Bipolar Pulse Active features for ECG biometric application

Safie, Sairul Izwan; Yusof, Mohd Ismail; Kadir, Kushsairy; Nasir, Haidawati

doi:10.1109/icbaps.2015.7292207

Cited by 3 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tilendra et al [6] suggested biometric recognition using ECG signals with normalized cross correlation metric. Sairul safie et al [7] proposed to extract bipolar active features and the authentication performance was computed with and without classifier of Linear Discriminant Analysis (LDA). Md.…”

Section: Fig1 Ecg Pulse With P-qrs-t Pointsmentioning

confidence: 99%

Swarm based Intelligent Feature Optimization Technique for ECG based Biometric Human Recognition

Patro¹,

Rao²,

Kumar³

2019

IJEAT

View full text Add to dashboard Cite

Recently, rapid growth in network technology and communication leads to widening human activities, so that a strong identification system is necessary. This work aims to build an accurate identification technology based on unique physiological characteristics of ECG. The Biometric recognition of ECG primarily depends on the quality of its features. Feature extraction is performed on parameters of a cardiac cycle based on the fiducial approach and large data sets of features have been extracted. The extracted dataset contains irrelevant, correlated and over-fitted features, which misleads the biometric system performance so that an effective feature optimization is needed to sort out those features to avoid redundancy in the data. In this paper, a novel swarm based intelligent feature optimization method; Particle Swarm Optimization (PSO) is used to generate feature subset based on a fitness function with joint entropy. The dataset from optimization phase are fed to classifiers such as ANN, K-NN and SVM for recognition. The proposed approach is tested with available open source MIT-BIH ECG ID database. Finally, a comparison is made with and without feature optimization in which PSO with KNN shows recognition accuracy of 97.8931%.

show abstract

Section: Fig1 Ecg Pulse With P-qrs-t Pointsmentioning

confidence: 99%

Swarm based Intelligent Feature Optimization Technique for ECG based Biometric Human Recognition

Patro¹,

Rao²,

Kumar³

2019

IJEAT

View full text Add to dashboard Cite

show abstract

“…In a high-tech world, various types of medical imaging modalities are used to assist diagnosis and analyze the diseases inside the human body [1]- [3]. The increasing number of patients annually will potentially increase the medical data generated.…”

Section: Introductionmentioning

confidence: 99%

Discrete Curvelet Transform Algorithm for Image Compression System

Ja’afar¹

2020

IJATCSE

View full text Add to dashboard Cite

A medical image has dominated the compression techniques since it requires to have a smaller size of the image and should maintain the relevant diagnostic information. Reducing the size of the image, directly give impact to the transmission speed. This paper presents an approach towards compression algorithm development using discrete curvelet transform. Curvelet functions signify functions which have discontinuities along straight lines where wavelet functions are not properly worked. The curvelet transform algorithm were synthesized using MATLAB and various medical modalities such as computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound are used as a sample's medical images. The results obtained clearly identify that discrete curvelet transform algorithm gives a good quality for the reconstructed images.

show abstract

“…In the high-tech world, various types of medical tools such as electrocardiogram (ECG), electromyography (EMG), computed tomography (CT), positron emission tomography (PET), ultrasound (US), magnetic resonance imaging (MRI) and X-ray routinely used to diagnose and analyze illness inside human body [1][2][3]. In the context of medical algorithms, a massive amount of data to be processed has affected the organization of the memory units.…”

Section: Introductionmentioning

confidence: 99%

Pipeline architectures of Three-dimensional daubechies wavelet transform using hybrid method

Ja’afar

Ahmad

2019

IJEECS

View full text Add to dashboard Cite

<span>The application of three-dimensional (3-D) medical image compression systems uses several building blocks for its computationally intensive algorithms to perform matrix transformation operations. Complexity in addressing large medical volumes data has resulted in vast challenges from a hardware implementation perspective. This paper presents an approach towards very-large-scale-integration (VLSI) implementation of 3-D Daubechies wavelet transform for medical image compression. Discrete wavelet transform (DWT) algorithm is used to design the proposed architectures with pipelined direct mapping technique. Hybrid method use a combination of hardware description language (HDL) and G-code, where this method provides an advantage compared to traditional method. The proposed pipelined architectures are deployed for adaptive transformation process of medical image compression applications. The soft IP core design was targeted on to Xilinx field programmable gate array (FPGA) single board RIO (sbRIO 9632). Results obtained for 3-D DWT architecture using Daubechies 4-tap (Daub4) implementation exhibits promising results in terms of area, power consumption and maximum frequency compared to Daubechies 6-tap (Daub6).</span>

show abstract

Bipolar Pulse Active features for ECG biometric application

Cited by 3 publications

References 14 publications

Swarm based Intelligent Feature Optimization Technique for ECG based Biometric Human Recognition

Swarm based Intelligent Feature Optimization Technique for ECG based Biometric Human Recognition

Discrete Curvelet Transform Algorithm for Image Compression System

Pipeline architectures of Three-dimensional daubechies wavelet transform using hybrid method

Contact Info

Product

Resources

About