Modeling of Drug Release from Matrix Tablets with Process Variables of Microwave-Assisted Modification of Arrowroot Starch Using Artificial Neural Network

2010 ◽  
Vol 152-153 ◽  
pp. 1700-1703 ◽  
Author(s):  
Suchada Piriyaprasarth ◽  
Pornsak Sriamornsak ◽  
Maneerat Juttulapa ◽  
Satit Puttipipatkhachorn

The objective of this study was to model the drug release property in terms of process variables of microwave-assisted modification of arrowroot starch using artificial neural network (ANN). The water content, microwave power and heating time were used as process variables for modification of arrowroot starch and the mean dissolution time was used as dependent variable. The correlation between process variables and dependent variable was examined using feed-forward back-propagation neural networks. The ANN model was optimized by considering goodness-of-fit and crossvalidated predictability. A “leave-one-out” cross-validation revealed that the neural network model could predict MDT values from matrix tablets with a reasonable accuracy (predictive r2 of 0.824 and predictive root mean square error of 19.53). The predictive ability of these models was validated by a set of 4 formulations that were not included in the training set. The predicted and observed MDT were well correlated.

2008 ◽  
Vol 33 (6) ◽  
pp. 1213-1222 ◽  
Author(s):  
Dean Charles Hay ◽  
Akinobu Wakayama ◽  
Ken Sakamura ◽  
Senshi Fukashiro

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.


In the present investigation, the transesterification of waste cooking oil (WCO) to biodiesel over homogenous catalyst KOH have been carried out. To optimize the transesterification process variables both response surface method (RSM) and artificial neural network (ANN) mathematical models were applied to study the impact of process variables temperature, catalyst loading, methanol to oil ratio and the reaction time on biodiesel yield. The experiments were planned with a central composite design matrix using 24 factorial designs. A performance validation assessment was conducted between RSM and ANN. ANN models showed a high precision prediction competence in terms of coefficient of determination (R2 = 0.9995), Root Mean Square Error (RMSE = 0.5702), Standard Predicted Deviation (SEP = 0.0133), Absolute Average Deviation (AAD = 0.0115) compared to RSM model. The concentration of catalyst load was identified as the most significant factor for the base catalyzed transesterification. Under optimum conditions, the maximum biodiesel yield of 88.3% was determined by the artificial neural network model at 60 ºC, 1.05 g catalyst load, 7:1 methanol to oil ratio and 90 min transesterification reaction time. The biodiesel was analyzed by GCMS and it showed the presence of hexadecanoic acid, 9- octadecenoic acid, 9, 12, 15-octadecatrienoic acid, eicosenoic acid, methyl 18-methyl-nonadecanoate, docosanoic acid, and tetracosanoic acid as key fatty acid methyl esters.


2018 ◽  
Vol 140 (11) ◽  
Author(s):  
Abhishek Paul ◽  
Subrata Bhowmik ◽  
Rajsekhar Panua ◽  
Durbadal Debroy

The present study surveys the effects on performance and emission parameters of a partially modified single cylinder direct injection (DI) diesel engine fueled with diesohol blends under varying compressed natural gas (CNG) flowrates in dual fuel mode. Based on experimental data, an artificial intelligence (AI) specialized artificial neural network (ANN) model have been developed for predicting the output parameters, viz. brake thermal efficiency (Bth), brake-specific energy consumption (BSEC) along with emission characteristics such as oxides of nitrogen (NOx), unburned hydrocarbon (UBHC), carbon dioxide (CO2), and carbon monoxide (CO) emissions. Engine load, Ethanol share, and CNG strategies have been used as input parameters for the model. Among the tested models, the Levenberg–Marquardt feed-forward back propagation with three input neurons or nodes, two hidden layers with ten neurons in each layer and six output neurons, and tansig-purelin activation function have been found to the optimal model topology for the diesohol–CNG platforms. The statistical results acquired from the optimal network topology such as correlation coefficient (0.992–0.999), mean square error (MSE) (0.0001–0.0009), and mean absolute percentage error (MAPE) (0.09–2.41%) along with Nash–Sutcliffe coefficient of efficiency (NSE), Kling–Gupta efficiency (KGE), mean square relative error, and model uncertainty established itself as a real-time robust type machine learning tool under diesohol–CNG paradigms. The study also incorporated a special type of measure, namely Pearson's Chi-square test or goodness of fit, which brings up the model validation to a higher level.


2011 ◽  
Vol 94 (1) ◽  
pp. 322-326
Author(s):  
Mohammadreza Khanmohammadi ◽  
Amir Bagheri Garmarudi ◽  
Mohammad Babaei Rouchi ◽  
Nafiseh Khoddami

Abstract A method has been established for simultaneous determination of sodium sulfate, sodium carbonate, and sodium tripolyphosphate in detergent washing powder samples based on attenuated total reflectance Fourier transform IR spectrometry in the mid-IR spectral region (800–1550 cm−1). Genetic algorithm (GA) wavelength selection followed by feed forward back-propagation artificial neural network (BP-ANN) was the chemometric approach. Root mean square error of prediction for BP-ANN and GA-BP-ANN was 0.0051 and 0.0048, respectively. The proposed method is simple, with no tedious pretreatment step, for simultaneous determination of the above-mentioned components in commercial washing powder samples.


