Prediction of groundwater drawdown using artificial neural networks

Abstract Groundwater drawdown is typically measured using pumping tests and field experiments; however, the traditional methods are time-consuming and costly when applied to extensive areas. In this research, a methodology is introduced based on artificial neural network (ANN)s and field measurements in an alluvial aquifer in the north of Iran. First, the annual drawdown as the output of the ANN models in 250 piezometric wells was measured, and the data were divided into three categories of training data, cross-validation data, and test data. Then, the effective factors in groundwater drawdown including groundwater depth, annual precipitation, annual evaporation, the transmissivity of the aquifer formation, elevation, distance from the sea, distance from water sources (recharge), population density, and groundwater extraction in the influence radius of each well (1000 m) were identified and used as the inputs of the ANN models. Several ANN methods were evaluated, and the predictions were compared with the observations. Results show that, the modular neural network (MNN) showed the highest performance in modeling groundwater drawdown (Training R-sqr = 0.96, test R-sqr = 0.81). The optimum network was fitted to available input data to map the annual drawdown across the entire aquifer. The accuracy assessment of the final map yielded favorable results (R-sqr = 0.8). The adopted methodology can be applied for the prediction of groundwater drawdown in the study site and similar settings elsewhere.

Prediction of Target Displacement of Reinforced Concrete Frames Using Artificial Neural Networks

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.255-260.2345 ◽

2011 ◽

Vol 255-260 ◽

pp. 2345-2349 ◽

Cited By ~ 2

Author(s):

Iman Kameli ◽

Mahmoud Miri ◽

Ali Raji

Keyword(s):

Neural Network ◽

Reinforced Concrete ◽

High Speed ◽

Back Propagation ◽

Training Data ◽

Target Displacement ◽

Base Shear ◽

Validation Data ◽

Rbf Network ◽

In this paper, the application of artificial neural network (ANN) in predicting seismic response of reinforced concrete (RC) frames with masonry infilled walls is investigated. The objective of this research is to predict roof displacement and base shear (ANN outputs) in the target displacement. The total of 855 database were prepared for modeling neural network using finite element method (FEM) by changing six parameters (the input parameters of ANN) including the number of bays, the number of stories, thickness of masonry infill, infilled wall ratio, existence of soft story and design spectral acceleration. A training set of 513 prepared database were used as training data and the validation set of 342 database were used as validation data in the next step. In the present study, two ANNs were trained; a multilayer perseptron (MLP) with Levenberg–Marquardt (LM) back propagation algorithms and a Radial Basis function (RBF), both with different structures and the best structure for each of them was obtained. The performance of ANNs was evaluated using mean square error (MSE) and correlation coefficient (R2) criteria. Results indicate that using both MLP and RBF ANNs for predicting target displacement have been appropriate and have low error as well as high speed. Furthermore, RBF network has a higher speed in training process of data compared to MLP network.

Artificial Neural Network Military Impulse Noise Classifier

Noise Control and Acoustics ◽

10.1115/imece2006-14065 ◽

2006 ◽

Author(s):

Brian Bucci ◽

Jeffrey Vipperman

Keyword(s):

Neural Network ◽

Impulse Noise ◽

Training Data ◽

Noise Sources ◽

Wind Noise ◽

Validation Data ◽

Data Set ◽

Different Types ◽

Civilian noise complaints and damage claims have created the need for stations to monitor the production of military impulse noise. However, these stations suffer from numerous false positive detections (due to wind noise) of impulse events and often miss many events of interest. There is also interest in identifying specific noise sources, such different types of ordinance or different types of aircraft. To improve the accuracy of military impulse noise monitoring and make and initial effort to specifically classify noise source, an algorithm based upon an artificial neural network with inputs of conventional and custom acoustic metrics was proposed. To train and evaluate the noise classifier approximately 1,000 waveforms were field collected (110 military aircraft noise, 330 military impulse noise, and 560 non-impulse noise). The final noise classifier used kurtosis and crest factor and the custom metrics spectral slope and weighted square error as inputs. The classifier was able to achieve 99.7% accuracy on the training data set and 99.4% accuracy on the validation data set.

