Pith. sign in

REVIEW 1 major objections 2 minor 49 references

A neural network shares parameters between real and imaginary parts of complex signals to reduce generalization error while keeping full expressive capacity.

Reviewed by Pith at T0; open to challenge. T0 means a machine referee read the full paper against a public rubric. the ladder, T0–T4 →

Challenge this review Re-run · record.json Download PDF Read on arXiv ↗

T0 review · grok-4.3

2026-07-01 06:04 UTC pith:IAN7KNTL

load-bearing objection DualNN's parameter-sharing idea for IQ channels is the actual novelty, but the claimed reduction in generalization error has no visible derivation. the 1 major comments →

arxiv 2606.31352 v1 pith:IAN7KNTL submitted 2026-06-30 cs.LG eess.SP

Dualformer: Efficient Feature Extractor for Complex-valued Blind Communication Signal Analysis

Yurui Zhao , Xiang Wang , Jingreng Lei , Wanlong Zhang , Yik-Chung Wu , Zhitao Huang This is my paper
classification cs.LG eess.SP
keywords complex-valued signalsparameter sharingdual-channel networktransformerautomatic modulation recognitionblind signal analysisgeneralization error
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

The pith

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

The paper presents DualNN as a way to handle complex-valued communication signals by using the same network weights for the real and imaginary channels. This sharing is said to lower generalization error compared with separate real-valued or complex-valued networks, yet the model can still represent the full range of functions needed for the task. The authors build Dualformer, a Transformer that splits signals into patch tokens and extracts features at different scales, to put DualNN into practice. Tests on automatic modulation recognition, signal scheme recognition, and signal structure parsing show steady gains over several baselines. The same modular structure also works for related blind tasks such as source separation and low-SNR spectrum sensing.

Core claim

DualNN reduces generalization error by sharing parameters across the real and imaginary parts of complex-valued inputs while preserving the network's expressive capacity; the Dualformer architecture realizes this idea through patch-level tokenization and multi-granularity feature capture, delivering consistent improvements on AMR, SSR, and SSP tasks and extending to other blind signal problems.

What carries the argument

DualNN, the framework that shares network parameters for processing the real and imaginary parts of complex-valued signals.

Load-bearing premise

Parameter sharing between the real and imaginary channels reduces generalization error while leaving the network's expressive capacity unchanged.

What would settle it

A controlled experiment in which a model without the parameter sharing achieves equal or lower generalization error on the same complex signal datasets would disprove the claimed benefit.

Watch this falsifier. Get emailed when new claim-graph text bears on it.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit.

Referee Report

1 major / 2 minor

Summary. The manuscript proposes DualNN, a dual-channel neural network architecture that shares parameters across the real (I) and imaginary (Q) channels when processing complex-valued signals for blind analysis tasks including automatic modulation recognition (AMR), signal scheme recognition (SSR), and signal structure parsing (SSP). It implements this idea via Dualformer, a Transformer-based model that tokenizes signals into patches to capture multi-granularity features. The authors assert that parameter sharing is theoretically shown to reduce generalization error while preserving expressive capacity, report consistent empirical gains over three Transformer baselines and four conventional DL methods, and claim the modular design extends to tasks such as blind source separation and low-SNR spectrum sensing.

Significance. If a rigorous derivation of the claimed generalization benefit were supplied, the parameter-sharing construction could offer a principled efficiency gain for complex-valued signal models. The multi-task experimental scope and modular framing suggest potential utility in communications applications, but the absence of the promised theoretical support leaves the core novelty unsubstantiated.

major comments (1)
  1. [Abstract] Abstract: the claim that DualNN 'is theoretically shown to reduce generalization error while preserving expressive capacity' via parameter sharing across IQ channels is asserted without any derivation, complexity bound, proof sketch, or section reference. This assertion is load-bearing for the paper's positioning as a 'groundbreaking framework' yet cannot be evaluated against standard real-valued, complex-valued, or independent dual-channel baselines.
minor comments (2)
  1. The abstract states that 'extensive experiments' demonstrate 'consistent performance improvements' but supplies no quantitative metrics, error bars, dataset sizes, or named baselines, hindering assessment of the practical gains.
  2. The distinction between the general DualNN framework and its specific Dualformer instantiation is introduced without an explicit definition or diagram in the opening paragraph.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the careful reading and for identifying the unsubstantiated theoretical claim in the abstract. We respond to the single major comment below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that DualNN 'is theoretically shown to reduce generalization error while preserving expressive capacity' via parameter sharing across IQ channels is asserted without any derivation, complexity bound, proof sketch, or section reference. This assertion is load-bearing for the paper's positioning as a 'groundbreaking framework' yet cannot be evaluated against standard real-valued, complex-valued, or independent dual-channel baselines.

