pith. machine review for the scientific record. sign in

arxiv: 2605.05055 · v1 · submitted 2026-05-06 · 💻 cs.LG · cs.AI· eess.SP

Recognition: unknown

Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework

Arsenia Chorti, Bac Trinh-Nguyen, Sara Berri, Sin G. Teo, Tram Truong-Huu

Authors on Pith no claims yet

Pith reviewed 2026-05-08 16:45 UTC · model grok-4.3

classification 💻 cs.LG cs.AIeess.SP
keywords AoA localizationadaptive learningonline learning5G networksmMIMO OFDMoutdoor localizationfew-shot learningchannel state information
0
0 comments X

The pith

An adaptive framework for AoA-based localization achieves high accuracy in outdoor 5G environments with either large or small training datasets through offline or online strategies.

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

The paper develops an adaptive framework for angle-of-arrival localization in massive MIMO OFDM outdoor settings that adapts to the amount of available training data. When large datasets exist, a hierarchical offline method first separates line-of-sight from non-line-of-sight regions and then performs finer position estimates within each region, supported by batch retraining and hyperparameter tuning. When only limited data is present, the framework switches to online incremental tree and ensemble models that process streaming channel measurements continuously, plus a few-shot component that initializes new location classes from small labeled sets. Tests on real outdoor channel state information show that the online path maintains accuracy while updating during operation, which matters because it removes the requirement for costly, large-scale data collection before service deployment in applications like smart transportation.

Core claim

The central claim is that an adaptive AoA-based localization system, using hierarchical offline learning for abundant data and incremental online models for scarce streaming data, delivers robust high-accuracy outdoor positioning on real mMIMO OFDM channel measurements and thereby enables effective localization without large upfront dataset collection campaigns.

What carries the argument

The adaptive framework that routes between a hierarchical offline classifier-localizer for large batches and incremental tree-based, ensemble, and few-shot models for handling streaming data and new classes.

If this is right

  • Localization services can start with minimal labeled data and improve accuracy as the network collects more measurements during normal operation.
  • Changing outdoor channel conditions can be handled through continuous model updates rather than periodic full retraining.
  • The same system architecture supports both data-rich and data-poor deployment scenarios without separate pipelines.
  • Fewer resources are needed for initial data gathering before launching location-based applications in 5G and 6G networks.

Where Pith is reading between the lines

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

  • The online approach might extend naturally to other wireless signals or frequency bands if similar hierarchical region distinctions are applied.
  • Integration with time-of-arrival or other features could provide fallback accuracy when angle information degrades in certain areas.
  • Long-term autonomous network self-calibration becomes feasible if the incremental models continue to adapt without human intervention.

Load-bearing premise

The online learning models can keep updating and maintain performance when continuously ingesting new streaming channel state information in real outdoor environments.

What would settle it

A clear and sustained drop in localization accuracy when the incremental models process additional real-world outdoor CSI streams over time would show that the online path does not deliver the claimed robustness.

Figures

Figures reproduced from arXiv: 2605.05055 by Arsenia Chorti, Bac Trinh-Nguyen, Sara Berri, Sin G. Teo, Tram Truong-Huu.

Figure 1
Figure 1. Figure 1: FIGURE 1: Overview of AoA-based localization framework. Offline learning performs batch training and retraining view at source ↗
Figure 2
Figure 2. Figure 2: FIGURE 2: Architecture of hierarchical two-stage clas view at source ↗
Figure 3
Figure 3. Figure 3: FIGURE 3: Architectures of the Conditional Genera view at source ↗
Figure 4
Figure 4. Figure 4: FIGURE 4: Architecture of prototypical networks (Pro view at source ↗
Figure 5
Figure 5. Figure 5: FIGURE 5: Nokia campus in Stuttgart, Germany. The red rectangle denotes the mMIMO antenna array mounted view at source ↗
Figure 6
Figure 6. Figure 6: FIGURE 6: Example of AoA estimation for track 11, view at source ↗
Figure 7
Figure 7. Figure 7: FIGURE 7: Compares original and synthetic samples view at source ↗
Figure 8
Figure 8. Figure 8: FIGURE 8: Compares original and synthetic AoA fea view at source ↗
Figure 9
Figure 9. Figure 9: FIGURE 9: t-SNE projection comparing real and synthetic AoA feature vectors (MUSIC) for the LoS and NLoS view at source ↗
Figure 10
Figure 10. Figure 10: FIGURE 10: Comparison of buffer and cumulative batch retraining for RF and SVM (mean accuracy over 10 trials view at source ↗
Figure 11
Figure 11. Figure 11: FIGURE 11: The hoeffding adaptive tree (HAT) classi view at source ↗
Figure 12
Figure 12. Figure 12: FIGURE 12: Online Accuracy (column chart) and Forgetting Rate (line chart) comparison across six incremental view at source ↗
Figure 13
Figure 13. Figure 13: FIGURE 13: Classification accuracy (mean view at source ↗
Figure 14
Figure 14. Figure 14: FIGURE 14: Evolution of the mean accuracy over training episodes for ProtoNet under three view at source ↗
read the original abstract

