Handy is a smart hand washing device that mitigates the rapid transmission of COVID-19 and other germs in public washrooms. The device encourages compliance with proper handwashing techniques and maintains hygenics within public washrooms. I am leading a team of four and protoptying version 2.0 of the device in my final year design project. I am leveraging ML to detect sound and voice triggers via neural network classification of spectrogram analysis.

Check out the patent and figures below for more information...

View Patent View Figures

I've have had 3 years of Swift experience, 5 personal iOS apps (2 of which available on Apple App Store). I'm familiar with concepts of UIKit, ARKit, CoreML, SceneKit and SpriteKit.

The objetive was to build an algorithm to automatically identify whether a patient is suffering from breast cancer or not by looking at biopsy images. The algorithm had to be extremely accurate because lives of people is at stake. The deeper we go into the CNN, the more filters we use to detect high-level features of each biopsy image Implemented ReduceLROnPlateau to improve accuracy

Data exploration on predicting sales prices and practice feature engineering, RFs, and gradient boosting With 79 explanatory variables describing (almost) every aspect of residential homes in Ames, Iowa, this competition challenges me to predict the final price of each home.

I have begun my quest on using ML on practical applications by practicing with Kaggle kernals. My notebooks contain data exploration, image classification, and competition notebooks. My most recent completed notebook includes a breast cancer biopsy image classification that resulted with 96.41% accuracy. My current project involves image classification via 4k video frames.

I was inspired to innovate smart device to prevent the increasing count of vehicle-bike collisions in hometown. The device connects to bicycle seat; prevents hit-n-runs and provides visual aid for vehicle drivers.

Bicycle safety patent figures and document available below

View Patent View Figures

I am in the process of creating my own alorithm for indoor localization using Apollonian Circle Theorem. Code will be available soon...

Founded FTC team #9097 in 2014. In FTC, Teams are responsible for designing, building, and programming their robots in a 10-week build period to compete in an alliance format against other teams. My team and I have constructed and coded 5 robots in 4 years. Throughout those years, I have switched from software lead to hardware lead and teaching new members of the team. I am self-taught on the in's and out's of robotization.