FPGA-based real-time epileptic seizure classification using Artificial Neural Network

Abnormal heart rhythms are one of the significant health concerns worldwide. The current state-of-the-art to recognize and classify abnormal heartbeats is manually performed by visual inspection by an expert practitioner. This is not just a tedious task; it is also error prone and, because it is performed, post-recordings may add unnecessary delay to the care. The real key to the fight to cardiac diseases is real-time detection that triggers prompt action. The biggest hurdle to real-time detection is represented by the rare occurrences of abnormal heartbeats and even more are some rare typologies that are not fully represented in signal datasets; the latter is what makes it difficult for doctors and algorithms to recognize them. This work presents an automated heartbeat classification based on nonlinear morphological features and a voting scheme suitable for rare heartbeat morphologies. Although the algorithm is designed and tested on a computer, it is intended ultimately to run on a portable i.e., field-programmable gate array (FPGA) devices. Our algorithm tested on Massachusetts Institute of Technology- Beth Israel Hospital(MIT-BIH) database as per Association for the Advancement of Medical Instrumentation(AAMI) recommendations. The simulation results show the superiority of the proposed method, especially in predicting minority groups: the fusion and unknown classes with 90.4% and 100%.

https://www.mdpi.com/1424-8220/19/23/5079/pdf

Towards Real-Time Heartbeat Classification: Evaluation of Nonlinear Morphological Features and Voting Method.

Thermal Error Prediction for Heavy-Duty CNC Machines Enabled by Long Short-Term Memory Networks and Fog-Cloud Architecture

The current COVID-19 public health crisis, caused by SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2), has produced a devastating toll both in terms of human life loss and economic disruption. In this paper we present a machine-learning algorithm capable of identifying whether a given patient (actually infected or suspected to be infected) is more likely to survive than to die, or vice-versa. We train this algorithm with historical data, including medical history, demographic data, as well as COVID-19-related information. This is extracted from a database of confirmed and suspected COVID-19 infections in Mexico, constituting the official COVID-19 data compiled and made publicly available by the Mexican Federal Government. We demonstrate that the proposed method can detect high-risk patients with high accuracy, in each of four identified clinical stages, thus improving hospital capacity planning and timely treatment. Furthermore, we show that our method can be extended to provide optimal estimators for hypothesis-testing techniques commonly-used in biological and medical statistics. We believe that our work could be of use in the context of the current pandemic in assisting medical professionals with real-time assessments so as to determine health care priorities.

/pdf/identification-of-high-risk-covid-19-patients-using-machine-3yd6ivb5he.pdf

Identification of high-risk COVID-19 patients using machine learning.

This work presents an efficient hybridized approach for the classification of electrocardiogram (ECG) samples into crucial arrhythmia classes to detect heartbeat abnormalities. The physiological detection using electrocardiogram (ECG) signals has been the most popular means and widely accepted automated detection system to monitor heart health. Additionally, arrhythmia beat classification plays a prominent role in electrocardiogram (ECG) analysis dedicated elucidate cardiac health status while analyzing heart rhythm. The authors aim to classify ECG samples into major arrhythmia classes precisely by removing the inherent noise of ECG signals in preprocessing phase using discrete wavelet transformation (DWT). The QRS complex plays a crucial role in ECG signal identification. Therefore, the position and amplitude of R-peaks are determined to detect the QRS complex. The feature vectors of the QRS complex are further optimized with cuckoo search (CS) optimization algorithm in addition to denoising signals using DWT to select the most relevant set of features. The Support vector machine (SVM)-trained support vector contains the best training information used to train feed-forward back-propagation neural network (FFBPNN) to propose the variant DWT + CS + SVM-FFBPNN to classify signals among five classes. MIT-BIH arrhythmia database is utilized for different types of heartbeats. The classification analysis based on a variant with optimized feature vector using cuckoo search algorithm and SVM-FFBPNN determines heart rate with an accuracy of 98.319%. In contrast, the variant FFBPNN without optimization obtains 97.95% accuracy. The improved performance of the novel combination of classifiers resulted in overall classification accuracy of 98.53% with precision and recall of 98.247% and 95.68%, respectively. The simulation analysis comprising 3600 samples and 1160 heartbeats also outperformed the existing arrhythmia classifications performed based on neural networks. This illustrates the success of the proposed ECG classification model in accurately categorizing ECG signals for arrhythmia classification.

