pith. sign in

arxiv: 2512.15067 · v3 · pith:IPZ6RN5Wnew · submitted 2025-12-17 · 💻 cs.LG · cs.AI· cs.SY· eess.SY

EMFusion: An Uncertainty-Aware Conditional Diffusion Framework for Frequency-Selective EMF Forecasting in Wireless Networks

Zijiang Yan , Yixiang Huang , Jianhua Pei , Hina Tabassum , Luca Chiaraviglio This is my paper

Pith reviewed 2026-05-21 17:34 UTC · model grok-4.3

classification 💻 cs.LG cs.AIcs.SYeess.SY
keywords EMF forecastingdiffusion modelsprobabilistic forecastingwireless networksuncertainty estimationfrequency-selective dataconditional generationnetwork planning
0
0 comments X

The pith

EMFusion generates probabilistic EMF forecasts by conditioning a diffusion model on contextual factors like time and season.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents EMFusion as a diffusion-based framework for forecasting electromagnetic field levels at specific frequencies in wireless networks. It learns a conditional distribution over future values to produce full probabilistic intervals rather than single point predictions. A residual U-Net with cross-attention incorporates external conditions while an imputation-based sampling approach treats the task as filling in missing segments to preserve temporal structure. This setup is shown to outperform prior methods on frequency-selective datasets. The approach addresses the need for uncertainty estimates when planning networks and checking compliance.

Core claim

EMFusion is a conditional multivariate diffusion-based probabilistic forecasting framework that integrates diverse contextual factors such as time of day, season, and holidays via a residual U-Net backbone with cross-attention, employs an imputation-based sampling strategy that treats forecasting as a structural inpainting task, and generates empirical probabilistic prediction intervals from the learned conditional distribution rather than point estimates.

What carries the argument

Residual U-Net backbone with cross-attention for dynamic integration of external conditions, paired with imputation-based sampling that frames forecasting as structural inpainting to maintain temporal coherence.

If this is right

  • EMFusion outperforms baseline models both with and without contextual information on frequency-selective EMF datasets.
  • It delivers a 23.85 percent improvement in continuous ranked probability score, 13.93 percent in normalized root mean square error, and 22.47 percent reduction in prediction CRPS error.
  • The model captures inter-operator and inter-frequency variations needed for proactive network planning.
  • Explicit uncertainty estimates support compliance assessment and health impact evaluation beyond simple point forecasts.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same conditional diffusion plus inpainting structure could extend to other environmental sensor networks with irregular sampling intervals.
  • Adding further context such as weather or user density might tighten the probabilistic intervals further.
  • Real-time deployment could allow networks to adjust transmit power proactively based on forecasted distribution tails.

Load-bearing premise

The imputation-based sampling strategy treats forecasting as a structural inpainting task that ensures temporal coherence even with irregular measurements.

What would settle it

Empirical coverage rates of the generated prediction intervals on held-out frequency-selective EMF data that fall significantly below the nominal probability levels, or no improvement over baselines when contextual factors are removed.

Figures

Figures reproduced from arXiv: 2512.15067 by Hina Tabassum, Jianhua Pei, Luca Chiaraviglio, Yixiang Huang, Zijiang Yan.