    Authors: We agree that the abstract currently asserts a theoretical result without derivation, bound, sketch, or section reference, making the claim impossible to evaluate. In the revised manuscript we will add either a short proof sketch (analyzing effective parameter count and generalization gap under shared vs. independent weights) or an appendix containing the argument, together with an explicit section reference in the abstract. If a complete derivation cannot be included without exceeding length limits, we will revise the abstract wording to remove the unsubstantiated claim and instead state that parameter sharing yields empirical gains while preserving dual-channel expressivity. The empirical comparisons to the listed baselines will remain unchanged. revision: yes

Circularity Check

0 steps flagged

No circularity: theoretical claim asserted without any derivation chain or self-referential reduction present

full rationale

The abstract asserts that DualNN 'is theoretically shown to reduce generalization error while preserving expressive capacity' via parameter sharing, but provides no equations, proof sketch, Rademacher bound, capacity equivalence, or section reference establishing this. No load-bearing derivation step exists in the provided text that could reduce to a fit, self-definition, or self-citation chain. Without any visible chain of equations or reductions to inspect, none of the enumerated circularity patterns apply. The central claim remains an unsupported assertion rather than a circular derivation.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract alone supplies no information on free parameters, axioms, or invented entities; no equations or modeling choices are described.

pith-pipeline@v0.9.1-grok · 5768 in / 1219 out tokens · 34530 ms · 2026-07-01T06:04:49.184503+00:00 · methodology

0 comments
read the original abstract

Designing effective feature extractors is critical for blind signal analysis tasks such as automatic modulation recognition (AMR), signal scheme recognition (SSR), and \color{black} signal structure parsing (SSP). In this work, we propose dual-channel neural network (DualNN) that efficiently exploits complex-valued signals through parameter sharing across IQ channels. Unlike traditional real-valued or complex-valued models, DualNN is a groundbreaking framework which shares the network parameters for processing the real and imaginary parts of the complex-valued signals, and is theoretically shown to reduce generalization error while preserving expressive capacity. Specifically, we propose a novel Transformer-based architecture to implement DualNN, called Dualformer. The Dualformer segments input signals into patch-level tokens and captures multi-granularity features, enabling robust performance across diverse signal analysis tasks. Furthermore, we conduct extensive experiments comparing Dualformer with three Transformer-based baselines and four conventional DL-based approaches. Results demonstrate consistent performance improvements on AMR, SSR, and SSP tasks. Besides, the modular design of DualNN allows it to generalize well to blind signal processing tasks such as blind source separation and low-SNR spectrum sensing. This work paves the way for a broader application of DualNN architectures in unsupervised and weakly supervised complex-valued signal analysis scenarios.

Figures

Figures reproduced from arXiv: 2606.31352 by Jingreng Lei, Wanlong Zhang, Xiang Wang, Yik-Chung Wu, Yurui Zhao, Zhitao Huang.

Figure 1
Figure 1. Figure 1: Schematic plot of the feature extractor in blind communication signal analysis. [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Comparison of real-valued and complex-valued paradigms. (a) RVNN. [PITH_FULL_IMAGE:figures/full_fig_p002_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Architecture of DualNN for communication signal analysis. [PITH_FULL_IMAGE:figures/full_fig_p004_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Visualization of generalization error for real-valued, complex-valued, [PITH_FULL_IMAGE:figures/full_fig_p005_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Pipeline of Dualformer-based feature extraction in blind communication signal analysis. [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Training dynamics of RVNN, CVNN, DualNN, and DualNN￾Comparable under optimal hyperparameter configurations. 2) Sample Efficiency: To evaluate the sample efficiency of each model, we trained RVNN, CVNN, and DualNN under varying levels of data availability, specifically with 500, 1000, 2000, 4000, 6000, 8000, and 10000 samples per class. The results are presented in [PITH_FULL_IMAGE:figures/full_fig_p010_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Classification accuracy of RVNN, CVNN, and DualNN as a function of dataset size, evaluated at 7 data scales, i.e. 500, 1000, 2000, 4000, 6000, 8000, and 10000 samples per class. 3) Effect of I/Q Imbalance: In practical communication sys￾tems, hardware imperfections inevitably introduce I/Q imbal￾ance into the received signal [43], [44]. Under such conditions, the signal xc(n) in Eq. (3) can be expressed as… view at source ↗
Figure 9
Figure 9. Figure 9: Comparison of real-valued, complex-valued, and Dualformer archi [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of real-valued, complex-valued, and Dualformer archi [PITH_FULL_IMAGE:figures/full_fig_p014_10.png] view at source ↗