Oversampling Method on Classifying Hypertension Using Naive Bayes, Decision Tree, and Artificial Neural Network

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v4i4.2015 ◽

2020 ◽

Vol 4 (4) ◽

pp. 635-641

Author(s):

Nurul Chamidah ◽

Mayanda Mega Santoni ◽

Nurhafifah Matondang

Keyword(s):

Neural Network ◽

Decision Tree ◽

Missing Values ◽

Naive Bayes ◽

Classification Performance ◽

Naïve Bayes ◽

Training Data ◽

Validation Data ◽

Oversampling is a technique to balance the number of data records for each class by generating data with a small number of records in a class, so that the amount is balanced with data with a class with a large number of records. Oversampling in this study is applied to hypertension dataset where hypertensive class has a small number of records when compared to the number of records for non-hypertensive classes. This study aims to evaluate the effect of oversampling on the classification of hypertension dataset consisting of hypertensive and non-hypertensive classes by utilizing the Naïve Bayes, Decision Tree, and Artificial Neural Network (ANN) as well as finding the best model of the three algorithms. Evaluation of the use of oversampling on hypertension dataset is done by processing the data by imputing missing values, oversampling, and transforming data into the same range, then using the Naïve Bayes, Decision Tree, and ANN to build classification models. By dividing 80% of data as training data to build models and 20% as validation data for testing models, we had an increase in classification performance in the form of accuracy, precision, and recall of the oversampled data when compared without oversampling. The best performance in this study resulted in the highest accuracy using ANN with 0.91, precision 0.86 and recall 0.99.

Artificial intelligence accurately identifies total hip arthroplasty implants: a tool for revision surgery

Hip International ◽

10.1177/1120700020987526 ◽

2021 ◽

pp. 112070002098752

Author(s):

Michael Murphy ◽

Cameron Killen ◽

Robert Burnham ◽

Fahad Sarvari ◽

Karen Wu ◽

...

Keyword(s):

Neural Network ◽

Neural Networks ◽

Learning Algorithm ◽

Revision Arthroplasty ◽

Femoral Stem ◽

Training Data ◽

Consecutive Series ◽

Validation Data ◽

Total Hip ◽

Background: A critical part in preoperative planning for revision arthroplasty surgery involves the identification of the failed implant. Using a predictive artificial neural network (ANN) model, the objectives of this study were: (1) to develop a machine-learning algorithm using operative big data to identify an implant from a radiograph; and (2) to compare algorithms that optimise accuracy in a timely fashion. Methods: Using 2116 postoperative anteroposterior (AP) hip radiographs of total hip arthroplasties from 2002 to 2019, 10 artificial neural networks were modeled and trained to classify the radiograph according to the femoral stem implanted. Stem brand and model was confirmed with 1594 operative reports. Model performance was determined by classification accuracy toward a random 706 AP hip radiographs, and again on a consecutive series of 324 radiographs prospectively collected over 2019. Results: The Dense-Net 201 architecture outperformed all others with 100.00% accuracy in training data, 95.15% accuracy on validation data, and 91.16% accuracy in the unique prospective series of patients. This outperformed all other models on the validation ( p < 0.0001) and novel series ( p < 0.0001). The convolutional neural network also displayed the probability (confidence) of the femoral stem classification for any input radiograph. This neural network averaged a runtime of 0.96 (SD 0.02) seconds for an iPhone 6 to calculate from a given radiograph when converted to an application. Conclusions: Neural networks offer a useful adjunct to the surgeon in preoperative identification of the prior implant.