Figure 1
Figure 1. Figure 1: The U-Net architecture used for EMFusion. The network processes a noisy input through a symmetric encoder-decoder [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: EMFusion for multivariate frequency selective EMF forecasting with cross-attention. [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Comparison of univariate (UV) and multivariate (MV) [PITH_FULL_IMAGE:figures/full_fig_p009_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: EMF levels in Italian dataset, as a function of network [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Correlation maps of EMF levels for (a) frequency bands, (b) cellular technologies, and (c) network operators. [PITH_FULL_IMAGE:figures/full_fig_p011_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Comparison of EMF Forecasts in Validation Set Across Technology Bands (Top) and Operators (Bottom) [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, frequency-selective multivariate forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper introduces EMFusion, a conditional multivariate diffusion-based probabilistic forecasting framework that integrates diverse contextual factors, such as time of day, season, and holidays, while providing explicit uncertainty estimates. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. Unlike standard point forecasters, EMFusion generates empirical probabilistic prediction intervals from the learned conditional distribution, providing uncertainty-aware probabilistic forecasting rather than simple point estimation. Numerical experiments conducted on frequency-selective EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS), 13.93% in normalized root mean square error, and reduces prediction CRPS error by 22.47%.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces EMFusion, a conditional multivariate diffusion-based probabilistic forecasting framework for frequency-selective EMF levels in wireless networks. It features a residual U-Net backbone enhanced by cross-attention to integrate contextual factors (time of day, season, holidays) and an imputation-based sampling strategy that frames forecasting as structural inpainting to maintain temporal coherence with irregular measurements. Unlike point estimators, it generates empirical probabilistic prediction intervals from the learned conditional distribution. Numerical experiments on frequency-selective EMF datasets report that EMFusion with working-hours context outperforms baselines, achieving a 23.85% improvement in CRPS, 13.93% in normalized RMSE, and 22.47% reduction in prediction CRPS error.

Significance. If the empirical claims hold under rigorous validation, the work offers a meaningful advance in uncertainty-aware forecasting for wireless infrastructure compliance and planning. The shift from univariate wideband aggregates to frequency-selective multivariate probabilistic forecasts, combined with explicit contextual conditioning via cross-attention, addresses practical needs for inter-operator and inter-frequency variation modeling. The diffusion-based approach to generating prediction intervals is a clear strength over deterministic baselines.

major comments (2)
  1. [§4] §4 (Numerical Experiments): The central performance claims (23.85% CRPS improvement, 13.93% NRMSE reduction) are presented without any description of dataset characteristics (number of frequencies, operators, measurement granularity, train/test split ratios, or total samples), baseline definitions (architectures, hyperparameters, or training protocols), or statistical validation (standard errors, confidence intervals, or significance tests). This absence directly undermines evaluation of the superiority claim over baselines with or without conditions.
  2. [§3.2] §3.2 (Imputation-based sampling strategy): The description of the imputation-based sampling as a structural inpainting task that ensures temporal coherence is central to the architecture's ability to handle irregular measurements and integrate cross-attention conditioning. However, no explicit equations, loss formulation, or pseudocode are supplied for the sampling process or its interaction with the residual U-Net, preventing verification that the strategy is not merely heuristic.
minor comments (2)
  1. [Abstract] Abstract: The phrase 'EMFusion with the contextual information of working hours' is ambiguous; it is unclear whether working hours are encoded as a distinct binary or categorical variable separate from the time-of-day embedding, or how this specific context is ablated in the reported results.
  2. [Throughout] Notation throughout: The manuscript uses 'CRPS' without an initial definition or reference to the continuous ranked probability score formula, which may confuse readers unfamiliar with probabilistic forecasting metrics.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed feedback. We address each major comment point by point below, indicating the specific revisions we will make to improve the manuscript's rigor and reproducibility.

read point-by-point responses

  1. Referee: [§4] §4 (Numerical Experiments): The central performance claims (23.85% CRPS improvement, 13.93% NRMSE reduction) are presented without any description of dataset characteristics (number of frequencies, operators, measurement granularity, train/test split ratios, or total samples), baseline definitions (architectures, hyperparameters, or training protocols), or statistical validation (standard errors, confidence intervals, or significance tests). This absence directly undermines evaluation of the superiority claim over baselines with or without conditions.

