1 code implementation • 24 Jan 2022 • Loris Nanni, Michelangelo Paci, Sheryl Brahnam, Alessandra Lumini
These novel methods are based on the Fourier Transform (FT), the Radon Transform (RT) and the Discrete Cosine Transform (DCT).
no code implementations • 24 Dec 2021 • Loris Nanni, Daniela Cuza, Alessandra Lumini, Andrea Loreggia, Sheryl Brahnam
Semantic segmentation consists in classifying each pixel of an image by assigning it to a specific label chosen from a set of all the available ones.
no code implementations • 9 Oct 2021 • Loris Nanni, Alessandra Lumini, Alessandro Manfe, Riccardo Rampon, Sheryl Brahnam, Giorgio Venturin
Multilabel learning tackles the problem of associating a sample with multiple class labels.
no code implementations • 28 Aug 2021 • Loris Nanni, Alessandro Manfe, Gianluca Maguolo, Alessandra Lumini, Sheryl Brahnam
The best performing ensemble, which combined the CNNs using the different augmentation methods and the two new Adam variants proposed here, achieved state of the art on both insect data sets: 95. 52% on Deng and 73. 46% on IP102, a score on Deng that competed with human expert classifications.
no code implementations • 8 Apr 2021 • Loris Nanni, Stefano Ghidoni, Sheryl Brahnam
Features play a crucial role in computer vision.
no code implementations • 2 Apr 2021 • Alessandra Lumini, Loris Nanni, Gianluca Maguolo
The basic architecture in image segmentation consists of an encoder and a decoder: the first uses convolutional filters to extract features from the image, the second is responsible for generating the final output.
no code implementations • 29 Mar 2021 • Loris Nanni, Gianluca Maguolo, Sheryl Brahnam, Michelangelo Paci
Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs.
no code implementations • 26 Mar 2021 • Loris Nanni, Gianluca Maguolo, Alessandra Lumini
In this work, we compare Adam based variants based on the difference between the present and the past gradients, the step size is adjusted for each parameter.
no code implementations • 22 Jan 2021 • Loris Nanni, Alessandra Lumini, Sheryl Brahnam
Motivation: Automatic Anatomical Therapeutic Chemical (ATC) classification is a critical and highly competitive area of research in bioinformatics because of its potential for expediting drug develop-ment and research.
no code implementations • 24 Nov 2020 • Loris Nanni, Alessandra Lumini, Stefano Ghidoni, Gianluca Maguolo
In this paper we classify biomedical images using ensembles of neural networks.
no code implementations • 11 Nov 2020 • Loris Nanni, Eugenio De Luca, Marco Ludovico Facin, Gianluca Maguolo
The set of handcrafted is mainly based on Local Binary Pattern variants, for each descriptor a different Support Vector Machine is trained, then the set of classifiers is combined by sum rule.
1 code implementation • 21 Sep 2020 • Lucas O. Teixeira, Rodolfo M. Pereira, Diego Bertolini, Luiz S. Oliveira, Loris Nanni, George D. C. Cavalcanti, Yandre M. G. Costa
We assessed the impact of creating a CXR image database from different sources, and the COVID-19 generalization from one source to another.
Computed Tomography (CT) Explainable artificial intelligence +2
no code implementations • 15 Jul 2020 • Loris Nanni, Gianluca Maguolo, Sheryl Brahnam, Michelangelo Paci
The best performing ensembles combining data augmentation techniques with different signal representations are compared and shown to outperform the best methods reported in the literature on these datasets.
no code implementations • 3 Jun 2020 • Luca Patarnello, Marco Celin, Loris Nanni
Dopamine (DA) is an organic chemical that influences several parts of behaviour and physical functions.
no code implementations • 5 May 2020 • Lorenzo Mantovan, Loris Nanni
This paper analyses the application of artificial intelligence techniques to various areas of archaeology and more specifically: a) The use of software tools as a creative stimulus for the organization of exhibitions; the use of humanoid robots and holographic displays as guides that interact and involve museum visitors; b) The analysis of methods for the classification of fragments found in archaeological excavations and for the reconstruction of ceramics, with the recomposition of the parts of text missing from historical documents and epigraphs; c) The cataloguing and study of human remains to understand the social and historical context of belonging with the demonstration of the effectiveness of the AI techniques used; d) The detection of particularly difficult terrestrial archaeological sites with the analysis of the architectures of the Artificial Neural Networks most suitable for solving the problems presented by the site; the design of a study for the exploration of marine archaeological sites, located at depths that cannot be reached by man, through the construction of a freely explorable 3D version.
9 code implementations • 27 Apr 2020 • Gianluca Maguolo, Loris Nanni
In this paper, we compare and evaluate different testing protocols used for automatic COVID-19 diagnosis from X-Ray images in the recent literature.
no code implementations • 16 Dec 2019 • Loris Nanni, Gianluca Maguolo, Michelangelo Paci
To the best of our knowledge this is the largest study on data augmentation for CNNs in animal audio classification audio datasets using the same set of classifiers and parameters.
1 code implementation • 11 Dec 2019 • Gianluca Maguolo, Michelangelo Paci, Loris Nanni, Ludovico Bonan
Audio data augmentation is a key step in training deep neural networks for solving audio classification tasks.
no code implementations • 1 Oct 2019 • Loris Nanni, Gianluca Maguolo, Fabio Pancino
Our best ensembles reaches the state of the art accuracy on both the smaller dataset (92. 43%) and the IP102 dataset (61. 93%), approaching the performance of human experts on the smaller one.
no code implementations • 15 Aug 2019 • Alessandra Lumini, Loris Nanni, Gianluca Maguolo
We study how to create an ensemble based of different CNN models, fine tuned on several datasets with the aim of exploiting their diversity.
no code implementations • 9 Aug 2019 • Alessandra Lumini, Loris Nanni, Alice Codogno, Filippo Berno
In this work we propose a novel post processing approach for skin detectors based on trained morphological operators.
no code implementations • 11 Jun 2019 • Loris Nanni, Alessandra Lumini, Federica Pasquali, Sheryl Brahnam
In this paper we address the problem of protein classification starting from a multi-view 2D representation of proteins.
no code implementations • 7 May 2019 • Gianluca Maguolo, Loris Nanni, Stefano Ghidoni
The goal of this work is to propose an ensemble of Convolutional Neural Networks trained using several different activation functions.
no code implementations • 20 Jul 2018 • Loris Nanni, Alessandra Lumini, Stefano Ghidoni
The aim of this work is to propose an ensemble of descriptors for Melanoma Classification, whose performance has been evaluated on validation and test datasets of the melanoma challenge 2018.
no code implementations • 7 Feb 2018 • Alessandra Lumini, Loris Nanni
Skin detection is the process of discriminating skin and non-skin regions in a digital image and it is widely used in several applications ranging from hand gesture analysis to track body parts and face detection.