pith. sign in

arxiv: 2604.17485 · v1 · submitted 2026-04-19 · 📡 eess.SP

Adaptive RIS Configuration Design with Environmental Sensing for User Localization in Dynamic Rich Scattering Environment

Anum Umer , Ivo M\"u\"ursepp , Muhammad Mahtab Alam This is my paper

Pith reviewed 2026-05-10 05:48 UTC · model grok-4.3

classification 📡 eess.SP
keywords reconfigurable intelligent surfacesuser localizationrich scattering environmentbidirectional LSTMadaptive configurationenvironmental sensinglocalization RMSE
0
0 comments X

The pith

Adaptive biLSTM model enables lower-error user localization via smart RIS configuration in rich scattering environments

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

This paper develops an adaptive method to configure reconfigurable intelligent surfaces for localizing users in environments full of dynamic scatterers that cause multiple signal reflections. It employs a bidirectional LSTM neural network to process sequences of pilot signals from the base station, estimate the scattering effects, and then adjust the RIS settings based on those estimates to improve positioning accuracy. Simulations in both single-antenna and multi-antenna setups show this method yields lower root mean squared error than random RIS settings, fixed codebooks, or other adaptive techniques. The design is shown to work across varying RIS sizes and network scales, pointing to its use in providing reliable location information where traditional systems struggle with scattering.

Core claim

The proposed biLSTM model with its Scattering Estimation Network and Adaptive RIS-Assisted User Localization Network uses sequential pilot transmissions to sense the environment, estimate scattering, and adaptively update RIS configurations, resulting in significantly lower localization root mean squared error in SISO and MIMO RIS-assisted networks operating in dynamic rich scattering environments.

What carries the argument

A bidirectional long short-term memory (biLSTM) model consisting of a Scattering Estimation Network (Bi-SEN) and an Adaptive RIS-Assisted User Localization Network (Bi-ARULN), which captures temporal correlations in pilot observations to estimate scattering and optimize RIS configurations.

If this is right

  • The proposed approach achieves significantly lower localization RMSE compared to random configuration, prestored codebook look-ups, and adaptive baselines.
  • It generalizes across different configurations and scales with RIS size and network dimensions.
  • The design supports both SISO and MIMO RIS-assisted networks in RSE.
  • Bayesian optimization tunes the hyperparameters to enhance model performance.

Where Pith is reading between the lines

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

  • The sequential sensing mechanism could enable tracking of moving users by continuously updating configurations as the environment changes.
  • Practical deployment would benefit from assessing the overhead of sequential pilots versus the localization gains achieved.
  • The scaling property suggests the method may yield even larger gains in larger RIS deployments for finer spatial resolution.

Load-bearing premise

The biLSTM model can reliably capture temporal correlations between sequential pilot observations to estimate scattering and minimize localization error in a dynamic rich scattering environment.

What would settle it

Observing no significant reduction in localization RMSE when testing the biLSTM approach in a scenario with faster scatterer dynamics than those simulated, compared to non-learning baselines.

Figures

Figures reproduced from arXiv: 2604.17485 by Anum Umer, Ivo M\"u\"ursepp, Muhammad Mahtab Alam.

Figure 2
Figure 2. Figure 2: Distribution of HBS−U in the complex plane for a SISO setup, shown over 100 random realizations of RIS configurations k and SOs locations p (red), of p with fixed k (green), and of k with fixed p (blue), simulated with [10]. The SO positions are sampled uniformly along their predefined trajectories (as shown in [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Proposed adaptive localization approach for [PITH_FULL_IMAGE:figures/full_fig_p008_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: RMSE loss curves for proposed and baseline ap [PITH_FULL_IMAGE:figures/full_fig_p010_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: RMSE of user localization versus NRIS, for T = 21 and SNR = -20 dB. in the architecture of the neural network, specifically, by modifying the output size of the neural network in the (L+1) layer following the biLSTM cells. The findings emphasize the importance of the adaptive RIS design in RIS-assisted and dynamic RSE. It is also observed that incorporating antenna array at the transceiver nodes further en… view at source ↗
Figure 8
Figure 8. Figure 8: Scattering Estimation RMSE from (22) versus T for SNR = 30dB. demonstrates its superior ability to refine RIS configurations using historical and current channel observations, ensuring its adaptive nature against other approaches. Both the SISO and MIMO networks in the proposed approach exhibit a consistent improvement with increasing SNR. MIMO generally outper￾forms SISO due to spatial diversity, particul… view at source ↗
Figure 10
Figure 10. Figure 10: RMSE of user localization versus time frames [PITH_FULL_IMAGE:figures/full_fig_p012_10.png] view at source ↗
read the original abstract

