scholarly journals Deep learning-based quantitative optoacoustic tomography of deep tissues in the absence of labeled experimental data

Optica ◽  
2021 ◽  
Author(s):  
jiao li ◽  
Tingting Chen ◽  
Cong Wang ◽  
tong lu ◽  
Shuai Li ◽  
...  
Keyword(s):  
Experimental Data ◽  
Deep Learning ◽  
Optoacoustic Tomography

scholarly journals Adaptive Intelligent Welding Manufacturing

2021 ◽  
Vol 100 (01) ◽  
pp. 63-83
Author(s):  
YUMING ZHANG ◽  
◽  
QIYUE WANG ◽  
YUKANG LIU
Keyword(s):  
Machine Learning ◽  
Experimental Data ◽  
Deep Learning ◽  
Welding Process ◽  
Welding Parameters ◽  
Weld Quality ◽  
Robotic Welding ◽  
Process Variables ◽  
Physical Constraints ◽  
Needed Information

Optimal design of the welding procedure gives the desired welding results under nominal welding conditions. During manufacturing, where the actual welding manufacturing conditions often deviate from the nominal ones used in the design, applying the designed procedure will produce welding results that are different from the desired ones. Adaption is needed to make corrections and adjust some of the welding parameters from those specified in the design. This is adaptive welding. While human welders can be adaptive to make corrections and adjustments, their performance is limited by their physical constraints and skill level. To be adaptive, automated and robotic welding systems require abilities in sensing the welding process, extracting the needed information from signals from the sensors, predicting the responses of the welding process to the adjustments on welding parameters, and optimizing the adjustments. This results in the application of classical sensing, modeling of process dynamics, and control system design. In many cases, the needed information for the weld quality and process variables of our concern is not easy to extract from the sensor’s data. Studies are needed to propose the phenomena to sense and establish the scientific foundation to correlate them to the weld quality or process variables of our concern. Such studies can be labor intensive, and a more automated approach is needed. Analysis suggests that artificial intelligence and machine learning, especially deep learning, can help automate the learning such that the needed intelligence for robotic welding adaptation can be directly and automatically learned from experimental data after the physical phenomena being represented by the experimental data has been appropriately selected to make sure they are fundamentally correlated to that with which we are concerned. Some adaptation abilities may also be learned from skilled human welders. In addition, human-robot collaborative welding may incorporate adaptations from humans with the welding robots. This paper analyzes and identifies the challenges in adaptive robotic welding, reviews efforts devoted to solve these challenges, analyzes the principles and nature of the methods behind these efforts, and introduces modern approaches, including machine learning/deep learning, learning from humans, and human-robot collaboration, to solve these challenges.

scholarly journals Boiling Heat Transfer Evaluation in Nanoporous Surface Coatings

Nanomaterials ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 3383
Author(s):  
Uzair Sajjad ◽  
Imtiyaz Hussain ◽  
Muhammad Imran ◽  
Muhammad Sultan ◽  
Chi-Chuan Wang ◽  
...  
Keyword(s):  
Heat Transfer ◽  
Experimental Data ◽  
Deep Learning ◽  
Thermophysical Properties ◽  
Boiling Heat Transfer ◽  
Parameters Estimation ◽  
Learning Method ◽  
Working Fluids ◽  
Coated Surfaces ◽  
Nanoporous Surfaces

The present study develops a deep learning method for predicting the boiling heat transfer coefficient (HTC) of nanoporous coated surfaces. Nanoporous coated surfaces have been used extensively over the years to improve the performance of the boiling process. Despite the large amount of experimental data on pool boiling of coated nanoporous surfaces, precise mathematical-empirical approaches have not been developed to estimate the HTC. The proposed method is able to cope with the complex nature of the boiling of nanoporous surfaces with different working fluids with completely different thermophysical properties. The proposed deep learning method is applicable to a wide variety of substrates and coating materials manufactured by various manufacturing processes. The analysis of the correlation matrix confirms that the pore diameter, the thermal conductivity of the substrate, the heat flow, and the thermophysical properties of the working fluids are the most important independent variable parameters estimation under consideration. Several deep neural networks are designed and evaluated to find the optimized model with respect to its prediction accuracy using experimental data (1042 points). The best model could assess the HTC with an R2 = 0.998 and (mean absolute error) MAE% = 1.94.

