arXiv subjects

Vahid Abolghasemi

Publications and source records attributed to Vahid Abolghasemi.

7 recordsLinked to original sources

arXiv2026

FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia and is associated with increased risks of stroke, heart failure, and mortality. Recent ECG foundation models offer transferable representations for automated AF detection. However, their relative effectiveness remains unclear because existing studies use different datasets, preprocessing procedures, classifiers, and validation protocols. This study presents FOUND-AF, a unified, leakage-controlled, and deployment-oriented benchmarking framework that evaluates the quality of pretrained ECG representations under identical experimental conditions. Nine publicly available foundation models from five families, including HuBERT-ECG, CLEF, ST-MEM, ECG-JEPA, and ECGFounder, were evaluated across four heterogeneous ECG datasets, namely AFDB, CinC2017, CPSC2021, and LTAFDB. All models were used as frozen feature extractors with standardized preprocessing, model-native resampling, a fixed XGBoost classifier, and recording-level grouped cross-validation. The evaluation included classification metrics, receiver operating characteristic analysis, paired recording-level bootstrap comparisons with Holm correction, embedding-space visualization, and computational efficiency profiling. The ECGFounder model consistently achieved the strongest overall performance across datasets while offering a favorable trade-off between accuracy, model size, inference time, and memory usage. FOUND-AF therefore provides a reproducible framework for selecting ECG foundation models and demonstrates that compact, clinically pretrained encoders can support robust and computationally efficient AF detection across heterogeneous acquisition settings.

cs.AI↗

arXiv2026

Universal Costas Matrices: Towards a General Framework for Costas Array Construction

Costas arrays are a special type of permutation matrices with ideal autocorrelation and low cross-correlation properties, making them valuable for radar, wireless communication, and integrated sensing and communication applications. This paper presents a novel unified framework for analyzing and discovering new Costas arrays. We introduce Universal Costas Matrices (UCMs) and Universal Costas Frequency Matrices (UCFMs) and investigate their structural characteristics. A framework integrating UCMs and UCFMs is proposed to pave the way for future artificial intelligence-assisted Costas array discovery. Leveraging the structural properties of UCMs and UCFMs, a reconstruction-based search method is developed to generate UCMs from UCFMs. Numerical results demonstrate that the proposed approach significantly accelerates the search process and enhances structural insight into Costas array generation.

cs.IT↗

arXiv2026

BRISC: Annotated Dataset for Brain Tumor Segmentation and Classification

Accurate segmentation and classification of brain tumors from Magnetic Resonance Imaging (MRI) remain key challenges in medical image analysis, primarily due to the lack of high-quality, balanced, and diverse datasets with expert annotations. In this work, we address this gap by introducing BRISC, a dataset designed for brain tumor segmentation and classification tasks, featuring high-resolution segmentation masks. The dataset comprises 6,000 contrast-enhanced T1-weighted MRI scans, which were collated from multiple public datasets that lacked segmentation labels. Our primary contribution is the subsequent expert annotation of these images, performed by certified radiologists and physicians. It includes three major tumor types, namely glioma, meningioma, and pituitary, as well as non-tumorous cases. Each sample includes high-resolution labels and is categorized across axial, sagittal, and coronal imaging planes to facilitate robust model development and cross-view generalization. To demonstrate the utility of the dataset, we provide benchmark results for both tasks using standard deep learning models. The BRISC dataset is made publicly available. datasetlink: https://www.kaggle.com/datasets/briscdataset/brisc2025/

eess.IV↗

arXiv2024

Coronary Artery Disease Classification Using One-dimensional Convolutional Neural Network

Coronary Artery Disease (CAD) diagnostic to be a major global cause of death, necessitating innovative solutions. Addressing the critical importance of early CAD detection and its impact on the mortality rate, we propose the potential of one-dimensional convolutional neural networks (1D-CNN) to enhance detection accuracy and reduce network complexity. This study goes beyond traditional diagnostic methodologies, leveraging the remarkable ability of 1D-CNN to interpret complex patterns within Electrocardiogram (ECG) signals without depending on feature extraction techniques. We explore the impact of varying sample lengths on model performance and conduct experiments involving layers reduction. The ECG data employed were obtained from the PhysioNet databases, namely the MIMIC III and Fantasia datasets, with respective sampling frequencies of 125 Hz and 250 Hz. The highest accuracy for unseen data obtained with a sample length of 250. These initial findings demonstrate the potential of 1D-CNNs in CAD diagnosis using ECG signals and highlight the sample size's role in achieving high accuracy.

