61 articles tagged with #signal-processing. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Over-the-Air Federated Learning (AirFL) integrates wireless signal processing with distributed machine learning to enable efficient edge AI by using wireless superposition to aggregate model updates directly at the receiver. The approach reduces latency, bandwidth, and energy consumption compared to traditional federated learning architectures.
Researchers developed EpiiSLM, a dual foundation model system that significantly improves identification of epileptogenic zones in drug-resistant epilepsy patients using stereo-electroencephalography data. The system achieved 97.8% contact-level accuracy and requires only one night of monitoring, potentially reducing invasive procedures and improving surgical outcomes where current seizure freedom rates remain below 50%.
Researchers propose principle-driven foundation models that encode physics-based principles rather than learn statistical correlations, achieving cross-modal transfer from radio-frequency data to audio, images, text, and video without fine-tuning. A 1.99M parameter frozen encoder reaches 77.7% average accuracy across 15 tasks, with performance varying systematically between physically-grounded (84.5%) and semantic tasks (70.0%), suggesting complementary approaches to AI generalization.
FreqLite is a new lightweight linear model for long-term time-series forecasting that uses frequency decomposition and adaptive normalization to achieve better accuracy than larger transformer models while requiring 4x fewer parameters and significantly less computational resources. The method introduces Adaptive Reversible Instance Normalization (A-RevIN) to handle non-stationary data more effectively than existing approaches.
Researchers introduce CoilDrop-MRI, a self-supervised deep learning method that improves accelerated MRI reconstruction by strategically dropping data across receiver coils rather than only in k-space. Validated across multiple hospital sites and field strengths, the approach matches supervised methods' quality without requiring fully sampled training data, offering practical efficiency gains for medical imaging.
Researchers propose Intelligent Partitioning for Self-supervised Denoising (iPSD), a deep learning method that eliminates the need for artifact-free training data to denoise electroencephalogram (EEG) signals from wearable devices. The technique achieves state-of-the-art performance even in extremely noisy conditions by learning to partition noisy EEG segments into independent realizations sharing the same underlying neural signal.
Researchers introduce AirFM-DDA, a foundation model for 6G wireless networks that processes channel state information in the Delay-Doppler-Angle domain rather than traditional space-time-frequency representations. The model uses window-based attention instead of computationally expensive global attention, achieving superior generalization on channel prediction tasks while reducing computational costs by an order of magnitude.
Researchers developed Uni-NTFM, a new foundation model for EEG signal analysis that incorporates biological neural mechanisms and achieved record-breaking 1.9 billion parameters. The model was pre-trained on 28,000 hours of EEG data and outperformed existing models across nine downstream tasks by aligning architecture with actual brain functionality.
Researchers propose SemKey, a novel framework that addresses key limitations in EEG-to-text decoding by preventing hallucinations and improving semantic fidelity through decoupled guidance objectives. The system redesigns neural encoder-LLM interaction and introduces new evaluation metrics beyond BLEU scores to achieve state-of-the-art performance in brain-computer interfaces.
Researchers introduce BrainAgent, an LLM-driven multi-agent framework that automates brain signal analysis by converting natural language instructions into executable processing pipelines. The system addresses current limitations in Brain-Computer Interface technology by reducing technical barriers and enabling complex, adaptive workflows for real-world clinical and research applications.
Researchers present a semi-supervised learning workflow for detecting and classifying satellites in radio-frequency data, combining Non-negative Matrix Factorization with expert interpretation to reduce dependence on large labeled datasets. This approach addresses the challenge of space domain awareness by leveraging unlabeled RF observations to identify patterns in satellite signals, space debris, and ionospheric conditions without extensive manual annotation.
Researchers propose HISR, a hypergraph-based framework for semantic-aware communication that captures complex multi-entity relationships beyond traditional pairwise graph structures. The system achieves 36.6% improvement in semantic interpretation accuracy by mapping entities into context-specific semantic subspaces, enabling robust information recovery even under noisy channel conditions.