    Authors: We agree that the current presentation of the numerical experiments lacks essential details needed to fully evaluate and reproduce the reported improvements. In the revised manuscript, we will expand §4 with a complete description of the frequency-selective EMF dataset, including the number of frequencies, operators, measurement granularity, train/test split ratios, and total samples. We will also specify the baseline architectures, their hyperparameters, and training protocols. Additionally, we will incorporate statistical validation such as standard errors, confidence intervals, and significance tests for the key metrics (e.g., the 23.85% CRPS improvement). These changes will strengthen the evaluation of the claims. revision: yes

  2. Referee: [§3.2] §3.2 (Imputation-based sampling strategy): The description of the imputation-based sampling as a structural inpainting task that ensures temporal coherence is central to the architecture's ability to handle irregular measurements and integrate cross-attention conditioning. However, no explicit equations, loss formulation, or pseudocode are supplied for the sampling process or its interaction with the residual U-Net, preventing verification that the strategy is not merely heuristic.

    Authors: We acknowledge that the description of the imputation-based sampling strategy requires greater formality to allow verification. In the revised version, we will augment §3.2 with explicit equations defining the sampling process as a structural inpainting task, the associated loss formulation, and pseudocode detailing its interaction with the residual U-Net backbone and cross-attention conditioning. This will clarify the method as a principled component of the framework. revision: yes

Circularity Check

0 steps flagged

No circularity in the EMFusion derivation or claims

full rationale

The paper presents an empirical ML framework: a conditional diffusion model with residual U-Net backbone, cross-attention for contextual factors, and an imputation-based sampling strategy framed as structural inpainting. All load-bearing claims (probabilistic intervals from the learned conditional distribution, 23.85% CRPS improvement) are supported by numerical experiments on frequency-selective EMF datasets against baselines. No derivation reduces by construction to fitted parameters renamed as predictions, no self-definitional loops in the architecture equations, and no load-bearing self-citations or uniqueness theorems are invoked. The forecasting setup is a standard modeling choice whose outputs are externally validated rather than tautological.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

Based on abstract only; the framework introduces new architectural components but does not detail numerical free parameters or external benchmarks.

axioms (1)
  • domain assumption Contextual factors such as time of day, season, and holidays influence EMF levels and can guide the diffusion generation process
    Invoked to dynamically integrate external conditions via cross-attention.
invented entities (2)
  • Imputation-based sampling strategy no independent evidence
    purpose: Treat forecasting as structural inpainting to maintain temporal coherence with irregular measurements
    New sampling approach introduced to handle missing data in the diffusion process.
  • Cross-attention enhanced residual U-Net backbone no independent evidence
    purpose: Dynamically integrate diverse contextual factors into the conditional generation
    Core architectural enhancement proposed for the diffusion model.

pith-pipeline@v0.9.0 · 5802 in / 1378 out tokens · 45826 ms · 2026-05-21T17:34:02.312146+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

62 extracted references · 62 canonical work pages · 1 internal anchor

  1. [1]

    EMForecaster: A deep learning framework for time series forecasting in wireless networks with distribution-free uncertainty quantification,

    X. Mootoo, H. Tabassum, and L. Chiaraviglio, “EMForecaster: A deep learning framework for time series forecasting in wireless networks with distribution-free uncertainty quantification,”IEEE Trans. on Netw. Science and Eng., vol. 13, pp. 1207–1225, 2026

    work page 2026

  2. [2]

    Health risks associ- ated with 5G exposure: A view from the communications engineering perspective,

    L. Chiaraviglio, A. Elzanaty, and M.-S. Alouini, “Health risks associ- ated with 5G exposure: A view from the communications engineering perspective,”IEEE Open J. Commun. Soc., vol. 2, pp. 2131–2179, 2021

    work page 2021

  3. [3]

    International Commission on Non-Ionizing Radiation Protection (IC- NIRP),Guidelines for limiting exposure to electromagnetic fields (100 kHz to 300 GHz), 2020, actual citation for ICNIRP 2020 guidelines

    work page 2020

  4. [4]

    Comparison of international policies on electromagnetic fields: (power frequency and radiofrequency fields),

    R. Stam, “Comparison of international policies on electromagnetic fields: (power frequency and radiofrequency fields),” National Institute for Public Health and the Environment (RIVM), Netherlands, Tech. Rep., 2018, placeholder for a general EMF policy comparison report

    work page 2018

  5. [5]

