This paper describes CAVIAR, a massively parallel hardware implementation of a spike-based sensing-processing-learning-actuating system inspired by the physiology of the nervous system. CAVIAR uses the asynchronous address-event representation (AER) communication framework and was developed in the context of a European Union funded project. It has four custom mixed-signal AER chips, five custom digital AER interface components, 45 k neurons (spiking cells), up to 5 M synapses, performs 12 G synaptic operations per second, and achieves millisecond object recognition and tracking latencies.

The spread of the SARS-CoV-2 virus has made the COVID-19 disease a worldwide epidemic. The most common tests to identify COVID-19 are invasive, time consuming and limited in resources. Imaging is a non-invasive technique to identify if individuals have symptoms of disease in their lungs. However, the diagnosis by this method needs to be made by a specialist doctor, which limits the mass diagnosis of the population. Image processing tools to support diagnosis reduce the load by ruling out negative cases. Advanced artificial intelligence techniques such as Deep Learning have shown high effectiveness in identifying patterns such as those that can be found in diseased tissue. This study analyzes the effectiveness of a VGG16-based Deep Learning model for the identification of pneumonia and COVID-19 using torso radiographs. Results show a high sensitivity in the identification of COVID-19, around 100%, and with a high degree of specificity, which indicates that it can be used as a screening test. AUCs on ROC curves are greater than 0.9 for all classes considered.

Glaucoma is a degenerative disease that affects vision, causing damage to the optic nerve that ends in vision loss. The classic techniques to detect it have undergone a great change since the intrusion of machine learning techniques into the processing of eye fundus images. Several works focus on training a convolutional neural network (CNN) by brute force, while others use segmentation and feature extraction techniques to detect glaucoma. In this work, a diagnostic aid tool to detect glaucoma using eye fundus images is developed, trained and tested. It consists of two subsystems that are independently trained and tested, combining their results to improve glaucoma detection. The first subsystem applies machine learning and segmentation techniques to detect optic disc and cup independently, combine them and extract their physical and positional features. The second one applies transfer learning techniques to a pre-trained CNN to detect glaucoma through the analysis of the complete eye fundus images. The results of both systems are combined to discriminate positive cases of glaucoma and improve final detection. The results show that this system achieves a higher classification rate than previous works. The system also provides information on the basis for the proposed diagnosis suggestion that can help the ophthalmologist to accept or modify it.

Falls have become a relevant public health issue due to their high prevalence and negative effects in elderly people. Wearable fall detector devices allow the implementation of continuous and ubiquitous monitoring systems. The effectiveness for analyzing temporal signals with low energy consumption is one of the most relevant characteristics of these devices. Recurrent neural networks (RNNs) have demonstrated a great accuracy in some problems that require analyzing sequential inputs. However, getting appropriate response times in low power microcontrollers remains a difficult task due to their limited hardware resources. This work shows a feasibility study about using RNN-based deep learning models to detect both falls and falls’ risks in real time using accelerometer signals. The effectiveness of four different architectures was analyzed using the SisFall dataset at different frequencies. The resulting models were integrated into two different embedded systems to analyze the execution times and changes in the model effectiveness. Finally, a study of power consumption was carried out. A sensitivity of 88.2% and a specificity of 96.4% was obtained. The simplest models reached inference times lower than 34 ms, which implies the capability to detect fall events in real-time with high energy efficiency. This suggests that RNN models provide an effective method that can be implemented in low power microcontrollers for the creation of autonomous wearable fall detection systems in real-time.