arXiv subjects

Pierluigi Salvo Rossi

Publications and source records attributed to Pierluigi Salvo Rossi.

8 recordsLinked to original sources

arXiv2026

Robust Prototypical Networks for Few-Shot Sensor Fault Diagnosis

Industrial fault diagnosis often operates with only a handful of labeled fault examples, making few-shot learning attractive for sensor monitoring. Standard prototypical networks are simple and effective; however, their class prototypes may become unstable in the very-low-shot regime because each decision relies on a small support set. We propose \emph{Multi-Episode Prototypical Networks} (MEPN), which aggregate prototypes from multiple disjoint support episodes and use their mean as the final class representative, reducing prototype variance without changing the encoder architecture. We evaluate MEPN on the DeFACTO sensor dataset using five-way fault classification with synthetic bias, drift, spike, and noise faults injected into real industrial measurements. Over 100 independent runs, MEPN reaches \textbf{\SensorOneShotGcpn\%} in the per-episode one-shot setting ($K\!=\!1$ shot, aggregated over $N_{\text{agg}}\!=\!10$ support episodes), substantially above single-episode baselines. Under an equal 10-sample support budget, MEPN and ProtoNet at $K\!=\!10$ are statistically indistinguishable, confirming prototype accumulation as the mechanism rather than superior fixed-budget learning.

cs.AI↗

arXiv2026

Digital Twin-Driven Communication-Efficient Federated Anomaly Detection for Industrial IoT

Anomaly detection is increasingly becoming crucial for maintaining the safety, reliability, and efficiency of industrial systems. Recently, with the advent of digital twins and data-driven decision-making, several statistical and machine-learning methods have been proposed. However, these methods face several challenges, such as dependence on only real sensor datasets, limited labeled data, high false alarm rates, and privacy concerns. To address these problems, we propose a suite of digital twin-integrated federated learning (DTFL) methods that enhance global model performance while preserving data privacy and communication efficiency. Specifically, we present five novel approaches: Digital Twin-Based Meta-Learning (DTML), Federated Parameter Fusion (FPF), Layer-wise Parameter Exchange (LPE), Cyclic Weight Adaptation (CWA), and Digital Twin Knowledge Distillation (DTKD). Each method introduces a unique mechanism to combine synthetic and real-world knowledge, balancing generalization with communication overhead. We conduct an extensive experiment using a publicly available cyber-physical anomaly detection dataset. For a target accuracy of 80%, CWA reaches the target in 33 rounds, FPF in 41 rounds, LPE in 48 rounds, and DTML in 87 rounds, whereas the standard FedAvg baseline and DTKD do not reach the target within 100 rounds. These results highlight substantial communication-efficiency gains (up to 62% fewer rounds than DTML and 31% fewer than LPE) and demonstrate that integrating DT knowledge into FL accelerates convergence to operationally meaningful accuracy thresholds for IIoT anomaly detection.

cs.LG↗

arXiv2026

Kalman Prototypical Networks for Few-shot Fault Detection in Combined Cycle Gas Turbines

Combined-cycle gas turbines (CCGTs) play a key role in modern power generation, offering both high efficiency and reduced environmental impact. However, their complex thermo-fluid and mechanical interactions complicate fault detection, particularly when labeled fault data are scarce. In this paper, we introduce the Kalman Prototypical Network (KPN), a metric-based few-shot learning (FSL) framework specifically tailored for CCGT fault diagnosis. We model the evolution of class prototypes as latent stochastic states in a dynamic system to reduce episodic variance and improve robustness in embedding representation. Synthetic data sets generated with a high-fidelity Modelica-based dynamic simulation of an offshore CCGT system were used, simulating both normal operation and progressive leak faults under transient conditions. Application of the proposed framework on simulated leak fault detection tasks demonstrate that KPN outperforms conventional FSL methods such as Matching Networks, Relation Networks, and MAML in both accuracy and stability under varying support and query configurations. The proposed framework significantly improves training convergence and generalization by stabilizing class representations, making it well-suited for real-world CCGT fault detection where labeled data is limited.

