arXiv subjects

Ervin Sejdic

Publications and source records attributed to Ervin Sejdic.

7 recordsLinked to original sources

arXiv2026

Multi-Phonation Graph Learning with Self-Supervised Speech Embeddings for ALS Detection and Progression Prediction

Amyotrophic lateral sclerosis (ALS) progressively impairs speech motor control, making acoustic analysis a promising biomarker for severity and progression estimation. We propose a subject-level graph framework that aggregates multiple phonation recordings into a unique k-nearest-neighbor graph built from pretrained SSL embeddings of 2s segments. We compare four SSL front-ends (wav2vec 2.0, HuBERT, data2vec-audio, and UniSpeech-SAT) and five graph neural networks (GCN, residual GCN, GAT, GraphSAGE, and GIN) on the SAND dataset tasks (339 participants: 205 ALS, 134 control): 5-class dysarthria severity and 4-class ALSFRS-R progression prediction. On the official validation set, the best configuration (HuBERT+GIN) achieves macro-F$_1$ of 0.73 for Task 1 and 0.69 for Task 2, outperforming SAND validation baselines (0.61 and 0.58). These results highlight the potential of combining GNNs with pretrained cross-lingual speech representations for low-resource ALS detection and progression monitoring.

eess.AS↗

arXiv2026

Self-Supervised Audio Representation Learning for Pediatric Asthma Detection in Emergency Care Using Digital Stethoscope Recordings

Accurate diagnosis of pediatric asthma in emergency departments remains challenging due to overlapping respiratory symptoms, time constraints, and the limited feasibility of pulmonary function testing in young children. This study investigates the feasibility of pediatric asthma detection in the emergency department using breath sound recordings and machine learning. Thirty-second breath sounds were collected from six chest locations in 31 pediatric patients (10 asthmatic, 21 non-asthmatic) and analyzed using pretrained self-supervised speech representation models (HuBERT, WavLM, and Wav2Vec 2.0) for feature extraction, with patient age and sex incorporated into the feature representations. Conventional machine learning classifiers were trained and evaluated using patient-level stratified group 5-fold cross-validation and leave-one-patient-out validation to ensure the generalizability of the findings. Among the evaluated approaches, Wav2Vec 2.0 combined with histogram-based gradient boosting achieved the strongest and most consistent performance, yielding an accuracy of 0.84, sensitivity of 0.80, specificity of 0.86, and F1-score of 0.76 under both evaluation protocols. The consistency of performance across validation strategies suggests promising generalization to unseen patients. These findings suggest that pretrained self-supervised audio representations offer a promising, non-invasive approach for pediatric asthma detection in real-world emergency department settings, where objective respiratory assessment is often limited.

eess.AS↗

arXiv2025

ECG-SMART-NET: A Deep Learning Architecture for Precise ECG Diagnosis of Occlusion Myocardial Infarction

Objective: In this paper we develop and evaluate ECG-SMART-NET for occlusion myocardial infarction (OMI) identification. OMI is a severe form of heart attack characterized by complete blockage of one or more coronary arteries requiring immediate referral for cardiac catheterization to restore blood flow to the heart. Two thirds of OMI cases are difficult to visually identify from a 12-lead electrocardiogram (ECG) and can be potentially fatal if not identified quickly. Previous works on this topic are scarce, and current state-of-the-art evidence suggests both feature-based random forests and convolutional neural networks (CNNs) are promising approaches to improve ECG detection of OMI. Methods: While the ResNet architecture has been adapted for use with ECG recordings, it is not ideally suited to capture informative temporal features within each lead and the spatial concordance or discordance across leads. We propose a clinically informed modification of the ResNet-18 architecture. The model first learns temporal features through temporal convolutional layers with 1xk kernels followed by a spatial convolutional layer, after the residual blocks, with 12x1 kernels to learn spatial features. Results: ECG-SMART-NET was benchmarked against the original ResNet-18 and other state-of-the-art models on a multisite real-word clinical dataset that consists of 10,393 ECGs from 7,397 unique patients (rate of OMI =7.2%). ECG-SMART-NET outperformed other models in the classification of OMI with a test AUC of 0.953 [0.921, 0.978]. Conclusion and Significance: ECG-SMART-NET can outperform the state-of-the-art random forest for OMI prediction and is better suited for this task than the original ResNet-18 architecture.

