C

Convolutional Neural Network

A real-time human counting system with age and gender classification.

My MSc thesis work. I essayed with a number of classifiers for two type of health-related time series: electrocardiogram and blood oxygen levels. The four approaches used on each type of signal were: (i) featured based approach, where integral and differential attributes where devised and used to classify the sets (ii) Direct Machine Learning application to the time series (Perceptron, Random Forest and others) (iii) 1D convolutional neural networks applied to the signals (iv) 2D convolutional neural networks applied to the signal spectrograms.

The thesis pdf file, included here, is written in Spanish.

Study and development of two neural network architectures for extreme ultraviolet pulse reconstruction

Multimodal Brain Tumor Segmentation (BRATS) Challenge 2019

Training of deep networks for medical image segmentation tasks Network and training strategy that relies on the strong use of data augmentation