cs.AI↗

arXiv2026

Temporal Data and Short-Time Averages Improve Multiphase Mass Flow Metering

Reliable flow measurements are essential in many industries, but current instruments often fail to accurately estimate multiphase flows, which are frequently encountered in real-world operations. Combining machine learning (ML) algorithms with accurate single-phase flowmeters has therefore received extensive research attention in recent years. The Coriolis mass flowmeter is a widely used single-phase meter that provides direct mass flow measurements, which ML models can be trained to correct, thereby reducing measurement errors in multiphase conditions. This paper demonstrates that preserving temporal information significantly improves model performance in such scenarios. We compare a multilayer perceptron, a windowed multilayer perceptron, and a convolutional neural network (CNN) on three-phase air-water-oil flow data from 342 experiments. Whereas prior work typically compresses each experiment into a single averaged sample, we instead compute short-time averages from within each experiment and train models that preserve temporal information at several downsampling intervals. The CNN performed best at 0.25 Hz with approximately 95 % of relative errors below 13 %, a normalized root mean squared error of 0.03, and a mean absolute percentage error of approximately 4.3 %, clearly outperforming the best single-averaged model and demonstrating that short-time averaging within individual experiments is preferable. Results are consistent across multiple data splits and random seeds, demonstrating robustness.

eess.SP↗

arXiv2020

Feature Selection based on Principal Component Analysis for Underwater Source Localization by Deep Learning

In this paper, we propose an interpretable feature selection method based on principal component analysis (PCA) and principal component regression (PCR), which can extract important features for underwater source localization by only introducing the source location without other prior information. This feature selection method is combined with a two-step framework for underwater source localization based on the semi-supervised learning scheme. In the framework, the first step utilizes a convolutional autoencoder to extract the latent features from the whole available dataset. The second step performs source localization via an encoder multi-layer perceptron (MLP) trained on a limited labeled portion of the dataset. The proposed approach has been validated on the public dataset SwllEx-96 Event S5. The result shows the framework has appealing accuracy and robustness on the unseen data, especially when the number of data used to train gradually decreases. After feature selection, not only the training stage has a 95\% acceleration but the performance of the framework becomes more robust on the depth and more accurate when the number of labeled data used to train is extremely limited.

cs.SD↗

arXiv2013

Decision Fusion with Unknown Sensor Detection Probability

In this correspondence we study the problem of channel-aware decision fusion when the sensor detection probability is not known at the decision fusion center. Several alternatives proposed in the literature are compared and new fusion rules (namely 'ideal sensors' and 'locally-optimum detection') are proposed, showing attractive performance and linear complexity. Simulations are provided to compare the performance of the aforementioned rules.

cs.IT↗

arXiv2013

Orthogonality and Cooperation in Collaborative Spectrum Sensing through MIMO Decision Fusion

This paper deals with spectrum sensing for cognitive radio scenarios where the decision fusion center (DFC) exploits array processing. More specifically, we explore the impact of user cooperation and orthogonal transmissions among secondary users (SUs) on the reporting channel. To this aim four protocols are considered: (i) non-orthogonal and non-cooperative; (ii) orthogonal and non-cooperative; (iii) non-orthogonal and cooperative; (iv) orthogonal and cooperative. The DFC employs maximum ratio combining (MRC) rule and performance are evaluated in terms of complementary receiver operating characteristic (CROC). Analytical results, coupled with Monte Carlo simulations, are presented.

cs.IT↗

arXiv2013

Low-complexity dominance-based Sphere Decoder for MIMO Systems

The sphere decoder (SD) is an attractive low-complexity alternative to maximum likelihood (ML) detection in a variety of communication systems. It is also employed in multiple-input multiple-output (MIMO) systems where the computational complexity of the optimum detector grows exponentially with the number of transmit antennas. We propose an enhanced version of the SD based on an additional cost function derived from conditions on worst case interference, that we call dominance conditions. The proposed detector, the king sphere decoder (KSD), has a computational complexity that results to be not larger than the complexity of the sphere decoder and numerical simulations show that the complexity reduction is usually quite significant.

cs.IT↗