Localization in 5G and 6G networks is essential for important use cases such as intelligent transportation, smart factories, and smart cities. Although deep learning has enabled improving localization accuracy, depending on the deployment scenario and the effort required for dataset collection campaigns on a given infrastructure, the training process for localization models can vary significantly. Furthermore, with respect to feature selection, recent works have demonstrated the robustness of angle-of-arrival (AoA) based localization. In view of these two points, we propose an adaptive framework for AoA-based localization that consists of two alternative learning strategies, each suited either for large or small training datasets. The proposed framework is evaluated on a real, massive multiple input multiple output (mMIMO) orthogonal frequency division multiplexing (OFDM) outdoor channel state information (CSI) dataset. First, we investigate offline learning when large training datasets are available; we propose a hierarchical framework that first distinguishes between line of sight (LoS) and non line of sight (NLoS) regions and then moves to more fine grained localization in the respective region. This approach provides high-performance localization through accumulated batch retraining and an integrated hyperparameter optimization mechanism. Second, when only a small training dataset is available, an online learning framework is proposed, using incremental tree-based and ensemble-based models for handling streaming data and continuously updating mode, as well as an online few-shot learning model for rapidly initializing new classes from a limited labeled support set. These results showcase that highly accurate robust localization can be achieved incrementally during network operation by exploiting online learning, alleviating the need for large dataset collection campaigns.

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 / 1 minor

Summary. The paper proposes an adaptive framework for AoA-based outdoor localization using real mMIMO OFDM CSI data. For large datasets it describes a hierarchical offline strategy that first classifies LoS/NLoS regions and then performs fine-grained localization via batch retraining and hyperparameter optimization. For small datasets it introduces an online strategy based on incremental tree-based and ensemble models for streaming updates plus an online few-shot model for new classes. The central claim is that these online methods enable highly accurate and robust localization incrementally during network operation, thereby reducing the need for large data-collection campaigns.

Significance. If the online models are shown to sustain accuracy on streaming CSI without degradation, the work would be significant for practical 5G/6G deployment in dynamic outdoor settings by enabling continuous adaptation with limited initial data. The use of a real mMIMO OFDM dataset and the explicit coverage of both large- and small-data regimes are strengths that ground the framework in realistic conditions.

major comments (2)
  1. [Abstract] Abstract: the claims of 'highly accurate robust localization' and 'high-performance localization' are unsupported by any quantitative metrics, baselines, error bars, or specific results from the real dataset; without these numbers the central empirical claim cannot be assessed.
  2. [Online learning framework (Section 3.2 / Evaluation)] Online learning framework (Section 3.2 / Evaluation): the incremental tree-based, ensemble, and few-shot models are asserted to handle streaming data and continuous updates effectively, yet no results are provided on accuracy versus number of streamed samples, performance under concept drift (e.g., NLoS transitions), or long-term stability; this directly undermines the claim that online learning alleviates large dataset campaigns.
minor comments (1)
  1. [Abstract] The transition threshold between 'large' and 'small' training datasets is not quantified, leaving the choice between the two strategies unclear for practitioners.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive feedback on our manuscript. We provide point-by-point responses to the major comments and indicate the changes we will implement in the revised version.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claims of 'highly accurate robust localization' and 'high-performance localization' are unsupported by any quantitative metrics, baselines, error bars, or specific results from the real dataset; without these numbers the central empirical claim cannot be assessed.

