A5070522623- Neonatal and fetal brain pathology
- Neonatal Respiratory Health Research
- Infant Development and Preterm Care
- Infant Health and Development
- EEG and Brain-Computer Interfaces
- Neonatal Health and Biochemistry
- Advanced Memory and Neural Computing
- Obstructive Sleep Apnea Research
- ECG Monitoring and Analysis
- Speech and Audio Processing
- Genomics and Rare Diseases
- Speech Recognition and Synthesis
- Non-Invasive Vital Sign Monitoring
- Ergonomics and Musculoskeletal Disorders
- Phonetics and Phonology Research
- Breastfeeding Practices and Influences
- Ferroelectric and Negative Capacitance Devices
- Semiconductor materials and devices
- Optical Imaging and Spectroscopy Techniques
- Diverse Approaches in Healthcare and Education Studies
- Antibiotic Use and Resistance
- Pediatric health and respiratory diseases
- Infection Control in Healthcare
- Context-Aware Activity Recognition Systems
- Antibiotics Pharmacokinetics and Efficacy
Amazon (Germany)
2025
Children's Hospital of Fudan University
2013-2024
Southwest University of Science and Technology
2024
Fudan University
2020-2022
Intelligent Health (United Kingdom)
2022
Philips (United Kingdom)
2020
Eindhoven University of Technology
2020
Tainan Municipal Hospital
2015
Leshan Normal University
2015
Macronix International (China)
2009-2011
Objective: Classification of sleep-wake states using multichannel electroencephalography (EEG) data that reliably work for neonates. Methods: A deep multilayer perceptron (MLP) neural network is developed to classify bipolar EEG signals, which takes an input vector size 108 containing the joint features 9 channels. The avoids any post-processing step in order as a full-fledged real-time application. For training and testing model, recordings 3525 30-second segments from 19 neonates...
Acquisition, analysis, and classification of repetitive human motion for the assessment postural stress is central importance to ergonomics practitioners. We present a two-threshold, multidimensional segmentation algorithm automatically decompose complex into sequence simple linear dynamic models. No priori assumptions were made about number models that comprise full or duration task cycle. A compact representation obtained each segment using parameters damped harmonic model. Event was...
For infants admitted at neonatal intensive care unit, the continuous monitoring of health parameters is critical for their optimal treatment and outcomes. So it's crucial to provide proper treatment, accurate comfortable conditions newborn infants. In this paper, we propose wearable sensor systems integrated with flexible material based non-invasive sensors monitoring. The system aims providing reliable vital signs as well clinical environments care. consists a smart vest cloud platform....
Sleep is a natural phenomenon controlled by the central nervous system. The sleep-wake pattern, which functions as an essential indicator of neurophysiological organization in neonatal period, has profound meaning prediction cognitive diseases and brain maturity. In recent years, unobtrusive sleep monitoring automatic staging have been intensively studied for adults, but much less neonates. This work aims to investigate novel video-based method classification analyzing behavioral changes...
We aimed to implement our Smart Use of Antibiotics Program ensure the proper use antimicrobials, improve patient care and outcomes, reduce risks adverse effects antimicrobial resistance.We compared time periods before (baseline) after (intervention) implementation an antibiotic protocol by performing surveillance assessments all during a 29-month interrupted period.Level 3-4 neonatal ICU in one referral center.All 13,540 infants who received antibiotics their hospital stay from 2015...
Abstract Emerging evidence demonstrates the clinical utility of genomic applications in newborn intensive care unit (NICU) patients with strong indications Mendelian etiology. However, such applications' diagnostic yield and remain unclear for NICU cohorts minimal phenotype selection. In this study, focused medical exome sequencing was used as a first‐tier, singleton‐focused tool 2303 unrelated sick neonates. Integrated analysis single nucleotide variants (SNVs), small insertions deletions...
In recent times, with the advancement of digital imaging, automatic facial recognition has been intensively studied for adults, while less neonates. Due to miniature structure and attributes, newborn remains a challenging area. this paper, an video-based Neonatal Face Attributes Recognition (NFAR) approach in hierarchical framework is proposed by coalescing intensity-based method, pose estimation, novel dedicated neonatal Feature Selection (FFS) algorithm. The method used face detection,...
