VFPred: A fusion of signal processing and machine learning techniques in detecting ventricular fibrillation from ECG signals

Multirate Processing with Selective Subbands and Machine Learning for Efficient Arrhythmia Classification

Sensors ◽

10.3390/s21041511 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1511

Author(s):

Saeed Mian Qaisar ◽

Alaeddine Mihoub ◽

Moez Krichen ◽

Humaira Nisar

Keyword(s):

Machine Learning ◽

Signal Reconstruction ◽

Computational Cost ◽

Machine Learning Techniques ◽

Features Selection ◽

Frequency Content ◽

Fixed Rate ◽

Ecg Signals ◽

Learning Techniques ◽

Multirate Processing

The usage of wearable gadgets is growing in the cloud-based health monitoring systems. The signal compression, computational and power efficiencies play an imperative part in this scenario. In this context, we propose an efficient method for the diagnosis of cardiovascular diseases based on electrocardiogram (ECG) signals. The method combines multirate processing, wavelet decomposition and frequency content-based subband coefficient selection and machine learning techniques. Multirate processing and features selection is used to reduce the amount of information processed thus reducing the computational complexity of the proposed system relative to the equivalent fixed-rate solutions. Frequency content-dependent subband coefficient selection enhances the compression gain and reduces the transmission activity and computational cost of the post cloud-based classification. We have used MIT-BIH dataset for our experiments. To avoid overfitting and biasness, the performance of considered classifiers is studied by using five-fold cross validation (5CV) and a novel proposed partial blind protocol. The designed method achieves more than 12-fold computational gain while assuring an appropriate signal reconstruction. The compression gain is 13 times compared to fixed-rate counterparts and the highest classification accuracies are 97.06% and 92.08% for the 5CV and partial blind cases, respectively. Results suggest the feasibility of detecting cardiac arrhythmias using the proposed approach.

Get full-text (via PubEx)

Application of signal processing and machine learning techniques for segmentation and spatial registration of material property data

10.1063/1.5099757 ◽

2019 ◽

Author(s):

Josiah Dierken ◽

Daniel Sparkman ◽

Sean Donegan ◽

Sarah Wallentine ◽

John Wertz ◽

...

Keyword(s):

Machine Learning ◽

Signal Processing ◽

Material Property ◽

Machine Learning Techniques ◽

Spatial Registration ◽

Learning Techniques ◽

Property Data ◽

Material Property Data

Get full-text (via PubEx)

Ecg Heartbeat Classification: Conceptual Understanding through Cnn & Rnn – A Machine Learning Approach

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.b8285.1210220 ◽

2020 ◽

Vol 10 (2) ◽

pp. 143-147

Author(s):

P. Rama Santosh Naidu ◽

K.Venkata Ramana ◽

G. Lavanya Devi

Keyword(s):

Neural Network ◽

Machine Learning ◽

Dominant Role ◽

Machine Learning Techniques ◽

Heartbeat Classification ◽

Ecg Signals ◽

The Past ◽

Learning Techniques ◽

Machine Learning Approach

In recent days Machine Learning has become major study aspect in various applications that includes medical care where convenient discovery of anomalies in ECG signals plays an important role in monitoring patient's condition regularly. This study concentrates on various MachineLearning techniques applied for classification of ECG signals which include CNN and RNN. In the past few years, it is being observed that CNN is playing a dominant role in feature extraction from which we can infer that machine learning techniques have been showing accuracy and progress in classification of ECG signals. Therefore, this paper includes Convolutional Neural Network and Recurrent Neural Network which is being classified into two types for better results from considerably increased depth.

Get full-text (via PubEx)