scholarly journals Using artificial neural networks to extract the 21-cm global signal from the EDGES data

2021 ◽  
Vol 502 (2) ◽  
pp. 2815-2825
Author(s):  
Madhurima Choudhury ◽  
Atrideb Chatterjee ◽  
Abhirup Datta ◽  
Tirthankar Roy Choudhury
Keyword(s):  
Neutral Hydrogen ◽  
Simulated Data ◽  
Physical Models ◽  
Data Sets ◽  
First Stars ◽  
Global Signal ◽  
Reconstructed Signal ◽  
Radio Background ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

ABSTRACT The redshifted 21-cm signal of neutral hydrogen is a promising probe into the period of evolution of our Universe when the first stars were formed (Cosmic Dawn), to the period where the entire Universe changed its state from being completely neutral to completely ionized (Reionization). The most striking feature of this line of neutral hydrogen is that it can be observed across an entire frequency range as a sky-averaged continuous signature, or its fluctuations can be measured using an interferometer. However, the 21-cm signal is very faint and is dominated by a much brighter Galactic and extragalactic foregrounds, making it an observational challenge. We have used different physical models to simulate various realizations of the 21-cm global signals, including an excess radio background to match the amplitude of the Experiment to Detect the Global EoR Signature (EDGES) 21-cm signal. First, we have used an artificial neural network (ANN) to extract the astrophysical parameters from these simulated data sets. Then, mock observations were generated by adding a physically motivated foreground model and an ANN was used to extract the astrophysical parameters from such data. The R2 score of our predictions from the mock observations is in the range of 0.65–0.89. We have used this ANN to predict the signal parameters giving the EDGES data as the input. We find that the reconstructed signal closely mimics the amplitude of the reported detection. The recovered parameters can be used to infer the physical state of the gas at high redshifts.

scholarly journals Data Augmentation and Artificial Neural Networks for Eddy Currents Testing

2020 ◽  
Author(s):  
Romain Cormerais ◽  
Roberto Longo ◽  
Aroune Duclos ◽  
Guillaume Wasselynck ◽  
Gérard Berthiau
Keyword(s):  
Eddy Currents ◽  
Data Augmentation ◽  
Numerical Models ◽  
Simulated Data ◽  
Principal Component ◽  
Physical Models ◽  
Destructive Testing ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Non Destructive

Eddy Currents (ECs) Non Destructive Testing (NDT) is widely used to determine the position and size of flaws in metal materials. Due to difficulties in estimating these parameters via inverse algorithms based on physical models, approaches focused on Artificial Neural Network (ANN) are nowadays of great interest. The main drawbacks of these techniques still reside in the complexity of the numerical models and the large number of simulated data needed to train and test the ANN, leading to a considerable amount of calculation time and resources. To overcome these limitations, this article proposes a new approach based on a data augmentation procedure via Principal Component Analysis (PCA) applied to numerical simulations.

scholarly journals Quantiles as Robust Probes of Non-Gaussianity in 21-cm Images

2021 ◽  
Author(s):  
Alon Banet ◽  
Rennan Barkana ◽  
Anastasia Fialkov ◽  
Or Guttman
Keyword(s):  
Galactic Halo ◽  
Angular Resolution ◽  
Research Effort ◽  
First Stars ◽  
X Ray ◽  
Global Signal ◽  
Radio Background ◽  
Halo Masses ◽  
The Universe ◽  
Cosmic History

Abstract The epoch in which the first stars and galaxies formed is among the most exciting unexplored eras of the Universe. A major research effort is focused on probing this era with the 21-cm spectral line of hydrogen. While most research focuses on statistics like the 21-cm power spectrum or the sky-averaged global signal, there are other ways to analyze tomographic 21-cm maps, which may lead to novel insights. We suggest statistics based on quantiles as a method to probe non-Gaussianities of the 21-cm signal. We show that they can be used in particular to probe the variance, skewness, and kurtosis of the temperature distribution, but are more flexible and robust than these standard statistics. We test these statistics on a range of possible astrophysical models, including different galactic halo masses, star-formation efficiencies, and spectra of the X-ray heating sources, plus an exotic model with an excess early radio background. Simulating data with angular resolution and thermal noise as expected for the Square Kilometre Array (SKA), we conclude that these statistics can be measured out to redshifts above 20 and offer a promising statistical method for probing early cosmic history.

scholarly journals Predicting the liquefaction potential of soil layers in Tabriz city via artificial neural network analysis

2021 ◽  
Vol 3 (7) ◽  
Author(s):  
Mohammad Alizadeh Mansouri ◽  
Rouzbeh Dabiri
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soil Liquefaction ◽  
Data Sets ◽  
Liquefaction Potential ◽  
Advantages And Disadvantages ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Prediction Approach ◽  
Empirical Approaches

