Frontiers in Signal Processing

Equation-level parameterized fusion reformulation for multimodal epileptic seizure detection using interaction control and data-quality screening

2026-03-06

Abdul-Mumin Khalid, Musah Sulemana, Iddrisu Wahab Abdul

Epileptic seizure detection remains challenging due to noise, inter-subject variability, and the poor generalization ability of unimodal learning models. To address these limitations, this study proposes an equation-level multimodal fusion reformulation for epileptic seizure detection that integrates EEG, ECG, EMG, and ACC signals using adaptive parameterized fusion and interaction control. The framework introduces four interpretable parameters: a fusion exponent (ρ), an interaction weight (δ), a stabilization factor λ, and a synergy amplifier η, which jointly regulate modality contribution, nonlinear cross-modal interaction, numerical stability, and synergistic enhancement within a unified mathematical formulation applicable to both traditional and deep learning models. The study is conducted on a multimodal dataset comprising recordings from 120 clinically diagnosed epilepsy patients, including 60 patients from Tamale Teaching Hospital and 60 from publicly available datasets. Signals were sampled at 512 Hz and segmented into 2-second windows with 50% overlap, yielding approximately 1,024,000 labeled samples. A formal Data Quality Assurance (DQA) model and a Novel Cosine Similarity (NCS) index were employed to assess signal reliability and cross-source alignment prior to fusion. Twelve machine learning and deep learning classifiers were evaluated using a strict patient-wise data split to prevent data leakage. Experimental results demonstrate consistent performance improvements across all models following equation-level reformulation. Traditional machine learning models improved from baseline accuracies of approximately 55–67% to 82–92%, while deep learning models improved from 70–82% to 89–97.9%, with the Transformer-based model achieving the highest performance. These results confirm that equation-level multimodal fusion provides a generalizable, interpretable, and computationally efficient approach for robust epileptic seizure detection.

Residual life prediction of progressive failure bearings based on NGO-AVMD hybrid domain features

2026-02-16

Jiong Zhou

Accurate bearing Remaining Useful Life (RUL) prediction is vital for equipment availability, cost reduction, and safety. Existing data-driven methods often yield insufficient accuracy due to single-scale feature extraction and poor differentiation of failure modes. This paper proposes a hybrid-domain feature extraction method, integrating original vibration signals with Adaptive Variational Mode Decomposition optimized by Northern Goshawk Optimization (NGO-AVMD) reconstructed signals and additional deep features. These mixed-domain features are used to compute a health index that effectively distinguishes progressive and sudden bearing failure modes. Focusing on progressive degradation, a multi-attention Temporal Convolutional Network (TCN) is then employed for RUL prediction, using these features as input. Validated on the PHM2012 dataset, the method achieves an R2 of 98%, demonstrating its high accuracy in bearing life prediction.

Correction: Convergence analysis of hyperparameter-free MCC-based channel-estimation for mmWave MIMO systems

2026-02-03

Vimal Bhatia, Rajat Kumar, Rangeet Mitra, Sandesh Jain, Vidya Bhasker Shukla, K. Venkateswaran, Ondrej Krejcar

Detection of inter-turn short circuits in induction motors using orthogonal matching pursuit and dictionary learning

2026-01-28

Carlos Morales-Perez, Juan Pablo Amezquita-Sanchez, Jose Rangel-Magdaleno, David Granados-Lieberman, Martin Valtierra-Rodriguez

Fault detection in induction motors is critical due to their extensive use in industrial applications. Among the various types of faults, stator faults are the most frequent and complex, making early detection particularly challenging. In this paper, a novel methodology for detecting inter-turn short circuits (ITSCs) through stator current analysis is presented. The methodology employs a sine–cosine filter to suppress the fundamental-frequency component, constructs a cumulative distribution function (CDF) to enhance ITSC-related features, and detects faults via a sparse representation of the CDF using the Orthogonal Matching Pursuit algorithm. To verify the methodology's effectiveness, the current stator signals have been analyzed across five levels of fault and four mechanical load conditions. Finally, experimental results show that the proposed method achieves a fault-detection accuracy of 98%, requires a small training dataset, and enables the detection of up to 10 short-circuited turns.

