- EEG and Brain-Computer Interfaces
- Obstructive Sleep Apnea Research
- Neural dynamics and brain function
- Heart Rate Variability and Autonomic Control
- Blind Source Separation Techniques
- Functional Brain Connectivity Studies
- Sleep and Wakefulness Research
- Advancements in Battery Materials
- Embedded Systems Design Techniques
- Advanced Battery Materials and Technologies
- ECG Monitoring and Analysis
- Interconnection Networks and Systems
- Optical Imaging and Spectroscopy Techniques
- Non-Invasive Vital Sign Monitoring
- Supercapacitor Materials and Fabrication
- Hydrogen Storage and Materials
- Fractal and DNA sequence analysis
- Advanced MRI Techniques and Applications
- Embedded Systems and FPGA Design
- Atmospheric aerosols and clouds
- Digital Media Forensic Detection
- Spectroscopy and Chemometric Analyses
- Urban Heat Island Mitigation
- Sleep and Work-Related Fatigue
- Fault Detection and Control Systems
Fudan University
2006-2024
Nanjing University of Information Science and Technology
2024
Tongji University
2020-2021
Uppsala University
2016-2019
Jiangsu Vocational Institute of Commerce
2019
Hangzhou Dianzi University
2012
Saitama Institute of Technology
2010-2012
The prevention, evaluation, and treatment of hypertension have attracted increasing attention in recent years. As photoplethysmography (PPG) technology has been widely applied to wearable sensors, the noninvasive estimation blood pressure (BP) using PPG method received considerable interest. In this paper, a for estimating systolic diastolic BP based only on signal is developed. multitaper (MTM) used feature extraction, an artificial neural network (ANN) estimation. Compared with previous...
Deep learning methods have become an important tool for automatic sleep staging in recent years. However, most of the existing deep learning-based approaches are sharply constrained by input modalities, where any insertion, substitution, and deletion modalities would directly lead to unusable model or a deterioration performance. To solve modality heterogeneity problems, novel network architecture named MaskSleepNet is proposed. It consists masking module, multi-scale convolutional neural...
Heart rate variability (HRV) is an effective predictor of congestive heart failure (CHF). However, important challenges exist regarding the temporal feature extraction and efficient classification using high-dimensional HRV representations. To solve these challenges, ensemble method for CHF detection short-term data deep neural networks was proposed. In this paper, five open-source databases, BIDMC database (BIDMC-CHF), RR interval (CHF-RR), MIT-BIH normal sinus rhythm (NSR) database,...
Sleep staging is the essential step in sleep quality assessment and disorders diagnosis. However, most current automatic approaches use recurrent neural networks (RNN), resulting a relatively large training burden. Moreover, these methods only extract information of whole epoch or adjacent epochs, ignoring local signal variations within epoch. To address issues, novel deep learning architecture named segmented attention network (SAN) proposed this paper. The can be divided into feature...
In response to food cues, obese vs normal-weight individuals show greater activation in brain regions involved the regulation of intake under both fasted and sated conditions. Putative effects obesity on task-independent low-frequency blood-oxygenation-level-dependent signals—that is, resting-state activity—in context are, however, less well studied. To compare eyes closed, whole-brain BOLD signals between severely females, as assessed by functional magnetic resonance imaging (fMRI)....
This letter addressed the development of split-window algorithm to estimate land surface temperature (LST) from measurements acquired by Visible and Infrared Radiometer on FengYun 3A using radiative transfer modeling experiment with moderate spectral resolution atmospheric transmittance computer model SeeBor V5.0 database. To improve accuracy, total precipitable water mean emissivities (LSEs) LST were divided into several subranges. The was applied Northeastern China area (115°E-135°E,...
Objective: The current state-of-the-art methods significantly improve the detection performance of steady-state visual evoked potentials (SSVEPs) by using individual calibration data. However, time-consuming sessions limit number training trials and may give rise to fatigue, which weakens effectiveness For addressing this issue, study proposes a novel inter- intra-subject maximal correlation (IISMC) method enhance robustness SSVEP recognition via employing similarity variability. Through...
Past studies utilizing resting-state functional MRI (rsfMRI), have shown that obese humans exhibit altered activity in brain areas related to reward compared normal-weight controls. However, what extent bariatric surgery-induced weight loss alters is less well-studied. Thus, we measured the fractional amplitude of low-frequency fluctuations from eyes-closed, rsfMRI females (n = 11, mean age 42 years, BMI 41 kg/m2 ) both a pre- and postprandial state at two time points: four weeks before,...
