Discrete Wavelet Transform based algorithm for recognition of QRS complexes

Haddadi, Rachid; Abdelmounim, Elhassane; Hanine, M.; Belaguid, Abdelaziz

doi:10.1109/icmcs.2014.6911261

Cited by 46 publications

(23 citation statements)

References 7 publications

(6 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Three classifiers are support vector machine (SVM ), K-nearest neighbour (KNN) and decision tree (D-tree), which are mainly considered to distinguish the behaviour and fres hness of fruit slices by estimating the M C of these slices fro m day 1 to 4. In this regard, the Radial Basis Function (RBF) kernel is applied in SVM classifier to set key parameters including the Gaussian kernel scale (γ), and the optimu m parameters of cos t (C) to 0.35 and 1 respectively, after the grid searching optimization of parameters γ(0.1: 0.05: 2) and C(0.5: 0.5: 2) [22]. For the key parameter in KNN classifier, we set the number of nearest neighbours k and the distance metric to 5 after examining the range of k(1:10) and Euclidean distance, respectively [23].…”

Section: A Classification Accuracy For Different Feature Datesetsmentioning

confidence: 99%

“…The wavelet-transform (WT) was more suitable for analyzing the short-duration pulse with fast and unpredictable changes to obtain interesting information [19]. After wavelet de-noising of the observations in time domain, the representation of the time-frequency domain was performed by three level wavelet decomposition using db8 wavelet, and a total of four sub-band signals are decomposed, in which one approximation coefficient, C 3 (n), and three detail wavelet coefficients, D 3 (n),D 2 (n), and D 1 (n), can be applied to extract time-frequency domain features [21] [22]. The features of the extracted wavelet coefficients can provide the energy distribution of the THz signal in time and frequency domain.…”

Section: Time-frequency Domain Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning Driven Approach Towards the Quality Assessment of Fresh Fruits Using Non-Invasive Sensing

et al. 2020

View full text Add to dashboard Cite

2020) Machine learning driven approach towards the quality assessment of fresh fruits using non-invasive sensing.Abstract-In agriculture science, accurate information of moisture content (MC) in fruits and vegetables in an automated fashion can be vital for astute quality and grading evaluation. This demands for a viable, feasible and cost-effective technique for the defect recognition using timely detection of MC in fruits and vegetables to maintain a healthy sensory characteristic of fruits. Here we propose a non-invasive machine learning (ML) driven technique to monitor variations of MC in fruits using the terahertz (THz) waves with Swissto12 material characterization kit (MCK) in the frequency range of 0.75 THz to 1.1 THz. In this regard, multi-domain features are extracted from time-, frequency-, and time-frequency domains, and applied three ML algorithms such as support vector machine (SVM), knearest neighbour (KNN) and Decision Tree (D-Tree) for the precise assessment of MC in both apple and mango slices. The results illustrated that the performance of SVM exceeded other classifiers results using 10-fold validation and leave-oneobservation-out-cross-validation techniques. Moreover, all three classifiers exhibited 100% accuracy for day 1 and 4 with 80% MC value (freshness) and 2% MC value (staleness) of both fruits' slices, respectively. Similarly, for day 2 and 3, an accuracy of 95% was achieved with intermediate MC values in both fruits' slices. This study will pave a new direction for the real-time quality evaluation of fruits in a non-invasive manner by incorporating ML with THz sensing at a cellular level. It also has a strong potential to optimize economic benefits by the timely detection of fruits quality in an automated fashion.

show abstract

Section: A Classification Accuracy For Different Feature Datesetsmentioning

confidence: 99%

Section: Time-frequency Domain Featuresmentioning

confidence: 99%

Machine Learning Driven Approach Towards the Quality Assessment of Fresh Fruits Using Non-Invasive Sensing

et al. 2020

View full text Add to dashboard Cite

show abstract

“…The method that we propose to eliminate the baseline is based on DWT decomposition up to level 8, which generates a set of approximation coefficients(C8), and eight sets of detail coefficients(d1,…,d8). By cancellation of approximations, the filtered signal is recovered from the details only [19]. Some results in the removal of baseline wanders is shown in Figure 2.…”

Section: Preprocessingmentioning

confidence: 99%

“…The ECG signal is reconstructed with the coefficient d4. To detect the R Peaks, we use a hard thresholding method [19]. Figure 4 shows the original ECG signal with R peaks localization.…”

Section: Detection Of Qrs Complexesmentioning

confidence: 99%

A Wavelet-Based ECG Delineation and Automated Diagnosis of Myocardial Infarction in PTB Database

Haddadi¹,

Abdelmounim²,

Hanine³

et al. 2019

Proceedings of the Third International Conference on Computing and Wireless Communication Systems, ICCWCS 2019, April 24-25, 20

Self Cite

View full text Add to dashboard Cite

In this work, we present an ECG delineation and the automated diagnosis of coronary artery disease in the electrocardiogram (ECG). In preprocessing stage, the baseline wander (BLW) and 60 Hz power line interference (PLI) were removed using discrete wavelet transform (DWT). The QRS detection is carried out using Daubechies (Db4) DWT. Feature extraction and classification is done using a convolutional neural network (CNN) containing three convolutional layers, three max-pooling layers, and three fully connected layers. The standard 12 lead ECG signals of 50 healthy subjects and 50 myocardial infarction subjects (MI) of one minute are obtained from the Physikalisch-Technische Bundesanstalt (PTB) database. We achieved an accuracy of 94.83%. sensitivity of 94.75%, and specificity of 94.93% on PTB database.

show abstract

“…DWT is a method of reduce noise and detect R-peak of ECG signal. However, it does not work as expected in the detection and delineation of low frequency waves such as P and T [10]. The discrete wavelet transform (DWT) can be writing as the following:…”

Section: Discrete Wavelet Transform (Dwt)mentioning

confidence: 99%

A Survey on Classification of ECG Signal Study

Taha¹,

El‐Sayed²,

Salma³

2016

CAE

View full text Add to dashboard Cite

Electrocardiogram (ECG) is a non-linear dynamic signal which plays the main role in diagnosis heart diseases. Classification of ECG signal is one of the most important reason of diagnosing the heart diseases. Detecting accurate ECG signal not only the most difficult task but also classifying heart signal is very difficult task. There are many types of classifiers are available for ECG classification. The most popular classifier that used in ECG classification is Artificial Neural Network (ANN) and in second degree is Support Vector Machine (SVM). In this paper, we discuss a survey of preprocessing, ECG database, feature extraction and classifiers. This paper also discusses background of Electrocardiogram, evaluation matrices of classifiers and issues of classifiers.

show abstract

Discrete Wavelet Transform based algorithm for recognition of QRS complexes

Cited by 46 publications

References 7 publications

Machine Learning Driven Approach Towards the Quality Assessment of Fresh Fruits Using Non-Invasive Sensing

Machine Learning Driven Approach Towards the Quality Assessment of Fresh Fruits Using Non-Invasive Sensing

A Wavelet-Based ECG Delineation and Automated Diagnosis of Myocardial Infarction in PTB Database

A Survey on Classification of ECG Signal Study

Contact Info

Product

Resources

About