    Authors: We agree with this observation. The abstract in the current version makes qualitative claims without embedding the supporting numbers from our experiments on the real mMIMO OFDM CSI dataset. To rectify this, we will revise the abstract to incorporate specific quantitative results, including localization accuracy figures, any error bars or statistics, and references to baselines used in the evaluation. This will allow readers to immediately assess the empirical claims. revision: yes

  2. Referee: [Online learning framework (Section 3.2 / Evaluation)] Online learning framework (Section 3.2 / Evaluation): the incremental tree-based, ensemble, and few-shot models are asserted to handle streaming data and continuous updates effectively, yet no results are provided on accuracy versus number of streamed samples, performance under concept drift (e.g., NLoS transitions), or long-term stability; this directly undermines the claim that online learning alleviates large dataset campaigns.

    Authors: We acknowledge the validity of this comment. Although the manuscript evaluates the online strategies on the small-data regime using the real dataset and reports overall high accuracy, it lacks the granular analyses requested, such as learning curves over streamed samples, explicit tests for concept drift in NLoS scenarios, and metrics for long-term stability. These details are crucial for supporting the practical benefits of the online approach. In the revised manuscript, we will add the corresponding experimental results and visualizations to demonstrate the incremental performance and robustness. revision: yes

Circularity Check

0 steps flagged

Empirical ML framework with no derivations or equations exhibits no circularity

full rationale

The paper presents an adaptive framework consisting of offline hierarchical LoS/NLoS classification plus fine-grained localization, and online incremental tree/ensemble/few-shot models for streaming CSI data. All claims rest on empirical evaluation against a real outdoor mMIMO OFDM dataset rather than any mathematical derivation chain. No equations, fitted parameters renamed as predictions, self-definitional loops, or load-bearing self-citations appear in the provided text. The central claim that online learning alleviates large dataset campaigns is therefore an empirical assertion, not a reduction to its own inputs by construction.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 0 invented entities

The framework rests on domain assumptions about AoA feature robustness and benefits of hierarchical/online learning without new theoretical support or independent evidence for the invented adaptive switching mechanism.

free parameters (1)
  • model hyperparameters
    Integrated hyperparameter optimization mechanism in the offline strategy; values are tuned but not specified as fixed inputs.
axioms (2)
  • domain assumption AoA-based features are robust for localization across LoS and NLoS regions
    Invoked when proposing the hierarchical framework and citing recent works on AoA robustness.
  • domain assumption Distinguishing LoS/NLoS first improves fine-grained localization accuracy
    Core premise of the offline hierarchical approach.

pith-pipeline@v0.9.0 · 5613 in / 1447 out tokens · 37357 ms · 2026-05-08T16:45:10.299492+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

55 extracted references · 3 canonical work pages · 1 internal anchor

  1. [1]

    Deep learning-based indoor localization using received signal strength and channel state information,

    C.-H. Hsieh, J.-Y. Chen, and B.-H. Nien, “Deep learning-based indoor localization using received signal strength and channel state information,” IEEE Access, vol. 7, pp. 33 256–33 267, 2019

    2019

  2. [2]

    ConFi: Convolutional neural networks based indoor Wi-Fi localization using channel state information,

    H. Chen, Y. Zhang, W. Li, X. Tao, and P. Zhang, “ConFi: Convolutional neural networks based indoor Wi-Fi localization using channel state information,” IEEE Access, vol. 5, pp. TABLE 15: The detailed performance of six incremental models is evaluated in the NLoS condition with MUSIC / ESPRIT, including warm-up training accuracy (Training Acc), online infe...

