AIMC-Spec: A Benchmark Dataset for Automatic Intrapulse Modulation Classification under Variable Noise Conditions

• URL: http://arxiv.org/abs/2601.08265v1
• Date: Tue, 13 Jan 2026 06:42:28 GMT
• Title: AIMC-Spec: A Benchmark Dataset for Automatic Intrapulse Modulation Classification under Variable Noise Conditions
• Authors: Sebastian L. Cocks, Salvador Dreo, Feras Dayoub,
• Abstract summary: This paper introduces AIMC-Spec, a comprehensive synthetic dataset for spectrogram-based image classification.<n>Five representative deep learning algorithms were re-implemented and evaluated under a unified input format.<n>Results reveal significant performance variation, with frequency-modulated (FM) signals classified more reliably than phase or hybrid types.
• Score: 4.448748938342291
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A lack of standardized datasets has long hindered progress in automatic intrapulse modulation classification (AIMC) - a critical task in radar signal analysis for electronic support systems, particularly under noisy or degraded conditions. AIMC seeks to identify the modulation type embedded within a single radar pulse from its complex in-phase and quadrature (I/Q) representation, enabling automated interpretation of intrapulse structure. This paper introduces AIMC-Spec, a comprehensive synthetic dataset for spectrogram-based image classification, encompassing 33 modulation types across 13 signal-to-noise ratio (SNR) levels. To benchmark AIMC-Spec, five representative deep learning algorithms - ranging from lightweight CNNs and denoising architectures to transformer-based networks - were re-implemented and evaluated under a unified input format. The results reveal significant performance variation, with frequency-modulated (FM) signals classified more reliably than phase or hybrid types, particularly at low SNRs. A focused FM-only test further highlights how modulation type and network architecture influence classifier robustness. AIMC-Spec establishes a reproducible baseline and provides a foundation for future research and standardization in the AIMC domain.

Related papers

• Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models [53.79667447811139]
  We show that a single deep neural architecture learns to jointly detect and separate when applied directly to the received signal.<n>These findings highlight UJM as a scalable and practical alternative to DTS, while opening new directions for unified separation under broader estimation.
  arXiv  Detail & Related papers  (2026-02-04T15:25:02Z)
• FAIM: Frequency-Aware Interactive Mamba for Time Series Classification [87.84511960413715]
  Time series classification (TSC) is crucial in numerous real-world applications, such as environmental monitoring, medical diagnosis, and posture recognition.<n>We propose FAIM, a lightweight Frequency-Aware Interactive Mamba model.<n>We show that FAIM consistently outperforms existing state-of-the-art (SOTA) methods, achieving a superior trade-off between accuracy and efficiency.
  arXiv  Detail & Related papers  (2025-11-26T08:36:33Z)
• CNN-LSTM Hybrid Architecture for Over-the-Air Automatic Modulation Classification Using SDR [0.6999740786886536]
  We propose an AMC system based on a hybrid Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) architecture.<n>The proposed architecture leverages CNNs for spatial feature extraction and LSTMs for capturing temporal dependencies.<n>The system's practical ability was demonstrated by identifying over-the-air (OTA) signals from a custom-built FM transmitter alongside other modulation schemes.
  arXiv  Detail & Related papers  (2025-11-26T04:16:54Z)
• Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation [60.9960601057956]
  We introduce Frequency-Aware Audio-Visualcomposer (FAVS) framework consisting of two key modules.<n>FAVS framework achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-23T12:33:48Z)
• DenoMAE: A Multimodal Autoencoder for Denoising Modulation Signals [21.25974800554959]
  DenoMAE is a novel framework for denoising modulation signals during pretraining.<n>It incorporates multiple input modalities, including noise, to enhance cross-modal learning.<n>It achieves state-of-the-art accuracy in automatic modulation classification tasks.
  arXiv  Detail & Related papers  (2025-01-20T15:23:16Z)
• MoE-AMC: Enhancing Automatic Modulation Classification Performance Using Mixture-of-Experts [2.6764607949560593]
  MoE-AMC is a novel Mixture-of-Experts (MoE) based model crafted to address Automatic Modulation Classification (AMC) in a well-balanced manner. MoE-AMC seamlessly combines the strengths of LSRM for handling low SNR signals and HSRM for high SNR signals. Experiments show that MoE-AMC achieved an average classification accuracy of 71.76% across different SNR levels, surpassing the performance of previous SOTA models by nearly 10%.
  arXiv  Detail & Related papers  (2023-12-04T19:31:15Z)
• You Only Train Once: A Unified Framework for Both Full-Reference and No-Reference Image Quality Assessment [45.62136459502005]
  We propose a network to perform full reference (FR) and no reference (NR) IQA. We first employ an encoder to extract multi-level features from input images. A Hierarchical Attention (HA) module is proposed as a universal adapter for both FR and NR inputs. A Semantic Distortion Aware (SDA) module is proposed to examine feature correlations between shallow and deep layers of the encoder.
  arXiv  Detail & Related papers  (2023-10-14T11:03:04Z)
• Multi-task Learning for Radar Signal Characterisation [48.265859815346985]
  This paper presents an approach for tackling radar signal classification and characterisation as a multi-task learning (MTL) problem. We propose the IQ Signal Transformer (IQST) among several reference architectures that allow for simultaneous optimisation of multiple regression and classification tasks. We demonstrate the performance of our proposed MTL model on a synthetic radar dataset, while also providing a first-of-its-kind benchmark for radar signal characterisation.
  arXiv  Detail & Related papers  (2023-06-19T12:01:28Z)
• Automatic Modulation Classification with Deep Neural Networks [0.0]
  We show that a combination of dilated convolutions, statistics pooling, and squeeze-and-excitation units results in the strongest performing classifier. We further investigate this best performer according to various other criteria, including short signal bursts, common misclassifications, and performance across differing modulation categories and modes.
  arXiv  Detail & Related papers  (2023-01-27T15:16:06Z)
• Model-based Deep Learning Receiver Design for Rate-Splitting Multiple Access [65.21117658030235]
  This work proposes a novel design for a practical RSMA receiver based on model-based deep learning (MBDL) methods. The MBDL receiver is evaluated in terms of uncoded Symbol Error Rate (SER), throughput performance through Link-Level Simulations (LLS) and average training overhead. Results reveal that the MBDL outperforms by a significant margin the SIC receiver with imperfect CSIR.
  arXiv  Detail & Related papers  (2022-05-02T12:23:55Z)
• Conditioning Trick for Training Stable GANs [70.15099665710336]
  We propose a conditioning trick, called difference departure from normality, applied on the generator network in response to instability issues during GAN training. We force the generator to get closer to the departure from normality function of real samples computed in the spectral domain of Schur decomposition.
  arXiv  Detail & Related papers  (2020-10-12T16:50:22Z)
• Ensemble Wrapper Subsampling for Deep Modulation Classification [70.91089216571035]
  Subsampling of received wireless signals is important for relaxing hardware requirements as well as the computational cost of signal processing algorithms. We propose a subsampling technique to facilitate the use of deep learning for automatic modulation classification in wireless communication systems.
  arXiv  Detail & Related papers  (2020-05-10T06:11:13Z)
• Time-Frequency Analysis based Blind Modulation Classification for Multiple-Antenna Systems [6.011027400738812]
  Blind modulation classification is an important step to implement cognitive radio networks. The multiple-input multiple-output (MIMO) technique is widely used in military and civil communication systems. Traditional likelihood-based and feature-based approaches cannot be applied in these scenarios.
  arXiv  Detail & Related papers  (2020-04-01T12:27:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.