    Probabilistic Net Load Forecasting for High-Penetration RES Grids Utilizing Enhanced Conditional Diffusion Model,

    Y . Huang, J. Pei, L. Chen, Z. Du, J. Chen, and Z. Peng, “Probabilistic Net Load Forecasting for High-Penetration RES Grids Utilizing Enhanced Conditional Diffusion Model,”arXiv preprint arXiv:2503.17770, 2025

    work page arXiv 2025

  6. [6]

    Deep unsupervised learning using nonequilibrium thermodynamics,

    J. Sohl-Dickstein, E. Weiss, N. Maheswaranathan, and S. Ganguli, “Deep unsupervised learning using nonequilibrium thermodynamics,” inProc. Int. Conf. Mach. Learn.pmlr, 2015, pp. 2256–2265

    work page 2015

  7. [7]

    Denoising diffusion probabilistic models,

    J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” inAdv. Neural Inf. Process. Syst., vol. 33, 2020, pp. 6840–6851. 16

    work page 2020

  8. [8]

    Detection and imputation based two-stage denoising diffusion power system measurement recovery under cyber-physical uncertainties,

    J. Pei, J. Wang, D. Shi, and P. Wang, “Detection and imputation based two-stage denoising diffusion power system measurement recovery under cyber-physical uncertainties,”IEEE Trans. Smart Grid, vol. 15, no. 6, pp. 5965–5980, Nov. 2024

    work page 2024

  9. [9]

    Latent diffusion model-enabled low-latency semantic communication in the presence of semantic ambiguities and wireless channel noises,

    J. Pei, C. Feng, P. Wang, H. Tabassum, and D. Shi, “Latent diffusion model-enabled low-latency semantic communication in the presence of semantic ambiguities and wireless channel noises,”IEEE Trans. Wireless Commun., vol. 24, no. 5, pp. 4055–4072, May 2025

    work page 2025

  10. [10]

    Conditional Time Series Forecasting with Convolutional Neural Networks

    A. Borovykh, S. Bohte, and C. W. Oosterlee, “Conditional time se- ries forecasting with convolutional neural networks,”arXiv preprint arXiv:1703.04691, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  11. [11]

    Mobile network traffic prediction using MLP, MLPWD, and SVM,

    A. Y . Nikravesh, S. A. Ajila, C.-H. Lung, and W. Ding, “Mobile network traffic prediction using MLP, MLPWD, and SVM,” inProc. IEEE Int. Congr. Big Data (BigData Congress). IEEE, 2016, pp. 402–409

    work page 2016

  12. [12]

    Multivariate time series characterization and forecasting of V oIP traffic in real mobile networks,

    M. Di Mauro, G. Galatro, F. Postiglione, W. Song, and A. Liotta, “Multivariate time series characterization and forecasting of V oIP traffic in real mobile networks,”IEEE Trans. on Netw. and Service Manage., vol. 21, no. 1, pp. 851–865, 2023

    work page 2023

  13. [13]

    Traffic forecasting in cellular networks using the LSTM RNN,

    A. Dalgkitsis, M. Louta, and G. T. Karetsos, “Traffic forecasting in cellular networks using the LSTM RNN,” inProc. of the 22nd Pan- Hellenic conference on informatics, 2018, pp. 28–33

    work page 2018

  14. [14]

    Transformer-based wireless traffic prediction and network optimization in o-ran,

    M. A. Habib, P. E. I. Rivera, Y . Ozcan, M. Elsayed, M. Bavand, R. Gaigalas, and M. Erol-Kantarci, “Transformer-based wireless traffic prediction and network optimization in o-ran,” inProc. IEEE Int. Conf. Commun. Wkshps. (ICC Wkshps.). IEEE, 2024, pp. 1–6

    work page 2024

  15. [15]

    AIChronoLens: advancing explainability for time series AI forecasting in mobile networks,