    2098

  3. [3]

    Physical Layer Security—From Theory to Practice,

    M. Mitev, T. M. Pham, A. Chorti, A. N. Barreto, and G. Fet- tweis, “Physical Layer Security—From Theory to Practice,” IEEE BITS the Information Theory Magazine, vol. 3, no. 2, pp. 67–79, 2023

    2023

  4. [4]

    How Physicality Enables Cy-Trust: A New Era of Trust-Centered Cyber–Physical Systems,

    S. Gil, M. Yemini, A. Chorti, A. Nedić, H. V. Poor, and A. J. Goldsmith, “How Physicality Enables Cy-Trust: A New Era of Trust-Centered Cyber–Physical Systems,” Proceedings of the IEEE, vol. 113, no. 10, pp. 1121–1154, 2025

    2025

  5. [5]

    Machine Learning-Based Robust Physical Layer Authentication Using Angle of Arrival Estimation,

    T. M. Pham, L. Senigagliesi, M. Baldi, G. P. Fettweis, and A. Chorti, “Machine Learning-Based Robust Physical Layer Authentication Using Angle of Arrival Estimation,” in IEEE GLOBECOM 2023, 2023

    2023

  6. [6]

    Aoa-based physical layer authentication in analog arrays under impersonation attacks,

    M. Srinivasan, L. Senigagliesi, H. Chen, A. Chorti, M. Baldi, and H. Wymeersch, “Aoa-based physical layer authentication in analog arrays under impersonation attacks,” in 2024 IEEE 25th International Workshop on Signal Processing Advances in Wireless Communications (SPA WC), 2024, pp. 496–500

    2024

  7. [7]

    T. M. Pham, L. Senigagliesi, M. Baldi, R. F. Schaefer, G. P. Fettweis, and A. Chorti, “Leveraging angle of arrival estimation against impersonation attacks in physical layer VOLUME , 21 Bac TN et al. : Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework authentication,” IEEE Transactions on Information Forensics and ...

    2026

  8. [8]

    On the robustness of aoa as an authentication feature under spoofing: Fundamental limits from misspecified cramer rao theory,

    S. Skaperas and A. Chorti, “On the robustness of aoa as an authentication feature under spoofing: Fundamental limits from misspecified cramer rao theory,” 2026. [Online]. A vailable:https://arxiv.org/abs/2603.21219

    work page arXiv 2026

  9. [9]

    A systematic survey and comparative analysis of angular-based indoor local- ization and positioning technologies,

    G. K. Fischer, T. Schaechtle, A. Gabbrielli, J. Bordoy, I. Häring, F. Höflinger, and S. J. Rupitsch, “A systematic survey and comparative analysis of angular-based indoor local- ization and positioning technologies,” IEEE Communications Surveys & Tutorials, 2025

    2025

  10. [10]

    High-Precision Indoor Localization via Dual-Modal AOA/TOA Fusion with Deep Learning and Particle Filters

    X. YAO, Z. XU, and F. QIANG, “High-Precision Indoor Localization via Dual-Modal AOA/TOA Fusion with Deep Learning and Particle Filters. ” Radioengineering, vol. 34, no. 4, 2025

    2025

  11. [11]

    Deep Learning-Enhanced Indoor Localization Using Joint AOA-TOA Fingerprints,

    D. Liu, L. Wu, and Z. Zhang, “Deep Learning-Enhanced Indoor Localization Using Joint AOA-TOA Fingerprints,” in 2025 6th Information Communication Technologies Confer- ence (ICTC), 2025, pp. 184–189

    2025

  12. [12]

    A Comprehensive Survey of Machine Learning Based Localization With Wireless Signals,

    D. Burghal, A. T. Ravi, V. Rao, A. A. Alghafis, and A. F. Molisch, “A Comprehensive Survey of Machine Learning Based Localization With Wireless Signals,” arXiv preprint arXiv:2012.11171, 2020

    work page arXiv 2012

  13. [13]

    CSI-MIMO: K- Nearest Neighbor Applied to Indoor Localization,

    A. Sobehy, É. Renault, and P. Mühlethaler, “CSI-MIMO: K- Nearest Neighbor Applied to Indoor Localization,” in IEEE ICC 2020, 2020

    2020

  14. [14]

    A Survey of Recent Indoor Localization Scenarios and Methodologies,

    T. Yang, A. Cabani, and H. Chafouk, “A Survey of Recent Indoor Localization Scenarios and Methodologies,” Sensors, vol. 21, 2021

    2021

  15. [15]

    Mobintel: Passive Outdoor Localization via RSSI and Machine Learning,

    F. Bao, S. Mazokha, and J. O. Hallstrom, “Mobintel: Passive Outdoor Localization via RSSI and Machine Learning,” in Proc. IEEE WiMob 2021, 2021, pp. 247–252

