Projects

This addresses a real-life challenge of Hyper Automation Support tickets, allowing the appropriate team to track down issues and resolve them. Used the K-MEAN Classification algorithm to cluster tickets into different categories. With the help of the Ski-Learn Feature Extraction Vectorizer library and pandas, the implementation was simplified.

Combined Visual-Based Localization with Received Signal Strength Indicator for an Indoor Navigation Application. Explored Bayesian Filters for Sensor Fusion. Incorporated multiuser experience where an indoor space is scanned for its visual & RSSI landmarks, and this data is stored in Firebase and it’s retrievable for all other users within the same space for navigation.

An ML model that aims to reduce child and maternal mortality rates by categorizing the health of fetal into suspect, normal, and pathological, with 99% accuracy using historical cardiotocograph data.