    C. Fiandrino, E. P. G ´omez, P. F. P´erez, H. Mohammadalizadeh, M. Fiore, and J. Widmer, “AIChronoLens: advancing explainability for time series AI forecasting in mobile networks,” inProc. IEEE Int. Conf. Comput. Commun. (INFOCOM). IEEE, 2024, pp. 1521–1530

    work page 2024

  16. [16]

    Multivariate forecasting of network traffic in SDN-based ubiquitous healthcare system,

    D. P. Isravel, S. Silas, J. W. Kathrine, E. B. Rajsingh, and J. Andrew, “Multivariate forecasting of network traffic in SDN-based ubiquitous healthcare system,”IEEE Open J. of the Commun. Soc., vol. 5, pp. 1537–1550, 2024

    work page 2024

  17. [17]

    Wireless traffic usage forecasting using real enterprise network data: Analysis and methods,

    S. P. Sone, J. J. Lehtom ¨aki, and Z. Khan, “Wireless traffic usage forecasting using real enterprise network data: Analysis and methods,” IEEE Open J. of the Commun. Soc., vol. 1, pp. 777–797, 2020

    work page 2020

  18. [18]

    Deep learning- based channel prediction for LEO satellite massive MIMO communica- tion system,

    Y . Zhang, Y . Wu, A. Liu, X. Xia, T. Pan, and X. Liu, “Deep learning- based channel prediction for LEO satellite massive MIMO communica- tion system,”IEEE Wireless Commun. Lett., vol. 10, no. 8, pp. 1835– 1839, 2021

    work page 2021

  19. [19]

    Toward QoS prediction based on temporal transformers for IoT applications,

    A. Hameed, J. Violos, A. Leivadeas, N. Santi, R. Gr ¨unblatt, and N. Mitton, “Toward QoS prediction based on temporal transformers for IoT applications,”IEEE Trans. on Netw. and Service Manage., vol. 19, no. 4, pp. 4010–4027, 2022

    work page 2022

  20. [20]

    Fore- casting video QoE with deep learning from multivariate time-series,

    H. E. Dinaki, S. Shirmohammadi, E. Janulewicz, and D. C ˆot´e, “Fore- casting video QoE with deep learning from multivariate time-series,” IEEE Open J. of Signal Process., vol. 2, pp. 512–521, 2021

    work page 2021

  21. [21]

    Short-term multivariate KPI fore- casting in rural fixed wireless LTE networks,

    A. G. Colpitts and B. R. Petersen, “Short-term multivariate KPI fore- casting in rural fixed wireless LTE networks,”IEEE Netw. Lett., vol. 5, no. 1, pp. 11–15, 2023

    work page 2023

  22. [22]

    Probabilistic QoS metric forecasting in delay-tolerant networks using conditional diffusion models on latent dynamics,

    E. Zhang, Z. Liu, Y . Xiang, and Y . Qu, “Probabilistic QoS metric forecasting in delay-tolerant networks using conditional diffusion models on latent dynamics,”arXiv preprint arXiv:2504.08821, 2025

    work page arXiv 2025

  23. [23]

    A comparative analysis of explainable artificial intelligence models for electric field strength pre- diction over eight european cities,

    Y . Kiouvrekis, I. Givisis, T. Panagiotakopoulos, I. Tsilikas, A. Ploussi, E. Spyratou, and E. P. Efstathopoulos, “A comparative analysis of explainable artificial intelligence models for electric field strength pre- diction over eight european cities,”Sensors, vol. 25, no. 1, p. 53, 2024

    work page 2024

  24. [24]

    Measurement and prediction of electromagnetic radiation exposure level in a university campus,

    M. R. Bakcanet al., “Measurement and prediction of electromagnetic radiation exposure level in a university campus,”Tehni ˇcki vjesnik, vol. 29, no. 2, pp. 449–455, 2022

    work page 2022

  25. [25]

