Machine Learning-Based Detection of Sleep-Disordered Breathing Type Using Time and Time-Frequency Features

As deep carbonate fracture-cavity paleokarst reservoirs are deeply buried and highly heterogeneous, and the responded seismic signals have weak amplitudes and low signal-to-noise ratios. Machine learning in seismic exploration provides a new perspective to solve the above problems, which is rapidly developing with compelling results. Applying machine learning algorithms directly on deep seismic signals or seismic attributes of deep carbonate fracture-cavity reservoirs without any prior knowledge constraints will result in wasted computation and reduce the accuracy. We propose a method of combining geological constraints and machine learning to describe deep carbonate fracture-cavity paleokarst reservoirs. By empirical mode decomposition, the time–frequency features of the seismic data are obtained and then a sensitive frequency is selected using geological prior constraints, which is input to fuzzy C-means cluster for characterizing the reservoir distribution. Application on Tahe oilfield data shows the potential of highlighting subtle geologic structures that might otherwise escape unnoticed by applying machine learning directly.

Download Full-text

844 Pediatric Vagus Nerve Stimulator-Induced Obstructive Sleep Apnea

SLEEP ◽

10.1093/sleep/zsab072.841 ◽

2021 ◽

Vol 44 (Supplement_2) ◽

pp. A328-A329

Author(s):

Nouraddin Nouraddin ◽

Louella Amos

Keyword(s):

Obstructive Sleep Apnea ◽

Sleep Apnea ◽

Vagus Nerve ◽

Sleep Disordered Breathing ◽

Vocal Cord Dysfunction ◽

Positive Pressure ◽

Output Current ◽

Time Frequency ◽

Obstructive Sleep ◽

Disordered Breathing

Abstract Introduction Vagus nerve stimulation (VNS) is an adjunct treatment for seizures refractory to medications. VNS in children with epilepsy can reduce seizures by up to 90%. VNS settings include stimulation on-time, off-time, frequency and output current. Complications of VNS include sleep-disordered breathing due to laryngopharyngeal dysfunction, which can also cause voice alteration, hoarseness, and cough. Both obstructive apneas (more common) and central apneas can be seen in those patients who have VNS-induced sleep-disordered breathing. Report of case(s) A 14-year-old male with Lennox-Gastaut syndrome treated with multiple antiepileptic drugs and VNS was admitted to the PICU with worsening seizures. He developed acute respiratory failure due to status epilepticus, requiring intubation. After extubation, he was observed to have repetitive respiratory obstruction at regular intervals, occurring throughout the day and night, and associated with mild oxygen desaturations. Polysomnography showed cyclical obstructive respiratory events lasting 30 seconds followed by approximately 2-minute intervals of regular breathing. Interrogation of his VNS device revealed the following settings: output current of 1.75 mA, 30 seconds on, and 1.8 minutes off. CPAP therapy improved his oxygen saturations, but he continued to clinically exhibit the repetitive obstructive apneas even on positive pressure. However, after his VNS device settings were decreased, repeat polysomnography showed resolution of his obstructive breathing. Conclusion This case report demonstrates pediatric VNS-induced obstructive sleep apnea. Activation of the vagus nerve can cause laryngopharyngeal dysfunction, including laryngospasm and vocal cord dysfunction, with subsequent upper airway obstruction, causing obstructive apneas or hypopneas. Treatment options for pediatric VNS-induced OSA include CPAP, decreasing the VNS settings and adenotonsillectomy. Support (if any):

Download Full-text

Emotion Recognition Based on DEAP Database using EEG Time-Frequency Features and Machine Learning Methods

Journal of Physics Conference Series ◽

10.1088/1742-6596/1501/1/012020 ◽

2020 ◽

Vol 1501 ◽

pp. 012020

Author(s):

T D Kusumaningrum ◽

A Faqih ◽

B Kusumoputro

Keyword(s):

Machine Learning ◽

Emotion Recognition ◽

Learning Methods ◽

Time Frequency ◽

Machine Learning Methods ◽

Frequency Features

Download Full-text

Can a Smartphone Diagnose Parkinson Disease? A Deep Neural Network Method and Telediagnosis System Implementation

Parkinson s Disease ◽

10.1155/2017/6209703 ◽

2017 ◽

Vol 2017 ◽

pp. 1-11 ◽

Cited By ~ 11

Author(s):

Y. N. Zhang

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Low Cost ◽

Walking Test ◽

Time Frequency ◽

Advantages And Disadvantages ◽

Stacked Autoencoders ◽

Knn Classifier ◽

Frequency Features

Parkinson’s disease (PD) is primarily diagnosed by clinical examinations, such as walking test, handwriting test, and MRI diagnostic. In this paper, we propose a machine learning based PD telediagnosis method for smartphone. Classification of PD using speech records is a challenging task owing to the fact that the classification accuracy is still lower than doctor-level. Here we demonstrate automatic classification of PD using time frequency features, stacked autoencoders (SAE), and K nearest neighbor (KNN) classifier. KNN classifier can produce promising classification results from useful representations which were learned by SAE. Empirical results show that the proposed method achieves better performance with all tested cases across classification tasks, demonstrating machine learning capable of classifying PD with a level of competence comparable to doctor. It concludes that a smartphone can therefore potentially provide low-cost PD diagnostic care. This paper also gives an implementation on browser/server system and reports the running time cost. Both advantages and disadvantages of the proposed telediagnosis system are discussed.

Download Full-text