This paper addresses the problem of adaptive reconfigurable intelligent surfaces (RIS) configuration design for user localization in rich-scattering environment (RSE), where electromagnetic waves undergo multiple interactions with dynamic scatterers and RIS elements. We propose an adaptive learning-based localization approach for a distributed RIS-assisted network in a RSE using a bidirectional long-short term memory (biLSTM) model that captures temporal correlations between observations. The proposed approach actively senses the environment using sequential pilot transmissions from the base station (BS), accounting for scattering effects, and adaptively updates the RIS configuration based on prior measurements to eventually accurately estimate and minimize the user localization error. The proposed model comprises two neural sub-networks: Scattering Estimation Network (Bi-SEN), for estimation of scattering in the environment, and Adaptive RIS-Assisted User Localization Network (Bi-ARULN), for RIS configuration and localization. Bayesian optimization is used for hyperparameter tuning of the model. The simulation results demonstrate the effectiveness of the proposed approach, achieving significantly lower localization root mean squared error (RMSE compared to random configuration, prestored codebook look-ups, and adaptive baselines in both single-input-single-output (SISO) and multiple-input-multiple output(MIMO) RIS-assisted networks in RSE. The design is generalized across configurations and scales with RIS size and network dimensions. The results highlight the strong potential of RIS deployment and of the proposed approach to enable reliable location services in RSE.

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 manuscript proposes an adaptive learning-based approach for RIS configuration design to enable user localization in dynamic rich scattering environments (RSE). It employs a bidirectional LSTM model with two sub-networks—Bi-SEN for scattering estimation from sequential BS pilots and Bi-ARULN for adaptive RIS configuration and localization—tuned via Bayesian optimization. Simulations in SISO and MIMO RIS-assisted networks demonstrate lower localization RMSE relative to random configurations, prestored codebooks, and adaptive baselines, with claimed generalization across RIS sizes and network dimensions.

Significance. If the simulation results are robust, the work could contribute to practical RIS deployment for reliable localization services in challenging RSE scenarios relevant to future wireless systems. The explicit use of sequential sensing and biLSTM for temporal correlations is a reasonable direction, and the scaling claims across configurations are potentially useful. However, the absence of detailed channel modeling, ablations, and statistical validation in the reported results reduces the immediate significance.

major comments (2)
  1. [Simulation Results] Simulation results (as summarized in the abstract and results discussion): the central claim of significantly lower RMSE due to the biLSTM capturing temporal correlations is not isolated from other components. No ablation removing the recurrent layers (while retaining the adaptive pilot schedule and Bayesian tuning) is provided, nor are variations in scatterer velocity or correlation time tested. This is load-bearing because the reported gains could arise from the overall adaptive framework rather than the biLSTM specifically.
  2. [Abstract / Simulation Setup] Abstract and simulation setup: the underlying channel model for generating dynamic RSE data (including scatterer dynamics, multiple-interaction paths, and pilot observation statistics) is not specified. Without this, the statistical significance of the RMSE reductions and their dependence on the simulated trajectories cannot be assessed, undermining claims of effectiveness in general RSE.
minor comments (2)
  1. [Abstract] Abstract: missing closing parenthesis in 'root mean squared error (RMSE compared' and missing space/hyphen in 'multiple-input-multiple output(MIMO'.
  2. [Simulation Results] The manuscript would benefit from explicit statements on the training dataset generation process and any cross-validation or statistical tests (e.g., confidence intervals on RMSE) to support the simulation claims.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our work regarding adaptive RIS configuration for user localization in dynamic rich scattering environments. We address each major comment below and indicate the revisions we will incorporate.

read point-by-point responses

  1. Referee: [Simulation Results] Simulation results (as summarized in the abstract and results discussion): the central claim of significantly lower RMSE due to the biLSTM capturing temporal correlations is not isolated from other components. No ablation removing the recurrent layers (while retaining the adaptive pilot schedule and Bayesian tuning) is provided, nor are variations in scatterer velocity or correlation time tested. This is load-bearing because the reported gains could arise from the overall adaptive framework rather than the biLSTM specifically.

