Tag
Keelix is a new open-source tool that uses free Sentinel-1 SAR satellite imagery to monitor naval bases without AIS data, detecting ship arrivals/departures and flagging unusual activity through before-and-after radar comparisons. Validated over 12 months at Norfolk Naval Base, it achieved ~65% detection rate with ~95% precision using signal processing rather than machine learning.
NIST researchers propose a Statistical Ensemble Method (SEM) for radio-frequency jamming detection in O-RAN networks that generalizes across heterogeneous 5G environments, outperforming ML/DL models under distribution shift while supporting cold-start deployment via the Non-RT RIC rApp framework.
MontageFlow 是一个流匹配模型，通过将输出限制在满足 EEG 导联（montage）线性约束的子空间内，生成物理上有效的高保真临床 EEG 信号，在三个大规模基准上将 TS-FID 提升了 1.6–3.6 倍。
一篇技术评论文章，批评 OpenAI 在数学论文集中声称的更快快速傅里叶变换（FFT）算法，指出其改进微乎其微，更像是利用理论模型在硬件上并不实际可行的“恶意利用”，而非真正的突破。
Los Alamos researchers extend a conditional VAE framework with a recurrent wavelet-decoding ensemble to perform inverse synthesis of shock acceleration waveforms from shock response spectra, achieving lower spectral error and 0.1–0.6 ms inference per waveform compared to traditional sum-of-decayed-sinusoids baselines.
一篇深入浅出的长文，讲述大肠杆菌（E. coli）趋化性——单细胞如何通过 CheY 信号分子、受体复合体与鞭毛马达实现类似嗅觉、记忆与决策的'智能'行为，展示蛋白质结构决定功能等系统生物学核心主题。
论文提出 Dynamic Band Splitting (DBS) 框架，可在固定 band-token 预算下学习音频源分离的频率轴切分方式，并在 DnR v2 上将 BSRNN 和 TIGER 的平均 SI-SDR 分别提升至 9.07 dB 和 10.13 dB。
A time-series conditioned diffusion framework for MIMO channel estimation that uses an LSTM to encode temporal dynamics and an SNR-gated late-fusion shortcut, with SNR-adaptive DDIM denoising for low-latency inference in 5G/6G systems.
提出了DenoFlow，一种基于整流流（rectified flow）的SSVEP脑电信号去噪方法，通过回归污染信号与干净信号间直线路径的速度场实现去噪，并在两个公开SSVEP数据集上超越了七个基线模型的信号保真度与解码准确率。
Tianjin University researchers unveiled a 3-gram non-invasive brain-computer interface small enough to be concealed in hair, marking a notable advance in ultra-lightweight wearable neurotechnology.
LiteEMG-FM is an efficient hybrid CNN-Transformer foundation model pretrained on 16 EMG datasets for robust, zero-calibration gesture recognition. The paper demonstrates real-time deployability on resource-constrained edge devices via a hierarchical wake-up gate and evaluates latency, power, and memory trade-offs across offloading paradigms.
This paper explores graph neural network encoders for projecting heterogeneously sampled signal sets from sensor networks and radars into fixed-size, sampling-invariant embedding spaces, evaluated via waveform discrimination on synthetic complex-valued RF signals.
GeoRVQ introduces a decoder-aware masked token model for physiological signals that improves accuracy and reduces decoded distortion by accounting for local response and residual dependencies in residual vector quantization.
Introduces leaky-integrator reconstruction to fix error accumulation in recursive differenced time-series forecasting, showing substantial error reduction across architectures and datasets.
This paper proposes PainNAS, a block-based Neural Architecture Search method that efficiently reduces computational complexity in Leave-One-Subject-Out evaluation for automated pain assessment systems.
This article provides detailed notes on discrete-time Fourier series (DTFS) and discrete-time Fourier transform (DTFT), covering their theoretical foundations and examples for signal processing applications.
This article discusses a method for communication using modulated Johnson noise, likely exploring thermal noise in electrical circuits for signal transmission.
This study introduces a rolling day-wise mortality prediction model for critically ill patients with acute kidney injury on CRRT, leveraging machine pressure waveforms and clinical data to enhance early risk assessment.
sdr-- is an open-source software-defined radio application with a visual patchable signal graph, built in Rust for DSP, and featuring a web UI for control and visualization.
The article discusses three converging toolchains in neural voice synthesis—vocal identity, signal manipulation, and performance realism—focusing on voice cloning and timbre transfer to transform vocal performances while preserving original phrasing and dynamics.