CAB: Classifying Arrhythmias based on Imbalanced Sensor Data

Abstract

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

Detecting Anomaly Data for IoT Sensor Networks

“…Assume that normal sensor nodes correctly sense and forward the data, while malicious nodes selectively falsify or modify the normal oxygen content data into the range rather than 18% ∼ 21% so as to damage the system. Besides, several other assumptions are also made: (1) all nodes form a star topology and are evenly distributed in a circular area centered on a base station; (2) each node has a unique ID, and the header of each packet includes source node ID, packet group length, and packet sequence number;…”

“…e Internet of ings, or IoT, has received extensive attention in the past few years by the research community owning to the progress of computing and real-time connections between data and devices and has been used in many application elds such as smart home/o ce, automobile, and medical assistance to solve practical problems [1][2][3]. e IoT depicts a future computing scenario where everyday physical objects will be connected to the Internet and identify themselves [4].…”

Time Series Based Data Explorer and Stream Analysis for Anomaly Prediction

“…Series. One of the basic techniques of time series mining is the similarity matching of time series [24,25,32,37,50,[56][57][58][59][60][61][62][63][64][65][66][67][68][69][70][71][72], while the advantages and disadvantages of similarity measures directly affect the performance of similarity matching. How to design similarity measures for compressed time series is the second important problem to be solved in the processing stage.…”

Improved Cam Shift Algorithm for Detecting Athletes' Action Targets in Sports Videos

“…erefore, in the subsequent tracking process, it is not necessary to recalculate the probability distribution map of the whole image, but we only need to calculate the centroid of the current search window as the central position; a probability distribution map of the area slightly larger than the search window can be used, which can greatly reduce the amount of calculation [20].…”