    Examining EMF time series using prediction algorithms with R,

    Z. Pala, “Examining EMF time series using prediction algorithms with R,”IEEE Can. J. Elect. Comput. Eng., vol. 44, no. 2, pp. 223–227, 2021

    work page 2021

  26. [26]

    Deep learning models for time-series forecasting of RF- EMF in wireless networks,

    C. Nguyen, A. A. Cheema, C. Kurnaz, A. Rahimian, C. Brennan, and T. Q. Duong, “Deep learning models for time-series forecasting of RF- EMF in wireless networks,”IEEE Open J. Commun. Soc., vol. 5, pp. 1399–1414, 2024

    work page 2024

  27. [27]

    G. E. P. Box, G. M. Jenkins, G. C. Reinsel, and G. M. Ljung,Time Series Analysis: Forecasting and Control, 5th ed. Hoboken, NJ: John Wiley & Sons, 2015

    work page 2015

  28. [28]

    Time-series-based model and validation for prediction of exposure to wideband radio frequency electromagnetic radiation,

    P. De Lellis, F. L. Iudice, and N. Pasquino, “Time-series-based model and validation for prediction of exposure to wideband radio frequency electromagnetic radiation,”IEEE Trans. Instrum. Meas., vol. 69, no. 6, pp. 3198–3205, 2019

    work page 2019

  29. [29]

    Machine learning modeling for radiofrequency electromagnetic fields (RF-EMF) signals from mmWave 5G signals,

    A. Al-Jumaily, A. Sali, M. Riyadh, S. Q. Wali, L. Li, and A. F. Osman, “Machine learning modeling for radiofrequency electromagnetic fields (RF-EMF) signals from mmWave 5G signals,”IEEE Access, vol. 11, pp. 79 648–79 658, 2023

    work page 2023

  30. [30]

    Generative time series forecasting with diffusion, denoise, and disentanglement,

    Y . Li, X. Lu, Y . Wang, and D. Dou, “Generative time series forecasting with diffusion, denoise, and disentanglement,”Adv. Neural Inf. Process. Syst., vol. 35, pp. 23 009–23 022, 2022

    work page 2022

  31. [31]

    Generative adversarial nets,

    I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, and Y . Bengio, “Generative adversarial nets,” Adv. Neural Inf. Process. Syst., vol. 27, 2014

    work page 2014

  32. [32]

    If you like it, gan it—probabilistic multivariate times series forecast with gan,

    A. Koochali, A. Dengel, and S. Ahmed, “If you like it, gan it—probabilistic multivariate times series forecast with gan,”Eng. Proc., vol. 5, no. 1, p. 40, 2021

    work page 2021

  33. [33]

    Generative modeling by estimating gradients of the data distribution,

    Y . Song and S. Ermon, “Generative modeling by estimating gradients of the data distribution,” inAdv. Neural Inf. Process. Syst., vol. 32, 2019

    work page 2019

  34. [34]

    Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting,

    K. Rasul, C. Seward, I. Schuster, and R. V ollgraf, “Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting,” inProc. Int. Conf. Mach. Learn.PMLR, 2021, pp. 8857– 8868

    work page 2021

  35. [35]

    CSDI: Conditional Score- based Diffusion Models for Probabilistic Time Series Imputation,

    Y . Tashiro, J. Song, Y . Song, and S. Ermon, “CSDI: Conditional Score- based Diffusion Models for Probabilistic Time Series Imputation,” in Adv. Neural Inf. Process. Syst., vol. 34, 2021, pp. 24 804–24 816

    work page 2021

  36. [36]

    Diffusion-based time series imputa- tion and forecasting with structured state space models,

    J. M. L. Alcaraz and N. Strodthoff, “Diffusion-based time series imputa- tion and forecasting with structured state space models,”arXiv preprint arXiv:2208.09399, 2022

    work page arXiv 2022

  37. [37]

    Semantic-aware adaptive video streaming using latent diffusion models for wireless networks,