eess.SP↗

arXiv2024

Joint Source-Channel Coding for Wireless Image Transmission: A Deep Compressed-Sensing Based Method

Nowadays, the demand for image transmission over wireless networks has surged significantly. To meet the need for swift delivery of high-quality images through time-varying channels with limited bandwidth, the development of efficient transmission strategies and techniques for preserving image quality is of importance. This paper introduces an innovative approach to Joint Source-Channel Coding (JSCC) tailored for wireless image transmission. It capitalizes on the power of Compressed Sensing (CS) to achieve superior compression and resilience to channel noise. In this method, the process begins with the compression of images using a block-based CS technique implemented through a Convolutional Neural Network (CNN) structure. Subsequently, the images are encoded by directly mapping image blocks to complex-valued channel input symbols. Upon reception, the data is decoded to recover the channel-encoded information, effectively removing the noise introduced during transmission. To finalize the process, a novel CNN-based reconstruction network is employed to restore the original image from the channel-decoded data. The performance of the proposed method is assessed using the CIFAR-10 and Kodak datasets. The results illustrate a substantial improvement over existing JSCC frameworks when assessed in terms of metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) across various channel Signal-to-Noise Ratios (SNRs) and channel bandwidth values. These findings underscore the potential of harnessing CNN-based CS for the development of deep JSCC algorithms tailored for wireless image transmission.

cs.CE↗

arXiv2020

Classification of Chinese Handwritten Numbers with Labeled Projective Dictionary Pair Learning

Dictionary learning is a cornerstone of image classification. We set out to address a longstanding challenge in using dictionary learning for classification; that is to simultaneously maximise the discriminability and sparse-representability power of the learned dictionaries. Upon this premise, we designed class-specific dictionaries incorporating three factors: discriminability, sparsity and classification error. We integrated these metrics into a unified cost function and adopted a new feature space, i.e., histogram of oriented gradients (HOG), to generate the dictionary atoms. The rationale of using HOG features for designing the dictionaries is their strength in describing fine details of crowded images. The results of applying the proposed method in the classification of Chinese handwritten numbers demonstrated enhanced classification performance $(\sim98\%)$ compared to state-of-the-art deep learning techniques (i.e., SqueezeNet, GoogLeNet and MobileNetV2), but with a fraction of parameters. Furthermore, combination of the HOG features with dictionary learning enhances the accuracy by $11\%$ compared to the case where only pixel domain data are used. These results were supported when the proposed method was applied to both Arabic and English handwritten number databases.

cs.CV↗

arXiv2015

Subsampled terahertz data reconstruction based on spatio-temporal dictionary learning

In this paper, the problem of terahertz pulsed imaging and reconstruction is addressed. It is assumed that an incomplete (subsampled) three dimensional THz data set has been acquired and the aim is to recover all missing samples. A sparsity-inducing approach is proposed for this purpose. First, a simple interpolation is applied to incomplete noisy data. Then, we propose a spatio-temporal dictionary learning method to obtain an appropriate sparse representation of data based on a joint sparse recovery algorithm. Then, using the sparse coefficients and the learned dictionary, the 3D data is effectively denoised by minimizing a simple cost function. We consider two types of terahertz data to evaluate the performance of the proposed approach; THz data acquired for a model sample with clear layered structures (e.g., a T-shape plastic sheet buried in a polythene pellet), and pharmaceutical tablet data (with low spatial resolution). The achieved signal-to-noise-ratio for reconstruction of T-shape data, from only 5% observation was 19 dB. Moreover, the accuracies of obtained thickness and depth measurements for pharmaceutical tablet data after reconstruction from 10% observation were 98.8%, and 99.9%, respectively. These results, along with chemical mapping analysis, presented at the end of this paper, confirm the accuracy of the proposed method.

cs.CV↗