2012 ◽  
Vol 576 ◽  
pp. 91-94 ◽  
Author(s):  
Erry Yulian Triblas Adesta ◽  
Muataz H.F. Al Hazza ◽  
M.Y. Suprianto ◽  
Muhammad Riza

Machining of hardened steel at high cutting speeds produces high temperatures in the cutting zone, which affects the surface quality and cutting tool life. Thus, predicting the temperature in early stage becomes utmost importance. This research presents a neural network model for predicting the cutting temperature in the CNC end milling process. The Artificial Neural Network (ANN) was applied as an effective tool for modeling and predicting the cutting temperature. A set of sparse experimental data for finish end milling on AISI H13 at hardness of 48 HRC have been conducted to measure the cutting temperature. The artificial neural network (ANN) was applied to predict the cutting temperature. Twenty hidden layer has been used with feed forward back propagation hierarchical neural networks were designed with Matlab2009b Neural Network Toolbox. The results show a high correlation between the predicted and the observed temperature which indicates the validity of the models.


2015 ◽  
Vol 19 (1) ◽  
pp. 85-93 ◽  
Author(s):  
Ehsan Momeni ◽  
Ramli Nazir ◽  
Danial Jahed Armaghani ◽  
Harnedi Maizir

<p class="MsoNormal" style="text-align: justify; line-height: 200%;">Axial bearing capacity (ABC) of piles is usually determined by static load test (SLT). However, conducting SLT is costly and time-consuming. High strain dynamic pile testing (HSDPT) which is provided by pile driving analyzer (PDA) is a more recent approach for predicting the ABC of piles. In comparison to SLT, PDA test is quick and economical. Implementing feed forward back-propagation artificial neural network (ANN) for solving geotechnical problems has recently gained attention mainly due to its ability in finding complex nonlinear relationships among different parameters. In this study, an ANN-based predictive model for estimating ABC of piles and its distribution is proposed. For network construction purpose, 36 PDA tests were performed on various concrete piles in different project sites. The PDA results, pile geometrical characteristics as well as soil investigation data were used for training the ANN models. Findings indicate the feasibility of ANN in predicting ultimate, shaft and tip bearing resistances of piles. The coefficients of determination, R², equal to 0.941, 0.936, and 0.951 for testing data reveal that the shaft, tip and ultimate bearing capacities of piles predicted by ANN-based model are in close agreement with those of HSDPT. By using sensitivity analysis, it was found that the length and area of the piles are dominant factors in the proposed predictive model.</p><p class="MsoNormal" style="text-align: justify; line-height: 200%;"> </p><p class="MsoNormal" style="text-align: justify; line-height: 200%;"><strong>Resumen</strong></p><p class="MsoNormal" style="text-align: justify; line-height: 200%;">La Capacidad Axial de Soporte (ABC, en inglés) de un pilote de construcción se determina usualmente a través de una Prueba de Carga Estática (SLT, inglés). Sin embargo, estas pruebas son costosas y demandan tiempo. La evaluación de las Dinámicas de Alto Esfuerzo de Pilotes (HSDPT, inglés), que la provee el programa de Análisis de Excavación (PDA, inglés), es una forma de aproximación más reciente para preveer la Capacidad Axial de Soporte. En comparación con la Prueba de Cargas Estática, la evaluación PDA es rápida y económica. La implementación de Redes Neuronales Arficiales (ANN, en inglés) que permita resolver problemas geotécnicos ha ganado atención recientemente debido a su posibilidad de hallar relaciones no lineales entre los diferentes parámetros. En este estudio se propone un modelo predictivo ANN para estimar la Capacidad Axial de Soporte de pilotes y su distribución. Para fines de una red de construcción se realizaron 36 pruebas PDA en pilotes de diferentes proyectos. Los resultados de los Análisis de Excavación, las características geométricas de los pilotes, al igual que los datos de investigación del suelo se utilizaron para probar los modelos ANN. Los resultados indican la viabilidad del modelo ANN en predecir la resistencia de los pilotes. Los coeficientes de correlación, R², que alcanzaron 0.941, 09.36 y 0.951 para la evaluación de los datos, revelan que la capacidad del pilotaje en el último rodamiento, en el cojinete del eje y en la punta que se predijeron con el modelo ANN concuerda con las establecidas a través del HSDPT. A través del análisis de respuesta se determinó que la longitud y el área de los pilotes son factores dominantes en el modelo predictivo propuesto.</p>


Sign in / Sign up

Export Citation Format

Share Document