    Z. Yan, J. Pei, H. Wu, H. Tabassum, and P. Wang, “Semantic-aware adaptive video streaming using latent diffusion models for wireless networks,”IEEE Wireless Commun., vol. 32, no. 5, pp. 30–38, 2025

    work page 2025

  38. [38]

    Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting,

    M. Kollovieh, A. F. Ansari, M. Bohlke-Schneider, J. Zschiegner, H. Wang, and Y . B. Wang, “Predict, refine, synthesize: Self-guiding diffusion models for probabilistic time series forecasting,”Adv. Neural Inf. Process. Syst., vol. 36, pp. 28 341–28 364, 2023

    work page 2023

  39. [39]

    arXiv preprint arXiv:2403.01742 , year=

    X. Yuan and Y . Qiao, “Diffusion-ts: Interpretable diffusion for general time series generation,”arXiv preprint arXiv:2403.01742, 2024

    work page arXiv 2024

  40. [40]

    Retrieval-augmented diffusion models for time series forecasting,

    J. Liu, L. Yang, H. Li, and S. Hong, “Retrieval-augmented diffusion models for time series forecasting,”Adv. Neural Inf. Process. Syst., vol. 37, pp. 2766–2786, 2024

    work page 2024

  41. [41]

    Multi-resolution diffusion models for time series forecasting,

    L. Shen, W. Chen, and J. Kwok, “Multi-resolution diffusion models for time series forecasting,” inProc. Int. Conf. Learn. Represent., 2024

    work page 2024

  42. [42]

    Diffusion-based decoupled deterministic and uncertain framework for probabilistic mul- tivariate time series forecasting,

    Q. Li, Z. Zhang, L. Yao, Z. Li, T. Zhong, and Y . Zhang, “Diffusion-based decoupled deterministic and uncertain framework for probabilistic mul- tivariate time series forecasting,” inProc. Int. Conf. Learn. Represent., 2025

    work page 2025

  43. [43]

    The rise of diffusion models in time-series forecasting,

    C. Meijer and L. Y . Chen, “The rise of diffusion models in time-series forecasting,”arXiv preprint arXiv:2401.03006, 2024

    work page arXiv 2024

  44. [44]

    Diffusion Models for Time Series Forecasting: A Survey,

    C. Su, Z. Cai, Y . Tian, Z. Zheng, and Y . Song, “Diffusion Models for Time Series Forecasting: A Survey,”arXiv preprint arXiv:2507.14507, 2025

    work page arXiv 2025

  45. [45]

    Denoising Diffusion Probabilistic Models,

    J. Ho, A. Jain, and P. Abbeel, “Denoising Diffusion Probabilistic Models,” inAdv. Neural Inf. Process. Syst., vol. 33, 2020

    work page 2020

  46. [46]

    Classifier-free diffusion guidance,

    J. Ho and T. Salimans, “Classifier-free diffusion guidance,” in Proc. NeurIPS 2021 Workshop on Deep Generative Models and Downstream Appl., 2021. [Online]. Available: https://openreview.net/ forum?id=qw8AKxfYbI

    work page 2021

  47. [47]

    (2025) N6850A broadband omni- directional antenna

    Keysight Technologies. (2025) N6850A broadband omni- directional antenna. Keysight Technologies. Product page. [Online]. Available: https://www.keysight.com/ca/en/product/N6850A/ broadband-omnidirectional-antenna.html

    work page 2025

  48. [48]

    U-net: Convolutional networks for biomedical image segmentation,

    O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” inProc. Int. Conf. Med. Image Comput. Comput.-Assist. Interv. (MICCAI). Springer, 2015, pp. 234– 241

    work page 2015

  49. [49]

    Deep residual learning for image recognition,

    K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” inProc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778

    work page 2016

  50. [50]

    Attention Is All You Need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention Is All You Need,” inAdv. Neural Inf. Process. Syst., vol. 30, 2017, pp. 5998–6008

    work page 2017

  51. [51]