eess.SP↗

arXiv2019

Vertex-Frequency Graph Signal Processing: A review

Graph signal processing deals with signals which are observed on an irregular graph domain. While many approaches have been developed in classical graph theory to cluster vertices and segment large graphs in a signal independent way, signal localization based approaches to the analysis of data on graph represent a new research direction which is also a key to big data analytics on graphs. To this end, after an overview of the basic definitions in graphs and graph signals, we present and discuss a localized form of the graph Fourier transform. To establish an analogy with classical signal processing, spectral- and vertex-domain definitions of the localization window are given next. The spectral and vertex localization kernels are then related to the wavelet transform, followed by a study of filtering and inversion of the localized graph Fourier transform. For rigour, the analysis of energy representation and frames in the localized graph Fourier transform is extended to the energy forms of vertex-frequency distributions, which operate even without the need to apply localization windows. Another link with classical signal processing is established through the concept of local smoothness, which is subsequently related to the particular paradigm of signal smoothness on graphs. This all represents a comprehensive account of the relation of general vertex-frequency analysis with classical time-frequency analysis, and important but missing link for more advanced applications of graphs signal processing. The theory is supported by illustrative and practically relevant examples.

eess.SP↗

arXiv2019

Single neuron-based neural networks are as efficient as dense deep neural networks in binary and multi-class recognition problems

Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of artificial neural networks. Previous work demonstrated that dense neural networks are needed to shape complex decision surfaces required for AI-level recognition tasks. We investigate the ability to model high dimensional recognition problems using single or several neurons networks that are relatively easier to train. By employing three datasets, we test the use of a population of single neuron networks in performing multi-class recognition tasks. Surprisingly, we find that sparse networks can be as efficient as dense networks in both binary and multi-class tasks. Moreover, single neuron networks demonstrate superior performance in binary classification scheme and competing results when combined for multi-class recognition.

cs.LG↗

arXiv2019

An Example-Driven Introduction to Data Analytics on Graphs

Graphs are irregular structures which naturally account for data integrity, however, traditional approaches have been established outside Signal Processing, and largely focus on analyzing the underlying graphs rather than signals on graphs. Given the rapidly increasing availability of multisensor and multinode measurements, likely recorded on irregular or ad-hoc grids, it would be extremely advantageous to analyze such structured data as graph signals and thus benefit from the ability of graphs to incorporate spatial awareness of the sensing locations, sensor importance, and local versus global sensor association. The aim of this lecture note is therefore to establish a common language between graph signals, defined on irregular signal domains, and some of the most fundamental paradigms in DSP, such as spectral analysis of multichannel signals, system transfer function, digital filter design, parameter estimation, and optimal filter design. This is achieved through a physically meaningful and intuitive real-world example of geographically distributed multisensor temperature estimation. A similar spatial multisensor arrangement is already widely used in Signal Processing curricula to introduce minimum variance estimators and Kalman filters \cite{HM}, and by adopting this framework we facilitate a seamless integration of graph theory into the curriculum of existing DSP courses. By bridging the gap between standard approaches and graph signal processing, we also show that standard methods can be thought of as special cases of their graph counterparts, evaluated on linear graphs. It is hoped that our approach would not only help to demystify graph theoretic approaches in education and research but it would also empower practitioners to explore a whole host of otherwise prohibitive modern applications.

eess.SP↗

arXiv2019

Radiological images and machine learning: trends, perspectives, and prospects

The application of machine learning to radiological images is an increasingly active research area that is expected to grow in the next five to ten years. Recent advances in machine learning have the potential to recognize and classify complex patterns from different radiological imaging modalities such as x-rays, computed tomography, magnetic resonance imaging and positron emission tomography imaging. In many applications, machine learning based systems have shown comparable performance to human decision-making. The applications of machine learning are the key ingredients of future clinical decision making and monitoring systems. This review covers the fundamental concepts behind various machine learning techniques and their applications in several radiological imaging areas, such as medical image segmentation, brain function studies and neurological disease diagnosis, as well as computer-aided systems, image registration, and content-based image retrieval systems. Synchronistically, we will briefly discuss current challenges and future directions regarding the application of machine learning in radiological imaging. By giving insight on how take advantage of machine learning powered applications, we expect that clinicians can prevent and diagnose diseases more accurately and efficiently.

eess.IV↗