scholarly journals An Artificial Neural Network Prediction Model for Posttraumatic Epilepsy: Retrospective Cohort Study (Preprint)

2020 ◽  
Author(s):  
Xueping Wang ◽  
Jie Zhong ◽  
Ting Lei ◽  
Deng Chen ◽  
Haijiao Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Cross Validation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Training Cohort ◽  
Posttraumatic Epilepsy ◽  
Artificial Neural ◽  
Sensitivity Specificity

BACKGROUND Posttraumatic epilepsy (PTE) is a common sequela after traumatic brain injury (TBI), and identifying high-risk patients with PTE is necessary for their better treatment. Although artificial neural network (ANN) prediction models have been reported and are superior to traditional models, the ANN prediction model for PTE is lacking. OBJECTIVE We aim to train and validate an ANN model to anticipate the risks of PTE. METHODS The training cohort was TBI patients registered at West China Hospital. We used a 5-fold cross-validation approach to train and test the ANN model to avoid overfitting; 21 independent variables were used as input neurons in the ANN models, using a back-propagation algorithm to minimize the loss function. Finally, we obtained sensitivity, specificity, and accuracy of each ANN model from the 5 rounds of cross-validation and compared the accuracy with a nomogram prediction model built in our previous work based on the same population. In addition, we evaluated the performance of the model using patients registered at Chengdu Shang Jin Nan Fu Hospital (testing cohort 1) and Sichuan Provincial People’s Hospital (testing cohort 2) between January 1, 2013, and March 1, 2015. RESULTS For the training cohort, we enrolled 1301 TBI patients from January 1, 2011, to December 31, 2017. The prevalence of PTE was 12.8% (166/1301, 95% CI 10.9%-14.6%). Of the TBI patients registered in testing cohort 1, PTE prevalence was 10.5% (44/421, 95% CI 7.5%-13.4%). Of the TBI patients registered in testing cohort 2, PTE prevalence was 6.1% (25/413, 95% CI 3.7%-8.4%). The results of the ANN model show that, the area under the receiver operating characteristic curve in the training cohort was 0.907 (95% CI 0.889-0.924), testing cohort 1 was 0.867 (95% CI 0.842-0.893), and testing cohort 2 was 0.859 (95% CI 0.826-0.890). Second, the average accuracy of the training cohort was 0.557 (95% CI 0.510-0.620), with 0.470 (95% CI 0.414-0.526) in testing cohort 1 and 0.344 (95% CI 0.287-0.401) in testing cohort 2. In addition, sensitivity, specificity, positive predictive values and negative predictors in the training cohort (testing cohort 1 and testing cohort 2) were 0.80 (0.83 and 0.80), 0.86 (0.80 and 0.84), 91% (85% and 78%), and 86% (80% and 83%), respectively. When calibrating this ANN model, Brier scored 0.121 in testing cohort 1 and 0.127 in testing cohort 2. Compared with the nomogram model, the ANN prediction model had a higher accuracy (<i>P</i>=.01). CONCLUSIONS This study shows that the ANN model can predict the risk of PTE and is superior to the risk estimated based on traditional statistical methods. However, the calibration of the model is a bit poor, and we need to calibrate it on a large sample size set and further improve the model.

scholarly journals An Artificial Neural Network Prediction Model for Posttraumatic Epilepsy: Retrospective Cohort Study

10.2196/25090 ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. e25090
Author(s):  
Xueping Wang ◽  
Jie Zhong ◽  
Ting Lei ◽  
Deng Chen ◽  
Haijiao Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Cross Validation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Training Cohort ◽  
Posttraumatic Epilepsy ◽  
Artificial Neural ◽  
Sensitivity Specificity