Artificial neural network, predictor variables and sensitivity threshold for DNA methylation-based age prediction using blood samples

Scientific Reports ◽

10.1038/s41598-021-81556-2 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Zhonghui Thong ◽

Jolena Ying Ying Tan ◽

Eileen Shuzhen Loo ◽

Yu Wei Phua ◽

Xavier Liang Shun Chan ◽

...

Keyword(s):

Neural Network ◽

Regression Model ◽

Sensitivity Threshold ◽

Ann Model ◽

Blood Samples ◽

Ann Models ◽

Artificial Neural ◽

The Impact ◽

Age Prediction

AbstractRegression models are often used to predict age of an individual based on methylation patterns. Artificial neural network (ANN) however was recently shown to be more accurate for age prediction. Additionally, the impact of ethnicity and sex on our previous regression model have not been studied. Furthermore, there is currently no age prediction study investigating the lower limit of input DNA at the bisulfite treatment stage prior to pyrosequencing. Herein, we evaluated both regression and ANN models, and the impact of ethnicity and sex on age prediction for 333 local blood samples using three loci on the pyrosequencing platform. Subsequently, we trained a one locus-based ANN model to reduce the amount of DNA used. We demonstrated that the ANN model has a higher accuracy of age prediction than the regression model. Additionally, we showed that ethnicity did not affect age prediction among local Chinese, Malays and Indians. Although the predicted age of males were marginally overestimated, sex did not impact the accuracy of age prediction. Lastly, we present a one locus, dual CpG model using 25 ng of input DNA that is sufficient for forensic age prediction. In conclusion, the two ANN models validated would be useful for age prediction to provide forensic intelligence leads.

Fully automated contrast and non-contrast cardiac view detection in echocardiography a multi-centre, multi-vendor study

European Heart Journal ◽

10.1093/ehjci/ehaa946.0078 ◽

2020 ◽

Vol 41 (Supplement_2) ◽

Author(s):

S Gao ◽

D Stojanovski ◽

A Parker ◽

P Marques ◽

S Heitner ◽

...

Keyword(s):

Neural Network ◽

Training Data ◽

Classification Model ◽

Validation Dataset ◽

Funding Source ◽

Private Company ◽

Validation Data ◽

Independent Test ◽

Model Training ◽

Confusion Matrices

Abstract Background Correctly identifying views acquired in a 2D echocardiographic examination is paramount to post-processing and quantification steps often performed as part of most clinical workflows. In many exams, particularly in stress echocardiography, microbubble contrast is used which greatly affects the appearance of the cardiac views. Here we present a bespoke, fully automated convolutional neural network (CNN) which identifies apical 2, 3, and 4 chamber, and short axis (SAX) views acquired with and without contrast. The CNN was tested in a completely independent, external dataset with the data acquired in a different country than that used to train the neural network. Methods Training data comprised of 2D echocardiograms was taken from 1014 subjects from a prospective multisite, multi-vendor, UK trial with the number of frames in each view greater than 17,500. Prior to view classification model training, images were processed using standard techniques to ensure homogenous and normalised image inputs to the training pipeline. A bespoke CNN was built using the minimum number of convolutional layers required with batch normalisation, and including dropout for reducing overfitting. Before processing, the data was split into 90% for model training (211,958 frames), and 10% used as a validation dataset (23,946 frames). Image frames from different subjects were separated out entirely amongst the training and validation datasets. Further, a separate trial dataset of 240 studies acquired in the USA was used as an independent test dataset (39,401 frames). Results Figure 1 shows the confusion matrices for both validation data (left) and independent test data (right), with an overall accuracy of 96% and 95% for the validation and test datasets respectively. The accuracy for the non-contrast cardiac views of >99% exceeds that seen in other works. The combined datasets included images acquired across ultrasound manufacturers and models from 12 clinical sites. Conclusion We have developed a CNN capable of automatically accurately identifying all relevant cardiac views used in “real world” echo exams, including views acquired with contrast. Use of the CNN in a routine clinical workflow could improve efficiency of quantification steps performed after image acquisition. This was tested on an independent dataset acquired in a different country to that used to train the model and was found to perform similarly thus indicating the generalisability of the model. Figure 1. Confusion matrices Funding Acknowledgement Type of funding source: Private company. Main funding source(s): Ultromics Ltd.

