Detection of apnea events from ECG segments using Fourier decomposition method

This article presents a study on the efficiency of implementing classifiers for the detection of sleep apnea moments based on a minute-to-minute Electrocardiogram (ECG) signal, detailing the comparison of the accuracy for different classifiers. At each ECG signal, a Sgolay filter was applied to extract the Heart Rate Variability (HRV) and the ECG-Derived Respiration (EDR) and they were used for the training, testing and validation of the classifiers. The same features were extended in a second phase in order to understand if all the classified features were important. According to the results obtained, the best accuracy was 82.12%, with a sensitivity and a specificity of 88.41% and 72.29%, respectively. This study shows the importance of choosing the right classifier for a specific problem as well as choosing and using the best features for a better accuracy. These promising early-stage results may lead to complementary studies to improve the classifiers for a possible real-world application. The performance of the proposed model was compared with other approaches used for the detection of sleep apnea.

/pdf/classifier-precision-analysis-for-sleep-apnea-detection-2o16vj97dp.pdf

Classifier Precision Analysis for Sleep Apnea Detection Using ECG Signals

Internet of Things (IoT) enabled wearable sensors for health monitoring are widely used to reduce the cost of personal healthcare and improve quality of life. The sleep apnea-hypopnea syndrome, characterized by the abnormal reduction or pause in breathing, greatly affects the quality of sleep of an individual. This paper introduces a novel method for apnea detection (pause in breathing) from electrocardiogram (ECG) signals obtained from wearable devices. The novelty stems from the high resolution of apnea detection on a second-by-second basis, and this is achieved using a 1-dimensional convolutional neural network for feature extraction and detection of sleep apnea events. The proposed method exhibits an accuracy of 99.56% and a sensitivity of 96.05%. This model outperforms several lower resolution state-of-the-art apnea detection methods. The complexity of the proposed model is analyzed. We also analyze the feasibility of model pruning and binarization to reduce the resource requirements on a wearable IoT device. The pruned model with 80% sparsity exhibited an accuracy of 97.34% and a sensitivity of 86.48%. The binarized model exhibited an accuracy of 75.59% and sensitivity of 63.23%. The performance of low complexity patient-specific models derived from the generic model is also studied to analyze the feasibility of retraining existing models to fit patient-specific requirements. The patient-specific models on average exhibited an accuracy of 97.79% and sensitivity of 92.23%. The source code for this work is made publicly available.

A 1D-CNN Based Deep Learning Technique for Sleep Apnea Detection in IoT Sensors

Sleep is very important for people to preserve their physical and mental health. The development of the ballistocardiography (BCG) sensor enables the possibility of day-to-day and portable monitoring at home. The goal of this study is to develop an IoT sleep quality monitoring system using BCG sensors, microcontrollers and cloud servers. The BCG sensor produces ECG data from the physical activity of the patient. The data is sent to the sensor and is read by the microcontroller. The sensor data is collected and pre-processed in the microcontroller. The microcontroller then transmits the data obtained from the BCG sensor to the cloud server for further analysis, i.e. to assess the sleep quality. The assessment of data transmission efficiency and resource consumption is carried out in this paper. The findings of the evaluation show that the proposed method achieves higher efficiency, lower response time and decreases memory usage by up to 77% compared to the conventional method.

IoT System for Sleep Quality Monitoring using Ballistocardiography Sensor

In the present state of health and wellness, Mental illness is always deemed less importance compared to other forms of physical illness. In reality, mental illness causes serious multi-dimensional adverse effect to the subject with respect to personal life, social life, as well as financial stability. In the area of mental illness, bipolar disorder is one of the most prominent type which can be triggered by any external stimulation to the subject suffering from this illness. There diagnosis as well as treatment process of bipolar disorder is very much different from other form of illness where the first step of impediment is the correct diagnosis itself. According to the standard body, there are classification of discrete forms of bipolar disorder viz. type-I, type-II, cyclothymic, etc. which is characterized by specific mood associated with depression and mania. However, there is no study associated with mixed-mood episode detection which is characterized by combination of various symptoms of bipolar disorder in random, unpredictable, and uncertain manner. Hence, the model contributes to obtain granular information with dynamics of mood transition. The simulated outcome of the proposed system in MATLAB shows that resulting model is capable enough for detection of mixed mood episode precisely.

/pdf/stochastic-modelling-of-transition-dynamic-of-mixed-mood-4cfc671fti.pdf

Stochastic modelling of transition dynamic of mixed mood episodes in bipolar disorder

Sleep apnea is a common sleep disorder that interferes with the breathing of a person. During sleep, people can stop breathing for a moment that causes the body lack of oxygen that lasts for several seconds to minutes even until the range of hours. If it happens for a long period, it can result in more serious diseases, e.g. high blood pressure, heart failure, stroke, diabetes, etc. Sleep apnea can be prevented by identifying the indication of sleep apnea itself from ECG, EEG, or other signals to perform early prevention. The purpose of this study is to build a classification model to identify sleep disorders from the Heart Rate Variability (HRV) features that can be obtained with Electrocardiogram (ECG) signals. In this study, HRV features were processed using several classification methods, i.e. ANN, KNN, N-Bayes and SVM linear Methods. The classification is performed using subject-specific scheme and subject-independent scheme. The simulation results show that the SVM method achieves higher accuracy other than three other methods in identifying sleep apnea. While, time domain features shows the most dominant performance among the HRV features.

/pdf/sleep-apnea-identification-using-hrv-features-of-ecg-signals-54nvf682xq.pdf

Billy Sulistyo

Papers

Sleep Apnea Identification using HRV Features of ECG Signals