    Authors: We agree that an explicit ablation isolating the biLSTM recurrent layers would strengthen attribution of the gains. Our comparisons already include adaptive baselines without sequential recurrent processing, but to directly address this we will add a new ablation experiment replacing the biLSTM with a non-recurrent feedforward network (retaining adaptive pilot scheduling and Bayesian optimization) and report the resulting RMSE. For scatterer dynamics, the current simulations use representative velocity and correlation time ranges for RSE; we will augment the results section with explicit sensitivity curves varying these parameters to demonstrate robustness. revision: yes

  2. Referee: [Abstract / Simulation Setup] Abstract and simulation setup: the underlying channel model for generating dynamic RSE data (including scatterer dynamics, multiple-interaction paths, and pilot observation statistics) is not specified. Without this, the statistical significance of the RMSE reductions and their dependence on the simulated trajectories cannot be assessed, undermining claims of effectiveness in general RSE.

    Authors: The geometry-based stochastic channel model with dynamic scatterers, multiple-interaction paths, and cascaded pilot statistics is fully specified in Section II-B, including the time-varying geometry parameters and Monte Carlo setup for statistical evaluation. We will revise the abstract to reference this model concisely and expand the simulation setup subsection to restate the scatterer velocity ranges, correlation times, and number of Monte Carlo trials with confidence intervals, improving accessibility without altering the technical content. revision: yes

Circularity Check

0 steps flagged

No significant circularity in proposed biLSTM adaptive RIS localization framework

full rationale

The paper proposes a biLSTM-based architecture (Bi-SEN for scattering estimation and Bi-ARULN for RIS configuration and localization) trained on simulated trajectories in dynamic RSE, with performance validated against external baselines (random configuration, prestored codebooks, and adaptive methods) in SISO/MIMO setups. No load-bearing derivation steps, equations, or claims reduce by construction to self-definition, fitted inputs renamed as predictions, or self-citation chains. Bayesian hyperparameter tuning and simulation RMSE reporting are standard empirical validation, not forced equivalence to inputs. The methodology is self-contained with independent benchmarks and does not invoke uniqueness theorems or ansatzes from prior self-work.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The approach depends on the assumption that dynamic scattering can be learned from sequential observations and that simulation environments adequately represent real RSE; no new physical entities are postulated.

free parameters (1)
  • biLSTM hyperparameters
    Tuned via Bayesian optimization; specific values not stated in abstract.
axioms (1)
  • domain assumption Sequential pilot transmissions from the BS produce observations whose temporal correlations reflect the dynamic scattering state.
    Invoked to justify the biLSTM's ability to estimate scattering and adapt RIS configuration.

pith-pipeline@v0.9.0 · 5563 in / 1285 out tokens · 49085 ms · 2026-05-10T05:48:04.280310+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

51 extracted references · 51 canonical work pages · 1 internal anchor

  1. [1]

    An Overview of Signal Processing Techniques for RIS/IRS-Aided Wireless Systems,

    C. Pan, G. Zhou, K. Zhi, S. Hong, T. Wu, Y . Pan, H. Ren, M. D. Renzo, A. Lee Swindlehurst, R. Zhang, and A. Y . Zhang, “An Overview of Signal Processing Techniques for RIS/IRS-Aided Wireless Systems,” IEEE J. Sel. Topics Signal Process., vol. 16, no. 5, pp. 883–917, 2022

    work page 2022

  2. [2]