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

49 extracted references · 49 canonical work pages · 2 internal anchors

  1. [1]

    Integrated sensing and communications: Toward dual-functional wire- less networks for 6g and beyond,

    F. Liu, Y . Cui, C. Masouros, J. Xu, T. X. Han, Y . C. Eldar, and S. Buzzi, “Integrated sensing and communications: Toward dual-functional wire- less networks for 6g and beyond,”IEEE journal on selected areas in communications, vol. 40, no. 6, pp. 1728–1767, 2022

    work page 2022

  2. [2]

    Blind spectrum sensing algorithms for cognitive radio networks,

    P. De and Y .-C. Liang, “Blind spectrum sensing algorithms for cognitive radio networks,”IEEE transactions on vehicular technology, vol. 57, no. 5, pp. 2834–2842, 2008. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 13 (a) (b) Fig. 8. Comparison of real-valued, complex-valued, and Dualformer archi- tectures in AMR. (a) Accuracy. (b) F1-score

    work page 2008

  3. [3]

    Blind spectrum sensing approaches for interweaved cognitive radio system: A tutorial and short course,

    F. Awin, E. Abdel-Raheem, and K. Tepe, “Blind spectrum sensing approaches for interweaved cognitive radio system: A tutorial and short course,”IEEE Communications Surveys & Tutorials, vol. 21, no. 1, pp. 238–259, 2018

    work page 2018

  4. [4]

    6g wireless communication systems: Applications, requirements, technolo- gies, challenges, and research directions,

    M. Z. Chowdhury, M. Shahjalal, S. Ahmed, and Y . M. Jang, “6g wireless communication systems: Applications, requirements, technolo- gies, challenges, and research directions,”IEEE Open Journal of the Communications Society, vol. 1, pp. 957–975, 2020

    work page 2020

  5. [5]

    A Unified Distributed Algorithm for Hybrid Near-Far Field Activity Detection in Cell-Free Massive MIMO

    J. Lei, Y . Li, Z. Wang, Q. Lin, Y .-F. Liu, and Y .-C. Wu, “A unified distributed algorithm for hybrid near-far field activity detection in cell- free massive mimo,”arXiv preprint arXiv:2509.15162, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  6. [6]

    Predicting ordinary differential equations with transformers,

    S. Becker, M. Klein, A. Neitz, G. Parascandolo, and N. Kilbertus, “Predicting ordinary differential equations with transformers,” 2023, published at the 40th International Conference on Machine Learning (ICML 2023). [Online]. Available: https://arxiv.org/abs/2307.12617

    work page arXiv 2023

  7. [7]

    Fluid-gpt (fast learning to understand and investigate dynamics with a generative pre-trained transformer): Efficient predictions of particle trajectories and erosion,

    S. D. Yang, Z. A. Ali, and B. M. Wong, “Fluid-gpt (fast learning to understand and investigate dynamics with a generative pre-trained transformer): Efficient predictions of particle trajectories and erosion,” Industrial & Engineering Chemistry Research, vol. 62, no. 37, pp. 15 278–15 289, 2023

    work page 2023

  8. [8]

    A time series is worth 64 words: Long-term forecasting with transformers,

    Y . Nie, N. H. Nguyen, P. Sinthong, and J. Kalagnanam, “A time series is worth 64 words: Long-term forecasting with transformers,” inThe Eleventh International Conference on Learning Representations (ICLR), 2023, accepted for publication at ICLR 2023. [Online]. Available: https://openreview.net/forum?id=Jbdc0vTOcol

    work page 2023

  9. [9]

    iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

    Y . Liu, T. Hu, H. Zhang, H. Wu, S. Wang, L. Ma, and M. Long, “itransformer: Inverted transformers are effective for time series forecasting,” 2023. [Online]. Available: https://arxiv.org/abs/2310.06625

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  10. [10]