All-solid-state alkali ion batteries represent a future trend in battery technology, as well provide an opportunity for low-cost metal fluoride electrode materials, if certain intrinsic problems can be resolved. In this work, liquid activation strategy is proposed which Ga elements are generated situ and doped into the LiF crystal structure by introducing small amount of GaF3 . Benefiting from these two states existence, continuously maintain conformable ion/electron-transport networks,...
The steady-state visually evoked potential (SSVEP) has been widely used in brain-computer interfaces (BCIs). Many studies have proved that the Multivariate synchronization index (MSI) is an efficient method for recognizing frequency components SSVEP-based BCIs. Despite its success, recognition accuracy not satisfactory because simplified pre-constructed sine-cosine waves lack abundant features from real electroencephalogram (EEG) data. Recent advances addressing this issue achieved a...
Electrical status epilepticus during sleep (ESES) is an epileptic encephalopathy in children with complex clinical manifestations. It accompanied by specific electroencephalography (EEG) patterns of continuous spike and slow-waves. Quantifying such EEG critical to the diagnosis ESES. While most existing automatic ESES quantification systems ignore morphological variations signal as well individual variability among subjects. To address these issues, this paper presents a hybrid expert system...
Sleep staging plays a critical role in evaluating the quality of sleep. Currently, most studies are either suffering from dramatic performance drops when coping with varying input modalities or unable to handle heterogeneous signals. To signals and guarantee favorable sleep single modality is available, pseudo-siamese neural network (PSN) incorporate electroencephalography (EEG), electrooculography (EOG) characteristics proposed (PSEENet). PSEENet consists two parts, spatial mapping modules...
Heart rate variability has been proven to be an effective prediction of risk heart failure. The tradition method required manual feature extraction, thus may lead potential error. In order improve the robustness, a deep learning based on long short-term memory presented in this paper. Three RR interval length (N) for detection are used. Without pre-processing, obtain 82.47%, 85.13% and 84.91% accuracy N=50 (average time is 37. 8s), N=100 73. 9s), N=500 369. 5s), respectively. This makes it...
Abstract All‐solid‐state sodium‐ion batteries have the potential to improve safety and mitigate cost bottlenecks of current lithium‐ion battery system if a high‐performance electrolyte with advantages can be easily synthesized. In this study, one‐step dehydrogenation‐assisted strategy synthesize novel thio‐borohydride (Na‐B‐H‐S) is proposed, in which both raw material preparation temperature are significantly reduced. By using sodium borohydride (NaBH 4 ) instead B as starting material,...
This paper presents the comparison of in-orbit calibrations between microwave sounders on National Oceanic and Atmospheric Administration (NOAA) 15, 16, 17, 18 19 FengYun 3A (FY-3A) FY-3B satellites using ray-matching method over South Pole North study area in 2011. The results show that NOAA Advanced Microwave Sounding Unit A (AMSU-A/NOAA) channels are identical with averaging errors less than 0.45K, except channel 8, which error is up to -1.53K. FY-3 Temperature Sounder (MWTS/FY-3)...
In this paper, we propose a hybrid router which combines circuit switching and packet with virtual channels for on-chip networks in order to efficiently transfer streaming best-effort traffics specific applications. Time Division Multiplexing (TDM) technique clock-gating scheme are used take the benefits from flexibility throughput advantage of packet-switched superior power efficiency performance circuit-switching. Synthesis simulation results show that proposed has gain optimization...
Abstract All‐solid‐state lithium batteries using solid electrolytes hold promise for enhancing energy density. However, some with high ionic conductivity are declared unusable because they failed to show compatible the anode, cathode or even worse, both. Herein, it simultaneously introduced doping and interfacial tuning prepare fast ion conductor LiBH 4 ‐MgO‐MgI 2 , which can achieve an of 1.45 × 10 −4 S cm −1 at 50 °C. This electrolyte has usable near room temperature, but faces most...
The pivotal role of sleep has led to extensive research endeavors aimed at automatic stage classification. However, existing methods perform poorly when classifying small groups or individuals, and these results are often considered outliers in terms overall performance. These may introduce bias during model training, adversely affecting feature selection diminishing To address the above issues, this paper proposes an ensemble-based sequential convolutional neural network (E-SCNN) that...