Page 64 - 2022

Ph.D.
(Pharmacy)
DEVELOPMENT OF GENERALIZED ARTIFICIAL NEURAL
NETWORK MODEL FOR PREDICTION OF THE PERFORMANCE OF
MODIFIED RELEASE TABLETS
Ph.D. Scholar : Tulsi Hareshkumar Vyas
Research Supervisor : Dr. Girish N. Patel

Regi. No.: 17146021004
Abstract :
Artificial Intelligence is the simulation of human intelligence. From delivering simple
groceries at our door steps to solving the toughest task in scientists’ lab, it is surrounding
human life in all the means. So how can the Pharma industry be untouched in the case of
AI?! Artificial Neural Network (ANN) is a type of AI used to solve non-linear problems and
predict the output for given input parameters from the training values. In this research
work, such generalized ANN is developed to predict drug release from the sustained-
release tablet. It is trained by the back propagation method under supervised learning.
For training purposes various data have been collected from practical work as well as
some openly available patents. An IFS (Input Feature Selection) was applied with a Leave-
one-out approach to attain a suitable dataset. Various learning variables like learning rate,
momentum coefficient have been studied at various levels to achieve optimum model.
This developed model is evaluated on the basis of RMSE, similarity and dissimilarity
factors and can predict the output with the best achieved average error ~0.0095 and R2
0.9953. Such ANNs can be the best combination of experience and intelligence, which
can eliminate tedious lab work that can be cost-effective and time-effective.

Key words: AI, ANN, Input Feature Selection, Back Propagation, Learning Rate,
Momentum Coefficient

33