    Convolutional radio mod- ulation recognition networks,

    T. J. O’Shea, J. Corgan, and T. C. Clancy, “Convolutional radio mod- ulation recognition networks,” inEngineering Applications of Neural Networks: 17th International Conference, EANN 2016, Aberdeen, UK, September 2-5, 2016, Proceedings 17. Springer, 2016, pp. 213–226. (a) (b) Fig. 9. Comparison of real-valued, complex-valued, and Dualformer archi- tecture...

    work page 2016

  11. [11]

    Class information guided reconstruction for automatic modulation open-set recognition,

    Z. Zhang, M. Zhu, J. Liu, Y . Li, and S. Wang, “Class information guided reconstruction for automatic modulation open-set recognition,”IEEE Transactions on Cognitive Communications and Networking, 2024

    work page 2024

  12. [12]

    An improved neural network pruning technology for automatic modulation classification in edge devices,

    Y . Lin, Y . Tu, and Z. Dou, “An improved neural network pruning technology for automatic modulation classification in edge devices,” IEEE Transactions on Vehicular Technology, vol. 69, no. 5, pp. 5703– 5706, 2020

    work page 2020

  13. [13]

    Deep learning models for wireless signal classification with distributed low- cost spectrum sensors,

    S. Rajendran, W. Meert, D. Giustiniano, V . Lenders, and S. Pollin, “Deep learning models for wireless signal classification with distributed low- cost spectrum sensors,”IEEE Transactions on Cognitive Communica- tions and Networking, vol. 4, no. 3, pp. 433–445, 2018

    work page 2018

  14. [14]

    Real-time radio technology and modulation classification via an lstm auto-encoder,

    Z. Ke and H. Vikalo, “Real-time radio technology and modulation classification via an lstm auto-encoder,”IEEE Transactions on Wireless Communications, vol. 21, no. 1, pp. 370–382, 2021

    work page 2021

  15. [15]

    Automatic modulation classification using cnn-lstm based dual-stream structure,

    Z. Zhang, H. Luo, C. Wang, C. Gan, and Y . Xiang, “Automatic modulation classification using cnn-lstm based dual-stream structure,” IEEE Transactions on Vehicular Technology, vol. 69, no. 11, pp. 13 521– 13 531, 2020

    work page 2020

  16. [16]

    Multidimensional cnn-lstm network for automatic modulation classification,

    N. Wang, Y . Liu, L. Ma, Y . Yang, and H. Wang, “Multidimensional cnn-lstm network for automatic modulation classification,”Electronics, vol. 10, no. 14, p. 1649, 2021

    work page 2021

  17. [17]

    Transformer-based radio modulation mode recognition,

    L. Li, C. Qin, G. Li, S. Hu, Y . Xie, and Z. Lei, “Transformer-based radio modulation mode recognition,” inJournal of Physics: Conference Series, vol. 2384, no. 1. IOP Publishing, 2022, p. 012017

    work page 2022

  18. [18]

    Tmrn-glu: A transformer-based auto- matic classification recognition network improved by gate linear unit,

    Y . Zheng, Y . Ma, and C. Tian, “Tmrn-glu: A transformer-based auto- matic classification recognition network improved by gate linear unit,” Electronics, vol. 11, no. 10, p. 1554, 2022

    work page 2022

  19. [19]

    Abandon locality: Frame-wise embedding aided transformer for automatic modulation recognition,

    Y . Chen, B. Dong, C. Liu, W. Xiong, and S. Li, “Abandon locality: Frame-wise embedding aided transformer for automatic modulation recognition,”IEEE Communications Letters, vol. 27, no. 1, pp. 327– 331, 2022

    work page 2022

  20. [20]

    Complex-valued networks for automatic modulation classification,

    Y . Tu, Y . Lin, C. Hou, and S. Mao, “Complex-valued networks for automatic modulation classification,”IEEE Transactions on Vehicular Technology, vol. 69, no. 9, pp. 10 085–10 089, 2020

    work page 2020

  21. [21]

    C. Xiao, S. Yang, and Z. Feng, “Complex-valued depthwise separable JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 14 (a) (b) (c) Fig. 10. Comparison of real-valued, complex-valued, and Dualformer archi- tectures in SSP. (a) RQ. (b) SQ. (c) PQ. convolutional neural network for automatic modulation classification,” IEEE Transactions on Instrument...

    work page 2021

  22. [22]

    Complex- valued convolution and frequency global filter for automatic modulation recognition,

    Q. Luo, M.-M. Zhao, Z. Chen, Z. Su, and M.-J. Zhao, “Complex- valued convolution and frequency global filter for automatic modulation recognition,”IEEE Communications Letters, vol. 27, no. 7, pp. 1779– 1783, 2023

    work page 2023

  23. [23]

