A simple FPGA system for ECG R-R interval detection
05 Jun 2016-pp 1379-1382
TL;DR: A simple and reliable Field Programmable Gate Array (FPGA) based ECG analysis system is discussed and an R peak detection system is modeled that identifies the time instances, at which the R peak occurred.
Abstract: The analysis of the electrocardiogram (ECG) signal is used extensively in the diagnosis of different heart diseases. One of the major tasks to be provided is the accurate determination of the QRS complex. Due to its characteristic shape QRS detection in an ECG signal is necessary for efficient extraction of beat-to-beat intervals (RR). In this paper, a simple and reliable Field Programmable Gate Array (FPGA) based ECG analysis system is discuss. An R peak detection system is modeled that identifies the time instances, at which the R peak occurred. The developed algorithm implements into a Field Programmable Gate Array for the ECG signals feature extraction. The proposed system is built using VHDL by Xilinx ISE 14.6 package. Simulation of the algorithm is performed using MATLAB Version 8.3.0.532 (R2014a) System Generator. Simulator was taking the MITBIH Arrhythmia ECG database as input.
Citations
More filters
TL;DR: In this work, three artificial neural networks methods, namely, Back Propagation neural network (BPNN), Radial Basis Function Network (RBFN) and, K-nearest neighbor (KNN), used to forecast the level of hepatitis intensity and the results show that the prediction result by the KNN network will be better than the two other methods in time record to reach an automatic diagnosis with an error rate of less than 1.
Abstract: This work aims to design an intelligent model capable of diagnosing and predicting the severity of the hepatitis of illness that assists physicians to make an accurate decision. The main contribution is achieved by adopting a new multiclass classifier approach based on a collected real database with new proposed features that reflect the precise situation of the disease. In this work, three artificial neural networks (ANNs) methods, namely, Back Propagation neural network (BPNN), Radial Basis Function Network (RBFN) and, K-nearest neighbor (KNN), used to forecast the level of hepatitis intensity. Real data Collected from the Gastroenterology and Liver Education Hospital of the City of Medicine in Baghdad used as modeling and forecasting samples, respectively, to compare the results of forecasting. The results show that the prediction result by the KNN network will be better than the two other methods in time record to reach an automatic diagnosis with an error rate of less than 1%. Diagnosis accuracy was 99.33% for 2-class and 88% for 5-class, which considered excellent accuracy.
2 citations
01 Dec 2018
TL;DR: The accuracy of the KNN overcome the rest of the classifier with 100% accuracy for the diagnosis of hepatitis disease.
Abstract: This study aims to optimize the accuracy of diseases diagnosis, where many studies have been conducted to challenge the highest diagnostic accuracy of hepatitis disease because the early and correct diagnosis increases the chance of saving the patient's life from this deadly disease. Therefore, in this paper, we have done a good test for three classifications, namely: support vector machine (SVM), multilayer perceptron (MLP) and K-nearest neighbor (KNN). The accuracy of the KNN overcome the rest of the classifier with 100% accuracy for the diagnosis of hepatitis disease. We used the same division of data used in previous works for a fair comparison using the datasets gotten from the UCI machine learning database, with 19 features. This result is the best yet.
2 citations
31 May 2022
TL;DR: The most important key parameters needed through the analysis of SNR measurements tools within the most used techniques for estimation and signal classification are surveyed.
Abstract: The fast and great developments of communication systems especially on wireless communication lead to big responsibilities on engineers to design systems have the ability for signal to noise ratio (SNR) estimation at the receivers. These developments as a result, must be parallel with solving the problems occurred during receiving the signals. The study and evaluation of digital communication systems by means of SNR at very low SNR environments and how to estimate and predict their values is very attractive topic using cognitive radio (CR). When the data rate is increased at higher order modulation schemes, estimation and prediction of the signal from noisy signal will be very difficult. This paper basically study and survey the most important key parameters needed through the analysis of SNR measurements tools within the most used techniques for estimation and signal classification. Most of the tools related to the estimation and predication SNR such as the role of Artificial intelligence (AI) are mentioned in this review because it is very helpfully in the performance evaluation of the predication system using detection systems i.e. CR. Different types of channels and their effects on the estimation performance are studied like AWGN and fading channels because of their effects on the reduction of detection probability.
31 May 2022
TL;DR: In this article , the most important key parameters needed through the analysis of signal to noise ratio (SNR) measurements tools within the most used techniques for estimation and signal classification are discussed. And most of the tools related to the estimation and predication SNR are mentioned in this review because it is very helpfully in the performance evaluation of the predication system using detection systems i.e. CR.