    2021

  16. [16]

    Multipath-Based CSI Fingerprinting Localization With a Machine Learning Approach,

    S. Chen, J. Fan, X. Luo, and Y. Zhang, “Multipath-Based CSI Fingerprinting Localization With a Machine Learning Approach,” in 2018 Wireless Advanced (WiAd), 2018

    2018

  17. [17]

    Continual learning-based MIMO channel estimation: A benchmarking study,

    M. Akrout, A. Feriani, F. Bellili, A. Mezghani, and E. Hos- sain, “Continual learning-based MIMO channel estimation: A benchmarking study,” in IEEE ICC 2023, 2023, pp. 2631–2636

    2023

  18. [18]

    CSI- based cross-scene human activity recognition with incremental learning,

    Y. Zhang, F. He, Y. Wang, D. Wu, and G. Yu, “CSI- based cross-scene human activity recognition with incremental learning,” Neural Computing and Applications, vol. 35, no. 17, pp. 12 415–12 432, 2023

    2023

  19. [19]

    CAREC: Continual Wireless Action Recognition with Expansion– Compression Coordination,

    T. Zhang, Q. Fu, H. Ding, G. Wang, and F. Wang, “CAREC: Continual Wireless Action Recognition with Expansion– Compression Coordination,” Sensors, vol. 25, no. 15, p. 4706, 2025

    2025

  20. [20]

    Continual Learning for Wireless Channel Prediction,

    M. A. Mohsin, M. Umer, A. Bilal, M. A. Jamshed, and J. M. Cioffi, “Continual Learning for Wireless Channel Prediction,” in Proc. 42nd International Conference on Machine Learning, Vancouver, 2025

    2025

  21. [21]

    Overcoming catastrophic for- getting in neural networks,

    J. Kirkpatrick, R. Pascanu, N. Rabinowitz, J. Veness, G. Des- jardins, A. A. Rusu, K. Milan, J. Quan, T. Ramalho, A. Grabska-Barwinska et al., “Overcoming catastrophic for- getting in neural networks,” Proceedings of the national academy of sciences, vol. 114, no. 13, 2017

    2017

  22. [22]

    Memory aware synapses: Learning what (not) to forget,

    R. Aljundi, F. Babiloni, M. Elhoseiny, M. Rohrbach, and T. Tuytelaars, “Memory aware synapses: Learning what (not) to forget,” in Proc. of the European Conference on Computer Vision (ECCV), 2018

    2018

  23. [23]

    icarl: Incremental classifier and representation learning,

    S.-A. Rebuffi, A. Kolesnikov, G. Sperl, and C. H. Lampert, “icarl: Incremental classifier and representation learning,” in Proc. IEEE conference on Computer Vision and Pattern Recognition, 2017

    2017

  24. [24]

    Mining time- changing data streams,

    G. Hulten, L. Spencer, and P. Domingos, “Mining time- changing data streams,” in Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining, 2001

    2001

  25. [25]

    Adaptive learning from evolving data streams,

    A. Bifet and R. Gavalda, “Adaptive learning from evolving data streams,” in International symposium on intelligent data analysis. Springer, 2009, pp. 249–260

    2009

  26. [26]

    Adaptive ran- dom forests for evolving data stream classification,

    H. M. Gomes, A. Bifet, J. Read, J. P. Barddal, F. Enembreck, B. Pfharinger, G. Holmes, and T. Abdessalem, “Adaptive ran- dom forests for evolving data stream classification,” Machine Learning, vol. 106, no. 9, pp. 1469–1495, 2017

    2017

  27. [27]

    Streaming random patches for evolving data stream classification,

    H. M. Gomes, J. Read, and A. Bifet, “Streaming random patches for evolving data stream classification,” in 2019 IEEE international conference on data mining (ICDM). IEEE, 2019, pp. 240–249

    2019

  28. [28]

    AMF: Aggregated Mondrian forests for online learning,

    J. Mourtada, S. Gaïffas, and E. Scornet, “AMF: Aggregated Mondrian forests for online learning,” Journal of the Royal Statistical Society Series B: Statistical Methodology, vol. 83, no. 3, pp. 505–533, 2021