scholarly journals Terminitor: Cleavage Site Prediction Using Deep Learning Models

2019 ◽  
Author(s):  
Chen Yang ◽  
Chenkai Li ◽  
Ka Ming Nip ◽  
René L Warren ◽  
Inanc Birol
Keyword(s):  
Experimental Data ◽  
Gene Regulation ◽  
Deep Learning ◽  
Cleavage Site ◽  
Differential Expression Analysis ◽  
Underlying Mechanism ◽  
Library Preparation ◽  
Rna Seq ◽  
Sequencing Data ◽  
Reference Transcriptome

AbstractAs a widespread RNA processing machinery, alternative polyadenylation plays a crucial role in gene regulation. To help decipher its underlying mechanism and understand its impact, it is desirable to comprehensively profile 3’-untranslated region cleavage and associated polyadenylation sites. State-of-the-art polyadenylation site detection tools are known to be influenced by library preparation artefacts or manually selected features. Moreover, recently published machine learning methods have only been tested on pre-constructed datasets, thus lacking validation on experimental data. Here we present Terminitor, the first deep neural network-based profiling pipeline to make predictions from RNA-seq data. We show how Terminitor outperforms competing tools in sensitivity and precision on experimental transcriptome sequencing data, and demonstrate its use with data from short- and long-read sequencing technologies. For species without a good reference transcriptome annotation, Terminitor is still able to pass on the information learnt from a related species and make reasonable predictions. We used Terminitor to showcase how single nucleotide variations can create or destroy polyadenylated cleavage sites in human RNA-seq samples.Author Summary3’ cleavage and polyadenylation of pre-mRNA is part of RNA maturation process. One gene can be cleaved at different positions at its 3’ end, namely alternatively polyadenylation, thus identifying the correct polyadenylated cleavage site (poly(A) CS) is essential to unveil its role in gene regulation under different physiological and pathological conditions. The current poly(A) CS prediction tools are either heavily influenced by RNA-Seq library preparation artefacts or have only been designed and tested on ad hoc datasets, lacking association with real world applications. In this study, we present a deep learning model, Terminitor, that predicts the probability of a nucleotide sequence containing a poly(A) CS, and validated its performance on human and mouse data. Along with the model, we propose a poly(A) CS profiling pipeline for RNA-seq data. We benchmarked our pipeline against competing tools and achieved higher sensitivity and precision in experimental data. The usage of Terminitor is not limited to genome and transcriptome annotation and we expect it to facilitate the identification of novel isoforms, improve the accuracy of transcript quantification and differential expression analysis, and contribute to the repertoire of reference transcriptome annotation.

scholarly journals New Design Method for Fabricating Multilayer Membranes Using CO2-Assisted Polymer Compression Process

Molecules ◽  
2020 ◽  
Vol 25 (24) ◽  
pp. 5786
Author(s):  
Takafumi Aizawa
Keyword(s):  
Experimental Data ◽  
Deep Learning ◽  
Design Method ◽  
Sufficient Accuracy ◽  
Compression Process ◽  
Compression Behavior ◽  
Multilayer Membranes ◽  
Learning Data

It was verified that deep learning can be used in creating multilayer membranes with multiple porosities using the CO2-assisted polymer compression (CAPC) method. To perform training while reducing the number of experimental data as much as possible, the experimental data of the compression behavior of two layers were expanded to three layers for training, but sufficient accuracy could not be obtained. However, the accuracy was dramatically improved by adding the experimental data of the three layers. The possibility of only simulating process results without the necessity for a model is a merit unique to deep learning. Overall, in this study, the results show that by devising learning data, deep learning is extremely effective in designing multilayer membranes using the CAPC method.