    High- resolution image synthesis with latent diffusion models,

    R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High- resolution image synthesis with latent diffusion models,” inProc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2022, pp. 10 674–10 685

    work page 2022

  52. [52]

    U-net transformer: Self and cross attention for medical image segmen- tation,

    O. Petit, N. Thome, C. Rambour, L. Themyr, T. Collins, and L. Soler, “U-net transformer: Self and cross attention for medical image segmen- tation,” inInt. Workshop on Mach. Learn. in Medical Imaging. Springer, 2021, pp. 267–276

    work page 2021

  53. [53]

    Six months in the life of a cellular tower: Is 5G exposure higher than pre-5G one?

    L. Chiaraviglio, C. Lodovisi, D. Franci, S. Pavoncello, and T. Aureli, “Six months in the life of a cellular tower: Is 5G exposure higher than pre-5G one?” inProc. IEEE Int. Symp. Meas. Netw.IEEE, 2022, pp. 1–6. 17

    work page 2022

  54. [54]

    (2022) Remote spectrum monitor MS27102A

    Anritsu Company. (2022) Remote spectrum monitor MS27102A. Anritsu Company. Product page. [Online]. Available: https://www. anritsu.com/en-us/test-measurement/products/ms27102a

    work page 2022

  55. [55]

    (2017) SearcH24 — software for remote control of non-vector spectrum analyzers

    ARPA Lazio. (2017) SearcH24 — software for remote control of non-vector spectrum analyzers. ARPA Lazio. AIRP 2017 proceedings. [Online]. Available: https://www.airp-asso.it/wp-content/ uploads/convegni/2017 Salerno/Atti%20Salerno%202017.pdf

    work page 2017

  56. [56]

    Antenna factor N6850A,

    Keysight Technologies, “Antenna factor N6850A,” https: //www.keysight.com/main/redirector.jspx?action=ref&ckey=3104458& cname=EDITORIAL, 2025, excel data file

    work page 2025

  57. [57]

    Tor Vergata

    Universit `a degli Studi di Roma “Tor Vergata”. (2025, 3) Academic Calendar 2024–2025. Accessed 2025-07-27. [Online]. Available: https://web.uniroma2.it/en/contenuto/academic-calendar

    work page 2025

  58. [58]

    Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting,

    K. Rasul, C. Seward, I. Schuster, and R. V ollgraf, “Autoregressive Denoising Diffusion Models for Multivariate Probabilistic Time Series Forecasting,” inProc. Int. Conf. Mach. Learn., vol. 139. PMLR, 2021. [Online]. Available: https://proceedings.mlr.press/v139/rasul21a.html

    work page 2021

  59. [59]

    Denoising diffusion probabilistic models for probabilistic energy forecasting,

    E. H. Capel and J. Dumas, “Denoising diffusion probabilistic models for probabilistic energy forecasting,” inProc. IEEE Belgrade PowerTech, Belgrade, Serbia, 2023, pp. 1–6

    work page 2023

  60. [60]

    Probabilistic indi- vidual short-term load forecasting using conditional variational autoen- coder,

    S. R. Khazeiynasab, R. Iyengar, and W. L. Leow, “Probabilistic indi- vidual short-term load forecasting using conditional variational autoen- coder,” inProc. IEEE Power Energy Soc. Gen. Meet. (PESGM), Orlando, FL, USA, 2023, pp. 1–5

    work page 2023

  61. [61]

    Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power,

    Q. Huang and S. Wei, “Improved quantile convolutional neural network with two-stage training for daily-ahead probabilistic forecasting of photovoltaic power,”Energy Conv. Manag., vol. 220, p. 113085, Sep. 2020

    work page 2020

  62. [62]

    Dropout as a bayesian approximation: Representing model uncertainty in deep learning,

    Y . Gal and Z. Ghahramani, “Dropout as a bayesian approximation: Representing model uncertainty in deep learning,” inProc. Int. Conf. Mach. Learn., vol. 48, 2016, pp. 1050–1059

    work page 2016