Multi-Class Sleep Stage Analysis and Adaptive Pattern Recognition

Abstract

Multimodal signal analysis based on sophisticated sensors, efficient communication systems and fast parallel processing methods has a rapidly increasing range of multidisciplinary applications. The present paper is devoted to pattern recognition, machine learning, and the analysis of sleep stages in the detection of sleep disorders using polysomnography (PSG) data, including electroencephalography (EEG), breathing (Flow), and electro-oculogram (EOG) signals. The proposed method is based on the classification of selected features by a neural network system with sigmoidal and softmax transfer functions using Bayesian methods for the evaluation of the probabilities of the separate classes. The application is devoted to the analysis of the sleep stages of 184 individuals with different diagnoses, using EEG and further PSG signals. Data analysis points to an average increase of the length of the Wake stage by 2.7% per 10 years and a decrease of the length of the Rapid Eye Movement (REM) stages by 0.8% per 10 years. The mean classification accuracy for given sets of records and single EEG and multimodal features is 88.7% ( standard deviation, STD: 2.1) and 89.6% (STD:1.9), respectively. The proposed methods enable the use of adaptive learning processes for the detection and classification of health disorders based on prior specialist experience and man-machine interaction.

Hybrid CNN-LSTM Network for Real-Time Apnea-Hypopnea Event Detection Based on IR-UWB Radar

“…Although polysomnography (PSG) is the gold standard method for diagnosing SAHS, its usefulness as a long-term monitoring system is reduced by several drawbacks [7]: it requires trained sleep technicians in specially equipped laboratories; and the large number of electrodes attached to the patient's body may cause discomfort and affect their sleeping behavior. To overcome the shortcomings of PSG, numerous studies have proposed alternative methods to monitor SAHS using various sensors such as accelerometers, depth and thermal cameras, and piezoelectric pressure sensors [8], [9]. Nevertheless, these methods still require the user to physically contact the sensor or pose other privacy issues.…”

Computational Sleep Behavior Analysis: A Survey

“…In this case, a one-channel EEG investigation from Sleep-EDF reached an accuracy of 93.55% with DT [99], 93.9% with DT [92], and 94.6% with RF [100]. Including participants with medical conditions, such as from 184 observations, using NNs reached 89.9% accuracy [38]. Extending the system with EEG, EOG, and Flow reached 89.6% accuracy for healthy individuals and those with restless legs syndrome and sleep apnea [38].…”

“…This follows, e.g., from the performance of NNs in fig. 2, where the performance is compared for different dataset sizes for which the number of sleep disorder patients can be found in table 5 (see [38]). The validation method, if mentioned, is rarely CV and is therefore not objective in terms of user-independent classification and representation of influences from the training data.…”

“…Including participants with medical conditions, such as from 184 observations, using NNs reached 89.9% accuracy [38]. Extending the system with EEG, EOG, and Flow reached 89.6% accuracy for healthy individuals and those with restless legs syndrome and sleep apnea [38]. In contrast, ECG data applying a CNN reached an accuracy of 75.3% for SHHS and 81.6% for 16 subjects with sleep issues [98].…”

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring

“…Computational intelligence and standard classification methods, including decision tree (DT), k-nearest neighbour (k-NN), support vector machines (SVM), Bayesian methods, and the two-layer neural network (NN) algorithms, are often used in this area [28]. All these methods assume the appropriate selection of features in the time, frequency and scale [29] domains.…”