Improved estimation of energy expenditure by artificial neural network modeling

Applied Physiology Nutrition and Metabolism ◽

10.1139/h08-117 ◽

2008 ◽

Vol 33 (6) ◽

pp. 1213-1222 ◽

Cited By ~ 4

Author(s):

Dean Charles Hay ◽

Akinobu Wakayama ◽

Ken Sakamura ◽

Senshi Fukashiro

Keyword(s):

Neural Network ◽

Heart Rate ◽

Energy Expenditure ◽

Network Modeling ◽

Neural Network Modeling ◽

Validation Data ◽

Artificial Neural Network Modeling ◽

Feed Forward Back Propagation ◽

Estimation of energy expenditure in daily living conditions can be a tool for clinical assessment of health status, as well as a self-measure of lifestyle and general activity levels. Criterion measures are either prohibitively expensive or restricted to laboratory settings. Portable devices (heart rate monitors, pedometers) have gained recent popularity, but accuracy of the prediction equations remains questionable. This study applied an artificial neural network modeling approach to the problem of estimating energy expenditure with different dynamic inputs (accelerometry, heart rate above resting (HRar), and electromyography (EMG)). Nine feed-forward back-propagation models were trained, with the goal of minimizing the mean squared error (MSE) of the training datasets. Model 1 (accelerometry only) and model 2 (HRar only) performed poorly and had significantly greater MSE than all other models (p < 0.001). Model 3 (combined accelerometry and HRar) had overall performance similar to EMG models. Validation of all models was performed by simulating untrained datasets. MSE of all models increased when tested with validation data. While models 1 and 2 again performed poorly, model 3 MSE was lower than all but 2 EMG models. Squared correlation coefficients of measured and predicted energy expenditure for models 3 to 9 ranged from 0.745 to 0.817. Analysis of mean error within specific movement categories indicates that EMG models may be better at predicting higher-intensity energy expenditure, but combined accelerometry and HRar provides an economical solution, with sufficient accuracy.

Identification Of Number Using Artificial Neural Network Backpropagation

MATEC Web of Conferences ◽

10.1051/matecconf/201821501011 ◽

2018 ◽

Vol 215 ◽

pp. 01011

Author(s):

Sitti Amalia

Keyword(s):

Neural Network ◽

Training Data ◽

Simulation Test ◽

Backpropagation Algorithm ◽

Network Parameter ◽

Artificial Intelligent ◽

Design And Implementation ◽

Network Training ◽

This research proposed to design and implementation system of voice pattern recognition in the form of numbers with offline pronunciation. Artificial intelligent with backpropagation algorithm used on the simulation test. The test has been done to 100 voice files which got from 10 person voices for 10 different numbers. The words are consisting of number 0 to 9. The trial has been done with artificial neural network parameters such as tolerance value and the sum of a neuron. The best result is shown at tolerance value varied and a sum of the neuron is fixed. The percentage of this network training with optimal architecture and network parameter for each training data and new data are 82,2% and 53,3%. Therefore if tolerance value is fixed and a sum of neuron varied gave 82,2% for training data and 54,4% for new data

Field Measurements of Surface and Near-Surface Turbulence in the Presence of Breaking Waves

Journal of Physical Oceanography ◽

10.1175/jpo-d-14-0133.1 ◽

2015 ◽

Vol 45 (4) ◽

pp. 943-965 ◽

Cited By ~ 62

Author(s):

Peter Sutherland ◽

W. Kendall Melville

Keyword(s):

