Automatic Identification of Insomnia Based on Single-Channel EEG Labelled With Sleep Stage Annotations

Yang, Bufang; Liu, Hongxing

doi:10.1109/access.2020.2999915

Cited by 26 publications

(7 citation statements)

References 39 publications

(50 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our CNN, all convolution and pooling operations are one-dimensional. The one-dimensional convolution operation is defined as follows [26]:…”

Section: The Classification Network That Combines the Optimal Sae And...mentioning

confidence: 99%

Trend Classification of InSAR Displacement Time Series Using SAE–CNN

Li,

Wu,

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Multi-temporal Interferometric Synthetic Aperture Radar technique (MTInSAR) has emerged as a valuable tool for measuring ground motion in a wide area. However, interpreting displacement time series and identifying dangerous signals from millions of InSAR coherent targets is challenging. In this study, we propose a method combining stacked autoencoder (SAE) and convolutional neural network (CNN) to classify InSAR time series and ease the interpretation of movements. The InSAR time series are classified into five categories, including stable, linear, accelerating, deceleration, and phase unwrapping error (PUE). The accuracy of labeled samples reaches 95.1%, reflecting the performance of the proposed method. This method was applied to the InSAR results for Kunming extracted from 171 ascending Sentinel-1 images from January 2017 to September 2022. The classification map of the InSAR time series shows that stable coherent points dominate around 79.28% of the area, with linear patterns at 10.70%, decelerating at 5.30%, accelerating at 4.72%, and PUE patterns at 3.60%. The results demonstrate that this method can distinguish different ground motion features and detect nonlinear deformation signals on a large scale without human intervention.

show abstract

“…In our CNN, all convolution and pooling operations are one-dimensional. The one-dimensional convolution operation is defined as follows [26]:…”

Section: The Classification Network That Combines the Optimal Sae And...mentioning

confidence: 99%

Trend Classification of InSAR Displacement Time Series Using SAE–CNN

Li,

Wu,

Yang

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Numerous machine learning (ML) algorithms have been proposed and widely employed for health monitoring systems [38]- [40]. In this work, four ML models are used for BP estimation, including linear regression (LR), support vector machine (SVM), decision tree (DT), and random forest (RF).…”

Section: E Regression Modelsmentioning

confidence: 99%

Non-invasive cuff-less blood pressure estimation using a hybrid deep learning model

et al. 2021

View full text Add to dashboard Cite

Conventional blood pressure (BP) measurement methods have different drawbacks such as being invasive, cuff-based or requiring manual operations. There is significant interest in the development of non-invasive, cuff-less and continual BP measurement based on physiological measurement. However, in these methods, extracting features from signals is challenging in the presence of noise or signal distortion. When using machine learning, errors in feature extraction result in errors in BP estimation, therefore, this study explores the use of raw signals as a direct input to a deep learning model. To enable comparison with the traditional machine learning models which use features from the photoplethysmogram and electrocardiogram, a hybrid deep learning model that utilises both raw signals and physical characteristics (age, height, weight and gender) is developed. This hybrid model performs best in terms of both diastolic BP (DBP) and systolic BP (SBP) with the mean absolute error being 3.23 ± 4.75 mmHg and 4.43 ± 6.09 mmHg respectively. DBP and SBP meet the Grade A and Grade B performance requirements of the British Hypertension Society respectively.

show abstract

“…In order to specify the signals only in the deep sleep stage, a sleep staging procedure was thus required. Yang and Liu [25] proposed a one-dimensional convolutional neural network model for automatic insomnia identification based on single-channel EEG labelled with sleep stage annotations.…”

Section: Shahin Et Al Employed a Set Of 57 Eeg Parameters (Time-frequ...mentioning

confidence: 99%

A financial audit on hospital costs in an inpatient Psychiatry Unit at Teaching Hospital, Anuradhapura, Sri Lanka

Udeshika¹,

Ellepola²

2020

Sri Lanka J. Psyc.

View full text Add to dashboard Cite

BackgroundThe Sri Lankan public health care system provides free health care. Psychiatric services in the public sector have expanded over the years to reach the whole country. Currently, the cost of care per patient in a government hospital is not calculated directly. AimsTo assess the total in-ward expenditure, expenditures incurred in different cost heads, average per patient cost and cost per patient day in a psychiatry unit at Teaching Hospital, Anuradhapura, Sri Lanka. MethodsA financial audit was carried out at Teaching Hospital, Anuradhapura. All patients admitted for in-patient psychiatry care from 1st to 30th of September 2019 were included. Data were collected retrospectively from patient documentations and hospital accounting using a data extraction form. ResultsNinety patients, 48 (53.3%) females and 42 (46.7%) males, were included in the study, with 711 in-patient days. The average length of stay was 7.9 days. The mean age was 39.8 years, ranging from 16 to 75 years, and most were married (55.6%). Schizophrenia and depressive disorder were the commonest diagnoses. The total cost per month in the psychiatry unit was LKR 3 321 050.60, with an average of LKR 110 701.70 per day. The average cost per patient per day was LKR 4 670.96. Staff wages accounted for 56.27% of the total expenses, and medications and other consumables accounted for 13.01%. ConclusionsClinicians can carry out cost analysis with data available to them. The results can be used to efficiently allocate resources from the total budget in the given institution, and to implement cost reduction plans to use limited resources effectively.

show abstract

Automatic Identification of Insomnia Based on Single-Channel EEG Labelled With Sleep Stage Annotations

Cited by 26 publications

References 39 publications

Trend Classification of InSAR Displacement Time Series Using SAE–CNN

Trend Classification of InSAR Displacement Time Series Using SAE–CNN

Non-invasive cuff-less blood pressure estimation using a hybrid deep learning model

A financial audit on hospital costs in an inpatient Psychiatry Unit at Teaching Hospital, Anuradhapura, Sri Lanka

Contact Info

Product

Resources

About