽

10.3389/fpubh.2020.599550 ◽

2020 ◽

Vol 8 ◽

Author(s):

Adil Khadidos ◽

Alaa O. Khadidos ◽

Srihari Kannan ◽

Yuvaraj Natarajan ◽

Sachi Nandan Mohanty ◽

...

Keyword(s):

Neural Network ◽

Deep Learning ◽

Input Data ◽

Training Data ◽

Learning Framework ◽

Learning Classifiers ◽

Tomography Image ◽

Mining Model ◽

Deep Learning Model

In this paper, a data mining model on a hybrid deep learning framework is designed to diagnose the medical conditions of patients infected with the coronavirus disease 2019 (COVID-19) virus. The hybrid deep learning model is designed as a combination of convolutional neural network (CNN) and recurrent neural network (RNN) and named as DeepSense method. It is designed as a series of layers to extract and classify the related features of COVID-19 infections from the lungs. The computerized tomography image is used as an input data, and hence, the classifier is designed to ease the process of classification on learning the multidimensional input data using the Expert Hidden layers. The validation of the model is conducted against the medical image datasets to predict the infections using deep learning classifiers. The results show that the DeepSense classifier offers accuracy in an improved manner than the conventional deep and machine learning classifiers. The proposed method is validated against three different datasets, where the training data are compared with 70%, 80%, and 90% training data. It specifically provides the quality of the diagnostic method adopted for the prediction of COVID-19 infections in a patient.

Download Full-text

GLE-Net: A Global and Local Ensemble Network for Aerial Object Detection

International Journal of Computational Intelligence Systems ◽

10.1007/s44196-021-00056-3 ◽

2022 ◽

Vol 15 (1) ◽

Author(s):

Jiajia Liao ◽

Yujun Liu ◽

Yingchao Piao ◽

Jinhe Su ◽

Guorong Cai ◽

...

Keyword(s):

Deep Learning ◽

Object Detection ◽

Aerial Images ◽

Visual Object ◽

Detection Algorithms ◽

Integration Strategy ◽

Bounding Boxes ◽

Global And Local ◽

Deep Learning Model

AbstractRecent advances in camera-equipped drone applications increased the demand for visual object detection algorithms with deep learning for aerial images. There are several limitations in accuracy for a single deep learning model. Inspired by ensemble learning can significantly improve the generalization ability of the model in the machine learning field, we introduce a novel integration strategy to combine the inference results of two different methods without non-maximum suppression. In this paper, a global and local ensemble network (GLE-Net) was proposed to increase the quality of predictions by considering the global weights for different models and adjusting the local weights for bounding boxes. Specifically, the global module assigns different weights to models. In the local module, we group the bounding boxes that corresponding to the same object as a cluster. Each cluster generates a final predict box and assigns the highest score in the cluster as the score of the final predict box. Experiments on benchmarks VisDrone2019 show promising performance of GLE-Net compared with the baseline network.

Download Full-text

Can a deep learning model based on intraoperative time-series monitoring data predict post-hysterectomy quality of recovery?

Perioperative Medicine ◽

10.1186/s13741-021-00178-4 ◽

2021 ◽

Vol 10 (1) ◽

Author(s):

Xu Zhao ◽

Ke Liao ◽

Wei Wang ◽

Junmei Xu ◽

Lingzhong Meng

Keyword(s):

Time Series ◽

Logistic Regression ◽

Deep Learning ◽

Intraoperative Monitoring ◽

Learning Model ◽

Monitoring Data ◽

Quality Of Recovery ◽

Model Based ◽

Deep Learning Model

Abstract Background Intraoperative physiological monitoring generates a large quantity of time-series data that might be associated with postoperative outcomes. Using a deep learning model based on intraoperative time-series monitoring data to predict postoperative quality of recovery has not been previously reported. Methods Perioperative data from female patients having laparoscopic hysterectomy were prospectively collected. Deep learning, logistic regression, support vector machine, and random forest models were trained using different datasets and evaluated by 5-fold cross-validation. The quality of recovery on postoperative day 1 was assessed using the Quality of Recovery-15 scale. The quality of recovery was dichotomized into satisfactory if the score ≥122 and unsatisfactory if <122. Models’ discrimination was estimated using the area under the receiver operating characteristics curve (AUROC). Models’ calibration was visualized using the calibration plot and appraised by the Brier score. The SHapley Additive exPlanation (SHAP) approach was used to characterize different input features’ contributions. Results Data from 699 patients were used for modeling. When using preoperative data only, all four models exhibited poor performance (AUROC ranging from 0.65 to 0.68). The inclusion of the intraoperative intervention and/or monitoring data improved the performance of the deep leaning, logistic regression, and random forest models but not the support vector machine model. The AUROC of the deep learning model based on the intraoperative monitoring data only was 0.77 (95% CI, 0.72–0.81), which was indistinct from that based on the intraoperative intervention data only (AUROC, 0.79; 95% CI, 0.75–0.82) and from that based on the preoperative, intraoperative intervention, and monitoring data combined (AUROC, 0.81; 95% CI, 0.78–0.83). In contrast, when using the intraoperative monitoring data only, the logistic regression model had an AUROC of 0.72 (95% CI, 0.68–0.77), and the random forest model had an AUROC of 0.74 (95% CI, 0.73–0.76). The Brier score of the deep learning model based on the intraoperative monitoring data was 0.177, which was lower than that of other models. Conclusions Deep learning based on intraoperative time-series monitoring data can predict post-hysterectomy quality of recovery. The use of intraoperative monitoring data for outcome prediction warrants further investigation. Trial registration This trial (Identifier: NCT03641625) was registered at ClinicalTrials.gov by the principal investigator, Lingzhong Meng, on August 22, 2018.

