Comparative Study of Artificial Neural Network (ANN) and Response Surface Methodology (RSM) on Optimization of Ethanol Production from Sawdust

This work focused on optimization of production of ethanol from saw dust using two empirical methods, the ANN and the RSM. It further investigated the modeling and optimization efficiencies of RSM and ANN in separate hydrolysis and fermentation of sawdust for ethanol production. Box - Behnken Design (BBD) was used to generate 17 individual experiments which were carried out, RSM and Genetic Algorithm (GA) of ANN which were used to optimize the production which was then compared. The optimum concentrations of ethanol yield predicted were 56.968 wt. % and 57. 387263 wt. % for RSM and ANN models respectively. R2 value obtained for ANN model was 0.9989 while R2 value of 0.9046 was obtained for RSM model. The Root Mean Square Error (RMSE) value for ANN was found to be 0.143 while the RMSE value for RSM was 2.17. It showed that ANN had relatively higher predictive model ability and thus shows to be a better optimization tool for the ethanol from saw dust compared to RSM which also a good modelling tool.

Download Full-text

Development of Neural Network Models for a Crude Oil Distillation Column

Jurnal Teknologi ◽

10.11113/jt.v38.509 ◽

2012 ◽

Author(s):

Khairiyah Mohd. Yusof ◽

Fakhri Karray ◽

Peter L. Douglas

Keyword(s):

Neural Network ◽

Steady State ◽

Crude Oil ◽

Distillation Column ◽

Network Models ◽

Ann Model ◽

Neural Network Models ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Crude Oil Distillation

This paper discusses the development of artificial neural network (ANN) models for a crude oil distillation column. Since the model is developed for real time optimisation (RTO) applications they are steady state, multivariable models. Training and testing data used to develop the models were generated from a reconciled steady-state model simulated in a process simulator. The radial basis function networks (RBFN), a type of feedforward ANN model, were able to model the crude tower very well, with the root mean square error for the prediction of each variable less than 1%. Grouping related output variables in a network model was found to give better predictions than lumping all the variables in a single model; this also allowed the overall complex, multivariable model to be simplified into smaller models that are more manageable. In addition, the RBFN models were also able to satisfactorily perform range and dimensional extrapolation, which is necessary for models that are used in RTO.

Download Full-text

Computational Performance Analysis of Neural Network and Regression Models in Forecasting the Societal Demand for Agricultural Food Harvests

10.4018/978-1-6684-2408-7.ch062 ◽

2022 ◽

pp. 1287-1300

Author(s):

Balaji Prabhu B. V. ◽

M. Dakshayini

Keyword(s):

Neural Network ◽

Crop Production ◽

Demand Forecasting ◽

Forecasting Model ◽

Ann Model ◽

Demand Prediction ◽

Computational Performance ◽

Societal Needs ◽

Ann Models ◽

Artificial Neural Network Ann

Demand forecasting plays an important role in the field of agriculture, where a farmer can plan for the crop production according to the demand in future and make a profitable crop business. There exist a various statistical and machine learning methods for forecasting the demand, selecting the best forecasting model is desirable. In this work, a multiple linear regression (MLR) and an artificial neural network (ANN) model have been implemented for forecasting an optimum societal demand for various food crops that are commonly used in day to day life. The models are implemented using R toll, linear model and neuralnet packages for training and optimization of the MLR and ANN models. Then, the results obtained by the ANN were compared with the results obtained with MLR models. The results obtained indicated that the designed models are useful, reliable, and quite an effective tool for optimizing the effects of demand prediction in controlling the supply of food harvests to match the societal needs satisfactorily.

Download Full-text

Computational Performance Analysis of Neural Network and Regression Models in Forecasting the Societal Demand for Agricultural Food Harvests

International Journal of Grid and High Performance Computing ◽

10.4018/ijghpc.2020100103 ◽

2020 ◽

Vol 12 (4) ◽

pp. 35-47

Author(s):

Balaji Prabhu B. V. ◽

M. Dakshayini

Keyword(s):

Neural Network ◽

Crop Production ◽

Demand Forecasting ◽

Ann Model ◽

Demand Prediction ◽

Computational Performance ◽

Societal Needs ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Agricultural Food

Download Full-text

Evaluation and ANN-Based Prediction on Functional Parameters of Surface Roughness in Precision Grinding of Cast Iron

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.1017.166 ◽

2014 ◽

Vol 1017 ◽

pp. 166-171

Author(s):

Bin Zhao ◽

Song Zhang ◽

Jian Feng Li

Keyword(s):

Surface Roughness ◽

Cast Iron ◽

Three Dimensional ◽

Ann Model ◽

Linear Speed ◽

Functional Parameters ◽

Grinding Parameters ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Dimensional Surface

Three-dimensional surface roughness parameters are widely applied to characterize frictional and lubricating properties, corrosion resistance, fatigue strength of surfaces. Among them, the functional parameters of surface roughness, such as Sbi, Sci, and Svi, are used to evaluate bearing and fluid retention properties of surfaces. In this study, the effects of grinding parameters, including wheel linear speed (Vs), workpiece linear speed (Vw), grinding depth (ap), longitudinal feed rate (fa), and dressing rate (F), on functional parameters were studied in grinding of cast iron. An artificial neural network (ANN) model was developed for predicting the functional parameters of three-dimensional surface roughness. The inputs of the ANN models were grinding parameters (Vs, Vw, ap, fa, F), and the output parameters of the models were functional parameters of surface roughness (Sbi, Sci, Svi). With small errors (e.g MSE = 0.09%, 0.61%, and 0.0014%. ), the ANN-based models are considered sufficiently accurate to predict functional parameters of surface roughness in grinding of cast iron.