AbstractSoil liquefaction is a phenomenon through which saturated soil completely loses its strength and hardness and behaves the same as a liquid due to the severe stress it entails. This stress can be caused by earthquakes or sudden changes in soil stress conditions. Many empirical approaches have been proposed for predicting the potential of liquefaction, each of which includes advantages and disadvantages. In this paper, a novel prediction approach is proposed based on an artificial neural network (ANN) to adequately predict the potential of liquefaction in a specific range of soil properties. To this end, a whole set of 100 soil data is collected to calculate the potential of liquefaction via empirical approaches in Tabriz, Iran. Then, the results of the empirical approaches are utilized for data training in an ANN, which is considered as an option to predict liquefaction for the first time in Tabriz. The achieved configuration of the ANN is utilized to predict the liquefaction of 10 other data sets for validation purposes. According to the obtained results, a well-trained ANN is capable of predicting the liquefaction potential through error values of less than 5%, which represents the reliability of the proposed approach.

scholarly journals Applicability of Fuzzy Logic and Artificial Neural Network for Unpaved Airfield Surface Bearing Strength Prediction

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3373
Author(s):  
Ludek Cicmanec
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Logic ◽  
Regression Function ◽  
Large Data ◽  
Soil Strength ◽  
Data Sets ◽  
Bearing Strength ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The main objective of this paper is to describe a building process of a model predicting the soil strength at unpaved airport surfaces (unpaved runways, safety areas in runway proximity, runway strips, and runway end safety areas). The reason for building this model is to partially substitute frequent and meticulous inspections of an airport movement area comprising the bearing strength evaluation and provide an efficient tool to organize surface maintenance. Since the process of building such a model is complex for a physical model, it is anticipated that it might be addressed by a statistical model instead. Therefore, fuzzy logic (FL) and artificial neural network (ANN) capabilities are investigated and compared with linear regression function (LRF). Large data sets comprising the bearing strength and meteorological characteristics are applied to train the likely model variations to be subsequently compared with the application of standard statistical quantitative parameters. All the models prove that the inclusion of antecedent soil strength as an additional model input has an immense impact on the increase in model accuracy. Although the M7 model out of the ANN group displays the best performance, the M3 model is considered for practical implications being less complicated and having fewer inputs. In general, both the ANN and FL models outperform the LRF models well in all the categories. The FL models perform almost equally as well as the ANN but with slightly decreased accuracy.

A New Approach to Image Reconstruction in Positron Emission Tomography Using Artificial Neural Networks

1998 ◽  
Vol 09 (01) ◽  
pp. 71-85 ◽  
Author(s):  
A. Bevilacqua ◽  
D. Bollini ◽  
R. Campanini ◽  
N. Lanconelli ◽  
M. Galli
Keyword(s):  
Positron Emission Tomography ◽  
Simulated Data ◽  
Emission Tomography ◽  
Source Distribution ◽  
New Approach ◽  
High Data ◽  
Positron Emission ◽  
Physical Effects ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

This study investigates the possibility of using an Artificial Neural Network (ANN) for reconstructing Positron Emission Tomography (PET) images. The network is trained with simulated data which include physical effects such as attenuation and scattering. Once the training ends, the weights of the network are held constant. The network is able to reconstruct every type of source distribution contained inside the area mapped during the learning. The reconstruction of a simulated brain phantom in a noiseless case shows an improvement if compared with Filtered Back-Projection reconstruction (FBP). In noisy cases there is still an improvement, even if we do not compensate for noise fluctuations. These results show that it is possible to reconstruct PET images using ANNs. Initially we used a Dec Alpha; then, due to the high data parallelism of this reconstruction problem, we ported the learning on a Quadrics (SIMD) machine, suited for the realization of a small medical dedicated system. These results encourage us to continue in further studies that will make possible reconstruction of images of bigger dimension than those used in the present work (32 × 32 pixels).

A Prediction Model of Deflection of Fixing Thin Parts

2012 ◽  
Vol 217-219 ◽  
pp. 1526-1529
Author(s):  
Yu Mei Liu ◽  
Wen Ping Liu ◽  
Zhao Liang Jiang ◽  
Zhi Li
Keyword(s):  
Neural Network ◽  
Experimental Data ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Simulated Data ◽  
Artificial Neural ◽  
Predicted Values ◽  
Artificial Neural Network Ann ◽  
Abaqus Software

A prediction model of deflection is presented. The Artificial Neural Network (ANN) is adopted, and ANN establishes the mapping relation between the clamping forces and the position of fixing and the value of deflection. The results of simulation of Abaqus software is used for Training and querying an ANN. The predicted values are in agreement with simulated data and experimental data.

Plasma spray process modelling using artificial neural networks: Application to Al2O3-TiO2 (13% by weight) ceramic coating structure

2004 ◽  
Vol 120 ◽  
pp. 363-370
Author(s):  
S. Guessasma ◽  
G. Montavon ◽  
C. Coddet
Keyword(s):  
Thermal Spraying ◽  
Processing Parameters ◽  
Ceramic Coatings ◽  
Physical Models ◽  
Spray Process ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
The Stability ◽  
Experimental Values ◽  
Physical Phenomena

Thermal spraying is a versatile technique of coating manufacturing implementing large variety of materials and processes. The manufacture control is constrained by the understanding of the physical phenomena occurring during the spraying. It is however penalized by the large number of processing parameters (up to 50), their interdependencies, their correlations with the coating attributes and the stability of the process. Numerous statistical, heuristic or physical models intended to response to these constrains, very often partially because considering some aspects of the process. This work aims at considering a more global approach based on a powerful statistical methodology using artificial intelligence. Following this approach, the physical phenomena are encoded in a structure called Artificial Neural Network (ANN). An application of the ANN methodology is discussed in the case of the APS spray process. Some processing parameters categories are related to some coating properties for alumina-titania (13% by weight) ceramic coatings. ANN optimization is presented and discussed. Predicted results show globally a well agreement with the experimental values. Some conclusions point out the advantages of the ANN on the conventional methods, such as the design of experiments, used usually to recognize the controlling factors in a process.

