My publications

Autori: M. Romano, L. Murra, A. De Luca

Data di pubblicazione: 25 Ottobre 2024

Conferenza: Sixth Italian Conference on Robotics and Intelligent Machines, Rome, Italy, 

Pagine: 55-57

DOI:10.5281/zenodo.14730999 

Abstract: A method is presented for planning a rest-to-rest motion in given time and with zero final vibration for a one-link flexible robot with an elastic joint. We combine in the dynamic model a finite-dimensional description of the flexible link with the transmission elasticity between motor and link. A flat output having no zero dynamics is defined for the system and a suitable smooth trajectory is designed for the task. The nominal torque is then obtained by inverse dynamics.

Autori: M. Romano, J. Tedeschi, I. Amerini

Data di pubblicazione: 20 May 2025

Conferenza: IEEE Symposium Series on Computational Intelligence, Trondheim, Norway

Pagine: 1-5

DOI: 10.1109/CIHMCompanion65205.2025.11002694

Abstract: Pneumonia is one of the most relevant and dangerous chest diseases in the world. It can be detected through images generated by Chest X-Rays (CXR) or CT scans. In recent years, several computer-aided diagnosis (CAD) systems have been developed, especially aided by recent advances in deep learning. One of the most recent innovations is the Kolmogorov-Arnold Network (KAN) which was proposed as an alternative to the classical Multi-Layer Perceptron (MLP): KANs outperform MLPs in terms of accuracy and interpretability. The concept of learning activation functions was applied also in convolutional layer: these are called Convolutional KANs (CKANs). At the moment, deep learning-based CAD systems use convolutional layers to extract features from images and the MLP classifier for classification tasks, while in this study an innovative solution using Convolutional KAN layers and KAN classifier is proposed. The aim of this study is to show how the most recent novelties in deep learning, KANs and CKANs, are better alternatives than the classical solutions in terms of performance. For this reason a deep neural network called “JAM-net” is presented for CXR binary classification tasks (normal/pneumonia). JAM-net is derived from the actual state-of-the-art model for pneumonia detection, a Fuzzy Attention-aided Deep Neural Network called “FA-net”, enriched by the CKAN and KAN layers. The new JAM-net model is able to overcome the actual state-of-the-art performance with 98.84% of accuracy.