Researchers present a systematic study of feature extraction techniques for acoustic gunshot detection using 23,000 recordings across 85 firearms, demonstrating that technique selection can improve classification accuracy by up to 20% and parameter optimization by an additional 4.7%. The work addresses gaps in current gunshot detection systems used in civilian safety, military, and conservation applications.
Researchers evaluated the realism of Sionna ray-tracing simulator for outdoor cellular networks in Rome using 1,664 real user equipment measurements across six base stations. The study found that while precise antenna geometry and positioning are critical for simulation accuracy, capturing urban environmental noise remains an unsolved challenge that limits the simulator's practical applicability for real-world RF learning tasks.
Researchers have developed a mathematical framework for optimal quantization that constrains output distributions while minimizing mean squared error. This theoretical advance has practical applications in entropy control, mutual information maximization, communication systems, and privacy-preserving data anonymization.
Researchers propose MeCo, a MeanFlow-based generative corrector that improves multi-channel speech separation by refining discriminative model outputs in a single step. The method combines Data-Space Optimization with specialized loss functions to achieve state-of-the-art performance in both signal fidelity and human listening quality with minimal computational cost.
Researchers introduce FADTI, a diffusion-based framework for multivariate time series imputation that combines Fourier frequency analysis with attention mechanisms to handle missing data in healthcare, traffic, and biological systems. The model demonstrates superior performance over existing methods, particularly when dealing with high missing data rates and distribution shifts.
Researchers developed a PPG foundation model that leverages multimodal physiological signals (ECG and respiratory data) to improve robustness on noisy wearable data, achieving better performance than existing approaches while requiring 3x fewer training subjects. This advancement could enhance the reliability of PPG-based health monitoring in consumer devices and clinical applications.
Researchers introduce Trilobyte, a byte-level tokenization approach that enables language models to perform lossless audio compression on full-fidelity 16/24-bit audio files. While LMs outperform FLAC at 8 and 16-bit depths, compression gains diminish at higher bit depths, suggesting practical limitations for real-world audio applications.
Researchers have developed an enhanced fiber-optic sensing system that combines phase-sensitive optical time-domain reflectometry with Sagnac interferometry to improve distributed acoustic sensing (DAS) performance over long distances. The new architecture addresses signal degradation issues and achieves 89.79% accuracy in acoustic event recognition, with an open-source benchmark framework for future development.
Researchers introduce LatentWave, a wireless foundation model that uses Joint-Embedding Predictive Architecture (JEPA) instead of traditional masked input reconstruction to learn more transferable representations from wireless spectrograms and channel state information. The model demonstrates improved performance across RF signal classification, 5G positioning, beam prediction, and LoS/NLoS classification tasks while supporting variable antenna configurations.
Researchers introduce FreqX, a novel interpretability method for machine learning models that leverages signal processing and information theory to address challenges in personalized federated learning. The approach achieves 10x faster performance than existing methods while providing both attribution and concept information while maintaining privacy.
Researchers have developed a neural radiated-noise field (NRNF) model that predicts underwater vehicle acoustic signatures across three-dimensional spaces using machine learning rather than traditional physics-based simulation. The model achieves 3.5 dB average prediction error in the 50-5000 Hz band and demonstrates improved spatial generalization through a learnable scene feature grid.
Researchers propose a channel-oriented design approach for EEG-to-music reconstruction that preserves weak neural signals by treating each electrode as an explicit token rather than mixing channels early. The method incorporates channel-wise tokenization, multi-view self-distillation, and structured data augmentation to improve brain-computer interface performance in a challenging domain where signals are noisy and distributed.
Researchers empirically compared eight input encoder architectures for Transformer models processing multi-channel signal data, finding that the standard per-channel linear projection matches all alternatives in performance while being simplest to implement. Two encoders underperformed significantly: shared-scalar baselines and channel-independent architectures, with practical differences between top performers remaining statistically small but modest.
