Intelligent Computation of Moisture Content in Shrinkable Biomaterials

Abstract

A technique of intelligent computation of moisture content in shrinkable biomaterials from multiple predictors was developed. All measurable predictors were structured in three sets: biomaterial properties (volume, density, porosity, diffusivity); drying conditions (time, air temperature, humidity, velocity, pressure); and drying technologies. Two typical drying models were considered: timedependent (thermodynamical) and time-independent (relational). The relationship between predictors and moisture content was established on the basis of multi-factorial linear regression (MLR) and neural networks (NN). Accuracy of statistical approximation was strongly dependent on drying model and chosen set of predictors. Time-independent models demonstrated better accuracy (MSE ¼ 0.214) than time-dependent models (MSE ¼ 0.254). Redundant predictors did not affect the accuracy and generalization ability of statistical models.Results of NN training and testing showed superior accuracy with respect to statistical models. NN worked perfectly well for any combination of non-correlated predictors, improving accuracy to MSE ¼ 0.01. Elimination of redundant predictors further improved accuracy and generalization ability of NN models.The performance of both models was tested for drying of ginseng roots in the range of temperatures from 38 to 50 C, sizes from 10 to 32 mm, and relative humidity from 12 to 40%. Due to the high accuracy and computational efficiency, NN can be used as online estimator of moisture content in drying process.

Non-Isothermal Drying of Medicinal Plants

“…[27,28] The problem of dynamic optimization of medicinal plants quality becomes complicated because of multi-dimensional and complex nature of the quality function. Usually quality of medicinal plant includes moisture content, [30] nutritional value, [27] texture, [31] color, [32] Downloaded by [Selcuk Universitesi] at 17:37 05 February 2015 5 water-soluble proteins, [33] bioactive polyphenols [34] and/or essential oils. [35] Some of quality attributes, such as moisture, texture and color, are measurable in real-time, whereas others are not directly measurable, but could be calculated through relational models.…”

Optimization of an Artificial Neural Network Topology for Predicting Drying Kinetics of Carrot Cubes Using Combined Response Surface and Genetic Algorithm

“…ANNs permit adequate and precise control of the drying process in industrial applications and have been extensively used by many researchers. [2][3][4][5][6][7][8][9][10][11][12] ANNs offer advantages over mathematical modeling, including the ability to handle large amounts of noisy data from dynamic and nonlinear systems, especially when the underlying physical relationships are not fully understood. There are many parameters affecting the performance of ANNs, and finding the optimum topology of ANNs is the most important aspect of ANN simulation.…”

A Novel Data Preprocessing Method for the Modeling and Prediction of Freeze-Drying Behavior of Apples: Multiple Output–Dependent Data Scaling (MODDS)

“…ANNs permit adequate and precise control of the drying process in industrial applications and have been extensively used by many researchers. [22][23][24][25][26] Menlik et al developed an ANN model for determination of drying behavior such as moisture content and moisture ratio. [27] The performance of freeze drying experiments is close to the performance characteristics of a real system, but preparation of an experimental setup is a very expensive and difficult task.…”