scholarly journals Single particle diffusion characterization by deep learning

2019 ◽  
Author(s):  
Naor Granik ◽  
Elias Nehme ◽  
Lucien E. Weiss ◽  
Maayan Levin ◽  
Michael Chein ◽  
...  
Keyword(s):  
Experimental Data ◽  
Brownian Motion ◽  
Deep Learning ◽  
Anomalous Diffusion ◽  
Single Particle ◽  
Single Particle Tracking ◽  
Cellular Systems ◽  
Accurate Analysis ◽  
Diffusion Type ◽  
Diffusion Parameters

AbstractDiffusion plays a crucial role in many biological processes including signaling, cellular organization, transport mechanisms, and more. Direct observation of molecular movement by single-particle tracking experiments has contributed to a growing body of evidence that many cellular systems do not exhibit classical Brownian motion, but rather anomalous diffusion. Despite this evidence, characterization of the physical process underlying anomalous diffusion remains a challenging problem for several reasons. First, different physical processes can exist simultaneously in a system. Second, commonly used tools to distinguish between these processes are based on asymptotic behavior, which is inaccessible experimentally in most cases. Finally, an accurate analysis of the diffusion model requires the calculation of many observables, since different transport modes can result in the same diffusion power-law α, that is obtained from the commonly used mean-squared-displacement (MSD) in its various forms. The outstanding challenge in the field is to develop a method to extract an accurate assessment of the diffusion process using many short trajectories with a simple scheme that is applicable at the non-expert level.Here, we use deep learning to infer the underlying process resulting in anomalous diffusion. We implement a neural network to classify single particle trajectories according to diffusion type – Brownian motion, fractional Brownian motion (FBM) and Continuous Time Random Walk (CTRW). We further use the net to estimate the Hurst exponent for FBM, and the diffusion coefficient for Brownian motion, demonstrating its applicability on simulated and experimental data. The networks outperform time averaged MSD analysis on simulated trajectories while requiring as few as 25 time-steps. Furthermore, when tested on experimental data, both network and ensemble MSD analysis converge to similar values, with the network requiring half the trajectories required for ensemble MSD. Finally, we use the nets to extract diffusion parameters from multiple extremely short trajectories (10 steps).

scholarly journals A Sparse Deep Learning Approach for Automatic Segmentation of Human Vasculature in Multispectral Optoacoustic Tomography

2019 ◽  
Author(s):  
Nikolaos-Kosmas Chlis ◽  
Angelos Karlas ◽  
Nikolina-Alexia Fasoula ◽  
Michael Kallmayer ◽  
Hans-Henning Eckstein ◽  
...  
Keyword(s):  
Deep Learning ◽  
Automatic Segmentation ◽  
Isosbestic Point ◽  
Learning Approach ◽  
Manual Segmentation ◽  
Signal Attenuation ◽  
Optoacoustic Tomography ◽  
Vascular Assessment ◽  
Tissue Interactions ◽  
Vascular Segmentation

AbstractMultispectral Optoacoustic Tomography (MSOT) resolves oxy- (HbO2) and deoxy-hemoglobin (Hb) to perform vascular imaging. MSOT suffers from gradual signal attenuation with depth due to light-tissue interactions: an effect that hinders the precise manual segmentation of vessels. Furthermore, vascular assessment requires functional tests, which last several minutes and result in recording thousands of images. Here, we introduce a deep learning approach with a sparse UNET (S-UNET) for automatic vascular segmentation in MSOT images to avoid the rigorous and time-consuming manual segmentation. We evaluated the S-UNET on a test-set of 33 images, achieving a median DICE score of 0.88. Apart from high segmentation performance, our method based its decision on two wavelengths with physical meaning for the task-at-hand: 850 nm (peak absorption of oxy-hemoglobin) and 810 nm (isosbestic point of oxy-and deoxy-hemoglobin). Thus, our approach achieves precise data-driven vascular segmentation for automated vascular assessment and may boost MSOT further towards its clinical translation.