Download Full-text

Neural Network MIMO Model for Production of Isopropyl Myristate in a Semibatch Reactive Distillation Column

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.284-287.403 ◽

2013 ◽

Vol 284-287 ◽

pp. 403-408

Author(s):

Nur Alwani Ali Bashah ◽

Mohd Roslee Othman ◽

Norashid Aziz

Keyword(s):

Neural Network ◽

Reactive Distillation ◽

Batch Reactor ◽

Isopropyl Myristate ◽

Ann Model ◽

Validation Data ◽

Testing Data ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Mimo Model

Batch reactive distillation is an integrated unit of batch reactor and distillation. It provides benefits of having higher conversion and yield by continuous removal of side product. The aim of this paper is to develop an artificial neural network (ANN) based model for production of isopropyl myristate in an industrial scaled semibatch reactive distillation. Two cases of the MIMO model were developed. Case 1 does not consider historical data as inputs while case 2 does. The trained ANN for both cases was validated with independent validation data and the best architecture was optimized. Case 1 resulted to 8 inputs, 14 hidden nodes and 2 outputs [8-14-2] ANN while Case 2 resulted to [12-13-2] ANN. The results show that both ANN models have ability to predict the unknown validation and testing data very well. However, the [8-14-2] ANN model produce higher accuracy than [12-13-2] ANN model with MSE of 0.00094 and 0.0013, respectively.

Download Full-text

Modeling of hourly river water temperatures using artificial neural networks

Water Quality Research Journal ◽

10.2166/wqrjc.2014.007 ◽

2014 ◽

Vol 49 (2) ◽

pp. 144-162 ◽

Cited By ~ 1

Author(s):

Cindie Hebert ◽

Daniel Caissie ◽

Mysore G. Satish ◽

Nassir El-Jabi

Keyword(s):

Water Temperature ◽

Coefficient Of Determination ◽

Ann Model ◽

Air Temperatures ◽

Level Data ◽

Water Level Data ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

The Many

Water temperature is an important component for water quality and biotic conditions in rivers. A good knowledge of river thermal regime is critical for the management of aquatic resources and environmental impact studies. The objective of the present study was to develop a water temperature model as a function of air temperatures, water temperatures and water level data using artificial neural network (ANN) techniques for two thermally different streams. This model was applied on an hourly basis. The results showed that ANN models are an effective modeling tool with overall root-mean-square-error of 0.94 and 1.23 °C, coefficient of determination (R2) of 0.967 and 0.962 and bias of −0.13 and 0.02 °C, for Catamaran Brook and the Little Southwest Miramichi River, respectively. The ANN model performed best in summer and autumn and showed a poorer performance in spring. Results of the present study showed similar or better results to those of deterministic and stochastic models. The present study shows that the predicted hourly water temperatures can also be used to estimate the mean and maximum daily water temperatures. The many advantages of ANN models are their simplicity, low data requirements, their capability of modeling long-term time series as well as having an overall good performance.

Download Full-text

Prediction of Locations in Medical Images Using Orthogonal Neural Networks

10.21203/rs.3.rs-649890/v1 ◽

2021 ◽

Author(s):

Jong Soo Kim ◽

Yongil Cho ◽

Tae Ho Lim

Keyword(s):

Neural Network ◽

Diagnostic Performance ◽

Medical Images ◽

Selection Criterion ◽

Activation Function ◽

X Rays ◽

Ann Model ◽

Ann Models ◽

Artificial Neural Network Ann ◽

Image Localization

Abstract An orthogonal neural network (ONN), a new deep-learning structure for medical image localization, is developed and presented in this paper. This method is simple, efficient, and completely different from a convolution neural network (CNN). The diagnostic performance of ONN for detecting the location of pneumothorax in chest X-rays was assessed and compared to that of CNN. An area under the receiver operating characteristic (ROC) curve (AUC) of 0.870, an accuracy of 85.3%, a sensitivity of 75.0%, and a specificity of 86.5% were achieved; the ONN outperformed the CNN. The diagnostic performance of the ONN with a sigmoid activation function for all the nodes obviously outperformed the ONN with the rectified linear unit (RELU) activation function for all the nodes other than the output nodes. In addition, by applying ONN and CNN to predict the location of the glottis in laryngeal images, we achieved accurate and adjacent prediction rates of 70.5% and 20.5%, respectively, with the ONN. The prediction accuracy of the ONN was compared favorably with that of the CNN. Compared to a CNN, an ONN required only approximately 10% of the computations using a CNN trained on images with an input resolution of 256 × 256 pixels. A fully-connected small artificial neural network (ANN), selected by comparing the test results of several dozens of small ANN models, achieved the best location prediction performance on medical images. This study demonstrated that an ONN can be used as a quick selection criterion to compare ANN models for image localization since an ONN performed well compared decently with the selected ANN model.