Predicting Fatigue Life of Pre-Corroded LC4 Aluminum Alloy by Artificial Neural Network

2010 ◽  
Vol 118-120 ◽  
pp. 221-225 ◽  
Author(s):  
Cheng Long Xu ◽  
Sheng Li Lv ◽  
Zhen Guo Wang ◽  
Wei Zhang
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Aluminum Alloy ◽  
Fatigue Life ◽  
Network Architecture ◽  
Fatigue Tests ◽  
Data Sets ◽  
Absolute Relative Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The purpose of this work was to predict the fatigue life of pre-corroded LC4 aluminum alloy by applying artificial neural network (ANN). Specimens were exposed to the same corrosive environment for 24h, 48h, and 72h. Fatigue tests were conducted under different stress levels. The existing experimental data sets were used for training and testing the construction of proposed network. A suitable network architecture (2-15-1) was proposed with good performance in this study. For evaluating the method efficiency, the experimental results have been compared to values predicted by ANN. The maximum absolute relative error for predicted values does not exceed 5%. Therefore it can be concluded that using neural networks to predict the fatigue life of LC4 is feasible and reliable.

scholarly journals LANL* V2.0: global modeling and validation

2011 ◽  
Vol 4 (1) ◽  
pp. 575-594
Author(s):  
J. Koller ◽  
S. Zaharia
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Space Weather ◽  
Radiation Belt ◽  
Geosynchronous Orbit ◽  
Data Sets ◽  
Magnetic Field Model ◽  
Integration Techniques ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Abstract. We describe in this paper the new version of LANL*. Just like the previous version, this new version V2.0 of LANL* is an artificial neural network (ANN) for calculating the magnetic drift invariant, L*, that is used for modeling radiation belt dynamics and for other space weather applications. We have implemented the following enhancements in the new version: (1) we have removed the limitation to geosynchronous orbit and the model can now be used for any type of orbit. (2) The new version is based on the improved magnetic field model by Tsyganenko and Sitnov (2005) (TS05) instead of the older model by Tsyganenko et al. (2003). We have validated the model and compared our results to L* calculations with the TS05 model based on ephemerides for CRRES, Polar, GPS, a LANL geosynchronous satellite, and a virtual RBSP type orbit. We find that the neural network performs very well for all these orbits with an error typically Δ L* < 0.2 which corresponds to an error of 3% at geosynchronous orbit. This new LANL-V2.0 artificial neural network is orders of magnitudes faster than traditional numerical field line integration techniques with the TS05 model. It has applications to real-time radiation belt forecasting, analysis of data sets involving decades of satellite of observations, and other problems in space weather.

scholarly journals A Comparison of Emotional Neural Network (ENN) and Artificial Neural Network (ANN) Approach for Rainfall-Runoff Modelling

2019 ◽  
Vol 5 (10) ◽  
pp. 2120-2130 ◽  
Author(s):  
Suraj Kumar ◽  
Thendiyath Roshni ◽  
Dar Himayoun
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Data Sets ◽  
Rainfall Runoff ◽  
Data Set ◽  
Discharge Data ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Emotional Neural Network ◽  
Selection Of

Reliable method of rainfall-runoff modeling is a prerequisite for proper management and mitigation of extreme events such as floods. The objective of this paper is to contrasts the hydrological execution of Emotional Neural Network (ENN) and Artificial Neural Network (ANN) for modelling rainfall-runoff in the Sone Command, Bihar as this area experiences flood due to heavy rainfall. ENN is a modified version of ANN as it includes neural parameters which enhance the network learning process. Selection of inputs is a crucial task for rainfall-runoff model. This paper utilizes cross correlation analysis for the selection of potential predictors. Three sets of input data: Set 1, Set 2 and Set 3 have been prepared using weather and discharge data of 2 raingauge stations and 1 discharge station located in the command for the period 1986-2014.  Principal Component Analysis (PCA) has then been performed on the selected data sets for selection of data sets showing principal tendencies.  The data sets obtained after PCA have then been used in the model development of ENN and ANN models. Performance indices were performed for the developed model for three data sets. The results obtained from Set 2 showed that ENN with R= 0.933, R2 = 0.870, Nash Sutcliffe = 0.8689, RMSE = 276.1359 and Relative Peak Error = 0.00879 outperforms ANN in simulating the discharge. Therefore, ENN model is suggested as a better model for rainfall-runoff discharge in the Sone command, Bihar.

Sign in / Sign up

Export Citation Format

Share Document