Back to selected work

THE PROJECT ARCHIVE / 7 EARLIER BUILDS

Past projects.
Built along the way.

Experiments in machine learning, desktop software, web and mobile development. A closer look at the questions I explored, the tools I used and the code behind each project.

01 Classification · Structured data

Heart disease classification

From a data question to a model comparison.

Concept illustration of a terracotta heart sculpture beside connected data tiles representing health-data classification.
Project illustration

Explored the UCI Cleveland heart-disease dataset in a Python notebook, comparing Logistic Regression, K-Nearest Neighbours and Random Forest against a binary target.

The work covers exploratory plots, a train/test split, randomised and grid searches, and five-fold cross-validation. I used ROC curves, confusion matrices, precision, recall and F1 to examine predictions, then inspected the logistic-regression coefficients.

Pythonpandasscikit-learn

02 Regression · Auction data

Bulldozer price prediction

Working with time, missing data and price prediction.

Concept illustration of a miniature bulldozer with auction tags and feature blocks.
Project illustration

Built a regression notebook around Kaggle’s Bluebook for Bulldozers dataset to estimate equipment sale prices from machine attributes and previous auction records.

Extracted calendar features from sale dates, handled missing values and encoded categories before training a Random Forest regressor. Used 2012 sales for validation, compared RMSLE, MAE and R², explored feature importance and exported test-set predictions.

PythonRandom Forestscikit-learn

03 Computer vision · Transfer learning

Dog breed identification

Taking an image from preprocessing to breed probabilities.

Concept illustration of three different dog breeds framed by computer-vision corner brackets.
Project illustration

Built a multi-class image-classification notebook for 120 dog breeds using Kaggle’s Dog Breed Identification dataset and a pretrained MobileNetV2 model from TensorFlow Hub.

The pipeline resizes images to 224 × 224 pixels and batches them with tf.data. A softmax classification layer produces breed probabilities; TensorBoard and early stopping support training, with prediction visualisations and CSV export completing the workflow.

TensorFlowTensorFlow HubMobileNetV2

04 C++ · Object-oriented programming

Address book application

Making stored records easy to find and maintain.

Original address-book terminal menu showing create, search, display, modify, most searched, delete and exit options.
Original README screenshot

Created a menu-driven address book as a degree course project, using classes and file storage to organise contact and business records.

The project supports creating, searching, displaying, modifying and deleting entries. I extended the search workflow with a “most searched” feature. The README illustrates hospital records and the main menu, while the repository preserves a source-code excerpt and sample data files.

C++File I/OObject-oriented design

05 Java · Desktop application

Restaurant queue management

Connecting an ordering interface with a queue model.

Concept illustration of a restaurant counter, a short customer queue, an unnumbered clock and order tickets.
Project illustration

Developed a Java desktop prototype for exploring restaurant orders and customer waiting times, with a Swing interface and first-come, first-served queue logic.

The source tracks item quantities, customer arrival times, service times and waiting times. Preparation-time calculations feed the queue model, making the connection between an order and the delay experienced by the next customer visible in the program.

JavaSwingQueue modelling

06 Web development · PHP & MySQL

E-commerce website

Following the journey from browsing to an order.

Concept illustration of a shopping trolley, parcels, a book, a folded shirt and a camera.
Project illustration

Built a shopping-site project with category pages, product details and a cart interface, using a Bootstrap-based storefront with PHP and MySQL workflows.

The repository includes registration and login, adding products to a cart, order confirmation and order history. PHP sessions connect customers to those workflows. The hosted preview shows the static storefront; the PHP application is available in the repository.

HTML / CSS / JavaScriptPHPMySQLBootstrap

07 Mobile development · Native integrations

Ionic application

Bringing web interfaces onto a mobile device.

Official Ionic Android interface example with blue tabs and a sample finance dashboard.Official Ionic custom-theme interface example with green controls and rounded dashboard cards.
Ionic Framework · official UI examples ↗

Created an Android demonstration app to explore Ionic interfaces and native device features through Cordova. The repository includes screenshots, the packaged app and bundled source maps.

The code covers profile forms, camera and photo-library access, geolocation, network-status events and social sharing. A local SQLite example adds and retrieves developer records, bringing interface components and device integrations into one project.

IonicAngular / TypeScriptCordovaSQLite

BACK TO THE PRESENT

Explore my recent work

↗