F
Francesco Renna
Researcher at University of Porto
Publications - 67
Citations - 1172
Francesco Renna is an academic researcher from University of Porto. The author has contributed to research in topics: Mixture model & Orthogonal frequency-division multiplexing. The author has an hindex of 14, co-authored 65 publications receiving 834 citations. Previous affiliations of Francesco Renna include University of Cambridge & University College London.
Papers
More filters
Journal ArticleDOI
On instabilities of deep learning in image reconstruction and the potential costs of AI.
TL;DR: The stability test with algorithms and easy-to-use software detects the instability phenomena and is aimed at researchers, to test their networks for instabilities, and for government agencies, such as the Food and Drug Administration (FDA), to secure safe use of deep learning methods.
Journal ArticleDOI
Physical-Layer Secrecy for OFDM Transmissions Over Fading Channels
TL;DR: This paper considers the information theoretic secrecy rates that are achievable by an orthogonal frequency-division multiplexing (OFDM) transmitter/receiver pair in the presence of an eavesdropper that might either use an OFDM structure or choose a more complex receiver architecture.
Journal ArticleDOI
Deep learning-based methods for individual recognition in small birds
André C. Ferreira,Liliana R. Silva,Francesco Renna,Hanja B. Brandl,Hanja B. Brandl,Julien P. Renoult,Damien R. Farine,Damien R. Farine,Rita Covas,Claire Doutrelant +9 more
TL;DR: In this article, the authors describe procedures for automating the collection of training data, generating training datasets, and training CNNs to allow identification of individual birds, including sociable weaver Philetairus socius, the great tit Parus major and the zebra finch Taeniopygia guttata.
Journal ArticleDOI
Reconstruction of Signals Drawn From a Gaussian Mixture Via Noisy Compressive Measurements
TL;DR: Borders are tighter and sharper than standard bounds on the minimum number of measurements needed to recover sparse signals associated with a union of subspaces model, as they are not asymptotic in the signal dimension or signal sparsity.
Journal ArticleDOI
Deep Convolutional Neural Networks for Heart Sound Segmentation
TL;DR: The proposed methods are shown to outperform current state-of-the-art segmentation methods by achieving an average sensitivity of 93.9% and an average positive predictive value of 94% in detecting S1 and S2 sounds.