Adaptive Rational Transformations in Biomedical Signal Processing

Bognár, G.; Fridli, S.; Kovács, Péter; Schipp, Ferenc

doi:10.1007/978-3-030-27550-1_30

Cited by 3 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous results show that several biomedical signal processing problems can be addressed efficiently with variable projection by means of adaptive rational and Hermite functions, as well as B-splines [20,24]. VP features were particularly utilized for ECG and EEG representation, compression, classification, and segmentation [25][26][27][28][29][30][31][32].…”

Section: Variable Projectionsmentioning

confidence: 99%

VPNet: Variable Projection Networks

Kovács,

Bognár,

Huber

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

In this paper, we introduce VPNet, a novel model-driven neural network architecture based on variable projections (VP). The application of VP operators in neural networks implies learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet as well as experiments. The concept was evaluated in the context of signal processing. We performed classification tasks on a synthetic dataset, and real electrocardiogram (ECG) signals. Compared to fully-connected and 1D convolutional networks, VPNet features fast learning ability and good accuracy at a low computational cost in both of the training and inference. Based on the promising results and mentioned advantages, we expect broader impact in signal processing, including classification, regression, and even clustering problems.Preprint. Under review.

show abstract

Section: Variable Projectionsmentioning

confidence: 99%

VPNet: Variable Projection Networks

Kovács,

Bognár,

Huber

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…A problémákra adap-tív racionális transzformációs módszert fejlesztettem. Fontos kiemelni, hogy ugyan a racionális modell [FriLocSch12] alapján adott, a valós alkalmazáshoz számos elvi és gyakorlati kérdést szükséges megvizsgálni, melyeknek átfogó diszkusszióját adom (lásd [Bog+19]). A 3. fejezetben a szegmentálási módszertanon kívül a racionális modell további részleteit is kidolgoztuk (lásd [BogSch18]), amely szívütések diagnosztikai jellemzők mentén történő szintetizálását is lehetővé teszi.…”

Section: Bevezetésunclassified

Orvosi jel- és képfeldolgozás transzformációs módszerekkel

Bognár¹

2019

View full text Add to dashboard Cite

Irodalomjegyzék 139 Approximáció és Fourier-sorokÁltalánosan tárgyalva a problémakört, tekintsük a (H, ⟨•, •⟩) Hilbert-teret adott alaphalmazzal és skaláris szorzattal. Jelölje ∥ • ∥ a skaláris szorzat által indukált normát:Ha a tér szeparábilis, azaz létezik egy e k ∈ H (k ∈ N) zárt ortonormált rendszer (N egy legfeljebb megszámlálható halmaz), akkor a Riesz-Fischer-tétel alapján minden f ∈ H eleme kölcsönösen egyértelműen előállítható az (e k ) rendszer szerinti Fourier-1.

show abstract

VPNET: Variable Projection Networks

Kovács

Bognár

Huber

et al. 2021

Int. J. Neur. Syst.

View full text Add to dashboard Cite

In this paper, we introduce VPNet, a novel model-driven neural network architecture based on variable projection (VP). Applying VP operators to neural networks results in learnable features, interpretable parameters, and compact network structures. This paper discusses the motivation and mathematical background of VPNet and presents experiments. The VPNet approach was evaluated in the context of signal processing, where we classified a synthetic dataset and real electrocardiogram (ECG) signals. Compared to fully connected and one-dimensional convolutional networks, VPNet offers fast learning ability and good accuracy at a low computational cost of both training and inference. Based on these advantages and the promising results obtained, we anticipate a profound impact on the broader field of signal processing, in particular on classification, regression and clustering problems.

show abstract

Adaptive Rational Transformations in Biomedical Signal Processing

Cited by 3 publications

References 14 publications

VPNet: Variable Projection Networks

VPNet: Variable Projection Networks

Orvosi jel- és képfeldolgozás transzformációs módszerekkel

VPNET: Variable Projection Networks

Contact Info

Product

Resources

About