Background Posttraumatic epilepsy (PTE) is a common sequela after traumatic brain injury (TBI), and identifying high-risk patients with PTE is necessary for their better treatment. Although artificial neural network (ANN) prediction models have been reported and are superior to traditional models, the ANN prediction model for PTE is lacking. Objective We aim to train and validate an ANN model to anticipate the risks of PTE. Methods The training cohort was TBI patients registered at West China Hospital. We used a 5-fold cross-validation approach to train and test the ANN model to avoid overfitting; 21 independent variables were used as input neurons in the ANN models, using a back-propagation algorithm to minimize the loss function. Finally, we obtained sensitivity, specificity, and accuracy of each ANN model from the 5 rounds of cross-validation and compared the accuracy with a nomogram prediction model built in our previous work based on the same population. In addition, we evaluated the performance of the model using patients registered at Chengdu Shang Jin Nan Fu Hospital (testing cohort 1) and Sichuan Provincial People’s Hospital (testing cohort 2) between January 1, 2013, and March 1, 2015. Results For the training cohort, we enrolled 1301 TBI patients from January 1, 2011, to December 31, 2017. The prevalence of PTE was 12.8% (166/1301, 95% CI 10.9%-14.6%). Of the TBI patients registered in testing cohort 1, PTE prevalence was 10.5% (44/421, 95% CI 7.5%-13.4%). Of the TBI patients registered in testing cohort 2, PTE prevalence was 6.1% (25/413, 95% CI 3.7%-8.4%). The results of the ANN model show that, the area under the receiver operating characteristic curve in the training cohort was 0.907 (95% CI 0.889-0.924), testing cohort 1 was 0.867 (95% CI 0.842-0.893), and testing cohort 2 was 0.859 (95% CI 0.826-0.890). Second, the average accuracy of the training cohort was 0.557 (95% CI 0.510-0.620), with 0.470 (95% CI 0.414-0.526) in testing cohort 1 and 0.344 (95% CI 0.287-0.401) in testing cohort 2. In addition, sensitivity, specificity, positive predictive values and negative predictors in the training cohort (testing cohort 1 and testing cohort 2) were 0.80 (0.83 and 0.80), 0.86 (0.80 and 0.84), 91% (85% and 78%), and 86% (80% and 83%), respectively. When calibrating this ANN model, Brier scored 0.121 in testing cohort 1 and 0.127 in testing cohort 2. Compared with the nomogram model, the ANN prediction model had a higher accuracy (P=.01). Conclusions This study shows that the ANN model can predict the risk of PTE and is superior to the risk estimated based on traditional statistical methods. However, the calibration of the model is a bit poor, and we need to calibrate it on a large sample size set and further improve the model.

A Nonlinear Autoregressive With Exogenous Inputs Artificial Neural Network Model for Building Thermal Load Prediction

2019 ◽  
Vol 142 (5) ◽  
Author(s):  
Byeongho Yu ◽  
Dongsu Kim ◽  
Heejin Cho ◽  
Pedro Mago
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Nonlinear System ◽  
Prediction Model ◽  
Thermal Load ◽  
Ann Model ◽  
Load Prediction ◽  
Artificial Neural ◽  
Nonlinear Autoregressive

Abstract Thermal load prediction is a key part of energy system management and control in buildings, and its accuracy plays a critical role to improve building energy performance and efficiency. Regarding thermal load prediction, various types of prediction model have been considered and studied, such as physics-based, statistical, and machine learning models. Physical models can be accurate but require extended lead time for model development. Statistical models are relatively simple to develop and require less computation time, but they may not provide accurate results for complex energy systems with intricate nonlinear dynamic behaviors. This study proposes an artificial neural network (ANN) model, one of the prevalent machine learning methods to predict building thermal load, combining with the concept of nonlinear autoregressive with exogenous inputs (NARX). NARX-ANN prediction model is distinguished from typical ANN models because the NARX concept can address nonlinear system behaviors effectively based on its recurrent architectures and time indexing features. To examine the suitability and validity of NARX-ANN model for building thermal load prediction, a case study is carried out using the field data of an academic campus building at Mississippi State University (MSU). Results show that the proposed NARX-ANN model can provide an accurate and robust prediction performance and effectively address nonlinear system behaviors in the prediction.

Surface Roughness Prediction in Turning of Free Machining Steel 1215 by Artificial Neural Network

2011 ◽  
Vol 188 ◽  
pp. 535-541
Author(s):  
Xiao Jiang Cai ◽  
Z.Q. Liu ◽  
Q.C. Wang ◽  
Shu Han ◽  
Qing Long An ◽  
...  
Keyword(s):  
Neural Network ◽  
Surface Roughness ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Mean Squared Error ◽  
Cutting Speed ◽  
Depth Of Cut ◽  
Ann Model ◽  
Roughness Prediction ◽  
Artificial Neural

Surface roughness is a significant aspect of the surface integrity concept. It is efficient to predict the surface roughness in advance by a prediction model. In this study, artificial neural network is used to model the surface roughness in turning of free machining steel 1215. The inputs considered in the prediction ANN model were cutting speed, feed rate and depth of cut, and the output was Ra. Several feed-forward neural networks with different architectures were compared in terms of prediction accuracy, and then the best prediction model, a 3-4-1-1 ANN was capable of predicting Ra with a mean squared error 5.46%, was presented.

scholarly journals Modeling Baseline Energy Using Artificial Neural Network – A Small Dataset Approach

2018 ◽  
Vol 12 (2) ◽  
pp. 662
Author(s):  
Wan Nazirah Wan Md Adnan ◽  
Nofri Yenita Dahlan ◽  
Ismail Musirin
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Cross Validation ◽  
Model Development ◽  
Energy Model ◽  
Ann Model ◽  
Data Set ◽  
Validation Technique ◽  
Artificial Neural ◽  
Small Dataset