    2021

  29. [29]

    River: machine learning for streaming data in Python,

    J. Montiel, M. Halford, S. M. Mastelini, G. Bolmier, R. Sourty, R. Vaysse, A. Zouitine, H. M. Gomes, J. Read, T. Abdessalem et al., “River: machine learning for streaming data in Python,” 2021

    2021

  30. [30]

    Meta-learning approaches for few-shot learning: A survey of recent advances,

    H. Gharoun, F. Momenifar, F. Chen, and A. H. Gandomi, “Meta-learning approaches for few-shot learning: A survey of recent advances,” ACM Computing Surveys, vol. 56, no. 12, pp. 1–41, 2024

    2024

  31. [31]

    Prototypical networks for few-shot learning,

    J. Snell, K. Swersky, and R. Zemel, “Prototypical networks for few-shot learning,” Advances in neural information processing systems, vol. 30, 2017

    2017

  32. [32]

    Model-agnostic meta- learning for fast adaptation of deep networks,

    C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta- learning for fast adaptation of deep networks,” in International conference on machine learning. PMLR, 2017, pp. 1126–1135

    2017

  33. [33]

    Few-shot learning in wi-fi-based indoor positioning,

    F. Xie, S. H. Lam, M. Xie, and C. Wang, “Few-shot learning in wi-fi-based indoor positioning,” Biomimetics, vol. 9, no. 9, p. 551, 2024

    2024

  34. [34]

    MetaLoc: Learning to learn wireless localization,

    J. Gao, D. Wu, F. Yin, Q. Kong, L. Xu, and S. Cui, “MetaLoc: Learning to learn wireless localization,” IEEE Journal on Selected Areas in Communications, vol. 41, no. 12, pp. 3831– 3847, 2023

    2023

  35. [35]

    Profi-net: Prototype-based feature attention with curriculum augmen- tation for wifi-based gesture recognition,

    Z. Cui, S. Zhang, K. Lou, and L.-N. Tran, “Profi-net: Prototype-based feature attention with curriculum augmen- tation for wifi-based gesture recognition,” in Asia-Pacific Web (APWeb) and Web-Age Information Management (W AIM) Joint International Conference on Web and Big Data. Springer, 2025, pp. 191–204

    2025

  36. [36]

    Lightweight and Gener- alizable AoA Estimation for IoT: A Novel Few-Shot Learning Approach,

    O. Mashaal, E. Mohammed, A. Digby, P. Leone, L. Swersky, A. Eshaghbeigi, and H. Abou-Zeid, “Lightweight and Gener- alizable AoA Estimation for IoT: A Novel Few-Shot Learning Approach,” in ICC 2025-IEEE International Conference on Communications, 2025

    2025

  37. [37]

    Generative adversarial networks,

    I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde- Farley, S. Ozair, A. Courville, and Y. Bengio, “Generative adversarial networks,” Communications of the ACM, vol. 63, no. 11, 2020

    2020

  38. [38]

    Variational autoencoder,

    L. Pinheiro Cinelli, M. Araújo Marins, E. A. Barros da Silva, and S. Lima Netto, “Variational autoencoder,” in Variational methods for machine learning with applications to deep net- works. Springer, 2021

    2021

  39. [39]

    Conditional Generative Adversarial Nets

    M. Mirza and S. Osindero, “Conditional generative adversarial nets,” arXiv preprint arXiv:1411.1784, 2014

    work page internal anchor Pith review arXiv 2014

  40. [40]

    Learning structured output representation using deep conditional generative models,

    K. Sohn, H. Lee, and X. Yan, “Learning structured output representation using deep conditional generative models,” Advances in neural information processing systems, vol. 28, 2015

    2015

  41. [41]

    Generative AI enabled robust data augmen- tation for wireless sensing in ISAC networks,

    J. Wang, C. Zhao, H. Du, G. Sun, J. Kang, S. Mao, D. Niyato, and D. I. Kim, “Generative AI enabled robust data augmen- tation for wireless sensing in ISAC networks,” IEEE Journal on Selected Areas in Communications, 2025

    2025

  42. [42]