Field Experiments ◽

North Pacific Ocean ◽

Large Fraction ◽

Field Measurements ◽

Breaking Waves ◽

Sea Surface ◽

Near Surface ◽

Wave Energy Dissipation ◽

Eddy Simulation ◽

The North

AbstractWave breaking removes energy from the surface wave field and injects it into the upper ocean, where it is dissipated by viscosity. This paper presents an investigation of turbulent kinetic energy (TKE) dissipation beneath breaking waves. Wind, wave, and turbulence data were collected in the North Pacific Ocean aboard R/P FLIP, during the ONR-sponsored High Resolution Air-Sea Interaction (HiRes) and Radiance in a Dynamic Ocean (RaDyO) experiments. A new method for measuring TKE dissipation at the sea surface was combined with subsurface measurements to allow estimation of TKE dissipation over the entire wave-affected surface layer. Near the surface, dissipation decayed with depth as z−1, and below approximately one significant wave height, it decayed more quickly, approaching z−2. High levels of TKE dissipation very near the sea surface were consistent with the large fraction of wave energy dissipation attributed to non-air-entraining microbreakers. Comparison of measured profiles with large-eddy simulation results in the literature suggests that dissipation is concentrated closer to the surface than previously expected, largely because the simulations did not resolve microbreaking. Total integrated dissipation in the water column agreed well with dissipation by breaking for young waves, (where cm is the mean wave frequency and is the atmospheric friction velocity), implying that breaking was the dominant source of turbulence in those conditions. The results of these extensive measurements of near-surface dissipation over three field experiments are discussed in the context of observations and ocean boundary layer modeling efforts by other groups.

DANNP: an efficient artificial neural network pruning tool

PeerJ Computer Science ◽

10.7717/peerj-cs.137 ◽

2017 ◽

Vol 3 ◽

pp. e137 ◽

Cited By ~ 7

Author(s):

Mona Alshahrani ◽

Othman Soufan ◽

Arturo Magana-Mora ◽

Vladimir B. Bajic

Keyword(s):

Neural Network ◽

State Of The Art ◽

Model Performance ◽

Training Data ◽

Classification Problems ◽

Link Type ◽

On Line ◽

Pruning Algorithms ◽

Artificial Neural ◽

The Impact

Background Artificial neural networks (ANNs) are a robust class of machine learning models and are a frequent choice for solving classification problems. However, determining the structure of the ANNs is not trivial as a large number of weights (connection links) may lead to overfitting the training data. Although several ANN pruning algorithms have been proposed for the simplification of ANNs, these algorithms are not able to efficiently cope with intricate ANN structures required for complex classification problems. Methods We developed DANNP, a web-based tool, that implements parallelized versions of several ANN pruning algorithms. The DANNP tool uses a modified version of the Fast Compressed Neural Network software implemented in C++ to considerably enhance the running time of the ANN pruning algorithms we implemented. In addition to the performance evaluation of the pruned ANNs, we systematically compared the set of features that remained in the pruned ANN with those obtained by different state-of-the-art feature selection (FS) methods. Results Although the ANN pruning algorithms are not entirely parallelizable, DANNP was able to speed up the ANN pruning up to eight times on a 32-core machine, compared to the serial implementations. To assess the impact of the ANN pruning by DANNP tool, we used 16 datasets from different domains. In eight out of the 16 datasets, DANNP significantly reduced the number of weights by 70%–99%, while maintaining a competitive or better model performance compared to the unpruned ANN. Finally, we used a naïve Bayes classifier derived with the features selected as a byproduct of the ANN pruning and demonstrated that its accuracy is comparable to those obtained by the classifiers trained with the features selected by several state-of-the-art FS methods. The FS ranking methodology proposed in this study allows the users to identify the most discriminant features of the problem at hand. To the best of our knowledge, DANNP (publicly available at www.cbrc.kaust.edu.sa/dannp) is the only available and on-line accessible tool that provides multiple parallelized ANN pruning options. Datasets and DANNP code can be obtained at www.cbrc.kaust.edu.sa/dannp/data.php and https://doi.org/10.5281/zenodo.1001086.