For a while now I’ve wanted a personal AI assistant that stays online all the time, that I can reach from my phone, and that lives on hardware I actually own. Cloud chatbots are great, but they don’t have a persistent home. They don’t really remember anything between sessions, and they can’t quietly work on something in the background while I’m off doing other things. So I decided to build my own.

Source: github.com/jackaholy/SpeedTyping

Why?

A team project for a software engineering course. The goal was to ship something end-to-end (backend, database, frontend) using Spring Boot and JPA.

The product side was a typing test aimed at younger learners: pick a difficulty, type the passage, get a WPM score, land on a leaderboard.

What?

A Spring Boot web app backed by MySQL via JPA. Three controllers handle the home/leaderboard view, the typing page, and score submission. Levels are seeded from a SQL file with thirty short passages tagged EASY, MEDIUM, or HARD. Vanilla JS on the frontend runs the timer, colors characters as you type, and auto-submits when the passage is finished.

Why?

To explore machine learning techniques for image classification

What?

OpenCV handles face detection. A CNN trained on FER2013 handles emotion classification. Chain them together for live video analysis.

Code

Setup data

For training, we are using the fer2013 black and white emotion-labelled faces dataset. The raw data is available on Kaggle here.

We load our data and apply transformations using the ImageDataGenerator class. Applying small transformations to our data prevents overfitting which helps when making predictions on new data.