Naïve Bayes Classifier for ECG Abnormalities Using Multivariate Maximal Time Series Motif

Padmavathi, S.; Ramanujam, E.

doi:10.1016/j.procs.2015.03.201

Cited by 55 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this field, the wavelet transform plays important role due to their significant nature of sub-band decomposition. Yadav [29] suggested that DWT based approaches are dependent on the inherit sparsity of clean signal in the transform domain hence these methods do not face issues of data sample estimation unlike the sample-based denoising algorithms [30]. However, the DWT method fails to exploit the non-redundancy information in the signal.…”

Section: Literature Surveymentioning

confidence: 99%

See 1 more Smart Citation

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

2019

IJITEE

View full text Add to dashboard Cite

Cardiovascular diseases (CVD) are the most chronic and dangerous diseases in worldwide. The early prediction of CVD can help to prevent deaths due to these diseases, using bio-medical signal analysis. In this field, the ECG signal plays an important role due to its significant nature of providing the health-related information. However, the signal acquisition process is a crucial step where signals get corrupted due to electrode movement, muscle movement and other types of interference which can degrade the performance of the signal analysis. Several approaches have been introduced but achieving the desired performance robustly is still considered as a challenging task. This paper presents a novel approach for ECG signal filtering by combining a combination of the extended Kalman filter, wavelet transform and an adaptive thresholding approach called as Linearized Kalman Filter aided Wavelet transform with Adaptive Thresholding (LKFWAT). In this process, the initial states of the signal are observed using a Kalman filter, later; a linearization scheme is presented to represent the signal in the linear form. Finally, an adaptive threshold method is applied to reduce the noise during signal construction. It will show the significant improvement in next level process of disease classification. A comparative experimental analysis is carried out which shows that the proposed approach achieves improved performance when compared with the state-of-art ECG denoising techniques.

show abstract

Section: Literature Surveymentioning

confidence: 99%

“…Several classification schemes are also present such as Deep Neural network [25], Neural Network [26], Support Vector Machine [27], and Naïve Bayes classifier [28] etc...…”

mentioning

confidence: 99%

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

2019

IJITEE

View full text Add to dashboard Cite

show abstract

“…For example, if a doctor initiates a clinical test for a patient, the report of the test is stored as quantitative data in a medical data repository as mentioned in [3] and used to predict the disease in near future. In this scenario, the data conversion from raw medical record to computerized data and storage of data is a critical one.…”

Section: Problem Statementmentioning

confidence: 99%

Rule based Medical Content Classification for Secure Remote Health Monitoring

Balachander¹,

Ramanujam²

2017

IJCA

Self Cite

View full text Add to dashboard Cite

Now days, Medical data records are computerized and it is essential to predict the disease / symptoms of a patient in near future. The medical data records are referred during multiple disease prediction and to implement patient health monitoring system. The clinical data is essential to create clinically applicable information in healthcare system for treatment analysis. Ontology based implementation helps to classify clinical data and provide better results which is helpful to identify relevant symptoms and causes for a disease identification in patient health monitoring from the past clinical records. The proposed system implements rule based ontology classification method such as pattern matching for patient's diseases and compare with other methods such as Resource Description Framework implementation and SPARQL query language method. The results from this analysis can be helpful to developers and hospitals that can use the results to reduce the incorrect medical decisions facilitated by these systems.

show abstract

“…normal ECG signals vs. abnormal ECG signals. Overall classification accuracy reported in[29] was 93.33. In[30], ECG signal classification was performed by using reservoir computing with logistic regression (LR).…”

mentioning

confidence: 94%

“…The authors reported that with this approach normal heartbeats can be classified with accuracy of 100 %, paced beats with accuracy of 83.3 %, LBBB beats with accuracy of 95.8 %, RBBB beats with accuracy of 91.6 % and PVC beats with accuracy of 83.3 %. In[29], system based on multivariate maximal time series motif and naïve Bayes classifier was proposed for ECG signal classification. In this study, only 2 classes were considered, i.e.…”

mentioning

confidence: 99%

The effect of denoising on classification of ECG signals

Aličković

Babić

2015

2015 XXV International Conference on Information, Communication and Automation Technologies (ICAT)

View full text Add to dashboard Cite

Electrocardiogram (ECG) signals are affected by different types of noise and artifacts which can hide significant information related to heart functioning. Therefore, denoising of signals is essential for accurate diagnosis of different heart diseases. This study examines and compares three different denoising techniques, namely Principal Component Analysis (PCA), Independent Component Analysis (ICA) and Multiscale Principal Component Analysis (MSPCA), and their influence on ECG signal classification. In order to extract significant features from ECG signals, wavelet packet decomposition (WPD) technique is employed. To classify ECG signals, ensemble machine learning classifier called Rotation Forest is proposed for classification task. In this study, three different systems, namely PCA-WPD-Rotation Forest, ICA-WPD-Rotation Forest and MSPCA-WPD-Rotation Forest were analyzed and evaluated in terms of three different statistical metrics, namely F-measure, AUC value and overall accuracy. To evaluate performances of proposed systems, MIT-BIH database is used. Obtained experimental results showed that MSPCA-WPD-Rotation Forest system resulted in the highest performances when compared to PCA-WPD-Rotation Forest and ICA-WPD-Rotation Forest. Therefore, in this study following system for classification of ECG signals is proposed: MSPCA as the first component for denoising, WPD as the second component which extracts important features from ECG signals and Rotation Forest as the third component which performs classification of ECG signals. The comparison to other systems for classification of EEG signals shown that proposed system outperforms other systems on the MIT-BIH arrhythmia database under investigated conditions.

show abstract

Naïve Bayes Classifier for ECG Abnormalities Using Multivariate Maximal Time Series Motif

Cited by 55 publications

References 18 publications

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

Linearized Kalman Filter aided Wavelet Transform with Adaptive Thresholding Methodfor ECG signal

Rule based Medical Content Classification for Secure Remote Health Monitoring

The effect of denoising on classification of ECG signals

Contact Info

Product

Resources

About