    Complex-valued parallel convolutional recurrent neural networks for automatic modulation classification,

    Y . Ren, W. Jiang, and Y . Liu, “Complex-valued parallel convolutional recurrent neural networks for automatic modulation classification,” in 2022 IEEE 25th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, 2022, pp. 804–809

    work page 2022

  24. [24]

    Automatic modulation mode recognition of communication signals based on complex-valued neural network,

    X. Yang, R. Zhang, H. Xie, H. Sun, and H. Li, “Automatic modulation mode recognition of communication signals based on complex-valued neural network,” in2022 International Conference on Computing, Com- munication, Perception and Quantum Technology (CCPQT). IEEE, 2022, pp. 32–37

    work page 2022

  25. [25]

    A novel complex- valued hybrid neural network for automatic modulation classification,

    Z. Xu, S. Hou, S. Fang, H. Hu, and Z. Ma, “A novel complex- valued hybrid neural network for automatic modulation classification,” Electronics, vol. 12, no. 20, p. 4380, 2023

    work page 2023

  26. [26]

    Understanding complex-valued transformer for modulation recognition,

    J. Lei, Y . Li, L.-Y . Yung, Y . Leng, Q. Lin, and Y .-C. Wu, “Understanding complex-valued transformer for modulation recognition,”IEEE Wireless Communications Letters, 2024

    work page 2024

  27. [27]

    Unveiling (a) (b) (c) Fig. 11. Comparison of Transformer-based architectures in SSP. (a) RQ. (b) SQ. (c) PQ. the power of complex-valued transformers in wireless communications,

    Y . Leng, Q. Lin, L.-Y . Yung, J. Lei, Y . Li, and Y .-C. Wu, “Unveiling (a) (b) (c) Fig. 11. Comparison of Transformer-based architectures in SSP. (a) RQ. (b) SQ. (c) PQ. the power of complex-valued transformers in wireless communications,” IEEE Transactions on Communications, vol. 74, pp. 612–627, 2026

    work page 2026

  28. [28]

    A complex-valued transformer for automatic modulation recognition,

    W. Li, W. Deng, K. Wang, L. You, and Z. Huang, “A complex-valued transformer for automatic modulation recognition,”IEEE Internet Things J., vol. 11, no. 12, pp. 22 197–22 207, 2024. [Online]. Available: https://doi.org/10.1109/JIOT.2024.3379429

    work page doi:10.1109/jiot.2024.3379429 2024

  29. [29]

    A survey of deep transfer learning in automatic modulation classification,

    X. Wang, Y . Zhao, and Z. Huang, “A survey of deep transfer learning in automatic modulation classification,”IEEE Transactions on Cognitive Communications and Networking, 2025

    work page 2025

  30. [30]

    Generalization error in deep learning,

    D. Jakubovitz, R. Giryes, and M. R. Rodrigues, “Generalization error in deep learning,” inCompressed sensing and its applications: third international MATHEOn conference 2017. Springer, 2019, pp. 153– 193

    work page 2017

  31. [31]

    Multilayered feedforward networks are universal ap- proximators,

    M. Stinchcomb, “Multilayered feedforward networks are universal ap- proximators,”Neural Networks, vol. 2, pp. 356–359, 1989

    work page 1989

  32. [32]

    Approximation theory of convolutional architectures for time series modelling,

    H. Jiang, Z. Li, and Q. Li, “Approximation theory of convolutional architectures for time series modelling,” inProceedings of the 38th International Conference on Machine Learning. PMLR, July 2021, pp. 4961–4970

    work page 2021

  33. [33]

    On the approximation properties of recurrent encoder-decoder architectures,

    Z. Li, H. Jiang, and Q. Li, “On the approximation properties of recurrent encoder-decoder architectures,” inInternational Conference on Learning Representations, September 2021. JOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2021 15

    work page 2021

  34. [34]

    Approximation and optimization theory for linear continuous-time recurrent neural networks,

    Z. Li, J. Han, W. E, and Q. Li, “Approximation and optimization theory for linear continuous-time recurrent neural networks,”Journal of Machine Learning Research, vol. 23, no. 42, pp. 1–85, 2022

    work page 2022

  35. [35]

