4.6 Article

Application of the Variance Delay Fuzzy Approximate Entropy for Autonomic Nervous System Fluctuation Analysis in Obstructive Sleep Apnea Patients

Journal

ENTROPY
Volume 22, Issue 9, Pages -

Publisher

MDPI
DOI: 10.3390/e22090915

Keywords

obstructive sleep apnea (OSA); autonomic nerve system (ANS) fluctuation; OSA severity analysis; heart rate variability (HRV); variance delay fuzzy approximate entropy (VD_fApEn)

Funding

  1. national natural science foundation of China [61401521, 51807134]
  2. Guangdong Basic and Applied Basic Research Foundation [:2020A1515010701]
  3. Shenzhen Science and Technology Plan for fundamental research [JCYJ20180307153213863, JCY20190807162003696]

Ask authors/readers for more resources

Obstructive sleep apnea (OSA) is a fatal respiratory disease occurring in sleep. OSA can induce declined heart rate variability (HRV) and was reported to have autonomic nerve system (ANS) dysfunction. Variance delay fuzzy approximate entropy (VD_fApEn) was proposed as a nonlinear index to study the fluctuation change of ANS in OSA patients. Sixty electrocardiogram (ECG) recordings of the PhysioNet database (20 normal, 14 mild-moderate OSA, and 26 severe OSA) were intercepted for 6 h and divided into 5-min segments. HRV analysis were adopted in traditional frequency domain, and nonlinear HRV indices were also calculated. Among these indices, VD_fApEn could significantly differentiate among the three groups (p< 0.05) compared with the ratio of low frequency power and high frequency power (LF/HF ratio) and fuzzy approximate entropy (fApEn). Moreover, the VD_fApEn (90%) reached a higher OSA screening accuracy compared with LF/HF ratio (80%) and fApEn (78.3%). Therefore, VD_fApEn provides a potential clinical method for ANS fluctuation analysis in OSA patients and OSA severity analysis.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.6
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

Article Energy & Fuels

A DC Series Arc Fault Detection Method Based on a Lightweight Convolutional Neural Network Used in Photovoltaic System

Yao Wang, Cuiyan Bai, Xiaopeng Qian, Wanting Liu, Chen Zhu, Leijiao Ge

Summary: A lightweight convolutional neural network-based method was proposed to detect DC series arc faults in PV systems, achieving a high detection accuracy of up to 98.81% under various test conditions. The efficientnet-B1 model showed the highest accuracy of 96.16% compared to other similar models. A attention mechanism was also introduced to focus on arc features and reduce unnecessary computation.

ENERGIES (2022)

Article Energy & Fuels

Short-Term Load Forecasting Model of Electric Vehicle Charging Load Based on MCCNN-TCN

Jiaan Zhang, Chenyu Liu, Leijiao Ge

Summary: This study proposes a model-based multi-channel convolutional neural network and temporal convolutional network to improve the short-term load forecasting performance of EV charging load. Experimental results demonstrate that the proposed model outperforms other models in terms of accuracy.

ENERGIES (2022)

Article Engineering, Electrical & Electronic

A frequency-doubling modulation method for LLC with optimizing thermal balance of power switches

Yu Tang, Xiang Liu, Zhe Shi, Leijiao Ge, Lin Jiang

Summary: In order to improve the energy efficiency of power electronic systems, DC-DC converters can increase the power density by increasing the operating frequency. A single-switch frequency-doubling (SS-FD) modulation method has been proposed, but it leads to uneven heating of the switches and reduces the overall device life. To optimize this problem, this paper proposes a dual-switches time-sharing frequency-doubling (DSTS-FD) modulation, which ensures balanced heating of each switch and increases the overall service life of the equipment. Theoretical analysis and experimental verification demonstrate the superiority of the proposed modulation method.

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS (2023)

Article Engineering, Electrical & Electronic

Two-line-same-phase AC standstill measurement method for obtaining accurate PMSM d-q-axis inductance values

Fang Yao, Mingwei Li, Leijiao Ge, Wenlong Liao, Kody Powell

Summary: This paper proposes a two-line-same-phase AC standstill measurement (TLSP-ACSM) method to solve the problem of accurate d-q-axis inductance values in permanent magnet synchronous motors (PMSM) under vector control. The effectiveness of the proposed method is verified through analysis of motor synthetic magnetomotive force and theoretical error of inductance measurement, followed by experiments. Comparing with another measurement method, it is demonstrated that TLSP-ACSM reduces the relative errors of d-axis and q-axis inductance measurements by about 23% and 21% respectively. TLSP-ACSM shows better measurement precision and tracking performance when considering magnetic flux leakage.