In this work, baseline energy model development using Artificial Neural Network (ANN) with resampling techniques; Cross Validation (CV) and Bootstrap (BS) are presented. Resampling techniques are used to examine the ability of the ANN model to deal with a small dataset. Working days, class days and Cooling Degree Days (CDD) are used as ANN input meanwhile the ANN output is monthly electricity consumption. The coefficient of correlation (R) is used as performance function to evaluate the model accuracy. For this analysis, R is calculated for the entire data set (R_all) and separately for training set (R_train), validation set (R_valid) dan testing set (R_test). The closer R to 1, the higher similarities between targeted and predicted output. The total of two different models with several number of neurons are developed and compared. It can be concluded that all models are capable to train the network. Artificial Neural Network with Bootstrap Cross Validation technique (ANN-BSCV) outperforms Artificial Neural Network with Cross Validation technique (ANN-CV).  The 3-6-1 ANN-BSCV, with R_train = 0.95668, R_valid = 0.97553, R_test = 0.85726 and R_all = 0.94079 is selected as the baseline energy model to predict energy consumption for Option C IPMVP.

Simultaneous Quantitative Analysis of Clorsulon and Ivermectin in a Veterinary Formulation by Artificial Neural Network

2008 ◽  
Vol 59 (10) ◽  
Author(s):  
Gozde Pektas ◽  
Erdal Dinc ◽  
Dumitru Baleanu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Transfer Function ◽  
Back Propagation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer

Simultaneaous spectrophotometric determination of clorsulon (CLO) and invermectin (IVE) in commercial veterinary formulation was performed by using the artificial neural network (ANN) based on the back propagation algorithm. In order to find the optimal ANN model various topogical networks were tested by using different hidden layers. A logsig input layer, a hidden layer of neurons using the logsig transfer function and an output layer of two neurons with purelin transfer function was found suitable for basic configuration for ANN model. A calibration set consisting of CLO and IVE in calibration set was prepared in the concentration range of 1-23 �g/mL and 1-14 �g/mL, repectively. This calibration set contains 36 different synthetic mixtures. A prediction set was prepared in order to evaluate the recovery of the investigated approach ANN chemometric calibration was applied to the simultaneous analysis of CLO and IVE in compounds in a commercial veterinary formulation. The experimental results indicate that the proposed method is appropriate for the routine quality control of the above mentioned active compounds.

scholarly journals Prediction of Drape Coefficient by Artificial Neural Network

2015 ◽  
Vol 15 (4) ◽  
pp. 266-274 ◽  
Author(s):  
Adel Ghith ◽  
Thouraya Hamdi ◽  
Faten Fayala
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Propagation Algorithm ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Hidden Layer ◽  
Different Diameters

Abstract An artificial neural network (ANN) model was developed to predict the drape coefficient (DC). Hanging weight, Sample diameter and the bending rigidities in warp, weft and skew directions are selected as inputs of the ANN model. The ANN developed is a multilayer perceptron using a back-propagation algorithm with one hidden layer. The drape coefficient is measured by a Cusick drape meter. Bending rigidities in different directions were calculated according to the Cantilever method. The DC obtained results show a good correlation between the experimental and the estimated ANN values. The results prove a significant relationship between the ANN inputs and the drape coefficient. The algorithm developed can easily predict the drape coefficient of fabrics at different diameters.

scholarly journals Prediction of Neutron Yield of IR-IECF Facility in High Voltages Using Artificial Neural Network

2014 ◽  
Vol 2014 ◽  
pp. 1-7 ◽  
Author(s):  
A. Sadighzadeh ◽  
A. Salehizadeh ◽  
M. Mohammadzadeh ◽  
F. Shama ◽  
S. Setayeshi ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Discharge Current ◽  
Back Propagation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Cathode Voltage ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Maximum Voltage

Artificial neural network (ANN) is applied to predict the number of produced neutrons from IR-IECF device in wide discharge current and voltage ranges. Experimentally, discharge current from 20 to 100 mA had been tuned by deuterium gas pressure and cathode voltage had been changed from −20 to −82 kV (maximum voltage of the used supply). The maximum neutron production rate (NPR) of 1.46 × 107 n/s had occurred when the voltage was −82 kV and the discharge current was 48 mA. The back-propagation algorithm is used for training of the proposed multilayer perceptron (MLP) neural network structure. The obtained results show that the proposed ANN model has achieved good agreement with the experimental data. Results show that NPR of 1.855 × 108 n/s can be achieved in voltage and current of 125 kV and 45 mA, respectively. This prediction shows 52% increment in maximum voltage of power supply. Also, the optimum discharge current can increase 1270% NPR.