Abstract: The fast and great developments of communication systems especially on wireless communication lead to big responsibilities on engineers to design systems have the ability for signal to noise ratio (SNR) estimation at the receivers. These developments as a result, must be parallel with solving the problems occurred during receiving the signals. The study and evaluation of digital communication systems by means of SNR at very low SNR environments and how to estimate and predict their values is very attractive topic using cognitive radio (CR). When the data rate is increased at higher order modulation schemes, estimation and prediction of the signal from noisy signal will be very difficult. This paper basically study and survey the most important key parameters needed through the analysis of SNR measurements tools within the most used techniques for estimation and signal classification. Most of the tools related to the estimation and predication SNR such as the role of Artificial intelligence (AI) are mentioned in this review because it is very helpfully in the performance evaluation of the predication system using detection systems i.e. CR. Different types of channels and their effects on the estimation performance are studied like AWGN and fading channels because of their effects on the reduction of detection probability.
TL;DR: In this paper , a fully-mapped field programmable gate array (FPGA) accelerator is proposed for artificial intelligence (AI)-based analysis of electrocardiogram (ECG).
Abstract: In this paper, a fully-mapped field programmable gate array (FPGA) accelerator is proposed for artificial intelligence (AI)-based analysis of electrocardiogram (ECG). It consists of a fully-mapped 1-D convolutional neural network (CNN) and a fully-mapped heart rate estimator, which constitute a complementary dual-function analysis. The fully-mapped design projects each layer of the 1-D CNN to a hardware module on an Intel Cyclone V FPGA, and a virtual flatten layer is proposed to effectively bridge the feature extraction layers and fully-connected layer. Also, the fully-mapped design maximizes computational parallelism to accelerate CNN inference. For the fully-mapped heart rate estimator, it performs pipelined transformations, self-adaptive threshold calculation, and heartbeat count on the FPGA, without multiplexed usage of hardware resources. Furthermore, heart rate calculation is elaborately analyzed and optimized to remove division and acceleration, resulting in an efficient method suitable for hardware implementation. According to our experiments on 1-D CNN, the accelerator can achieve 43.08× and 8.38× speedup compared with the software implementations on ARM-Cortex A53 quad-core processor and Intel Core i7-8700 CPU, respectively. For the heart rate estimator, the hardware implementations are 25.48× and 1.55× faster than the software implementations on the two aforementioned platforms. Surprisingly, the accelerator achieves an energy efficiency of 63.48 GOPS/W, which obviously surpasses existing studies. Considering its power consumption is only 67.74 mW, it may be more suitable for resource-limited applications, such as wearable and portable devices for ECG monitoring.
References
More filters
TL;DR: Some records of ECG signals in MIT-BIH arrhythmia database are tested to show the proposed Difference Operation Method (DOM) has a much more precise detection rate and faster speed than other methods.
268 citations
"A simple FPGA system for ECG R-R in..." refers background in this paper
...REFERENCES [1] Y....
[...]
...A complete ECG beat is shown in Figure 1[1]....
[...]
TL;DR: This study presents a comparative study of the classification accuracy of ECG signals using a well-known neural network architecture named multi-layered perceptron (MLP) with backpropagation training algorithm, and a new fuzzy clustering NN architecture (FCNN) for early diagnosis.
244 citations
"A simple FPGA system for ECG R-R in..." refers methods in this paper
...In the recent decade, many techniques have been proposed for the detection of QRS complexes, for example, algorithms based on filter banks [4], artificial neural networks [5, 6], Fuzzy Logic methods [7]....
[...]
TL;DR: A technique to truthfully classify ECG signal data into two classes (abnormal and normal class) using various neural classifier is proposed using Back Propagation Network, Feed Forward Network, and Multilayered Perceptron.
187 citations
06 Apr 2013
TL;DR: A survey of various types of noises corrupting ECG signal and various approaches based on Wavelet Transform, Fuzzy logic, FIR filtering, Empirical Mode Decomposition used in denoising the signal effectively are presented.
Abstract: Noise always degrades the quality of ECG signal. ECG noise removal is complicated due to time varying nature of ECG signal. As the ECG signal is used for the primary diagnosis and analysis of heart diseases, a good quality of ECG signal is necessary. A survey of various types of noises corrupting ECG signal and various approaches based on Wavelet Transform, Fuzzy logic, FIR filtering, Empirical Mode Decomposition used in denoising the signal effectively are presented in this paper. The result tables comparing the performances of various denoising techniques based on related parameters are included.
99 citations
Additional excerpts
...[2] S....
[...]
...5mV [2]....
[...]
31 Oct 1996
TL;DR: The proposed algorithm uses a Filter Bank (FB) based method to detect heart beats in the electrocardiogram (ECG) and the beat detection accuracy is comparable to that of other algorithms reported in the literature.
Abstract: The proposed algorithm uses a Filter Bank (FB) based method to detect heart beats in the electrocardiogram (ECG) The FB-based method allows for time and frequency dependent analysis to be performed on a signal The beat detection algorithm operates at a reduced rate as compared to the input signal rate The beat detection accuracy is comparable to that of other algorithms reported in the literature
25 citations
"A simple FPGA system for ECG R-R in..." refers methods in this paper
...In the recent decade, many techniques have been proposed for the detection of QRS complexes, for example, algorithms based on filter banks [4], artificial neural networks [5, 6], Fuzzy Logic methods [7]....
[...]
...org/ physiobank/ database/ mitdb/ [4] V....
[...]