Publications tagged with Deep learning
Published:
Publications tagged with "Deep learning"
- DetailsNapoli, F., Castaldo, M., Marrone, S., & Campanile, L. (2026). Comparing Emerging Technologies in Image Classification: From Quantum to Kolmogorov [Conference paper]. Lecture Notes in Computer Science, 15886 LNCS, 260–273. https://doi.org/10.1007/978-3-031-97576-9_17
Abstract
The rapid evolution of Artificial Intelligence has led to significant advancements in image classification, with novel approaches emerging beyond traditional deep learning paradigms. This paper presents a comparative analysis of three distinct methodologies for image classification: classical Convolutional Neural Networks (CNNs), Kolmogorov-Arnold Networks (KANs) and KAN-based CNNs and Quantum Machine Learning using Quantum Convolutional Neural Networks. The study evaluates these models on the Labeled Faces in the Wild dataset, implementing the different classifiers with existing, well-assessed technologies. Given the fundamental differences in computational paradigms, performance assessment extends beyond traditional accuracy metrics to include computational efficiency, interpretability, and, for quantum models, gate depth and noise. As a summary of the results, the proposed Quantum Convolutional Neural Network (QCNN) model achieves an accuracy of 75% on the target images classification task, indicating promising performance within current quantum computational limits. All the experiments strongly suggest that Convolutional Kolmogorov-Arnold Networks (CKANs) exhibit increased accuracy as image resolution decreases, QCNN performance meaningfully changes in relation to noise level, while CNNs still keeping strong discriminative capabilities. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. - DetailsCampanile, L., Marrone, S., Marulli, F., & Verde, L. (2022). Challenges and Trends in Federated Learning for Well-being and Healthcare [Conference paper]. Procedia Computer Science, 207, 1144–1153. https://doi.org/10.1016/j.procs.2022.09.170
Abstract
Currently, research in Artificial Intelligence, both in Machine Learning and Deep Learning, paves the way for promising innovations in several areas. In healthcare, especially, where large amounts of quantitative and qualitative data are transferred to support studies and early diagnosis and monitoring of any diseases, potential security and privacy issues cannot be underestimated. Federated learning is an approach where privacy issues related to sensitive data management can be significantly reduced, due to the possibility to train algorithms without exchanging data. The main idea behind this approach is that learning models can be trained in a distributed way, where multiple devices or servers with decentralized data samples can provide their contributions without having to exchange their local data. Recent studies provided evidence that prototypes trained by adopting Federated Learning strategies are able to achieve reliable performance, thus by generating robust models without sharing data and, consequently, limiting the impact on security and privacy. This work propose a literature overview of Federated Learning approaches and systems, focusing on its application for healthcare. The main challenges, implications, issues and potentials of this approach in the healthcare are outlined. © 2022 The Authors. Published by Elsevier B.V. - DetailsMarulli, F., Verde, L., & Campanile, L. (2021). Exploring data and model poisoning attacks to deep learning-based NLP systems [Conference paper]. Procedia Computer Science, 192, 3570–3579. https://doi.org/10.1016/j.procs.2021.09.130
Abstract
Natural Language Processing (NLP) is being recently explored also to its application in supporting malicious activities and objects detection. Furthermore, NLP and Deep Learning have become targets of malicious attacks too. Very recent researches evidenced that adversarial attacks are able to affect also NLP tasks, in addition to the more popular adversarial attacks on deep learning systems for image processing tasks. More precisely, while small perturbations applied to the data set adopted for training typical NLP tasks (e.g., Part-of-Speech Tagging, Named Entity Recognition, etc..) could be easily recognized, models poisoning, performed by the means of altered data models, typically provided in the transfer learning phase to a deep neural networks (e.g., poisoning attacks by word embeddings), are harder to be detected. In this work, we preliminary explore the effectiveness of a poisoned word embeddings attack aimed at a deep neural network trained to accomplish a Named Entity Recognition (NER) task. By adopting the NER case study, we aimed to analyze the severity of such a kind of attack to accuracy in recognizing the right classes for the given entities. Finally, this study represents a preliminary step to assess the impact and the vulnerabilities of some NLP systems we adopt in our research activities, and further investigating some potential mitigation strategies, in order to make these systems more resilient to data and models poisoning attacks. © 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of KES International. - DetailsCampanile, L., Marulli, F., Mastroianni, M., Palmiero, G., & Sanghez, C. (2021). Machine Learning-aided Automatic Calibration of Smart Thermal Cameras for Health Monitoring Applications [Conference paper]. International Conference on Internet of Things, Big Data and Security, IoTBDS - Proceedings, 2021-April, 343–353. https://www.scopus.com/inward/record.uri?eid=2-s2.0-85137959400&partnerID=40&md5=eb78330cb4d585e500b77cd906edfbc7
Abstract
In this paper, we introduce a solution aiming to improve the accuracy of the surface temperature detection in an outdoor environment. The temperature sensing subsystem relies on Mobotix thermal camera without the black body, the automatic compensation subsystem relies on Raspberry Pi with Node-RED and TensorFlow 2.x. The final results showed that it is possible to automatically calibrate the camera using machine learning and that it is possible to use thermal imaging cameras even in critical conditions such as outdoors. Future development is to improve performance using computer vision techniques to rule out irrelevant measurements. © 2021 by SCITEPRESS - Science and Technology Publications, Lda.