    Available: https://arxiv.org/abs/2006.01779

    A. Bourdoux, A. N. Barreto, B. van Liempd, C. de Lima, D. Dardari, D. Belot, E.-S. Lohan, G. Seco-Granados, H. Sarieddeen, H. Wymeersch et al., “6G white paper on localization and sensing,”arXiv preprint arXiv:2006.01779, 2020

    work page arXiv 2006

  3. [3]

    Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How It Works, State of Research, and The Road Ahead,

    M. Di Renzo, A. Zappone, M. Debbah, M.-S. Alouini, C. Yuen, J. de Rosny, and S. Tretyakov, “Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How It Works, State of Research, and The Road Ahead,”IEEE J. Sel. Areas Commun., vol. 38, no. 11, pp. 2450–2525, 2020

    work page 2020

  4. [4]

    Intelligent Metasurfaces with Continuously Tunable Local Surface Impedance for Multiple Reconfigurable Functions,

    F. Liu, O. Tsilipakos, A. Pitilakis, A. C. Tasolamprou, M. S. Mirmoosa, N. V . Kantartzis, D.-H. Kwon, J. Georgiou, K. Kossifos, M. A. Antoni- ades, M. Kafesaki, C. M. Soukoulis, and S. A. Tretyakov, “Intelligent Metasurfaces with Continuously Tunable Local Surface Impedance for Multiple Reconfigurable Functions,”Phys. Rev. Appl., vol. 11, p. 044024, Apr 2019

    work page 2019

  5. [5]

    Electromagnetic reprogrammable coding- metasurface holograms,

    L. Li, T. Jun Cui, W. Ji, S. Liu, J. Ding, X. Wan, Y . Bo Li, M. Jiang, C.-W. Qiu, and S. Zhang, “Electromagnetic reprogrammable coding- metasurface holograms,”Nature communications, vol. 8, no. 1, p. 197, 2017

    work page 2017

  6. [6]

    Wireless Fingerprinting Localization in Smart Environments Using Reconfig- urable Intelligent Surfaces,

    C. L. Nguyen, O. Georgiou, G. Gradoni, and M. Di Renzo, “Wireless Fingerprinting Localization in Smart Environments Using Reconfig- urable Intelligent Surfaces,”IEEE Access, vol. 9, pp. 135 526–135 541, 2021

    work page 2021

  7. [7]

    Leveraging RIS-Enabled Smart Signal Propagation for Solving Infeasible Localization Problems: Scenarios, Key Research Directions, and Open Challenges,

    K. Keykhosravi, B. Denis, G. C. Alexandropoulos, Z. S. He, A. Al- banese, V . Sciancalepore, and H. Wymeersch, “Leveraging RIS-Enabled Smart Signal Propagation for Solving Infeasible Localization Problems: Scenarios, Key Research Directions, and Open Challenges,”IEEE Veh. Technol. Mag., vol. 18, no. 2, pp. 20–28, 2023

    work page 2023

  8. [8]

    Reconfig- urable Intelligent Surfaces in 6G Radio Localization: A Survey of Recent Developments, Opportunities, and Challenges,

    A. Umer, I. M ¨u¨ursepp, M. M. Alam, and H. Wymeersch, “Reconfig- urable Intelligent Surfaces in 6G Radio Localization: A Survey of Recent Developments, Opportunities, and Challenges,”IEEE Commun. Surveys & Tutorials, pp. 1–1, 2025

    work page 2025

  9. [9]

    Towards 6G wireless communication networks: Vision, enabling technologies, and new paradigm shifts,

    X. You, C.-X. Wang, J. Huang, X. Gao, Z. Zhang, M. Wang, Y . Huang, C. Zhang, Y . Jiang, J. Wanget al., “Towards 6G wireless communication networks: Vision, enabling technologies, and new paradigm shifts,”Sci. China Informat. Sci., vol. 64, pp. 1–74, 2021

    work page 2021

  10. [10]

    PhysFad: Physics-Based End-to-End Channel Modeling of RIS-Parametrized Environments With Adjustable Fading,

    R. Faqiri, C. Saigre-Tardif, G. C. Alexandropoulos, N. Shlezinger, M. F. Imani, and P. del Hougne, “PhysFad: Physics-Based End-to-End Channel Modeling of RIS-Parametrized Environments With Adjustable Fading,” IEEE Trans. Wireless Commun., vol. 22, no. 1, pp. 580–595, 2023

    work page 2023

  11. [11]