A novel hybrid deep learning method with cuckoo search algorithm for classification of arrhythmia disease using ECG signals

The automatic detection and cardiac classification are essential tasks for real-time cardiac diseases diagnosis. In this context, this paper describes a field programmable gates array (FPGA) implementation of arrhythmia recognition system, based on artificial neural network. Firstly, we have developed an optimized software-based medical diagnostic approach, capable of defining the best electrocardiogram (ECG) signal classes. The main advantage of this approach is the significant features minimization, compared to the existing researches, which leads to minimize the FPGA prototype size and saving energy consumption. Secondly, to provide a continuous and mobile arrhythmia monitoring system for patients, we have performed a hardware implementation.
The FPGA has been referred due to their easy testing and quick implementation. The optimized approach implementation has been designed on the Nexys4 Artix7 evaluation kit using the Xilinx System Generator for DSP. In order to evaluate the performance of our proposal system, the classification performances of proposed FPGA fixed point have been compared to those obtained from the MATLAB floating point. The proposed architecture is validated on FPGA to be a customized mobile ECG classifier for long-term real-time monitoring of patients.

FPGA-based system for artificial neural network arrhythmia classification

The continuous monitoring of cardiac patients requires an ambulatory system that can automatically detect heart diseases. This study presents a new field programmable gate array (FPGA)-based hardware implementation of the QRS complex detection. The proposed detection system is mainly based on the Pan and Tompkins algorithm, but applying a new, simple, and efficient technique in the detection stage. The new method is based on the centred derivative and the intermediate value theorem, to locate the QRS peaks. The proposed architecture has been implemented on FPGA using the Xilinx System Generator for digital signal processor and the Nexys-4 FPGA evaluation kit. To evaluate the effectiveness of the proposed system, a comparative study has been performed between the resulting performances and those obtained with existing QRS detection systems, in terms of reliability, execution time, and FPGA resources estimation. The proposed architecture has been validated using the 48 half-hours of records obtained from the Massachusetts Institute of Technology - Beth Israel Hospital (MIT-BIH) arrhythmia database. It has also been validated in real time via the analogue discovery device.

https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/iet-cds.2018.5204

FPGA-based system for heart rate monitoring

In order to develop a prototype of upper limb prosthetic, we present in this paper our contribution to the design of an intelligent classification system for the arm's flexion and extension. The first step, we designed a simple and efficient single channel of electro myogram signal (EMG) acquisition circuit in order to create two databases that contains EMG signals matrices of both flexion and extension of the arm. Our work proves that only one statistical feature, the energy of detail coefficients for the first four decomposition levels, is sufficient to represent these databases. We applied the principal component analysis PCA to reduce the data space and keep the most relevant ones. In order to detect flexion or extension movement, classification by Support Vector Machines (SVM) has made possible for us to achieve recognition rate of 100% using a wise choice of discret wavelet transform (DWT).

Single channel EMG classification using DWT and SVM

Due to the rising number of cardiovascular diseases death, the monitoring of cardiac patients has become a primary objective in the world. In this context, a fully FPGA-based system, for ECG signal...

Fpga implementation system for qrs complex detection

The study aims to establish an FPGA design model for epileptic seizures with discrete wavelet decomposition (DWT) and principal component analysis (PCA) to determine the optimum parameters of support vector machine (SVMs) for the EEG classification data. The FPGA Hardware implementation is described in this paper. Firstly, an optimized software-based medical diagnostic approach has been developed to determine the EEG class using only the variance calculated for each DWT level. This features extracted optimization leads to reduce the FPGA prototype size and to save energy consumption. Secondly, the proposed method has been designed and implemented on the Nexys 4 Artix 7 board using the Xilinx System Generator (XSG) for DSP. The performance evaluation of the proposed system has been made through two comparative studies, the first one, between the floating-point Matlab results and the fixed-point XSG results. The classification performances obtained from the proposed FPGA fixed-point implementation were compared to those obtained from the MATLAB floating-point. The second comparison was performed between the resulting performances and those obtained with the existing work in literature.

Karim Meddah

Papers

FPGA-based system for artificial neural network arrhythmia classification

FPGA-based system for heart rate monitoring

Single channel EMG classification using DWT and SVM

Fpga implementation system for qrs complex detection

FPGA implementation of Epileptic Seizure detection based on DWT, PCA and Support Vector Machine