Wildlife Sound Monitoring
This project involved enhancing a better way for scientist to monitor endangered species using my advanced algorithm to build a machine learning model.
Visit website
Cancer Prediction
This project focuses on developing a predictive model for cancer diagnosis using the Support Vector Machine (SVM) algorithm. By analyzing clinical and demographic data, the SVM model identifies patterns that differentiate between malignant and benign cases. The project aims to enhance early detection accuracy, providing healthcare professionals with a powerful tool for effective diagnosis and treatment planning.
The model is evaluated on various datasets to ensure robustness and reliability, making it a significant step forward in computational oncology and personalized medicine.
Australian Wildfire Analysis
The Australian Wildfire Analysis project aims to improve the understanding and management of wildfire data through an advanced data annotation platform. In response to users' challenges in finding previously viewed or annotated images of wildfires, we introduced a new feature that provides a comprehensive tab listing all annotated slides. This allows users to efficiently track and revisit their analysis of wildfire images. Additionally, we implemented a favoriting system, enabling users to save and prioritize slides of particular interest for further study or annotation. This project enhances the ability of researchers and analysts to monitor and study wildfires, contributing to more effective response and prevention strategies.
Meaningful details
Marking and annotating areas on high resolution biomedical images is the core experience of the app, and it was easy to get lost or lose sense of scale when zooming in on details. Adding measurements for the perimeter and area of an annotation both helped to communicate the overall scale of the image and how large the annotated feature is in comparison.
Project outcomes
Real-time collaborative annotation facilitated better collaboration between learners, and was much easier to run group exercises with the new shared layers feature. Learners gave feedback that is was enjoyable to work together and see what others were doing, and liked how interactive and easy to use the application was.