    On the Tacit Lin- earity Assumption in Common Cascaded Models of RIS-Parametrized Wireless Channels,

    A. Rabault, L. Le Magoarou, J. Sol, G. C. Alexandropoulos, N. Shlezinger, H. Vincent Poor, and P. del Hougne, “On the Tacit Lin- earity Assumption in Common Cascaded Models of RIS-Parametrized Wireless Channels,”IEEE Trans. Wireless Commun., vol. 23, no. 8, pp. 10 001–10 014, 2024

    work page 2024

  12. [12]

    Do linear cascaded models of RIS- parametrized wireless channels violate wave physics?

    A. Rabault and P. del Hougne, “Do linear cascaded models of RIS- parametrized wireless channels violate wave physics?” in2023 17th European Conf. Antennas and Propag. (EuCAP), 2023, pp. 1–5

    work page 2023

  13. [13]

    Self-Adaptive RISs Beyond Free Space: Convergence of Localization, Sensing, and Communication Un- der Rich-Scattering Conditions,

    C. Saigre-Tardif and P. del Hougne, “Self-Adaptive RISs Beyond Free Space: Convergence of Localization, Sensing, and Communication Un- der Rich-Scattering Conditions,”IEEE Wireless Commun., vol. 30, no. 1, pp. 24–30, 2023

    work page 2023

  14. [14]

    Hybrid Reconfigurable Intelligent Metasur- faces: Enabling Simultaneous Tunable Reflections and Sensing for 6G Wireless Communications,

    G. C. Alexandropoulos, N. Shlezinger, I. Alamzadeh, M. F. Imani, H. Zhang, and Y . C. Eldar, “Hybrid Reconfigurable Intelligent Metasur- faces: Enabling Simultaneous Tunable Reflections and Sensing for 6G Wireless Communications,”IEEE Veh. Technol. Mag., vol. 19, no. 1, pp. 75–84, 2024

    work page 2024

  15. [15]

    A self-adaptive RIS that estimates and shapes fading rich-scattering wireless channels,

    C. Saigre-Tardif and P. D. Hougne, “A self-adaptive RIS that estimates and shapes fading rich-scattering wireless channels,” in2022 IEEE 95th Veh. Technol. Conf.: (VTC2022-Spring), 2022, pp. 1–5

    work page 2022

  16. [16]

    RIS-Based Radio Localization in Rich Scattering Environments: Harnessing Multi-Path with ANN Decoders,

    P. del Hougne, “RIS-Based Radio Localization in Rich Scattering Environments: Harnessing Multi-Path with ANN Decoders,” in2021 IEEE 22nd Int. Workshop Signal Process. Advances Wireless Commun. (SPAWC), 2021, pp. 511–515

    work page 2021

  17. [17]

    Long short -term memory,

    S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,”Neural Comput., vol. 9, no. 8, pp. 1735–1780, 11 1997. [Online]. Available: https://doi.org/10.1162/neco.1997.9.8.1735

    work page doi:10.1162/neco.1997.9.8.1735 1997

  18. [18]

    Time-Aware LSTM Neural Networks for Dynamic Personalized Recommendation on Business Intelligence,

    X. Yang and J. A. Esquivel, “Time-Aware LSTM Neural Networks for Dynamic Personalized Recommendation on Business Intelligence,” Tsinghua Sci. and Technol., vol. 29, no. 1, pp. 185–196, 2024

    work page 2024

  19. [19]

    Wireless Positioning Network Location Prediction Based on Machine Learning Techniques,

    F. Al-Obaidy, N. Razfar, P. Moeini, and F. Mohammadi, “Wireless Positioning Network Location Prediction Based on Machine Learning Techniques,” in2020 IEEE Canadian Conf. Electr. and Comput. Eng. (CCECE), 2020, pp. 1–5

    work page 2020

  20. [20]