    A survey on data augmentation for WiFi fingerprinting indoor positioning,

    X. Feng, K. A. Nguyen, and Z. Luo, “A survey on data augmentation for WiFi fingerprinting indoor positioning,” IEEE Sensors Reviews, vol. 2, pp. 246 – 264, June 2025

    2025

  43. [43]

    High-accuracy aoa-based localization using hier- archical ml classifiers in outdoor environments,

    B. Trinh-Nguyen, S. Berri, S. G. Teo, T. Truong-Huu, and A. Chorti, “High-accuracy aoa-based localization using hier- archical ml classifiers in outdoor environments,” in GLOBE- COM 2025-2025 IEEE Global Communications Conference. IEEE, 2025, pp. 2180–2185

    2025

  44. [44]

    Multiple Emitter Location and Signal Parameter Estimation,

    R. Schmidt, “Multiple Emitter Location and Signal Parameter Estimation,” IEEE Trans. Antennas Propag., vol. 34, no. 3, 1986

    1986

  45. [45]

    ESPRIT-Estimation of Signal Pa- rameters via Rotational Invariance Techniques,

    R. Roy and T. Kailath, “ESPRIT-Estimation of Signal Pa- rameters via Rotational Invariance Techniques,” IEEE Trans. Acoust., Speech, Signal. Process., vol. 37, no. 7, pp. 984–995, 1989. 22 VOLUME ,

    1989

  46. [46]

    Stacked Generalization,

    D. H. Wolpert, “Stacked Generalization,” Neural Networks, 1992

    1992

  47. [47]

    Owen, Hyperparameter Tuning with Python: Boost your machine learning model’s performance via hyperparameter tuning

    L. Owen, Hyperparameter Tuning with Python: Boost your machine learning model’s performance via hyperparameter tuning. Packt Publishing Ltd, 2022

    2022

  48. [48]

    Op- tuna: A next-generation hyperparameter optimization frame- work,

    T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Op- tuna: A next-generation hyperparameter optimization frame- work,” in The 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2623–2631

    2019

  49. [49]

    Wasserstein gen- erative adversarial networks,

    M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein gen- erative adversarial networks,” in International conference on machine learning. PMLR, 2017, pp. 214–223

    2017

  50. [50]

    Improved training of wasserstein gans,

    I. Gulrajani, F. Ahmed, M. Arjovsky, V. Dumoulin, and A. C. Courville, “Improved training of wasserstein gans,” Advances in neural information processing systems, vol. 30, 2017

    2017

  51. [51]

    Variational dropout and the local reparameterization trick,

    D. P. Kingma, T. Salimans, and M. Welling, “Variational dropout and the local reparameterization trick,” Advances in neural information processing systems, vol. 28, 2015

    2015

  52. [52]

    ML- Based Massive MIMO Channel Prediction: Does It Work on Real-World Data?

    M. K. Shehzad, L. Rose, S. Wesemann, and M. Assaad, “ML- Based Massive MIMO Channel Prediction: Does It Work on Real-World Data?” IEEE Wireless Communications Letters, vol. 11, no. 4, 2022

    2022

  53. [53]

    Multiclass classifica- tion - River — riverml.xyz,

    T. F. of Online Machine Learning, “Multiclass classifica- tion - River — riverml.xyz,” https://riverml.xyz/0.23.0/ benchmarks/{M}ulticlass%20classification/, [Accessed 11-02- 2026]

    2026

  54. [54]

    A Framework for Global Trust and Reputation Management in 6G Networks,

    B. Trinh-Nguyen, S. Berri, S. G. Teo, T. Truong-Huu, and A. Chorti, “A Framework for Global Trust and Reputation Management in 6G Networks,” in 7th International Confer- ence on Machine Learning for Networking (MLN 2024), Reims, France, 2024. Bac Trinh-Nguyen received his B.Sc. and M.Sc. degrees from the University of Infor- mation Technology, VNU-HCM in ...

    2024

  55. [55]

    Standard profiles for ISO 8583 authentication services

    and member of the IEEE Teaching Awards Committee (2017- 19). She is currently member of various ITU Working Groups including on CGDatasets. She has participated in the reduction of the ITU report M.2516-0 on Future technology trends of terrestrial International Mobile Telecommunications systems towards 2030 and beyond (section on trustworthiness). She has...

    2017