scholarly journals A hybrid data envelopment analysis—artificial neural network prediction model for COVID-19 severity in transplant recipients

2021 ◽  
Author(s):  
Ignacio Revuelta ◽  
Francisco J. Santos-Arteaga ◽  
Enrique Montagud-Marrahi ◽  
Pedro Ventura-Aguiar ◽  
Debora Di Caprio ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Data Envelopment Analysis ◽  
Hospital Admission ◽  
Prediction Model ◽  
Data Envelopment ◽  
Transplant Recipients ◽  
Ann Model ◽  
Hybrid Data ◽  
Artificial Neural

AbstractIn an overwhelming demand scenario, such as the SARS-CoV-2 pandemic, pressure over health systems may outburst their predicted capacity to deal with such extreme situations. Therefore, in order to successfully face a health emergency, scientific evidence and validated models are needed to provide real-time information that could be applied by any health center, especially for high-risk populations, such as transplant recipients. We have developed a hybrid prediction model whose accuracy relative to several alternative configurations has been validated through a battery of clustering techniques. Using hospital admission data from a cohort of hospitalized transplant patients, our hybrid Data Envelopment Analysis (DEA)—Artificial Neural Network (ANN) model extrapolates the progression towards severe COVID-19 disease with an accuracy of 96.3%, outperforming any competing model, such as logistic regression (65.5%) and random forest (44.8%). In this regard, DEA-ANN allows us to categorize the evolution of patients through the values of the analyses performed at hospital admission. Our prediction model may help guiding COVID-19 management through the identification of key predictors that permit a sustainable management of resources in a patient-centered model.

scholarly journals Prediction of the thermo-physical properties of deep-fat frying plantain chips (ipekere) using artificial neural network

2021 ◽  
Vol 25 (2) ◽  
pp. 253-260
Author(s):  
James Abiodun Adeyanju ◽  
John Oluranti Olajide ◽  
Emmanuel Olusola Oke ◽  
Jelili Babatunde Hussein ◽  
Chiamaka Jane Ude
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Physical Properties ◽  
Back Propagation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Deep Fat Frying ◽  
Feed Forward Back Propagation ◽  
Artificial Neural ◽  
Thermo Physical Properties

Abstract This study uses artificial neural network (ANN) to predict the thermo-physical properties of deep-fat frying plantain chips (ipekere). The frying was conducted with temperature and time ranged of 150 to 190 °C and 2 to 4 minutes using factorial design. The result revealed that specific heat was most influenced by temperature and time with the value 2.002 kJ/kg°C at 150 °C and 2.5 minutes. The density ranged from 0.997 – 1.005 kg/m3 while thermal diffusivity and conductivity were least affected with 0.192 x 10−6 m2/s and 0.332 W/m°C respectively at 190 °C and 4 minutes. The ANN architecture was developed using Levenberg–Marquardt (TRAINLM) and Feed-forward back propagation algorithm. The experimentation based on the ANN model produced a desirable prediction of the thermo-physical properties through the application of diverse amount of neutrons in the hidden layer. The predictive experimentation of the computational model with R2 ≥ 0.7901 and MSE ≤ 0.1125 does not only show the validity in anticipating the thermo-physical properties, it also indicates the capability of the model to identify a relevant association between frying time, frying temperatures and thermo-physical properties. Hence, to avoid a time consuming and expensive experimental tests, the developed model in this study is efficient in prediction of the thermo-physical properties of deep-fat frying plantain chips.

scholarly journals APPLICABILITY OF ARTIFICIAL NEURAL NETWORK MODEL FOR SIMULATION OF MONTHLY RUNOFF IN COMPARISON WITH SOM OTHER TRADITIONAL MODELS

2009 ◽  
Vol 12 (4) ◽  
pp. 94-106 ◽  
Author(s):  
Duc Van Le
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Back Propagation ◽  
Research Trend ◽  
Rainfall Runoff ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Runoff Forecasting ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Artificial Neural Network (ANN) model along with Back Propagation Algorithm (BPA) has been applied in many fields, especially in hydrology and water resources management to simulate or forecast rainfall runoff process, discharge and water level - time series, and other hydrological variables. Several researches have recently been focusing to compare the applicability of ANN model with other theory-driven and data-driven approaches. The comparison of ANN with M5 model trees for rainfall-runoff forecasting, with ARMAX models for deriving flow series, with AR models and regression models for forecasting and estimating daily river flows have been carried out. The better results that were implemented by ANN model have been concluded. So, this research trend is continued for the comparison of ANN model with Tank, Harmonic, Thomas and Fiering models in simulation of the monthly runoffs at Dong Nai river basin, Viet Nam. The results proved ANN being the best choice among these models, if suitable and enough data sources were available.

Sign in / Sign up

Export Citation Format

Share Document