Application of metaheuristic based artificial neural network and multilinear regression for the prediction of higher heating values of fuels

2020 ◽  
pp. 1-22 ◽  
Author(s):  
Adeyemi Emman Aladejare ◽  
Moshood Onifade ◽  
Abiodun Ismail Lawal
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Multilinear Regression ◽  
Artificial Neural

scholarly journals Application of Gene Expression Programming, Artificial Neural Network and Multilinear Regression in Predicting Hydrochar Physicochemical Properties

2020 ◽  
Author(s):  
Jibril Abdulsalam ◽  
Abiodun Ismail Lawal ◽  
Ramadimetja Lizah Setsepu ◽  
Moshood Onifade ◽  
Samson Bada
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Artificial Neural Network ◽  
Performance Metrics ◽  
Gene Expression Programming ◽  
Mean Bias Error ◽  
Energy Yield ◽  
Multilinear Regression ◽  
Soft Computing Techniques ◽  
Artificial Neural

Abstract Globally, the provision of energy is becoming an absolute necessity. Biomass resources are abundant and have been described as a potential alternative source of energy. However, it is important to assess the fuel characteristics of the various available biomass sources. Soft computing techniques are presented in this study to predict the mass yield (MY), energy yield (EY), and higher heating value (HHV) of hydrothermally carbonized biomass by using Gene Expression Programming (GEP), multiple-input single output-artificial neural network (MISO-ANN), and Multilinear regression (MLR). The three techniques were compared using statistical performance metrics. The coefficient of determination (R2), mean absolute error (MAE), and mean bias error (MBE) were used to evaluate the performance of the models. The MISO-ANN with 5-10-10-1 and 5-15-15-1 network architectures provided the most satisfactory performance of the three proposed models (R2 = 0.976, 0.955, 0.996; MAE = 2.24, 2.11, 0.93; MBE = 0.16, 0.37, 0.12) for MY, EY and HHV respectively. The GEP technique’s ability to predict hydrochar properties based on the input parameters was found to be satisfactory, while MLR provided an unsatisfactory predictive model. Sensitivity analysis was conducted, and the analysis revealed that volatile matter (VM) and temperature (Temp) have more influence on the MY, EY, and HHV.

Soft Computing Tools to Predict Progression of Percent Embedment of Aggregates in Chip Seals

2018 ◽  
Vol 2672 (12) ◽  
pp. 32-39 ◽  
Author(s):  
Aksel Seitllari ◽  
M. Emin Kutay
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soft Computing ◽  
Embedment Depth ◽  
Test Results ◽  
Multilinear Regression ◽  
Neuro Fuzzy ◽  
Chip Seal ◽  
Regression Techniques ◽  
Artificial Neural

In this study, soft computing and multilinear regression techniques were employed to develop models for prediction of progression of chip seal percent embedment depth ( Pe). The model uses inputs such as cumulative equivalent traffic volume, Vialit test results, dust content of aggregates, and initial embedment depth. Multilinear regression, adaptive neuro-fuzzy system, and artificial neural network techniques were used to estimate the Pe. The contribution of the variables affecting Pe was evaluated through a sensitivity analysis. The results indicate that while most of the proposed models were able to predict the Pe reasonably, the artificial neural network model performed the best.

scholarly journals Modeling the Essential Oil and Trans-Anethole Yield of Fennel (Foeniculum vulgare Mill. var. vulgare) by Application Artificial Neural Network and Multiple Linear Regression Methods

Agriculture ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1191
Author(s):  
Mohsen Sabzi-Nojadeh ◽  
Gniewko Niedbała ◽  
Mehdi Younessi-Hamzekhanlu ◽  
Saeid Aharizad ◽  
Mohammad Esmaeilpour ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Essential Oil ◽  
Direct Selection ◽  
Multilinear Regression ◽  
Foeniculum Vulgare ◽  
Breeding Programs ◽  
Artificial Neural ◽  
Input Variables ◽  
Number Of Seeds