Download Full-text

Optimization and Assessment of Residual Chlorine using Response Surface Methodology (RSM) and Artificial Neural Network (ANN) Modeling

International Journal of Recent Technology and Engineering - 2 ◽

10.35940/ijrte.c4122.098319 ◽

2019 ◽

Vol 8 (3) ◽

pp. 258-263

Keyword(s):

Neural Network ◽

Artificial Neural Network ◽

Distribution System ◽

Water Distribution ◽

Residual Chlorine ◽

Urban Water ◽

Ann Model ◽

Artificial Neural ◽

Artificial Neural Network Ann ◽

Rsm Model

Water polluted with microorganisms and pathogens is one of the most significant hazards to public health. Potential microorganisms unsafe to human health can be destroyed through effective disinfection. To stop the re-growth of microorganisms, it is also advisable to take care of the residual disinfectant in the water distribution networks. The most frequently used cleanser material is chlorine. When the chlorine dosage is too low, there will be a deficiency of enough residues at the end of the water network system, leading to re-growth of microorganisms. Addition of an excessive amount of chlorine will lead to corrosion of the pipeline network and also the development of disinfection by-products (DBPs) including carcinogens. Thus, to determine the best rate of chlorine dosage, it is essential to model the system to forecast chlorine decay within the network. In this research study, two major modeling and optimization strategies were employed to assess the optimum dosage of chlorine for municipal water disinfection and also to predict residual chlorine at any predetermined node within the water distribution network. Artificial neural network (ANN) modeling techniques were used to forecast chlorine concentrations in different nodes in the urban water distribution system in Muscat, the capital of the Sultanate of Oman. One-year dataset from one of the distribution system was used for conducting network modeling in this study. The input factors to RSM model considered were pH, chlorine dosage and time. Response variables for RSM model were fixed as total organic carbon (TOC), Biological oxygen demand (BOD) and residual chlorine An Artificial neural network (ANN) model for residual chlorine was created with pH, inlet-concentration of chlorine and initial temperature as input parameters and residual chlorine in the piping network as an output parameter. The ANN model created using these data can be employed to forecast the residual chlorine value in the urban water network at any given specific location. The results from this study utilizing the uniqueness of an ANN model to predict residual chlorine and water quality parameters have the potential to detect complex, higher-order behavior between input and output parameters exist in urban water distribution system.

Download Full-text

Prediction of Rate of Penetration for wells at Nam Con Son basin using Artificial Neural Networks models

10.29007/4sdt ◽

2022 ◽

Author(s):

Vu Khanh Phat Ong ◽

Quang Khanh Do ◽

Thang Nguyen ◽

Hoang Long Vo ◽

Ngoc Anh Thy Nguyen ◽

...

Keyword(s):

Network Model ◽

Oil And Gas ◽

Research Approach ◽

Ann Model ◽

Rate Of Penetration ◽

Drilling Parameters ◽

Drilling Operations ◽

Ann Models ◽

Artificial Neural ◽

Artificial Neural Network Ann

The rate of penetration (ROP) is an important parameter that affects the success of a drilling operation. In this paper, the research approach is based on different artificial neural network (ANN) models to predict ROP for oil and gas wells in Nam Con Son basin. The first is the process of collecting and evaluating drilling parameters as input data of the model. Next is to find the network model capable of predicting ROP most accurately. After that, the study will evaluate the number of input parameters of the network model. The ROP prediction results obtained from different ANN models are also compared with traditional models such as the Bingham model, Bourgoyne & Young model. These results have shown the competitiveness of the ANN model and its high applicability to actual drilling operations.

Download Full-text

Forecasting Inflation in India

International Journal of Asian Business and Information Management ◽

10.4018/jabim.2011040105 ◽

2011 ◽

Vol 2 (2) ◽

pp. 64-73

Author(s):

Rudra P. Pradhan

Keyword(s):

Neural Network ◽

The Other ◽

Ann Model ◽

Multivariate Models ◽

Mean Squared Errors ◽

Forecasting Performance ◽

Ann Models ◽

Univariate Model ◽

Forecasting Inflation ◽

Artificial Neural Network Ann

This paper presents an application of Artificial Neural Network (ANN) to forecast inflation in India during the period 1994-2009. The study presents four different ANN models on the basis of inflation (WPI), economic growth (IIP), and money supply (MS). The first model is a univariate model based on past WPI only. The other three are multivariate models based on WPI and IIP, WPI and MS, WPI, and IIP and MS. In each case, the forecasting performance is measured by mean squared errors and mean absolute deviations. The paper finally concludes that multivariate models show better forecasting performance over the univariate model. In particular, the multivariate ANN model using WPI, IIP, and MS resulted in better performance than the rest of other models to forecast inflation in India.

Download Full-text