Microfluidic Injector Models Based on Artificial Neural Networks

Magargle, Ryan; Hoburg, James F.; Mukherjee, Tamal

doi:10.1109/tcad.2005.855936

Cited by 10 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Processing these solutions is costly. As the design of LoC systems requires many repeated simulations, iterative design using numerical simulation is computationally infeasible [1]. The proposal [2] simplifies this process applying MOR (Model Order Reduction) for splitting the spatial dependency of device behavior, extracting the most typical characteristics of the governing equations and, hence, reduces the complexity of the problem.…”

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

“…In particular, applying MOR is undertaken to reduce the number of parameters in the simulation. The methodology proposed in [1] uses the results of MOR applied to specific LoC components as input for training an artificial neural network. This trained neural network simulates the behavior and performance of the specified LoC components.…”

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

“…Finally, the result obtained is a model for designing LoC components generated through the neural architecture. This approach is tested in [1] modeling an injector component because it defines the shape and quantity of analytes that will be used for separation and analysis. The injector components modeled were cross, double-tee and gated-cross.…”

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

“…Modeling an injector is a very difficult task. The approach [1] tries to simplify the mathematical model maintaining accuracy with respect to physical features. The steps for modeling the injector described in [1] are 1.…”

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

“…Microfluidic lab-on-a-chip (LoC) systems have been studied for more than a decade and have many applications in biology, medicine, and chemistry [7,8]. LoC devices perform chemical analysis involving sample preparation, mixing, reaction, injection, separation analysis and detection [1]. The most highly integrated Lab-on-a-Chip devices include all processes and devices on a single chip or card so that the introduction of an unprocessed sample leads to the output of an analytical result -an "answer" -from that same chip [4].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Suitability of Artificial Neural Networks for Designing LoC Circuits

Moreno

Gómez

Castellanos

2011

Advances in Computational Intelligence

View full text Add to dashboard Cite

Abstract. The simulation of complex LoC (Lab-on-a-Chip) devices is a process that requires solving computationally expensive partial differential equations. An interesting alternative uses artificial neural networks for creating computationally feasible models based on MOR techniques. This paper proposes an approach that uses artificial neural networks for designing LoC components considering the artificial neural network topology as an isomorphism of the LoC device topology. The parameters of the trained neural networks are based on equations for modeling microfluidic circuits, analogous to electronic circuits. The neural networks have been trained to behave like AND, OR, Inverter gates. The parameters of the trained neural networks represent the features of LoC devices that behave as the aforementioned gates. This would mean that LoC devices universally compute.

show abstract

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

Section: Artificial Neural Network For Simulating Loc Componentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Suitability of Artificial Neural Networks for Designing LoC Circuits

Moreno

Gómez

Castellanos

2011

Advances in Computational Intelligence

View full text Add to dashboard Cite

show abstract

Microfluidic modeling and design for continuous flow in electrokinetic mixing‐reaction channels

Hauan

2006

AIChE Journal

View full text Add to dashboard Cite

Keywords: lab-on-a-chip design, microscale reactors, reduced order models IntroductionMicrototal analysis systems (TAS), also known as "Labon-a-Chip," 1 are terms used to connote the miniaturization of chemical, biological and biochemical analysis devices. 2,3 A Lab-on-a-Chip (LoC) system is a microfluidic device that mimics the functions of a standard analytical chemistry laboratory: sample preparation, mixing, reaction, injection, separation, and detection. 3 Miniaturization provides LoC devices with some key benefits: the drastic reduction of reagent consumption, which translates to cost savings; integration, which offers the advantages of faster analysis and sometimes novel, synergistic capabilities that may not be attainable otherwise; automation, that allows more precise and reproducible operations resulting in higher data quality. 2 LoC systems have various applications in clinical diagnosis, such as analysis of drugs in biological fluids, 4 DNA separation and detection, 5 and immunoassay. 6 A LoC device can also be used for countering bioterrorism threats and is typically capable of performing sampling and real time testing of samples for biochemical toxins. 7 There exist a large variety of LoC devices that differ in their functional tasks, as well as detection methods. Consequently, using a library of generic LoC designs for all applications may either fail for some analytical procedures or be over designed as for performances, costs and chip size. To avoid these problems, a design methodology is needed to make it easy to customize LoC devices according to applications. LoC designWhile the advantages of microfluidic systems have been demonstrated, 8 systematic design methods are only begun to emerge. 7,9,10 Most often, to design a LoC device with optimized geometry and performance, the designer is reduced to using trial-and-error approaches that involve a large number of experimental tests and long development cycles. This deficiency becomes even more acute when large-scale microfluidic integration is needed. 11 Our long term goal is to develop a fast, robust, and accurate design methodology for integrated and multiplexed microfluidic systems. This general methodology will accelerate the design and customization of LoC devices for specific applications. In our approach to automated LoC design, the inner loop, that is, the evaluation of a particular layout instance of the unit operation, must be solved a large number of times; the typical place-and-route algorithms from integrated circuit design take on the order of ten to hundred thousand iterations. It is, thus, computationally intractable to even think about approaches where the evaluation of single unit operations are measured in minutes.In LoC devices, the subsystem design and ultimate chip layout are intimately linked due to the influence that channel geometry has on device performance. 9 The different operations of a LoC requires modules for subsystems: mixing, reaction, injection, and separation. Several component modules have already been develop...

show abstract

Implementation of a genetically tuned neural platform in optimizing fluorescence from receptor–ligand binding interactions on microchips

et al. 2012

View full text Add to dashboard Cite

This paper describes the use of a genetically tuned neural network platform to optimize the fluorescence realized upon binding 5-carboxyfluorescein-D-Ala-D-Ala-D-Ala (5-FAM-(D-Ala)(3) ) (1) to the antibiotic teicoplanin from Actinoplanes teichomyceticus electrostatically attached to a microfluidic channel originally modified with 3-aminopropyltriethoxysilane. Here, three parameters: (i) the length of time teicoplanin was in the microchannel; (ii) the length of time 1 was in the microchannel, thereby, in equilibrium with teicoplanin, and; (iii) the amount of time buffer was flushed through the microchannel to wash out any unbound 1 remaining in the channel, are examined at a constant concentration of 1, with neural network methodology applied to optimize fluorescence. Optimal neural structure provided a best fit model, both for the training set (r(2) = 0.985) and testing set (r(2) = 0.967) data. Simulated results were experimentally validated demonstrating efficiency of the neural network approach and proved superior to the use of multiple linear regression and neural networks using standard back propagation.

show abstract

Microfluidic Injector Models Based on Artificial Neural Networks

Cited by 10 publications

References 18 publications

Suitability of Artificial Neural Networks for Designing LoC Circuits

Suitability of Artificial Neural Networks for Designing LoC Circuits

Microfluidic modeling and design for continuous flow in electrokinetic mixing‐reaction channels

Implementation of a genetically tuned neural platform in optimizing fluorescence from receptor–ligand binding interactions on microchips

Contact Info

Product

Resources

About