Journal of Pharmaceutical Care & Health Systems
Open Access

A framework for harmala alkaloid extraction process development using fuzzy-rough sets feature selection with fuzzy rough NN by using Weka

8^th Annual Pharma Middle East Congress

October 10-12, 2016 Dubai, UAE

Farid A Badria, Mohamed M Abu Habib and Mohammed Elmogy

Mansoura University, Egypt

Posters & Accepted Abstracts: J Pharma Care Health Sys

Abstract :

Peganum harmala is a widespread species growing as wild plant in Egypt and proved to be useful as an anti-hemorrhoid, anthelmintic, and central nervous system (CNS) stimulating agent in folk medicine. Alkaloids, mainly Harmine, Harmaline, Harmol and Harmalol, represent the major active constituent of the seeds of Peganum harmala. Therefore optimization and development an efficient and economic method for extraction of alkaloids from its seeds will be of great importance from both medical and economic point of view. Therefore, dried powdered seeds of Peganum harmala were extracted using 70% methanol by the conventional maceration method. The extraction process was carried out 80 times for three runs using 11 variables including the volume and concentration of organic solvent, HCl, temperature, and pH. Using machine learning algorithms to explore most important rules affecting extraction process from complex, real data with understandable form and good classification performance is considered as a great challenge. Therefore, this study proposes a Fuzzy Rough with J48 classification model. It integrates Fuzzy Rough and J48 in three phases. The first phase is preparing the input data to construct the information table. The second phase is to reduce features to get the minimum important ones and exclude the redundant attribute for saving training time. The last phase is the classification stage which is based on J48. In the following subsections, we will introduce basic stages of our proposed technique in more detail. J48 classification algorithm is applied to the reduced feature set of Harmla Alkaloid Extraction Process. The accuracy is evaluated using 10-fold cross validation. The experimental results of this proposed intelligent model and J48 Tree view showed a better understanding tool to present the scientific rule for increasing Harmala alkaloid yield range to be around (5%).

Biography :

Email: faridbadria@gmail.com