Deep learning of image- and time-domain data enhances visibility of structures in optoacoustic tomography

2021 ◽  
Author(s):  
Neda Davoudi ◽  
Ali Özbek ◽  
Berkan Lafci ◽  
XOSÉ DEÁN-BEN ◽  
Daniel Razansky
Keyword(s):  
Deep Learning ◽  
Time Domain ◽  
Optoacoustic Tomography ◽  
Time Domain Data

scholarly journals Deep Learning Methods On Neutron Scattering Data

2020 ◽  
Vol 225 ◽  
pp. 01004
Author(s):  
Guanghan Song ◽  
Lionel Porcar ◽  
Martin Boehm ◽  
Franck Cecillon ◽  
Charles Dewhurst ◽  
...  
Keyword(s):  
Experimental Data ◽  
Deep Learning ◽  
Neutron Scattering ◽  
Human Performance ◽  
Early Stage ◽  
Scientific Information ◽  
Scattering Data ◽  
Learning Methods ◽  
Structure Geometry ◽  
Instrument Configuration

Recently, by using deep learning methods, a computer is able to surpass or come close to matching human performance on image analysis and recognition. This advanced methods could also help extracting features from neutron scattering experimental data. Those data contain rich scientific information about structure and dynamics of materials under investigation. Deep learning could help researchers better understand the link between experimental data and materials properties. Moreover,it could also help to optimize neutron scattering experiment by predicting the best possible instrument configuration. Among all possible experimental methods, we begin our study on the small-angle neutron scattering (SANS) data and by predicting the structure geometry of the sample material at an early stage. This step is a keystone to predict the experimental parameters to properly setup the instrument as well as the best measurement strategy. In this paper, we propose to use transfer learning to retrain a convolutional neural networks (CNNs) based pre rained model to adapt the scattering images classification, which could predict the structure of the materials at an early stage in the SANS experiment. This deep neural network is trained and validated on simulated database, and tested on real scattering images.

scholarly journals Automatic Defects Segmentation and Identification by Deep Learning Algorithm with Pulsed Thermography: Synthetic and Experimental Data

2021 ◽  
Vol 5 (1) ◽  
pp. 9
Author(s):  
Qiang Fang ◽  
Clemente Ibarra-Castanedo ◽  
Xavier Maldague
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Neural Networks ◽  
Deep Learning ◽  
Infrared Thermography ◽  
Learning Algorithm ◽  
Synthetic Data ◽  
Training Data ◽  
Experimental Database ◽  
The Neural Network

In quality evaluation (QE) of the industrial production field, infrared thermography (IRT) is one of the most crucial techniques used for evaluating composite materials due to the properties of low cost, fast inspection of large surfaces, and safety. The application of deep neural networks tends to be a prominent direction in IRT Non-Destructive Testing (NDT). During the training of the neural network, the Achilles heel is the necessity of a large database. The collection of huge amounts of training data is the high expense task. In NDT with deep learning, synthetic data contributing to training in infrared thermography remains relatively unexplored. In this paper, synthetic data from the standard Finite Element Models are combined with experimental data to build repositories with Mask Region based Convolutional Neural Networks (Mask-RCNN) to strengthen the neural network, learning the essential features of objects of interest and achieving defect segmentation automatically. These results indicate the possibility of adapting inexpensive synthetic data merging with a certain amount of the experimental database for training the neural networks in order to achieve the compelling performance from a limited collection of the annotated experimental data of a real-world practical thermography experiment.

Deep learning optoacoustic tomography with sparse data

2019 ◽  
Vol 1 (10) ◽  
pp. 453-460 ◽  
Author(s):  
Neda Davoudi ◽  
Xosé Luís Deán-Ben ◽  
Daniel Razansky
Keyword(s):  
Deep Learning ◽  
Sparse Data ◽  
Optoacoustic Tomography
Sign in / Sign up

Export Citation Format

Share Document