    LSTM-Based Prediction Method of Surrounding Vehicle Trajectory,

    K. Wang, Y . Qian, T. An, Z. Zhang, and J. Zhang, “LSTM-Based Prediction Method of Surrounding Vehicle Trajectory,” in2022 Int. Conf. Artificial Intell. Everything (AIE), 2022, pp. 100–105

    work page 2022

  21. [21]

    Adap- tive Beamforming Design for mmWave RIS-Aided Joint Localization and Communication,

    J. He, H. Wymeersch, T. Sanguanpuak, O. Silven, and M. Juntti, “Adap- tive Beamforming Design for mmWave RIS-Aided Joint Localization and Communication,” in2020 IEEE Wireless Commun. Netw. Conf. Workshops (WCNCW), 2020, pp. 1–6

    work page 2020

  22. [22]

    Reconfigurable Intelligent Surface Aided Wireless Localization,

    Y . Liu, E. Liu, R. Wang, and Y . Geng, “Reconfigurable Intelligent Surface Aided Wireless Localization,” inICC 2021 - IEEE Int. Conf. Commun., 2021, pp. 1–6

    work page 2021

  23. [23]

    SISO RIS-Enabled Joint 3D Downlink Localization and Synchroniza- tion,

    K. Keykhosravi, M. F. Keskin, G. Seco-Granados, and H. Wymeersch, “SISO RIS-Enabled Joint 3D Downlink Localization and Synchroniza- tion,” inICC 2021 - IEEE Int. Conf. Commun., 2021, pp. 1–6

    work page 2021

  24. [24]

    Near-field Localization with a Reconfigurable Intelligent Surface Acting as Lens,

    Z. Abu-Shaban, K. Keykhosravi, M. F. Keskin, G. C. Alexandropoulos, G. Seco-Granados, and H. Wymeersch, “Near-field Localization with a Reconfigurable Intelligent Surface Acting as Lens,” inICC 2021 - IEEE Int. Conf. Commun., 2021, pp. 1–6

    work page 2021

  25. [25]

    Channel Estimation and User Localization for IRS-Assisted MIMO-OFDM Systems,

    Y . Lin, S. Jin, M. Matthaiou, and X. You, “Channel Estimation and User Localization for IRS-Assisted MIMO-OFDM Systems,”IEEE Trans. Wireless Commun., vol. 21, no. 4, pp. 2320–2335, 2022

    work page 2022

  26. [26]

    Towards Ubiquitous Positioning by Leveraging Reconfigurable Intelligent Sur- face,

    H. Zhang, H. Zhang, B. Di, K. Bian, Z. Han, and L. Song, “Towards Ubiquitous Positioning by Leveraging Reconfigurable Intelligent Sur- face,”IEEE Commun. Lett., vol. 25, no. 1, pp. 284–288, 2021

    work page 2021

  27. [27]

    MetaLocalization: Reconfig- urable Intelligent Surface Aided Multi-User Wireless Indoor Localiza- tion,

    H. Zhang, H. Zhang, B. Di, and Bian, “MetaLocalization: Reconfig- urable Intelligent Surface Aided Multi-User Wireless Indoor Localiza- tion,”IEEE Trans. Wireless Commun., vol. 20, no. 12, pp. 7743–7757, 2021

    work page 2021

  28. [28]

    Joint Localization and Com- munication Study for Intelligent Reflecting Surface Aided Wireless Communication System,

    R. Wang, Z. Xing, E. Liu, and J. Wu, “Joint Localization and Com- munication Study for Intelligent Reflecting Surface Aided Wireless Communication System,”IEEE Trans. Commun., vol. 71, no. 5, pp. 3024–3042, 2023

    work page 2023

  29. [29]

    Localization With Reconfigurable Intelligent Surface: An Active Sensing Approach,

    Z. Zhang, T. Jiang, and W. Yu, “Localization With Reconfigurable Intelligent Surface: An Active Sensing Approach,”IEEE Trans. Wireless Commun., vol. 23, no. 7, pp. 7698–7711, 2024

    work page 2024

  30. [30]

    Location Prediction Using Bayesian Optimization LSTM for RIS-Assisted Wireless Communications,

