Mining Student data by Ensemble Classification and Clustering for Profiling and Prediction of Student Academic Performance

Ensemble techniques have been successfully applied in the context of supervised learning to increase the accuracy and stability of prediction. In this paper, we present a hybrid procedure based on ensemble classification and clustering that enables academicians to firstly predict students’ academic performance and then place each student in a well-defined cluster for further advising

SmartRouter - IBM Research Hackathon Winner

Advanced routing system that takes into consideration road conditions , type of traffic , crime rates and greener areas.

Applying Genetic Algorithms for Traffic Light Control

dBot: AI Based Conversational Agent

Designed and developed an artificial intelligence bot that works on top of desktop applications.Performed NLP, part of speech tagging, sentiment analysis and classification.

Emulator for CLR Parser

The LR(1) parsing is a technique of bottom-up parsing. ‘L’ says that the input string is scanned from left to right, ‘R’ says that the parsing technique uses rightmost derivations, and ‘1’ stands for the look-ahead. Thus the canonical-LR parser makes full use of look-ahead symbols. This method uses a large set of items, called LR(1) items.

Inference Using Resolution and First Order Logic

Developed a program that checks whether a given query holds True in a given Knowledge Base which consisted of sentences with operators : AND, OR ,NOT. Implemented using Resolution Refutation.