biostudies-literatureKam KNIA NIH HHSNHLBI NIH HHSMerck &amp; Co IncNIHAlzheimer&apos;s Association109224https://www.ebi.ac.uk/biostudies/studies/S-EPMC8457529biostudies-literatureUnknown360<h4>Background</h4>Recent advancement in deep learning provides a pivotal opportunity to potentially supplement or supplant the limiting step of manual sleep scoring.<h4>New method</h4>In this paper, we characterize the WaveSleepNet (WSN), a deep convolutional neural network (CNN) that uses wavelet transformed images of mouse EEG/EMG signals to autoscore sleep and wake.<h4>Results</h4>WSN achieves an epoch by epoch mean accuracy of 0.86 and mean F1 score of 0.82 compared to manual scoring by a human expert. In mice experiencing mechanically induced sleep fragmentation, an overall epoch by epoch mean accuracy of 0.80 is achieved by WSN and classification of non-REM (NREM) sleep is not compromised, but the high level of sleep fragmentation results in WSN having greater difficulty differentiaJournal of neuroscience methodsWaveSleepNet: An interpretable deep convolutional neural network for the continuous classification of mouse sleep and wake.PMC8457529R01 AG066870K25 HL151912K24 HL109156R21 AG0591792018-AARG-589632L30 AG057120R01 AG056682Ayappa IParekh AVarga AWKam KRapoport DMfalseWaveSleepNet: An interpretable deep convolutional neural network for the continuous classification of mouse sleep and wake.<h4>Background</h4>Recent advancement in deep learning provides a pivotal opportunity to potentially supplement or supplant the limiting step of manual sleep scoring.<h4>New method</h4>In this paper, we characterize the WaveSleepNet (WSN), a deep convolutional neural network (CNN) that uses wavelet transformed images of mouse EEG/EMG signals to autoscore sleep and wake.<h4>Results</h4>WSN achieves an epoch by epoch mean accuracy of 0.86 and mean F1 score of 0.82 compared to manual scoring by a human expert. In mice experiencing mechanically induced sleep fragmentation, an overall epoch by epoch mean accuracy of 0.80 is achieved by WSN and classification of non-REM (NREM) sleep is not compromised, but the high level of sleep fragmentation results in WSN having greater difficulty differentia2021-01-01T00:00:00Z2021 Aug2025-04-04T09:37:35.559Z2025-04-04T09:37:35.559ZS-EPMC84575293405229110.1016/j.jneumeth.2021.109224