scholarly journals Searching for Premature Ventricular Contraction from Electrocardiogram by Using One-Dimensional Convolutional Neural Network

Electronics ◽  
2020 ◽  
Vol 9 (11) ◽  
pp. 1790
Author(s):  
Junsheng Yu ◽  
Xiangqing Wang ◽  
Xiaodong Chen ◽  
Jinglin Guo
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Time Window ◽  
Premature Ventricular Contraction ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Ventricular Contraction ◽  
Test Set ◽  
One Dimensional

Premature ventricular contraction (PVC) is a common cardiac arrhythmia that can occur in ordinary healthy people and various heart disease patients. Clinically, cardiologists usually use a long-term electrocardiogram (ECG) as a medium to detect PVC. However, it is time-consuming and labor-intensive for cardiologists to analyze the long-term ECG accurately. To this end, this paper suggests a simple but effective approach to search for PVC from the long-term ECG. The recommended method first extracts each heartbeat from the long-term ECG by applying a fixed time window. Subsequently, the model based on the one-dimensional convolutional neural network (CNN) tags these heartbeats without any preprocessing, such as denoise. Unlike previous PVC detection methods that use hand-crafted features, the proposed plan rationally and automatically extracts features and identify PVC with supervised learning. The proposed PVC detection algorithm acquires 99.64% accuracy, 96.97% sensitivity, and 99.84% specificity for the MIT-BIH arrhythmia database. Besides, when the number of samples in the training set is 3.3 times that of the test set, the proposed method does not misjudge any heartbeat from the test set. The simulation results show that it is reliable to use one-dimensional CNN for PVC recognition. More importantly, the overall system does not rely on complex and cumbersome preprocessing.

scholarly journals Automatic Arrhythmia Detection Using One-Dimensional Convolutional Neural Network

2020 ◽  
Author(s):  
Zhong Liu ◽  
Xin’an Wang
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Cardiac Activity ◽  
The Elderly ◽  
Accurate Method ◽  
Detection Algorithm ◽  
Dynamic Monitoring ◽  
Ecg Signal ◽  
One Dimensional ◽  
Ecg Signals

Abstract Background: Cardiovascular diseases (CVDs) are common diseases that pose significant threats to human health. Statistics have demonstrated that a large number of individuals die unexpectedly from sudden CVDs. Therefore, real-time monitoring and diagnosis of abnormal changes in cardiac activity are critical, as they can help the elderly and patients handle emergencies in a timely manner. To this end, a round-the-clock electrocardiogram (ECG) monitoring system can be developed with the quick detection of an ECG signal, segmentation of the detected ECG signal, and rapid diagnosis of a single segmented ECG beat. In this paper, to achieve the automatic detection and diagnosis of an ECG signal, five common types of ECG signals are used for recognition. For pre-processing the original ECG signal, the dual-slope detection algorithm is proposed and developed. Then, with the pre-processed ECG data, a five-layer one-dimensional convolutional neural network is constructed to classify five categories of heartbeats, namely, a normal heartbeat and four types of abnormal heartbeats. Results: To be able to compare the results of the experiment, the experimental data used in this study are obtained from the open-source MIT-BIH arrhythmia database. This database is authoritative, as each ECG signal cycle is annotated by at least two cardiologists, and abnormal ECG signals are classified into different categories. By comparing the detection and recognition results in this study with the results annotated in the MIT-BIH arrhythmia database, an overall accuracy of 96.20% is achieved in the classification of normal ECG signals and four categories of abnormal ECG signals.Conclusions: This paper provides an accurate method with low computational complexity for 24-hour dynamic monitoring and automated diagnosis of heartbeat conditions. With wearable devices, this method can be used at home for the initial screening of CVDs. In addition, it can perform diagnosis and warning for postoperative patients or patients with chronic CVDs.

Very Large-Scale Integration for Premature Ventricular Contraction Detection Using a Convolutional Neural Network

2021 ◽  
Author(s):  
Yuan-Ho Chen ◽  
Hsin-Tung Hua
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Premature Ventricular Contraction ◽  
Very Large Scale Integration ◽  
Cmos Process ◽  
Clock Frequency ◽  
Ventricular Contraction ◽  
Large Scale Integration ◽  
Scale Integration

We propose a very large-scale integration (VLSI) chip for premature ventricular contraction (PVC) detection. The chip contains a convolutional neural network (CNN) for detecting the abnormal heartbeats associated with PVCs in 12-lead electrocardiogram signals. The proposed CNN comprises two convolutional layers and a fully connected layer; in testing, it achieved a high PVC detection accuracy of [Formula: see text]. Created by using a [Formula: see text]-[Formula: see text]m CMOS process, the developed chip consumes [Formula: see text] mW with a clock frequency of 50 MHz and gate count of [Formula: see text] K. Compared with the previously designed VLSI chips, the proposed CNN chip achieves higher accuracy in abnormal heartbeat detection.

scholarly journals A real-time video smoke detection algorithm based on Kalman filter and CNN

2021 ◽  
Author(s):  
Alessio Gagliardi ◽  
Francesco de Gioia ◽  
Sergio Saponara
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Large Scale ◽  
Moving Objects ◽  
Time Window ◽  
Hybrid Approach ◽  
Detection Algorithm ◽  
Regions Of Interest ◽  
Raspberry Pi ◽  
Smoke Detection