    X. Hu, Y . Tian, Y . H. Kho, B. Xiao, Q. Li, Z. Yang, Z. Li, and W. Li, “Location Prediction Using Bayesian Optimization LSTM for RIS-Assisted Wireless Communications,”IEEE Trans. Veh. Technol., vol. 73, no. 10, pp. 15 156–15 171, 2024

    work page 2024

  31. [31]

    Reconfigurable Intelligent Surfaces for Localization: Position and Orientation Error Bounds,

    A. Elzanaty, A. Guerra, F. Guidi, and M.-S. Alouini, “Reconfigurable Intelligent Surfaces for Localization: Position and Orientation Error Bounds,”IEEE Trans. Signal Process., vol. 69, pp. 5386–5402, 2021

    work page 2021

  32. [32]

    RIS-aided Joint Channel Estimation and Localization at mmWave under Hardware Impairments: A Dictionary Learning-based Approach,

    M. Bayraktar, N. Gonz ´alez-Prelcic, G. C. Alexandropoulos, and H. Chen, “RIS-aided Joint Channel Estimation and Localization at mmWave under Hardware Impairments: A Dictionary Learning-based Approach,”IEEE Trans. Wireless Commun., pp. 1–1, 2024

    work page 2024

  33. [33]

    Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment,

    F. Sohrabi, Z. Chen, and W. Yu, “Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment,” inICASSP 2021 - 2021 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2021, pp. 4940–4944

    work page 2021

  34. [34]

    Reconfigurable Intelligent Surfaces in Dynamic Rich Scattering Environments: BiLSTM-Based Optimization for Accurate User Localization,

    A. Umer, I. M ¨u¨ursepp, and M. M. Alam, “Reconfigurable Intelligent Surfaces in Dynamic Rich Scattering Environments: BiLSTM-Based Optimization for Accurate User Localization,” in2024 3rd Int. Conf. 6G Net. (6GNet), 2024, pp. 122–126

    work page 2024

  35. [35]

    Beyond 5G Wireless Localization with Reconfigurable Intelligent Surfaces,

    H. Wymeersch and B. Denis, “Beyond 5G Wireless Localization with Reconfigurable Intelligent Surfaces,” inICC 2020 - 2020 IEEE Int. Conf. Commun. (ICC), 2020, pp. 1–6

    work page 2020

  36. [36]

    Cram ´er-Rao Lower Bound Analysis of Multiple-RIS-Aided mmWave Positioning Systems,

    Y . Liu, S. Hong, C. Pan, Y . Wang, Y . Pan, and M. Chen, “Cram ´er-Rao Lower Bound Analysis of Multiple-RIS-Aided mmWave Positioning Systems,” in2022 IEEE 33rd Ann. Int. Symp. Personal, Indoor Mobile Radio Commun. (PIMRC), 2022, pp. 1110–1115. 14

    work page 2022

  37. [37]

    Optimal adaptive waveform design for cognitive mimo radar,

    W. Huleihel, J. Tabrikian, and R. Shavit, “Optimal adaptive waveform design for cognitive mimo radar,”IEEE Trans. on Signal Process., vol. 61, no. 20, pp. 5075–5089, 2013

    work page 2013

  38. [38]

    Bayesian user localization and tracking for reconfigurable intelligent surface aided mimo systems,

    B. Teng, X. Yuan, R. Wang, and S. Jin, “Bayesian user localization and tracking for reconfigurable intelligent surface aided mimo systems,” IEEE J. Sel. Topics Signal Process., vol. 16, no. 5, pp. 1040–1054, 2022

    work page 2022

  39. [39]

    Active Learning and CSI Ac- quisition for mmWave Initial Alignment,

    S.-E. Chiu, N. Ronquillo, and T. Javidi, “Active Learning and CSI Ac- quisition for mmWave Initial Alignment,”IEEE J. Sel. Areas Commun., vol. 37, no. 11, pp. 2474–2489, 2019

    work page 2019

  40. [40]

    Active Sensing for Commu- nications by Learning,

    F. Sohrabi, T. Jiang, W. Cui, and W. Yu, “Active Sensing for Commu- nications by Learning,”IEEE J. Sel. Areas Commun., vol. 40, no. 6, pp. 1780–1794, 2022

    work page 2022

  41. [41]

