EEG electrode setup optimization using feature extraction techniques for neonatal sleep state classification

被引：0
作者：
Siddiqa, Hafza Ayesha [1 ]
Qureshi, Muhammad Farrukh [2 ]
Khurshid, Arsalan [3 ]
Xu, Yan [4 ]
Wang, Laishuan [5 ]
Abbasi, Saadullah Farooq [6 ]
Chen, Chen [7 ]
Chen, Wei [8 ]
机构：
[1] Fudan Univ, Ctr Intelligent Med Elect, Sch Informat Sci & Technol, Dept Elect Engn, Shanghai, Peoples R China
[2] Namal Univ Mianwali, Dept Elect Engn, Mianwali, Pakistan
[3] Engn Inst Technol, Dept Elect Engn, Melbourne, Vic, Australia
[4] Fudan Univ, Childrens Hosp, Natl Childrens Med Ctr, Dept Neurol, Shanghai, Peoples R China
[5] Fudan Univ, Childrens Hosp, Dept Neonatol, Shanghai, Peoples R China
[6] Univ Birmingham, Dept Elect Elect & Syst Engn, Birmingham, England
[7] Fudan Univ, Human Phenome Inst, Shanghai, Peoples R China
[8] Univ Sydney, Sch Biomed Engn, Sydney, NSW, Australia
来源：
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE | 2025年 / 19卷
关键词：
EEG; sleep analysis; neonatal sleep state classification; principal component analysis; SMOTE; LSTM; STAGE CLASSIFICATION;
D O I：
10.3389/fncom.2025.1506869
中图分类号：
Q [生物科学];
学科分类号：
07 ; 0710 ; 09 ;
摘要：
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 long-short-term memory (LSTM) classifier categorizes neonatal sleep states. An 16,803 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 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.
引用
收藏
页数：17
相关论文
共 53 条
  • [1] Abbasi S.F., Ahmad J., Tahir A., Awais M., Chen C., Irfan M., Et al., EEG-based neonatal sleep-wake classification using multilayer perceptron neural network, IEEE Access, 8, pp. 183025-183034, (2020)
  • [2] Abbasi S.F., Jamil H., Chen W., EEG-based neonatal sleep stage classification using ensemble learning, Comput. Mater. Contin, 70, pp. 4619-4633, (2022)
  • [3] Ali A., Shaukat S., Tayyab M., Khan M.A., Khan J.S., Ahmad J., Et al., “Network intrusion detection leveraging machine learning and feature selection,”, 2020 IEEE 17th International Conference on Smart Communities: Improving Quality of Life Using ICT, IoT and AI (HONET), pp. 49-53, (2020)
  • [4] Ansari A.H., De Wel O., Lavanga M., Caicedo A., Dereymaeker A., Jansen K., Et al., Quiet sleep detection in preterm infants using deep convolutional neural networks, J. Neural Eng, 15, (2018)
  • [5] Ansari A.H., De Wel O., Pillay K., Dereymaeker A., Jansen K., Van Huffel S., Et al., A convolutional neural network outperforming state-of-the-art sleep staging algorithms for both preterm and term infants, J. Neural Eng, 17, (2020)
  • [6] Ansari A.H., Pillay K., Dereymaeker A., Jansen K., Van Huffel S., Naulaers G., Et al., A deep shared multi-scale inception network enables accurate neonatal quiet sleep detection with limited eeg channels, IEEE J. Biomed. Health Inform, 26, pp. 1023-1033, (2021)
  • [7] Arasteh E., de Groot E.R., Van den Ende D., Alderliesten T., Long X., de Goederen R., Et al., Unobtrusive cot side sleep stage classification in preterm infants using ultra-wideband radar, Front. Sleep, 2, (2023)
  • [8] Arif S., Khan M.J., Naseer N., Hong K.-S., Sajid H., Ayaz Y., Vector phase analysis approach for sleep stage classification: a functional near-infrared spectroscopy-based passive brain-computer interface, Front. Hum. Neurosci, 15, (2021)
  • [9] Arif S., Munawar S., Ali H., Driving drowsiness detection using spectral signatures of EEG-based neurophysiology, Front. Physiol, 14, (2023)
  • [10] Awais M., Long X., Yin B., Abbasi S.F., Akbarzadeh S., Lu C., Et al., A hybrid DCNN-SVM model for classifying neonatal sleep and wake states based on facial expressions in video, IEEE J. Biomed. Health Inform, 25, pp. 1441-1449, (2021)
123456