Foeniculum vulgare Mill. (commonly known as fennel) is used in the pharmaceutical, cosmetic, and food industries. Fennel widely used as a digestive, carminative, galactagogue and diuretic and in treating gastrointestinal and respiratory disorders. Improving low heritability traits such as essential oil yield (EOY%) and trans-anethole yield (TAY%) of fennel by direct selection does not result in rapid gains of EOY% and TAY%. Identification of high-heritable traits and using efficient modeling methods can be a beneficial approach to overcome this limitation and help breeders select the most advantageous traits in medicinal plant breeding programs. The present study aims to compare the performance of the artificial neural network (ANN) and multilinear regression (MLR) to predict the EOY% and TAY% of fennel populations. Stepwise regression (SWR) was used to assess the effect of various input variables. Based on SWR, nine traits—number of days to 50% flowering (NDF50%), number of days to maturity (NDM), final plant height (FPH), number of internodes (NI), number of umbels (NU), seed yield per square meter (SY/m2), number of seeds per plant (NS/P), number of seeds per umbel (NS/U) and 1000-seed weight (TSW)—were chosen as input variables. The network with Sigmoid Axon transfer function and two hidden layers was selected as the final ANN model for the prediction of EOY%, and the TanhAxon function with one hidden layer was used for the prediction of TAY%. The results revealed that the ANN method could predict the EOY% and TAY% with more accuracy and efficiency (R2 of EOY% = 0.929, R2 of TAY% = 0.777, RMSE of EOY% = 0.544, RMSE of TAY% = 0.264, MAE of EOY% = 0.385 and MAE of TAY% = 0.352) compared with the MLR model (R2 of EOY% = 0.553, R2 of TAY% = 0.467, RMSE of EOY% = 0.819, RMSE of TAY% = 0.448, MAE of EOY% = 0.624 and MAE of TAY% = 0.452). Based on the sensitivity analysis, SY/m2, NDF50% and NS/P were the most important traits to predict EOY% as well as SY/m2, NS/U and NDM to predict of TAY%. The results demonstrate the potential of ANNs as a promising tool to predict the EOY% and TAY% of fennel, and they can be used in future fennel breeding programs.

scholarly journals Application of gene expression programming, artificial neural network and multilinear regression in predicting hydrochar physicochemical properties

2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Jibril Abdulsalam ◽  
Abiodun Ismail Lawal ◽  
Ramadimetja Lizah Setsepu ◽  
Moshood Onifade ◽  
Samson Bada
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Artificial Neural Network ◽  
Performance Metrics ◽  
Gene Expression Programming ◽  
Mean Bias Error ◽  
Energy Yield ◽  
Multilinear Regression ◽  
Soft Computing Techniques ◽  
Artificial Neural

AbstractGlobally, the provision of energy is becoming an absolute necessity. Biomass resources are abundant and have been described as a potential alternative source of energy. However, it is important to assess the fuel characteristics of the various available biomass sources. Soft computing techniques are presented in this study to predict the mass yield (MY), energy yield (EY), and higher heating value (HHV) of hydrothermally carbonized biomass using Gene Expression Programming (GEP), multiple-input single output-artificial neural network (MISO-ANN), and Multilinear regression (MLR). The three techniques were compared using statistical performance metrics. The coefficient of determination (R2), mean absolute error (MAE) and mean bias error (MBE) were used to evaluate the performance of the models. The MISO-ANN with 5-10 to 10-1 and 5-15-15-1 network architectures provided the most satisfactory performance of the three proposed models (R2 = 0.976, 0.955, 0.996; MAE = 2.24, 2.11, 0.93; MBE = 0.16, 0.37, 0.12) for MY, EY and HHV, respectively. The GEP technique’s ability to predict hydrochar properties based on the input parameters was found to be satisfactory, while MLR provided an unsatisfactory predictive model. Sensitivity analysis was conducted, and the analysis revealed that volatile matter (VM) and temperature (Temp) have more influence on the MY, EY, and HHV.

scholarly journals Kajian HKSA Antimalaria Senyawa Turunan Quinolon-4(1H)-imines Menggunakan Metode MLR-ANN

2019 ◽  
Vol 1 (1) ◽  
pp. 21-26
Author(s):  
Jafar La Kilo ◽  
Akram La Kilo
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Correlation Coefficient ◽  
Qsar Model ◽  
Ann Model ◽  
Multilinear Regression ◽  
Qsar Study ◽  
Structure Activity ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Quantitatif Structure-Activity Relationship (QSAR) study of 22 antimalarial compounds of Quinolon-4(1H)-imines derivatives has been done using multilinear regression (MLR) and artificial neural network (ANN) methods. The best QSAR model was obtained from ANN analysis indicated by its higher correlation coefficient (r2) compared to MLR method, i.e. 0.931 with most influential descriptors is qC1, qC5, qC11, qN14 and log P.Keywords: Quinolon-4(1H)-imines, Antimalarial, QSAR, MLR-ANNTelah dilakukan kajian analisis Hubungan Kuantitatif Struktur Aktivitas (HKSA) terhadap 22 senyawa antimalaria turunan Quinolon-4(1H)-imines menggunakan metode regresi multilinear (MLR) dan artificial neural network (ANN). Model HKSA terbaik diperoleh dari hasil analisis menggunakan metode ANN yang ditunjukkan oleh nilai koefisien korelasi (r2) paling tinggi dibandingkan dengan metode MLR yaitu sebesar 0,931 dengan deskriptor paling berpengaruh terhadap aktivitas antimalaria turunan Quinolon-4(1H)-imines, yaitu qC1, qC5, qC11, qN14 dan log P.Kata Kunci: Quinolon-4(1H)-imines, Antimalaria, HKSA, MLR-ANN

Sign in / Sign up

Export Citation Format

Share Document