Modeling of a roller-compaction process using neural networks and genetic algorithms

Türkoğlu, Murat; Aydın, İsmail; Murray, Megan G.; Sakr, Adel

doi:10.1016/s0939-6411(99)00054-5

Cited by 54 publications

(25 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various models are available for the optimisation of formulation and processing variables during the development of novel drug delivery systems, including multiple regression analysis (Umrethia and Murthy, 2004), response surface methodology (McCarron et al, 1999), genetic algorithms and the artificial neural networks (ANN) concept (Turkoglu et al, 1999). ANNs are a type of mathematical model that simulates the biological nervous system, drawing on analogues of adaptive biological neurons.…”

Section: Artificial Neural Network Optimisation and Check Point Analysismentioning

confidence: 99%

Freeze-dried, mucoadhesive system for vaginal delivery of the HIV microbicide, dapivirine: Optimisation by an artificial neural network

Woolfson

Umrethia

Kett

et al. 2010

International Journal of Pharmaceutics

View full text Add to dashboard Cite

b s t r a c tDapivirine mucoadhesive gels and freeze-dried tablets were prepared using a 3 × 3 × 2 factorial design. An artificial neural network (ANN) with multi-layer perception was used to investigate the effect of hydroxypropyl-methylcellulose (HPMC): polyvinylpyrrolidone (PVP) ratio (X1), mucoadhesive concentration (X2) and delivery system (gel or freeze-dried mucoadhesive tablet, X3) on response variables; cumulative release of dapivirine at 24 h (Q 24 ), mucoadhesive force (F max ) and zero-rate viscosity. Optimisation was performed by minimising the error between the experimental and predicted values of responses by ANN. The method was validated using check point analysis by preparing six formulations of gels and their corresponding freeze-dried tablets randomly selected from within the design space of contour plots. Experimental and predicted values of response variables were not significantly different (p > 0.05, two-sided paired t-test). For gels, Q 24 values were higher than their corresponding freeze-dried tablets. F max values for freeze-dried tablets were significantly different (2-4 times greater, p > 0.05, twosided paired t-test) compared to equivalent gels. Freeze-dried tablets having lower values for X1 and higher values for X2 components offered the best compromise between effective dapivirine release, mucoadhesion and viscosity such that increased vaginal residence time was likely to be achieved.

show abstract

Section: Artificial Neural Network Optimisation and Check Point Analysismentioning

confidence: 99%

Freeze-dried, mucoadhesive system for vaginal delivery of the HIV microbicide, dapivirine: Optimisation by an artificial neural network

Woolfson

Umrethia

Kett

et al. 2010

International Journal of Pharmaceutics

View full text Add to dashboard Cite

show abstract

“…Due to those advantages, roller compaction has been increasingly utilized to improve the flow and compression properties of materials in the pharmaceutical industry. Several authors have attempted to understand the roller compaction process by mathematically modeling the densification process (4)(5)(6). The fundamental mechanism of roller compaction is still poorly understood due to the complexity of the materials properties and the process variables.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Variability of NIR In-line Monitoring of Roller Compaction Process by Using Fast Fourier Transform (FFT) Analysis

et al. 2008

View full text Add to dashboard Cite

Abstract. The purpose of this research was to investigate the variability of the roller compaction process while monitoring in-line with near-infrared (NIR) spectroscopy. In this paper, a pragmatic method in determining this variability of in-line NIR monitoring roller compaction process was developed and the variability limits were established. Fast Fourier Transform (FFT) analysis was used to study the source of the systematic fluctuations of the NIR spectra. An off-line variability analysis method was developed as well to simulate the in-line monitoring process in order to determine the variability limits of the roller compaction process. For this study, a binary formulation was prepared composed of acetaminophen and microcrystalline cellulose. Different roller compaction parameters such as roll speed and feeding rates were investigated to understand the variability of the process. The best-fit line slope of NIR spectra exhibited frequency dependence only on the roll speed regardless of the feeding rates. The eccentricity of the rolling motion of rollers was identified as the major source of variability and correlated with the fluctuations of the slopes of NIR spectra. The off-line static and dynamic analyses of the compacts defined two different variability of the roller compaction; the variability limits were established. These findings were proved critical in the optimization of the experimental setup of the roller compaction process by minimizing the variability of NIR in-line monitoring.

show abstract

“…Despite widespread use, the effect of the densification of powder undergoing roller compaction is poorly understood, although a number of authors have attempted to model this process. [5][6][7] Recently, Zinchuk et al 8 have reported the use of a compaction simulator to prepare simulated ribbons under different compression pressure. They found good agreement between the physical and mechanical properties of the simulated ribbons and the roller compacted samples.…”

Section: Introductionmentioning

confidence: 99%

Influence of Ambient Moisture on the Compaction Behavior of Microcrystalline Cellulose Powder Undergoing Uni-Axial Compression and Roller-Compaction: A Comparative Study Using Near-Infrared Spectroscopy

Gupta

Peck

Miller

et al. 2005

Journal of Pharmaceutical Sciences

View full text Add to dashboard Cite

Modeling of a roller-compaction process using neural networks and genetic algorithms

Cited by 54 publications

References 7 publications

Freeze-dried, mucoadhesive system for vaginal delivery of the HIV microbicide, dapivirine: Optimisation by an artificial neural network

Freeze-dried, mucoadhesive system for vaginal delivery of the HIV microbicide, dapivirine: Optimisation by an artificial neural network

Investigation of the Variability of NIR In-line Monitoring of Roller Compaction Process by Using Fast Fourier Transform (FFT) Analysis

Influence of Ambient Moisture on the Compaction Behavior of Microcrystalline Cellulose Powder Undergoing Uni-Axial Compression and Roller-Compaction: A Comparative Study Using Near-Infrared Spectroscopy

Contact Info

Product

Resources

About