N-BEATS for Heart Dysfunction Classification

Puszkarski, Bartosz; Hryniów, Krzysztof; Sarwas, Grzegorz

doi:10.23919/cinc53138.2021.9662740

Cited by 5 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the paper, N-BEATS was compared to other state-of-the-art RNNs adopted to use the αβ architecture introduced in Saadatnejad et al (2019). In this paper, we extended the experiments conducted in Puszkarski et al (2021) in the field of use of N-BEATS architecture as a multi-label classifier. We modified it into the αβ scheme and thoroughly compared it with other SotA RNN architectures like LSTM, GRU, and LSTM with peepholes.…”

Section: Discussionmentioning

confidence: 99%

“…In the paper (Saadatnejad et al 2019), authors introduced versions of the LSTM and GRU algorithms, consisting of additional wavelet analysis and merged predictions from smaller models to lower the computational cost. In the study, (Puszkarski et al 2021) we examined for the 2021 PhysioNet Challenge the use of modified N-BEATS as a multi-label classifier for cardiac problems. The study showed that while its results were sub-par, for a low number of electrocardiogram leads, it achieved acceptable results while maintaining low complexity that would allow use on a wearable device.…”

Section: Introductionmentioning

confidence: 99%

“…As an extension to the study (Puszkarski et al 2021) in this article, we present the comparison of N-BEATS and three common architectures (LSTM, LSTM with peepholes (Gers et al 2002) and Gated Recurrent Unit (GRU) (Cho et al 2014)), modified with added two blended sub-networks and wavelet analysis. Furthermore, we present a performance comparison for a different number of electrocardiogram leads.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

2022

View full text Add to dashboard Cite

Objective: The primary purpose of this work is to analyze the ability of N-BEATS architecture for the problem of prediction and classification of electrocar- diogram (ECG) signals. To achieve this, performance comparison with various types of other SotA (state-of-the-art) recurrent neural network architectures commonly used for such problems is conducted. Approach: Four architectures (N-BEATS, LSTM, LSTM with peepholes, GRU) were tested for performance and dimension reduction problems for different number of leads (2, 3, 4, 6, 12), both in variants consisting of blended branches, allowing retaining ac- curacy while reducing the computational capacity needed. The analysis was performed on datasets and using metrics from Challenges in Cardiology (CinC) 2021 competition. Main results: Best results were achieved for LSTM with peepholes, then LSTM, GRU and the worst for N-BEATS (challenge metrics respectively: 0.42, 0.40, 0.39, 0.35; for times: 0.0395 s, 0.0036 s, 0.0027 s, 0.0002 s). Commonly used LSTM outperforms N- BEATS in terms of multi-label classification, data set resilience, and obtained challenge metrics. Still, N-BEATS can obtain acceptable results for 2 lead classification (metric of 0.35 for N-BEATS and 0.38 for other networks) and outperforms other solutions in terms of complexity and speed. Significance: This paper features a novel approach of using the N-BEATS, which was previously used only for forecasting, to classify ECG signals with success. While N- BEATS multi-label classification capacity is lower than LSTM, its speed obtaining results with a reduced number of leads (faster by one to two degrees of magnitude) allows for arrhythmias detection and classification while using off-the-shelf wearable devices (Holter monitors, sport bands, etc.)

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

2022

View full text Add to dashboard Cite

show abstract

“…The authors reported that N‐BEATS outperformed the M4 forecast competition winner by 3%. Recently, the architecture has gained a number of desirable properties, including being interpretable, applicable without modification to a wide array of target domains (Jossou et al, 2022; Puszkarski et al, 2021; Sbrana et al, 2020; Siddardha et al, 2021), and fast to train.…”

Section: Brief Review Of Related Workmentioning

confidence: 99%

A deep learning hierarchical approach to road traffic forecasting

Benabdallah Benarmas,

Beghdad Bey

2024

Journal of Forecasting

View full text Add to dashboard Cite

Traffic forecasting is a crucial task of an Intelligent Transportation System (ITS), which remains very challenging as it is affected by the complexity and depth of the road network. Although the decision‐makers focus on the accuracy of the top‐level roads, the forecasts on the lower levels also improve the overall performance of ITS. In such a situation, a hierarchical forecasting strategy is more appropriate as well as a more accurate prediction methods to reach an efficient forecast. In this paper, we present a deep learning (DL) approach for hierarchical forecasting of traffic flow by exploring the hierarchical structure of the road network. The proposed approach is considered an improved variation on the top‐down strategy for the reconciliation process. We propose a model based on two deep neural network components to generate a coherent forecast for the total number of road segments. We use N‐BEATS, a pure deep learning forecasting method, at the highest levels for traffic time series, then disaggregate these downwards to get coherent forecasts for each series of the hierarchy using a combination of CNN and LSTM. Experiments were carried out using Beijing road traffic dataset to demonstrate the effectiveness of the approach.

show abstract

“…This transformation is moving the industry from the traditional manufacturing era to the intelligent manufacturing era 4.0, creating new opportunities. N-BETAS (Neural Basis Expansion Analysis for Interpretable Time Series Forecasting) [6]. The methodology for the architectural design of this system is based on a set of fundamental principles.…”

Section: Introductionmentioning

confidence: 99%

Business Intelligence Using N-Beats And Rnn Methods End Influence On Decision Making In The Flexible Packaging Manufacturing

Wahyudi

Sen

2023

JISA

View full text Add to dashboard Cite

Today's complex decision-making solutions for intelligent manufacturing depend on the ability to be able to model a manufacturing system realistically, valid and consistent data integrated easily and in a timely manner, able to solve problems efficiently with computational effort to obtain optimal production and product quality optimizations continuously. When an organization uses a data-driven approach, it means that it makes strategic decisions based on data collection, analysis, and interpretations or insights. The purpose of this research is to analyze the business intelligence approach in optimizing print machines by speed, material and time. in this research, using the N-Beats is a deep neural architecture based on backward and forward residual links and a very deep stack of fully-connected layers and Recurrent Neural Networks (RNN). The novelty of this research is increasing machine speed using new insights by combining two deep learning methods. Observing and retrieving raw data from the printing machine process with sensors data for use and ensuring the justification of the addition of new methods. The result is expected to be able to provide new insights that can increase engine speed, the data based decision making provides businesses with the capabilities to generate real time insights and predictions to optimize their performance and provide confidence in decision making that are fast, precise and better.

show abstract

N-BEATS for Heart Dysfunction Classification

Cited by 5 publications

References 4 publications

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification

A deep learning hierarchical approach to road traffic forecasting

Business Intelligence Using N-Beats And Rnn Methods End Influence On Decision Making In The Flexible Packaging Manufacturing

Contact Info

Product

Resources

About