Comparing compressive sensing and downsampling for COVID-19 diagnosis from cough and speech audio signals

2026-01-22

Leticia Silva, Alan Floriano, Carlos Valadão, Eliete Caldeira, Sridhar Krishnan, Teodiano Bastos Filho

IntroductionSince the onset of the COVID-19 pandemic, extensive research has focused on developing non-invasive diagnostic approaches of respiratory syndrome using biomedical signals, particularly cough and speech audio. Time-frequency representations combined with Machine Learning models have shown potential in identifying acoustic biomarkers associated with respiratory conditions. Although many existing approaches demonstrate high performance, their use may be limited in resource-constrained environments due to processing or implementation demands.MethodsIn this study, we propose an end-to-end approach for COVID-19 inference based on compressed time-domain audio signals. The method combines temporal signal compression strategies - Downsampling (DS) and Compressive Sensing (CS) - with a Convolutional Neural Network (CNN) trained directly on the waveforms. This design eliminates the need for handcrafted features or spectrograms, aiming to reduce computational complexity while preserving classification performance.ResultsTo evaluate the proposed structure, we used data from two open-access datasets, one for coughing and one for speech. Experimental results, assessed using accuracy and F1-score metrics, indicate that CS outperformed DS in most scenarios, particularly under high compression rates (e.g., 200 Hz and 100 Hz).DiscussionThese findings support the use of compressed audio-based classification in real-world embedded and mobile health systems, where computational efficiency is essential.

Convergence analysis of hyperparameter-free MCC-based channel estimation for mmWave MIMO systems

2026-01-06

Vimal Bhatia, Rajat Kumar, Rangeet Mitra, Sandesh Jain, Vidya Bhasker Shukla, K. Venkateswaran, Ondrej Krejcar

Accurate channel-estimation algorithms are critical for enhancing the throughput of wireless communication systems, including millimetre wave (mmWave) multiple-input multiple-output (MIMO) systems, where precise channel knowledge enables reliable signal detection and beamforming. In practical wireless environments, impulsive non-Gaussian noise with unknown statistics often occurs due to electromagnetic interference and harsh propagation conditions, significantly degrading estimation accuracy and overall system performance. In this context, the maximum correntropy criterion (MCC) has emerged as an attractive solution for robust channel estimation that outperforms state-of-the-art algorithms. However, the MCC-based algorithm’s performance is sensitive to the tuning of hyperparameters, which is challenging in the presence of non-Gaussian noise, such as impulsive noise (IN). Furthermore, a recent genre of kernel width sampling methods makes MCC hyperparameter-free and allows for asymptotic convergence to the squared-error performance of MCC with the ideal kernel width. To ensure their practical applicability, convergence analysis is essential to theoretically guarantee stability and performance under various IN scenarios. This study presents convergence analysis of hyperparameter-free MCC-based channel estimation for mmWave MIMO systems considering various IN scenarios. To validate the theoretical analysis, simulations are conducted on practical mmWave MIMO system models. Simulation results closely match the analytical findings, which confirms the accuracy and effectiveness of the analysis we here present.

4DRadarRBD: 4D mmWave radar-based road boundary detection in autonomous driving

2025-11-20

Yuyan Wu, Hae Young Noh

IntroductionDetecting road boundaries, the static physical edges of the available driving area, is important for safe navigation and effective path planning in autonomous driving and advanced driver-assistance systems. Traditionally, road boundary detection in autonomous driving relies on cameras and LiDAR. However, they are vulnerable to poor lighting conditions, such as nighttime and direct sunlight glare, or prohibitively expensive for low-end vehicles.MethodsThis paper introduces 4DRadarRBD, the first road boundary curve detection method based on 4D mmWave radar, which is cost-effective and robust in complex driving scenarios. The main idea is that road boundaries (e.g., fences, bushes, roadblocks) reflect millimeter waves, thus generating point cloud data for the radar. To overcome the challenge that the 4D mmWave radar point clouds contain many noisy points, we initially reduce noisy points via physical constraints for road boundaries and then segment the road boundary points from the noisy points by incorporating a distance-based loss which penalizes for falsely detecting the points far away from the actual road boundaries. In addition, we capture the temporal dynamics of point cloud sequences by utilizing each point’s deviation from the vehicle motion-compensated road boundary detection result obtained from the previous frame, along with the spatial distribution of the point cloud for point-wise road boundary segmentation.ResultsWe evaluated 4DRadarRBD through real-world driving tests and achieved a road boundary point segmentation accuracy of 93%, with a median distance error of up to 0.023 m and an error reduction of 92.6% compared to the baseline model.