Falls are the most common cause of fatal injuries in elderly people, causing even death if there is no immediate assistance. Fall detection systems can be used to alert and request help when this type of accident happens. Certain types of these systems include wearable devices that analyze bio-medical signals from the person carrying it in real time. In this way, Deep Learning algorithms could automate and improve the detection of unintentional falls by analyzing these signals. These algorithms have proven to achieve high effectiveness with competitive performances in many classification problems. This work aims to study 16 Recurrent Neural Networks architectures (using Long Short-Term Memory and Gated Recurrent Units) for falls detection based on accelerometer data, reducing computational requirements of previous research. The architectures have been tested on a labeled version of the publicly available SisFall dataset, achieving a mean F1-score above 0.73 and improving state-of-the-art solutions in terms of network complexity.

No abstract

No abstract

No abstract

Colorectal cancer is the third most frequently diagnosed malignancy in the world. To prevent this disease, polyps, the principal precursor, are removed during a colonoscopy. Automatic detection of polyps in this technique could play an important role to assist doctors for achieving an accurate diagnosis. In this work, we apply a state-of-the-art Deep Learning algorithm called Faster Regional Convolutional Neural Network to each colonoscopy frame in order to detect the presence of polyps. The proposed detection system contains two main stages: (1) processing of the colonoscopy frames for training and testing datasets generation, where artifacts are extracted and the number of images in the dataset is augmented; and (2) the Neural Network model, which performs feature extraction over the frames in order to detect polyps within the frames. After training the algorithm under different conditions, our result shows that the proposed system detection has a precision of 80.31%, a recall of 75.37%, an accuracy of 71.99% and a specificity of 65.70%.