A hybrid DCNN-SVM model for classifying neonatal sleep and wake states based on facial expressions in video

Muhammad Awais, Xi Long (Corresponding author), Bin Yin, Saadullah Farooq Abbasi, Saeed Akbarzadeh, Chunmei Lu (Corresponding author), Xinhua Wang, Laishuan Wang, Jiong Zhang, Jeroen Dudink, W. Chen (Corresponding author)

Research output: Contribution to journalArticleAcademicpeer-review

25 Citations (Scopus)
278 Downloads (Pure)


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 the neonatal period, has profound meaning in the prediction of cognitive diseases and brain maturity. In recent years, unobtrusive sleep monitoring and automatic sleep staging have been intensively studied for adults, but much less for neonates. This work aims to investigate a novel video-based unobtrusive method for neonatal sleep-wake classification by analyzing the behavioral changes in the neonatal facial region. A hybrid model is proposed to monitor the sleep-wake patterns of human neonates. The model combines two algorithms: deep convolutional neural network (DCNN) and support vector machine (SVM), where DCNN works as a trainable feature extractor and SVM as a classifier. Data was collected from nineteen Chinese neonates at the Children's Hospital of Fudan University, Shanghai, China. The classification results are compared with the gold standard of video-electroencephalography scored by pediatric neurologists. Validations indicate that the proposed hybrid DCNN-SVM model achieved reliable performances in classifying neonatal sleep and wake states in RGB video frames (with the face region detected), with an accuracy of 93.8 ± 2.2% and an F1-score 0.93 ± 0.3.
Original languageEnglish
Article number9405399
Pages (from-to)1441-1449
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
Issue number5
Early online date15 Apr 2021
Publication statusPublished - May 2021


dateofcurrentversionMay11,2021.ThisworkwassupportedinpartApril2,2021;acceptedApril6,2021.DateofpublicationApril15,2021; Swhichisassociatedwithreducedresponsivenesstoexternal bytheShanghaiMunicipalScienceandTechnologyMajorProjectunder stimuli [1], [2]. According to research on human development Grant 2017SHZDZX01, and in part by the National Key R&D Program in early life, sleep is an essential factor for the development of ofChinaunderGrant2017YFE0112000.(Correspondingauthors:Wei the nervous system in infants [3], [4]. Newborn babies usually MuhammadAwais,SaadullahFarooqAbbasi,andSaeedAkbarzadehChen;XiLong;andChunmeiLu.) sleep between 16 and 18 hours per day in equispaced periods. are with the Center for Intelligent Medical Electronics, Department of As age increases, sleep changes from an ultradian rhythm to a ElectronicEngineering,SchoolofInformationScienceandTechnology, circadian rhythm [5]. Consistent evidence indicates that sleep fudan.edu.cn;18110720168@fudan.edu.cn;sd.akbarzadeh@gmail.com).Fudan University, Shanghai 200433, China(e-mail: 17110720061@ is vital for the brain development of neonates (in particular for Xi Long is with the Philips Research, 5656 AE Eindhoven, The Nether-preterm infants) and help them in recovering from illness [2], [6]. lands, and also with the Department of Electrical Engineering, Eind- Further, the reliable measures for the tracking and assessment (e-mail:x.long@tue.nl).hovenUniversityofTechnology,5612AZEindhoven,TheNetherlands of wake-sleep patterns, over multiple nights could potentially Bin Yin is with the Connected Care and Personal provide an indication of neonatal development over time [7], Department, Philips Research, Shanghai 200032, China [8], [9], [10].

FundersFunder number
National Key Research and Development Program of China


    • Brain modeling
    • Electroencephalography
    • Hospitals
    • Monitoring
    • Neonatal sleep monitoring
    • Pediatrics
    • Sleep
    • Support vector machines
    • deep convolutional neural network
    • facial expression
    • support vector machine
    • video and image analysis


    Dive into the research topics of 'A hybrid DCNN-SVM model for classifying neonatal sleep and wake states based on facial expressions in video'. Together they form a unique fingerprint.

    Cite this