Download Full-text

Self-Attention based model forde-novoantibiotic resistant gene classification with enhanced reliability for Out of Distribution data detection

10.1101/543272 ◽

2019 ◽

Author(s):

Md-Nafiz Hamid ◽

Iddo Friedberg

Keyword(s):

Deep Learning ◽

Optimization Method ◽

Distribution Data ◽

Data Detection ◽

Antibiotic Resistant ◽

Global Epidemic ◽

Resistant Genes ◽

Uncertainty Estimates ◽

The Face ◽

Deep Learning Model

AbstractAntibiotic resistance monitoring is of paramount importance in the face of this ongoing global epidemic. Using traditional alignment based methods to detect antibiotic resistant genes results in huge number of false negatives. In this paper, we introduce a deep learning model based on a self-attention architecture that can classify antibiotic resistant genes into correct classes with high precision and recall by just using protein sequences as input. Additionally, deep learning models trained with traditional optimization algorithms (e.g. Adam, SGD) provide poor posterior estimates when tested against Out-of-Distribution (OoD) antibiotic resistant/non-resistant genes. We train our model with an optimization method called Preconditioned Stochastic Gradient Langevin Dynamics (pSGLD) which provides reliable uncertainty estimates when tested against OoD data.

Download Full-text

Deep learning based quantification of the accelerated brain aging rate in glioma patients after radiotherapy

10.1101/2021.12.22.21267899 ◽

2021 ◽

Author(s):

Selena I. Huisman ◽

Arthur T.J. van der Boog ◽

Fia Cialdella ◽

Joost J.C. Verhoeff ◽

Szabolcs David

Keyword(s):

Deep Learning ◽

Brain Aging ◽

Accelerated Aging ◽

Learning Model ◽

Aging Rate ◽

Saliency Maps ◽

Mri Scans ◽

Brain Age ◽

Deep Learning Model

Background and purpose. Changes of healthy appearing brain tissue after radiotherapy have been previously observed, however, they remain difficult to quantify. Due to these changes, patients undergoing radiotherapy may have a higher risk of cognitive decline, leading to a reduced quality of life. The experienced tissue atrophy is similar to the effects of normal aging in healthy individuals. We propose a new way to quantify tissue changes after cranial RT as accelerated brain aging using the BrainAGE framework. Materials and methods. BrainAGE was applied to longitudinal MRI scans of 32 glioma patients, who have undergone radiotherapy. Utilizing a pre-trained deep learning model, brain age is estimated for all patients' pre-radiotherapy planning and follow-up MRI scans to get a quantification of the changes occurring in the brain over time. Saliency maps were extracted from the model to spatially identify which areas of the brain the deep learning model weighs highest for predicting age. The predicted ages from the deep learning model were used in a linear mixed effects model to quantity aging and aging rates for patients after radiotherapy. Results. The linear mixed effects model resulted in an accelerated aging rate of 2.78 years per year, a significant increase over a normal aging rate of 1 (p <0.05, confidence interval (CI) = 2.54-3.02). Furthermore, the saliency maps showed numerous anatomically well-defined areas, e.g.: Heschl's gyrus among others, determined by the model as important for brain age prediction. Conclusion. We found that patients undergoing radiotherapy are affected by significant radiation- induced accelerated aging, with several anatomically well-defined areas contributing to this aging. The estimated brain age could provide a method for quantifying quality of life post-radiotherapy.

Download Full-text

A Deep Learning Approach to Mobile Camera Image Signal Processing

10.5753/sibgrapi.est.2020.13016 ◽

2020 ◽

Author(s):

Jose Ivson S. Silva ◽

Gabriel G. Carvalho ◽

Marcel Santana Santos ◽

Diego J. C. Santiago ◽

Lucas Pontes De Albuquerque ◽

...

Keyword(s):

Signal Processing ◽

Deep Learning ◽

Deep Neural Network ◽

Learning Approach ◽

Image Capture ◽

Camera Image ◽

Mobile Cameras ◽

Physical Resources ◽

Deep Learning Model

The quality of the images obtained from mobile cameras has been an important feature for modern smartphones. The camera Image Signal Processing (ISP) is a significant procedure when generating high-quality images. However, the existing algorithms in the ISP pipeline need to be tuned according to the physical resources of the image capture, limiting the final image quality. This work aims at replacing the camera ISP pipeline with a deep learning model that can better generalize the procedure. A Deep Neural Network based on the UNet architecture was employed to process RAW images into RGB. Pre-processing stages were applied, and some resources for training were added incrementally. The results demonstrated that the test images were obtained efficiently, indicating that the replacement of traditional algorithms by deep models is indeed a promising path.

Download Full-text