    Approximation rate of the transformer architecture for sequence modeling,

    H. Jiang and Q. Li, “Approximation rate of the transformer architecture for sequence modeling,”Advances in Neural Information Processing Systems, vol. 37, pp. 68 926–68 955, 2024

    work page 2024

  36. [36]

    Approximation error bounds that use vc-bounds,

    F. Girosi, “Approximation error bounds that use vc-bounds,” inProc. International Conference on Artificial Neural Networks, F . Fogelman- Soulie and P . Gallinari, editors, vol. 1, 1995, pp. 295–302

    work page 1995

  37. [37]

    Approximation and estimation bounds for artificial neural networks,

    A. R. Barron, “Approximation and estimation bounds for artificial neural networks,”Machine learning, vol. 14, pp. 115–133, 1994

    work page 1994

  38. [38]

    Spectrally-normalized margin bounds for neural networks,

    P. L. Bartlett, D. J. Foster, and M. J. Telgarsky, “Spectrally-normalized margin bounds for neural networks,”Advances in neural information processing systems, vol. 30, 2017

    work page 2017

  39. [39]

    Spectral complexity-scaled generalisation bound of complex-valued neural networks,

    H. Chen, F. He, S. Lei, and D. Tao, “Spectral complexity-scaled generalisation bound of complex-valued neural networks,”Artificial Intelligence, vol. 322, p. 103951, 2023

    work page 2023

  40. [40]

    Over-the-air deep learning based radio signal classification,

    T. J. O’Shea, T. Roy, and T. C. Clancy, “Over-the-air deep learning based radio signal classification,”IEEE Journal of Selected Topics in Signal Processing, vol. 12, no. 1, pp. 168–179, 2018

    work page 2018

  41. [41]

    A review on evaluation metrics for data classification evaluations,

    M. Hossin and M. N. Sulaiman, “A review on evaluation metrics for data classification evaluations,”International journal of data mining & knowledge management process, vol. 5, no. 2, p. 1, 2015

    work page 2015

  42. [42]

    Panoptic segmentation,

    A. Kirillov, K. He, R. Girshick, C. Rother, and P. Doll ´ar, “Panoptic segmentation,” inProceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019, pp. 9404–9413

    work page 2019

  43. [43]

    Frequency independent iq imbalance estimation and compen- sation,

    Y . Li, “Frequency independent iq imbalance estimation and compen- sation,” inIn-Phase and Quadrature Imbalance: Modeling, Estimation, and Compensation. Springer, 2013, pp. 29–47

    work page 2013

  44. [44]

    Specific emitter identification using convolutional neural network-based iq imbalance estimators,

    L. J. Wong, W. C. Headley, and A. J. Michaels, “Specific emitter identification using convolutional neural network-based iq imbalance estimators,”IEEE Access, vol. 7, pp. 33 544–33 555, 2019

    work page 2019

  45. [45]

    Robust and fast automatic modulation classification with cnn under multipath fading channels,

    K. Tekbıyık, A. R. Ekti, A. G ¨orc ¸in, G. K. Kurt, and C. Kec ¸eci, “Robust and fast automatic modulation classification with cnn under multipath fading channels,” in2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring). IEEE, 2020, pp. 1–6

    work page 2020

  46. [46]

    Deep neural network architectures for modulation classification,

    X. Liu, D. Yang, and A. El Gamal, “Deep neural network architectures for modulation classification,” in2017 51st Asilomar Conference on Signals, Systems, and Computers. IEEE, 2017, pp. 915–919

    work page 2017

  47. [47]

    Enhancing automatic modulation recog- nition for iot applications using transformers,

    N. Rashvand, K. Witham, G. Maldonado, V . Katariya, N. Marer Prabhu, G. Schirner, and H. Tabkhi, “Enhancing automatic modulation recog- nition for iot applications using transformers,”IoT, vol. 5, no. 2, pp. 212–226, 2024

    work page 2024

  48. [48]

    A lightweight deep learning architecture for automatic modulation classification of wireless internet of things,

    J. Han, Z. Yu, and J. Yang, “A lightweight deep learning architecture for automatic modulation classification of wireless internet of things,” IET Communications, vol. 18, no. 18, pp. 1220–1230, 2024

    work page 2024

  49. [49]

    Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting,

    H. Wu, J. Xu, J. Wang, and M. Long, “Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting,” Advances in neural information processing systems, vol. 34, pp. 22 419– 22 430, 2021. Yurui Zhaoreceived her B.Eng. and M.Phil. degrees in Electronic Science and Engineering from the National University of Defense Technology...

    work page 2021