International Journal of Computer Applications (0975 – 8887) Volume 81 – No.4, November 2013 29 Osmotic Drying Rate Estimation for Dehydration of Beetroot Slices using Artificial Neural Network Shekhar Pandharipande Associate Professor, Department of Chemical Engineering, Laxminarayan Institute of Technology, Rashtrasant Tukadoji Maharaj Nagpur University, Bharat Nagar, Amravati Road, Nagpur, India. Bhushan Bele B. Tech. Chemical Engineering. Laxminarayan Institute of Technology, Rashtrasant Tukadoji Maharaj Nagpur University, Bharat Nagar, Amravati Road, Nagpur, India. ABSTRACT Osmotic dehydration can be viewed as an alternative method for drying of food materials with advantages of retention of gloss, texture & colour of dried products. Artificial neural network is emerging as a modeling tool for complex operations involving non linear multivariable relationships. The present work is aimed at estimation of the osmotic drying rates & weight reduction of beetroot slices as a function of concentration of sodium chloride, time & temperature using artificial neural network. Based on the observations, results & discussion, it can be said that, beetroot slices can be partially dewatered by osmotic dehydration in salt solution and percent weight loss is from 10 to 29 % depending upon the operating parameters. It can be concluded that the present work has successfully demonstrated the potential of ANN in modeling of osmotic dehydration of beetroot slices with high accuracy. Keywords: Osmotic dehydration, Artificial neural network modeling, Beetroot slices 1. INTRODUCTION Drying is a method of food preservation that works by removing water from the food, which inhibits the growth of microorganisms. Osmotic dehydration has been investigated by researchers and scientist as an alternative method for drying of food materials. Osmotic dehydration is gaining importance as an alternative process of dehydrating fruits and vegetables. It is an efficient water removal method due to its major advantage of retention of gloss, texture & colour of dried products. In osmotic dehydration, the material is immersed in a osmotic solution which is usually a concentrated solution of sucrose or sodium chloride in water. The mechanism of water removal is based on the natural and non-destructive phenomenon of osmosis across cell membrane & the diffusion of water from the material into the solution results due to the higher osmotic pressure of the osmotic solution. The process of dehydration is accompanied by the counter diffusion of solutes from the osmotic solution into the material. Osmotic dehydration is used as a pretreatment to improve nutritional, sensorial and functional properties of food. The use of the osmotic dehydration process in the food industry has several advantages; quality improvement, energy efficiency, packaging and distribution cost reduction, better product stability and retention of nutrients during storage. Beetroot or beet is a flowering plant species in the family Chenopodiaceous & can be peeled, steamed, cooked, pickled, shredded raw, in order to make it eatable. Betanin, obtained from the roots, is used industrially as red food colorants, e.g. to improve the color and flavor of tomato paste, sauces, desserts, jams and jellies, ice cream, sweets and breakfast cereals. There are numerous studies on osmotic dehydration of vegetables. Various researchers have investigated the effect of varying conditions of temperature, concentration and time duration on water loss solid gain and weight reduction. P. Manivannan and M. Rajasimman developed quadratic regression equations describing the effects of temperature (25- 45ºC), time duration (30-150min), salt concentration (5-25%, w/w) and solution to sample ratio (5:1 – 25:1) on the water loss and solids gain [1]. Abhijit Kar reported his work related to osmotic dehydration of banana slices and used Response Surface Methodology to optimize the osmotic dehydration with special reference to maximum moisture removal and minimum solids gain [2]. Graziella C. Antonio studied osmotic dehydration of papaya slices and found that temperature and sample geometry had more influence on water loss and weight loss, followed by sucrose and lactic acid concentration they had also observed that slices provided more water loss, weight loss and solid gain than cubic geometry [3]. Nikolaos E. Mavroudis investigated effects of agitation and structural differences on osmotic dehydration [4]. Md. Shafiq Alam used Response Surface Methodology to investigate the effect of sugar concentration (50-70° Brix), solution temperature (30– 60°C), solution to fruit ratio (4:1–8:1) and immersion time (60–180 min) on the water loss, solute gain, rehydration ratio, vitamin-C loss, colour change and sensory overall acceptability of Indian gooseberry (aonla) slices [5]. Gordana B. Koprivica studied osmotic dehydration process of carrot in sugar beet molasses solutions and investigated the effects of immersion time, working temperature and molasses concentration on mass transfer kinetics during osmotic dehydration [6]. Fernanda E. X. Murr studied the effects of temperature (11.9 to 33.1°C) and NaCl concentration (3 to 17 % w/w) on solid gain and water loss ratio (SG/WL) during osmotic dehydration process of carrot [7]. Artificial Neural Network (ANN) is emerging as an interdisciplinary theme for modeling of complex processes involving non linear multivariable correlation ships. It is inspired by the way biological neural network processes information. It is composed of large number of highly interconnected processing elements called as nodes or neurons working together to solve a specific problem [8]. Multi Layer Perception (MLP) is the most common type of feed forward neural network employed for chemical engineering applications. It consists of more than two layers of a hierarchical structure of input and output layers & at least one hidden layer of processing units in between them. The nodes or