Exploring interpretable representations for heart sound abnormality detection

Wang, Zhihua; Qian, Kun; Liu, Houguang; Hu, Bin; Schuller, Björn W.; Yamamoto, Yoshiharu

doi:10.1016/j.bspc.2023.104569

Cited by 13 publications

(4 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Te authors in [3] presents a TQWT-based two-stage abnormality detection approach, where SVM is used in the frst stage for binary classifcation and the KNN is used in the second stage for further classifcation. In addition, Shannon energy [4], cochleagram features [5], and mel-frequency cepstral coefcients (MFCC) [6] are also considered as other characteristics to detect abnormalities in signals. To detect abnormalities in signals, Karhade et al.…”

Section: Introductionmentioning

confidence: 99%

Heart Signal Analysis Using Multistage Classification Denoising Model

Choudhary,

Rani,

Kaur

et al. 2024

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

Cardiovascular disease is a major cause of death worldwide, and the COVID-19 pandemic has only made the situation worse. The purpose of this work is to explore various time-frequency analysis methods that can be used to classify heart sound signals and identify multiple abnormalities in the heart, such as aortic stenosis, mitral stenosis, and mitral valve prolapse. The signal has been modified using three techniques—tunable quality wavelet transform (TQWT), discrete wavelet transform (DWT), and empirical mode decomposition—to detect heart signal abnormality. The proposed model detects heart signal abnormality at two stages, the user end and the clinical end. At the user end, binary classification of signals is performed, and if signals are abnormal then further classification is done at the clinic. The approach starts with signal preprocessing and uses the discrete wavelet transform (DWT) coefficients to train the hybrid model, which consists of one long short-term memory (LSTM) network layer and three convolutional neural network (CNN) layers. This method produced comparable results, with a 98.9% classification accuracy for signals, through the utilization of the CNN and LSTM model. Combining the CNN’s skill in feature extraction with the LSTM’s capacity to record time-dependent features improves the efficacy of the model. Identifying issues early and initiating appropriate medication can alleviate the burden associated with heart valve diseases.

show abstract

Section: Introductionmentioning

confidence: 99%

Heart Signal Analysis Using Multistage Classification Denoising Model

Choudhary,

Rani,

Kaur

et al. 2024

Journal of Electrical and Computer Engineering

View full text Add to dashboard Cite

show abstract

“…With the aid of explainable AI (XAI), these methods can be better explained and more transparent to decision-makers. 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).…”

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

“…Consequently, the importance of Explainable Artificial Intelligence (XAI) [5] in sound recognition has grown significantly. Within this field, a common approach involves the transformation of sound into spectrograms through feature extraction, followed by recognition and interpretation [6,7]. Traditional sound recognition methods rely on shallow classifiers, such as Mel-frequency cepstral coefficients (MFCCs) and decision trees [8], known for their model interpretability.…”

Section: Introductionmentioning

confidence: 99%

An Evaluation Method for Interpretable Models in Sound Recognition

Lu,

Guan,

Yuan

2023

Preprint

View full text Add to dashboard Cite

In recent years, the application scope of artificial intelligence voice recognition has been expanding rapidly. Investigating the interpretability of sound recognition and enhancing the effectiveness of sound interpretation hold significant importance for both theoretical research and practical applications. However, there is currently a lack of an effective method to assess the interpretability of sound explanations. Therefore, this paper introduces an evaluation method called AI-SCORE, which focuses on interpretable models for sound recognition. AI-SCORE processes the features of sound spectrograms based on their interpretability importance and then re-predicts to calculate the model's positive and negative feature correlations. Based on this, we examine the impact of different feature extraction methods, various neural network models, and parameter settings during the interpretation on interpretation performance. Experiments show that under the ResNet network model, the model trained using mel spectrogram as a feature extraction method achieves the best interpretation performance. Additionally, appropriate iterative precision can further enhance the interpretation effect during the interpretation process.

show abstract

Exploring interpretable representations for heart sound abnormality detection

Cited by 13 publications

References 91 publications

Heart Signal Analysis Using Multistage Classification Denoising Model

Heart Signal Analysis Using Multistage Classification Denoising Model

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

An Evaluation Method for Interpretable Models in Sound Recognition

Contact Info

Product

Resources

About