AbstractSmoke detection represents a critical task for avoiding large scale fire disaster in industrial environment and cities. Including intelligent video-based techniques in existing camera infrastructure enables faster response time if compared to traditional analog smoke detectors. In this work presents a hybrid approach to assess the rapid and precise identification of smoke in a video sequence. The algorithm combines a traditional feature detector based on Kalman filtering and motion detection, and a lightweight shallow convolutional neural network. This technique allows the automatic selection of specific regions of interest within the image by the generation of bounding boxes for gray colored moving objects. In the final step the convolutional neural network verifies the actual presence of smoke in the proposed regions of interest. The algorithm provides also an alarm generator that can trigger an alarm signal if the smoke is persistent in a time window of 3 s. The proposed technique has been compared to the state of the art methods available in literature by using several videos of public and non-public dataset showing an improvement in the metrics. Finally, we developed a portable solution for embedded systems and evaluated its performance for the Raspberry Pi 3 and the Nvidia Jetson Nano.

scholarly journals A Deep Temporal Convolutional Neural Network for Regional and Teleseismic Detection

2018 ◽  
Author(s):  
Joshua Dickey ◽  
Brett Borghetti ◽  
William Junek
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Monitoring Network ◽  
Recall Rate ◽  
Detection Algorithm ◽  
Training Data ◽  
Type I ◽  
Test Set ◽  
Treaty Monitoring ◽  
Single Trace

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like performance from a single trace. We achieve this directly, by training our single-trace detector against labeled events from an array catalog, and by utilizing a deep temporal convolutional neural network. The training data consists of all arrivals in the International Seismological Centre Catalog for seven seismic arrays over a five year window from 1 Jan 2010 to 1 Jan 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 Jan 2015 to 1 Jan 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the transportability and generalization of the technique to new stations. Detection performance against this test set is outstanding. Fixing a type-I error rate of 1%, the algorithm achieves an overall recall rate of 73% on the 141,095 array beam picks in the test set, yielding 102,394 correct detections. This is more than 4 times the 23,259 detections found in the analyst-reviewed single-trace catalogs over the same period, and represents an 8dB improvement in detector sensitivity over current methods. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

P1887Development and validation of a novel premature ventricular contraction detector in an insertable cardiac monitor

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
G Rajagopal ◽  
S Sarkar ◽  
J Reiland ◽  
J Koehler ◽  
D L Lustgarten
Keyword(s):  
Negative Predictive Value ◽  
Predictive Value ◽  
Premature Ventricular Contraction ◽  
Detection Algorithm ◽  
Ventricular Contraction ◽  
Validation Data ◽  
Rr Interval ◽  
Wave Morphology ◽  
Interval Sequence

Abstract Background High premature ventricular contraction (PVC) burden may increase the risk of cardiac arrhythmias, PVC-induced cardiomyopathy and heart failure. Purpose We developed and validated an algorithm for continuous long-term monitoring of PVC burden in implantable loop recorders or insertable cardiac monitors (ICM). Methods The PVC algorithm uses long-short-long RR interval sequence and similarity and differences in r-wave morphology for three consecutive beats to detect the occurrence of a single PVC beat. Various threshold combinations were used for long-short-long RR interval sequence and degree of difference and similarity of R-wave morphology to be able to detect various types of PVCs including monomorphic, polymorphic, bigeminal, trigeminal, and interpolated PVCs. For example, a high degree of difference in R-wave morphology only required the short interval to be less than the longer interval by a smaller amount. The algorithm was designed with the intention to achieve minimum over reporting of PVC burden, i.e. maximum specificity. The algorithm was developed and validated using ECG strips stored in an ICM from real world patients. Gross, patient average and generalized estimating equation (GEE) estimates for sensitivity, specificity, positive and negative predictive value are reported. Results The PVC detection algorithm was developed using 87 2-minute ECG strips recorded by an ICM containing 2129 single PVC beats and 12,402 non-PVC beats to obtain a gross sensitivity and specificity of 75.9% and 98.8%. The validation data cohort consisted of 787 ICM recorded ECG strips 7–10 minutes in duration from 134 patients, providing over 460,000 beats of which 439,106 (94%) were normal beats, 8398 (2%) single PVC beats and 16,634 (4%) noisy beats. Couplets and triplets were excluded. Table 1 shows the performance results of the PVC detection algorithm in this validation set. Performance of PVC detector Gross Patient average GEE (95% CI) Sensitivity 75.2% 69.9% 72.5% (65.8–78.3) Specificity 99.6% 99.4% 99.4% (99.2–99.6) Positive Predictive Value (PPV) 75.9% 40.6% 40.6% (33.6–48.0) Negative Predictive Value (NPV) 99.5% 99.6% 99.6% (99.3–99.7) Conclusions The PVC detection algorithm was able to achieve a high specificity, which ensures that 99.6% of the normal events are not incorrectly identified as PVCs, while detecting 75% of PVCs on a continuous long-term basis in insertable cardiac monitors. The accuracy of PVC burden estimates during continuous monitoring using this algorithm needs further validation using Holter studies. Acknowledgement/Funding Medtronic Plc

Sign in / Sign up

Export Citation Format

Share Document