Abstract Objective In this paper, we propose to evaluate the use of pre-trained convolutional neural networks (CNNs) as a features extractor followed by Principal Component Analysis (PCA) find best discriminant perform classification using support vector machine (SVM) algorithm for neonatal sleep and wake states Fluke ® facial video frames. Using CNNs feature would hugely reduce effort collecting new data training network which could be computationally expensive. The are extracted after...
Heart rate (HR) measurement is crucial for newborn infant monitoring in the neonatal intensive care unit (NICU). The widely used contact HR methods based on electrocardiography (ECG) and photoplethysmography (PPG) signals can lead to discomfort possible skin irritation neonates, which limit its application NICU scenarios. In this work, we propose a non-contact method simply using RGB camera. Eulerian video magnification (EVM) employed detect subtle changes of faces results from blood...
Importance Neonatal seizures pose a significant challenge in critical care, and continuous video electroencephalography (cEEG) monitoring holds promise for early detection of seizures. However, large-scale data on the incidence neonatal systems China are lacking. Objectives To determine infants with high risk China. Design, Setting, Participants A large, cross-sectional multicenter study was conducted from January 2017 to December 2018 intensive care units (NICUs) 7 tertiary medical centers...
A novel wearable sensor system for seizure monitoring of neonates comprised smart clothing, video recording and cloud platform is presented. Textile electrodes Inertial Measurement Unit (IMU) are embedded in the clothing to obtain ECG signal motion whereby epileptic detection algorithm performed. Moreover, a module provides real-time information about patients. The receives pre-processed data enables remote monitoring, centralized processing management. Comparison with commercial instruments...
The present study attempted to investigate the acoustic characteristics of Mandarin laryngeal and esophageal speech. Eight normal seven speakers participated in experiments. Results from analyses syllables ∕ma∕and ∕ba∕ indicated that, F0, intensity, signal-to-noise ratio speech were significantly higher than those However, opposite results found for vowel duration, jitter, shimmer. Mean word per minute reading greater but number pauses was smaller Similar patterns F0 contours duration as a...
The present study attempted to investigate if alaryngeal speakers of Mandarin Chinese could differentially produce the four tone levels Mandarin: high-level, mid-rising, falling-rising and high-falling, as perceived by native listeners. Syllables /ma/ /ba/ produced at different 8 normal laryngeal (NL), 7 standard esophageal (SE), electrolaryngeal (EL) were naïve Results from listening experiments showed a higher percent correct identification for NL speech than SE EL speech. Perceptual data...
Neonatal seizure is an important clinical symptom of brain dysfunction, which more common in infancy than childhood. At present, video electroencephalogram (VEEG) technology widely used practice. However, has several disadvantages. For example, the wires connecting medical instruments may interfere with infant's movement and gel patch electrode or disk commonly to monitor EEG cause skin allergies even tears. above reasons, we developed a wearable multi-sensor platform for newborns collect...
Music contains substantial contents that humans can perceive and thus has the capability to evoke positive emotions. Even though neonatal intensive care units (NICUs) provide preterm infants a developmental environment, they still cannot fully simulate environment in womb. The reduced maternal would increase stress levels premature infants. Fortunately, music intervention been proved it improve NICU such as stabilize heart rate respiratory rate, reduce incidence of apnea, feeding. However,...
Abstract Background: Therapeutic hypothermia (TH) is the standard therapy for hypoxic-ischemic encephalopathy (HIE) and associated with a wide range of physiological changes. Objective: We re-evaluated effects HIE TH on bilirubin measurements following in center involved China cooling randomized controlled trial (RCT). Methods: Serial serum concentrations measured during first week life were compared among + NT (normothermia) group, treatment group control (without HIE). Survivors followed...
Humans have the ability to appreciate and create music.However, why how humans this distinctive perceive music remains unclear.Additionally, investigation of innate perceiving skill in is compounded by fact that we been actively passively exposed auditory stimuli or systematically learnt after birth.Therefore, explore musical ability, infants with preterm birth may be most suitable population.In study, brain networks were explored using dynamic functional connectivity-based reliable...