JOURNAL OF POWER ELECTRONICS (2023)

Article Computer Science, Hardware & Architecture

Dynamic State Estimation for Synchronous Generator With Communication Constraints: An Improved Regularized Particle Filter Approach

Xingzhen Bai, Feiyu Qin, Leijiao Ge, Lin Zeng, Xinlei Zheng

Summary: This article proposes a dynamic state estimation method for synchronous generators with an event-triggered scheme to address the challenges of distorted measurement results and data transmission pressure. The method first establishes a nonlinear model to describe the dynamics of generators, and then adopts a measure-based event-triggering scheme to schedule data transmission, reducing communication pressure and enhancing resource utilization. Finally, an improved regularized particle filter (IRPF) algorithm is designed to ensure estimation performance.

IEEE TRANSACTIONS ON SUSTAINABLE COMPUTING (2023)

Article Engineering, Electrical & Electronic

Dynamic event-based forecasting-aided state estimation for active distribution systems subject to limited communication resource

Xingzhen Bai, Xinlei Zheng, Leijiao Ge, Wenlong Liao, Kody Powell, Jiaan Zhang

Summary: In this paper, a dynamic event-based forecasting-aided state estimation (FASE) method is proposed to solve the state estimation problem of active distribution systems (ADS) with communication constraints and non-linear measurements. The method constructs a state-space model of ADS to describe system state evolution and uses a dynamic event-triggered scheme (ETS) to optimize data transmission. To handle non-linear measurements, the Gaussian integral is approximated using the spherical cubature rule. The proposed method also minimizes the upper bound of estimation error covariance and develops the dynamic event-triggered cubature Kalman filter (DET-CKF) algorithm for state estimation in ADS.

ELECTRIC POWER SYSTEMS RESEARCH (2023)

Article Engineering, Multidisciplinary

Shared Energy and Reserve Based Coordinated Operation Between Electric Vehicle Charging Stations and Distribution Power Network

Yuanzheng Li, Xiao Ren, Zhixian Ni, Tianyang Zhao, Leijiao Ge, Xi Li, Yunfeng Luo, Yong Zhao

Summary: In this paper, a coordinated operation method for a system containing electric vehicle charging stations and a distribution power network is proposed. This method considers integrated energy and reserve regulation. Firstly, a multi-objective optimization model is proposed based on the network calculus theory, considering economic cost and quality of service. Secondly, a characteristic function and a modified Shapely value method based on the coalition game are adopted to study the allocation of economic benefits brought by the coordinated operation. Finally, simulation studies validate the effectiveness of the proposed method by comparing the operation costs of the system in non-coordinated and coordinated modes.

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS (2023)

Article Engineering, Electrical & Electronic

A Modified Carrier-Based DPWM With Reduced Switching Loss and Current Distortion for Vienna Rectifier

Yushuo Pei, Yu Tang, Hucheng Xu, Jincai Niu, Leijiao Ge

Summary: This article proposes a modified carrier-based discontinuous pulsewidth modulation (MCB-DPWM) scheme for the Vienna rectifier with improved zero-sequence voltage injection. The MCB-DPWM effectively eliminates zero-crossing distortion, reduces NP voltage fluctuation, and switching loss, resulting in higher input current quality and efficiency. It features a simpler implementation and less computational burden than space-vector-based PWM, making it more suitable for high-frequency applications.

IEEE TRANSACTIONS ON POWER ELECTRONICS (2023)

Article Engineering, Electrical & Electronic

Adaptive droop control strategy of parallel LLC converters

Yu Tang, Hucheng Xu, Yushuo Pei, Fang Yao, Leijiao Ge

Summary: This paper proposes an adaptive droop control method to address the issue of unbalanced output current in parallel-connected resonant converters caused by differences in resonant components. By analyzing the output voltage accuracy of the converter under traditional droop control when the load changes, the effectiveness of the adaptive droop control method is demonstrated.

