An explainable attention-based TCN heartbeats classification model for arrhythmia detection

Zhao, Yuxuan; Ren, Jiadong; Zhang, Bing; Wu, Jiasheng; Lyu, Yeoung-Su

doi:10.1016/j.bspc.2022.104337

Cited by 12 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, [10] used methods based on machine learning and required a lot of manual handling but also reported low accuracy. [12] reported a higher f1-score than us, but they did not show the result with detailed metric computation. We computed the macro f1-score, which is commonly used for imbalanced datasets.…”

Section: Originalcontrasting

confidence: 62%

“…Following the inter-patient paradigm, the resulting framework demonstrated an accuracy of 94.7% when assessed on the MIT-BIH Arrhythmia database. In the work detailed in [12], Zhao et al introduced an arrhythmia classification technique that leveraged the temporal Convolutional Neural Network (CNN) to extract ECG features. They achieved an accuracy of 87.8%.…”

Section: A Ecg Feature Extractionmentioning

confidence: 99%

See 1 more Smart Citation

A Task-Generic High-Performance Unsupervised Pre-Training Framework for ECG

Wang,

Nag

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

Electrocardiogram (ECG) feature extraction is becoming increasingly important in the biomedical field. In deep learning studies centred on ECG data, established methods mainly rely on labelled signals. However, obtaining high-quality labelled records from open-source datasets is challenging, whereas many unlabeled data remain underutilized. Unsupervised pre-training methods have shown significant efficacy in utilizing datasets and improving performance. Therefore, incorporating unsupervised pretraining paradigms into ECG feature extraction is a strategic choice. This paper presents an unsupervised pre-training framework based on the Masked Autoencoder for extracting ECG signal features. An encoder-decoder framework is designed to recover artificially masked ECGs. During the reconstruction process, the framework can learn knowledge from masked samples. Benefiting from the utilization of large-scale datasets and the reconstruction design, the framework is general and has a high level of performance across a wide range of tasks. In particular, the framework achieves an accuracy of 95.6% on the MITDB dataset for the ECG arrhythmia classification task and 98.8% on the ECGIDDB dataset for the human identification task. Our method introduces novel strategies for training on large-scale unlabeled data. Empirical evaluations, including multiple downstream tasks and comparisons with the state of the art, confirm the validity of our proposed approach.

show abstract

Section: Originalcontrasting

confidence: 62%

Section: A Ecg Feature Extractionmentioning

confidence: 99%

A Task-Generic High-Performance Unsupervised Pre-Training Framework for ECG

Wang,

Nag

et al. 2024

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…According to this standard, heartbeats are recommended to be grouped into five main classes (Shi et al 2019): Normal (N), Supraventricular ectopic beat (S), Ventricular ectopic beat (V), Fusion of ventricular and normal beat (F), and Unknown beat (Q). Although most studies adhere to this standard (Li et al 2022b;Zhao et al 2023;Wang et al 2019;Han et al 2022), some may choose alternative classification schemes (Lu et al 2021). The extensive use of this database has resulted in numerous published studies, providing ample opportunities for comparisons with previous results.…”

Section: Datasetsmentioning

confidence: 99%

Cost-sensitive learning for imbalanced medical data: a review

Araf,

Idri,

Chairi

2024

Artif Intell Rev

View full text Add to dashboard Cite

Integrating Machine Learning (ML) in medicine has unlocked many opportunities to harness complex medical data, enhancing patient outcomes and advancing the field. However, the inherent imbalanced distribution of medical data poses a significant challenge, resulting in biased ML models that perform poorly on minority classes. Mitigating the impact of class imbalance has prompted researchers to explore various strategies, wherein Cost-Sensitive Learning (CSL) arises as a promising approach to improve the accuracy and reliability of ML models. This paper presents the first review of CSL for imbalanced medical data. A comprehensive exploration of the existing literature encompassed papers published from January 2010 to December 2022 and sourced from five major digital libraries. A total of 173 papers were selected, analysed, and classified based on key criteria, including publication years, channels and sources, research types, empirical types, medical sub-fields, medical tasks, CSL approaches, strengths and weaknesses of CSL, frequently used datasets and data types, evaluation metrics, and development tools. The results indicate a noteworthy publication rise, particularly since 2020, and a strong preference for CSL direct approaches. Data type analysis unveiled diverse modalities, with medical images prevailing. The underutilisation of cost-related metrics and the prevalence of Python as the primary programming tool are highlighted. The strengths and weaknesses analysis covered three aspects: CSL strategy, CSL approaches, and relevant works. This study serves as a valuable resource for researchers seeking to explore the current state of research, identify strengths and gaps in the existing literature and advance CSL’s application for imbalanced medical data.

show abstract

“…XAI is most frequently applied in industries requiring high decision-making accuracies and accountability levels, such as healthcare (Faust et al, 2023;Rivera et al, 2023;Z. Wang et al, 2023;Zhao, Ren, Zhang, Wu, & Lyu, 2023) and management (Angelotti & Díaz-Rodríguez, 2023;Langer & König, 2023;Lee, Jung, Lee, Kim, & Park, 2021). There is relatively less research in the area of explainable artificial intelligence in predictive maintenance.…”

Section: Introductionmentioning

confidence: 99%

Explainable artificial intelligence (XAI) enabled anomaly detection and fault classification of an industrial asset

Sharma

Mittal

Soni

2023

Preprint

View full text Add to dashboard Cite

Predictive maintenance helps organizations to reduce equipment downtime, optimize maintenance schedules, and enhance operational efficiency. By leveraging machine learning algorithms to predict when equipment failure will likely occur, maintenance teams can proactively schedule maintenance activities and prevent unexpected breakdowns. Anomaly detection and fault classification are essential components of predictive maintenance. Anomaly detection involves analyzing sensor data collected from equipment to identify deviations from normal behavior. Fault classification, on the other hand, involves identifying the root cause of a fault or failure. A dataset of an industrial asset is used to evaluate the proposed study. Four distinct data-driven anomaly detection methodologies were employed after the pre-processing of the data, with the deep learning-based autoencoder producing the best results of all the techniques. Implementing machine learning-based fault categorization approaches revealed that Random Forest had the best results. Bayesian optimization and sequential model-based hyperparameter optimization technique is used for greater accuracy and optimized hyperparameters. Significant progress has been made in anomaly detection and fault classification using machine learning, but the degree of their explainability is significantly limited by the ``black-box" character of some machine learning techniques. Less emphasis has been placed on explainable artificial intelligence (XAI) approaches in the domain of maintenance. Therefore, the XAI tools have been used to acknowledge the extent of the variables to analyze the influence of respective features. A stability metric has been included to improve the explanation's overall quality. The findings of this article suggest that the utilization of eXplainable Artificial Intelligence (XAI) can offer significant contributions in terms of insights and solutions for addressing critical maintenance issues. As a result, decision-making processes can become more informed and effective.

show abstract

An explainable attention-based TCN heartbeats classification model for arrhythmia detection

Cited by 12 publications

References 16 publications

A Task-Generic High-Performance Unsupervised Pre-Training Framework for ECG

A Task-Generic High-Performance Unsupervised Pre-Training Framework for ECG

Cost-sensitive learning for imbalanced medical data: a review

Explainable artificial intelligence (XAI) enabled anomaly detection and fault classification of an industrial asset

Contact Info

Product

Resources

About