    Deep Sequential Beamformer Learn- ing for Multipath Channels in Mmwave Communication Systems,

    A. Sant, A. Abdi, and J. Soriaga, “Deep Sequential Beamformer Learn- ing for Multipath Channels in Mmwave Communication Systems,” in ICASSP 2022 - 2022 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2022, pp. 5198–5202

    work page 2022

  42. [42]

    Active Beam Tracking with Reconfig- urable Intelligent Surface,

    H. Han, T. Jiang, and W. Yu, “Active Beam Tracking with Reconfig- urable Intelligent Surface,” inICASSP 2023 - 2023 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2023, pp. 1–5

    work page 2023

  43. [43]

    Active Sensing for Localization with Reconfigurable Intelligent Surface,

    Z. Zhang, T. Jiang, and W. Yu, “Active Sensing for Localization with Reconfigurable Intelligent Surface,” inICC 2023 - IEEE Int. Conf. Commun., 2023, pp. 4261–4266

    work page 2023

  44. [44]

    Radio Localization and Mapping With Reconfigurable Intelligent Surfaces: Challenges, Opportunities, and Research Directions,

    H. Wymeersch, J. He, B. Denis, A. Clemente, and M. Juntti, “Radio Localization and Mapping With Reconfigurable Intelligent Surfaces: Challenges, Opportunities, and Research Directions,”IEEE Veh. Technol. Mag., vol. 15, no. 4, pp. 52–61, 2020

    work page 2020

  45. [45]

    Automated machine learning: methods, systems, challenges,

    F. Hutter, L. Kotthoff, and J. Vanschoren, “Automated machine learning: methods, systems, challenges,”Springer Nature, 2019

    work page 2019

  46. [46]

    Practical Bayesian Optimiza- tion of Machine Learning Algorithms,

    J. Snoek, H. Larochelle, and R. P. Adams, “Practical Bayesian Optimiza- tion of Machine Learning Algorithms,”Curran Associates, Inc., vol. 25, 2012

    work page 2012

  47. [47]

    Hyperparameter Optimization,

    M. Feurer and F. Hutter, “Hyperparameter Optimization,”Springer Int. Publishing, pp. 3–33, 2019. [Online]. Available: https://doi.org/10. 1007/978-3-030-05318-5 1

    work page 2019

  48. [48]

    Recon- figurable Intelligent Surfaces for Rich Scattering Wireless Commu- nications: Recent Experiments, Challenges, and Opportunities,

    G. C. Alexandropoulos, N. Shlezinger, and P. del Hougne, “Recon- figurable Intelligent Surfaces for Rich Scattering Wireless Commu- nications: Recent Experiments, Challenges, and Opportunities,”IEEE Commun. Mag., vol. 59, no. 6, pp. 28–34, 2021

    work page 2021

  49. [49]

    Deep-Learning-Assisted Configuration of Reconfigurable Intelligent Surfaces in Dynamic Rich-Scattering Environments,

    K. Stylianopoulos, N. Shlezinger, P. del Hougne, and G. C. Alexan- dropoulos, “Deep-Learning-Assisted Configuration of Reconfigurable Intelligent Surfaces in Dynamic Rich-Scattering Environments,” in ICASSP 2022 - 2022 IEEE Int. Conf. Acoust., Speech, Signal Process. (ICASSP), 2022, pp. 8822–8826

    work page 2022

  50. [50]

    Adam: A Method for Stochastic Optimization

    D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” CoRR, vol. abs/1412.6980, 2014. Anum Umerreceived the B.E. degree in electri- cal (telecommunication) engineering and the M.S. degree in electrical engineering from the National University of Science and Technology (NUST), Pak- istan, in 2015 and 2017, respectively, where she was a Rese...

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  51. [51]

    Rapporteur

    Since 2019, he has been the Communication Systems Research Group Leader. He has over 15 years of combined academic and industrial multina- tional experiences while working in Denmark, Belgium, France, Qatar, and Estonia. He has several leading roles as PI in multimillion Euros international projects funded by European Commission (Horizon Europe LATEST-5GS...

    work page 2019