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS (2023)

Article Engineering, Electrical & Electronic

Economic Optimization Operation Approach of Integrated Energy System Considering Wind Power Consumption and Flexible Load Regulation

Qinglin Meng, Jing Xu, Leijiao Ge, Zhongguan Wang, Jianxiao Wang, Liang Xu, Zhipeng Tang

Summary: In this study, an optimal operation model of integrated energy system in coastal areas was developed, with the goal of minimizing the daily total operating cost and the amount of abandoned wind. The output conditions of the corresponding equipment were also taken into consideration. The adjustable characteristics of seawater desalination load were analyzed, and the adjustment range of seawater desalination load was calculated. A new optimization operation method for the integrated energy system in coastal areas, considering the desalination load, was proposed. Simulation verification using a winter scene in a coastal area in northern China showed that the proposed strategy effectively reduced the total daily operation cost by 4.6% and increased the wind power consumption rate by 2.87%, demonstrating the significant role of the designed integrated energy system operation strategy in improving the system operation economy and promoting the consumption of new energy.

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY (2023)

Article Energy & Fuels

Day-ahead optimal scheduling strategy for electrolytic water to hydrogen production in zero-carbon parks type microgrid for optimal utilization of electrolyzer

Wentao Huang, Bohan Zhang, Leijiao Ge, Jun He, Wenlong Liao, Peilei Ma

Summary: Under the goal of achieving carbon peaking and carbon neutrality, this paper proposes an optimal scheduling strategy for electrolytic water to hydrogen production in a zero-carbon park type microgrid for optimal utilization of the electrolyzer. The Beluga Whale Optimization (BWO) algorithm is improved to solve the model faster and with better optimization finding capability. The simulation results demonstrate that the proposed dispatching strategy yields a 12.5% higher daily revenue value compared to the traditional dispatching strategy for microgrids, and the impact of hydrogen selling price and new energy feed-in tariff on the proposed strategy is also analyzed.

JOURNAL OF ENERGY STORAGE (2023)

Article Engineering, Electrical & Electronic

A Virtual Data Collection Model of Distributed PVs Considering Spatio-Temporal Coupling and Affine Optimization Reference

Leijiao Ge, Hangxu Liu, Jun Yan, Yuanzheng Li, Jiaan Zhang

Summary: This paper proposes a virtual collection technology based on computational intelligence to enable high-precision data collection of distributed photovoltaics (DPVs). A deep recurrent denoising autoencoder (D-RDAE) is used to capture the spatial-temporal correlation of DPVs and find the optimal reference power station (RPS). An affine artificial neural network (AANN) is constructed to tackle the uncertainty of solar radiation intensity and select RPSs. Experimental results demonstrate the effectiveness and superiority of the proposed method.

IEEE TRANSACTIONS ON POWER SYSTEMS (2023)

Article Engineering, Electrical & Electronic

A Unified Control of Super-capacitor System Based on Bi-directional DC-DC Converter for Power Smoothing in DC Microgrid

Xialin Li, Pengfei Li, Leijiao Ge, Xunyang Wang, Zhiwang Li, Lin Zhu, Li Guo, Chengshan Wang

Summary: A unified control method is proposed for a bi-directional DC-DC converter based super-capacitor (SC) system in DC microgrids (DCMGs), enabling power smoothing and SC terminal voltage regulation simultaneously. The proposed control utilizes only local measurements and features plug-and-play capability. Two indices, equivalent power supporting time and inertia contributed by the unified controlled SC system, are introduced for quantitative analysis and effective design. Analytical solutions are obtained for the two indices using a simplified model of a DCMG. A systematic design method is presented for the proposed unified control. The proposed control is verified through theoretical analyses and a switching model in PSCAD/EMTDC.

JOURNAL OF MODERN POWER SYSTEMS AND CLEAN ENERGY (2023)

Article Computer Science, Artificial Intelligence

Automatic Metric Search for Few-Shot Learning

Yuan Zhou, Jieke Hao, Shuwei Huo, Boyu Wang, Leijiao Ge, Sun-Yuan Kung

Summary: Few-shot learning aims to learn a model that can identify unseen classes using only a few training samples from each class. Existing methods often require manually predefined metric functions, while we propose a novel automatic metric search (Auto-MS) model, which automatically searches task-specific metric functions. By incorporating the episode-training mechanism into the bilevel search strategy, the proposed Auto-MS achieves superior performance in few-shot learning problems, as demonstrated by extensive experiments on miniImageNet and tieredImageNet datasets.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

Article Energy & Fuels

Distributed optimal dispatching method of smart distribution network considering integrated energy microgrid with multiple gird-connected points

Bing Sun, Ruipeng Jing, Yuan Zeng, Leijiao Ge, Gang Liang, Shimeng Dong

Summary: This study proposes a distributed optimal dispatching method that considers the interactive demand between IEMG and SDN with multiple gird-connected points. The method enhances the operation flexibility of SDN and increases the benefits for all entities.

IET ENERGY SYSTEMS INTEGRATION (2023)

No Data Available