Marco Montuori

In many multi-channel engineering problems, the information relevant to the task is concentrated in one channel, while the other information plays an auxiliary role. In forecasting, the quantity to be predicted is the primary source of information and the covariates support it; in image processing, the image itself is primary and contextual data are auxiliary. This paper introduces multi-channel neighborhood-constrained variational mode decomposition (NCVMD), an extension of variational mode decomposition (VMD) built on this hierarchy. Where multivariate VMD (MVMD) aligns the modes’ central frequencies symmetrically and exactly across all channels, NCVMD distinguishes a main channel from auxiliary ones and makes the degree of alignment tunable, reallocating the decomposition error away from the priority channel by a controllable amount. A second contribution is a formal analysis of the resulting optimization problem, which delimits what can be asserted and what cannot. Every subproblem of the alternating scheme is convex and admits a unique closed-form solution, and the main channel provably attains the unconstrained VMD optimum, which MVMD cannot. The joint problem, however, remains nonconvex, so global optimality is not guaranteed. Experiments on synthetic and real-world data confirm the predicted behaviour.

This paper introduces Neighborhood-Constrained Decomposition-based Prediction (NCD-Pred), the first system to leverage Neighborhood-Constrained Variational Mode Decomposition (NCVMD) for multichannel forecasting by integrating time series decomposition and neural networks. NCD-Pred leverages NCVMD to decompose a multichannel signal into simpler, band-limited components—referred to as intrinsic mode functions or simply modes—by prioritizing the most informative channel (the main channel) over less informative ones (the auxiliary channels) and bringing their central frequencies into alignment up to a tunable extent. This frequency synchronization provides a framework for cooperative mode forecasting, where predictions of signal components are recombined to produce the original signal prediction. For mode-level forecasting, Long Short-Term Memory (LSTM) networks are utilized. NCD-Pred’s performance is evaluated against similarly designed mode-level forecasting systems using a multichannel dataset with weak cross-correlation, representing power load on a large vessel. The results show that NCD-Pred outperforms benchmark methods, demonstrating its practical utility in real signal processing scenarios.

Context. Thin stellar streams, such as those resulting from the tidal disruption of globular clusters, have long been known and used as probes of the gravitational potential of our Galaxy, both its visible and dark contents. The literature commonly interprets the presence of underdensity regions, or gaps, along these streams as being due to the close passage of dark matter subhalos. Aims. In this work, we investigate the perturbations induced on streams by the passage of dense stellar systems, such as globular clusters themselves, to test the possibility that they may cause the formation of gaps as well. In particular, we focus on the study of the stream generated by a cluster with characteristics (mass, size, and orbit) similar to those of Palomar 5, a well-known globular cluster in the Galactic halo that has particularly long tidal tails. Methods. For this purpose, we used a particle-test code to simulate the formation and evolution of the stream when subjected to the Galaxy’s gravitational field plus its whole system of globular clusters. Results. Our study shows that such a stream can be strongly perturbed by the close passage of other clusters, in particular NGC 2808, NGC 7078, and NGC 104, and that these perturbations induce the formation of gaps in the tails. Conclusions. The results of this work show that globular clusters can induce gaps in cold streams–just as it has been demonstrated in the literature for that other baryonic components, such as giant molecular clouds and the Galactic bar. Therefore, a future work that attempts to infer the dark matter subhalo distribution from stellar stream gaps must include the contributions from globular clusters.

In this study, a comprehensive examination, both theoretically and practically, is undertaken on Multi-Agent Reinforcement Learning algorithms (MARL). The investigation is situated within the context of real adaptive traffic signal control (ATSC) scenarios, with the primary objective being to validate the algorithms theoretical framework and evaluate their effectiveness, robustness, and applicability in real-world settings. The study uses two traffic networks in the city of Bologna, Italy, as examples. Key findings underscore the necessity of situating the algorithms within the context of a Partially Observable Markov Decision Process (POMDP), inherently characterizing them as non-Markovian. The equations are reformulated within this framework. Simulation results reveal that one of the studied algorithms, MA2C, consistently achieves significant traffic de-congestion in the considered scenarios. In general, its performance continually improves over time, resulting in a reduction of running vehicles by a factor of approximately 70 at the conclusion of the simulation. A training strategy independent of the specific vehicle flow has been implemented, rendering it adaptable for use with various traffic loads.

Background: There is a growing interest in bone tissue MRI and an even greater interest in using low-cost MR scanners. However, the characteristics of bone MRI remain to be fully defined, especially at low field strength. This study aimed to characterize the signal-to-noise ratio (SNR), T₂, and T₂* in spongy bone at 0.3 T, 1.5 T, and 3.0 T. Furthermore, relaxation times were characterized as a function of bone-marrow lipid/water ratio content and trabecular bone density. Methods: Thirty-two women in total underwent an MR-imaging investigation of the calcaneus at 0.3 T, 1.5 T, and 3.0 T. MR-spectroscopy was performed at 3.0 T to assess the fat/water ratio. SNR, T₂, and T₂* were quantified in distinct calcaneal regions (ST, TC, and CC). ANOVA and Pearson correlation statistics were used. Results: SNR increase depends on the magnetic field strength, acquisition sequence, and calcaneal location. T₂* was different at 3.0 T and 1.5 T in ST, TC, and CC. Relaxation times decrease as much as the magnetic field strength increases. The significant linear correlation between relaxation times and fat/water found in healthy young is lost in osteoporotic subjects. Conclusion: The results have implications for the possible use of relaxation vs. lipid/water marrow content for bone quality assessment and the development of quantitative MRI diagnostics at low field strength.

In this study, we present a statistical forecasting framework and assess its efficacy using a range of established machine learning algorithms for predicting Particulate Matter (PM) concentrations in the Arctic, specifically in Pallas (FI), Reykjavik (IS), and Tromso (NO). Our framework leverages historical ground measurements and 24 h predictions from nine models by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM₁₀ predictions for the following 24 h. Furthermore, we compare the performance of various memory cells based on artificial neural networks (ANN), including recurrent neural networks (RNNs), gated recurrent units (GRUs), long short-term memory networks (LSTMs), echo state networks (ESNs), and windowed multilayer perceptrons (MLPs). Regardless of the type of memory cell chosen, our results consistently show that the proposed framework outperforms the CAMS models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Furthermore, we examine the impact of outliers on the overall performance of the model.

In this study, we present a statistical forecasting framework and assess its efficacy using a range of established machine learning algorithms for predicting Particulate Matter (PM) concentrations in the Arctic, specifically in Pallas (FI), Reykjavik (IS), and Tromso (NO). Our framework leverages historical ground measures and 24-hour predictions from 9 models provided by the Copernicus Atmosphere Monitoring Service (CAMS) to provide PM predictions for the following 24 hours. Furthermore, we compare the performance of various memory cells based on artificial neural networks (ANN), including recurrent neural networks (RNNs), gated recurrent units (GRUs), long short-term memory networks (LSTMs), echo state networks (ESNs), and windowed multi-layer perceptrons (MLPs), which are commonly employed in time series forecasting tasks. Irrespective of the chosen memory cell type, our results demonstrate that the proposed framework consistently outperforms the CAM models in terms of mean squared error (MSE), with average improvements ranging from 25% to 40%. Additionally, we investigate the impact of outliers on the overall model performance.