Hafza Ayesha Siddiqa ^1* Muhammad Farrukh Qureshi ² Arsalan Khurshid ³ Yan Xu ⁴ Laishuan Wang ^5* Saadullah Farooq Abbasi ⁶ Chen Chen ⁷ Wei Chen ^8*

• ¹ Department of Electronic Engineering, School of Information Science and Technology, Fudan University, Shanghai, China
• ² Department of Electrical Engineering, Namal University Mianwali, Mianwali 42250, Pakistan, Mianwali, Punjab, Pakistan
• ³ Department of Electrical Engineering, Engineering Institute of Technology, Melbourne, Australia, Melbourne, Australia
• ⁴ Department of Neurology, Childern’s Hospital of Fudan University, National Childern’s Medical-Center, Shanghai, China
• ⁵ Department of Neonatology, Children's Hospital, Fudan University, Shanghai, Shanghai Municipality, China
• ⁶ Department of Electronic, Electrical and Systems Engineering, University of Birmingham, Birmingham B15 2TT, United Kingdom\, Birmingham, United Kingdom
• ⁷ Human Phenome Institute, Fudan University, Shanghai, Shanghai Municipality, China
• ⁸ School of Biomedical Engineering, The University of Sydney, Australia, Sydney, Australia

An optimal arrangement of electrodes during data collection is essential for gaining a deeper understanding of neonatal sleep and assessing cognitive health in order to reduce technical complexity and reduce skin irritation risks. Using electroencephalography (EEG) data, a longshort-term memory (LSTM) classifier categorizes neonatal sleep states. An 16803 30-second segment was collected from 64 infants between 36 and 43 weeks of age at Fudan University Children's Hospital to train and test the proposed model. To enhance the performance of an LSTM-based classification model, 94 linear and nonlinear features in the time and frequency domains with three novel features (Detrended Fluctuation Analysis (DFA), Lyapunov exponent, and multiscale fluctuation entropy) are extracted. An imbalance between classes is solved using the SMOTE technique. In addition, the most significant features are identified and prioritized using principal component analysis (PCA). In comparison to other single channels, the C3 channel has 1 Sample et al.an accuracy value of 80.75±0.82%, with a kappa value of 0.76. Classification accuracy for four left-side electrodes is higher (82.71±0.88%) than for four right-side electrodes (81.14±0.77%), while kappa values are respectively 0.78 and 0.76. Study results suggest that specific EEG channels play an important role in determining sleep stage classification, as well as suggesting optimal electrode configuration. Moreover, this research can be used to improve neonatal care by monitoring sleep, which can allow early detection of sleep disorders. As a result, this study captures information effectively using a single channel, reducing computing load and maintaining performance at the same time. With the incorporation of time and frequency-domain linear and nonlinear features into sleep staging, newborn sleep dynamics and irregularities can be better understood.