TY - GEN
T1 - Comparative Study of Brain Signals for Early Detection of Sleep Disorder Using Machine and Deep Learning Algorithm
AU - Satapathy, Santosh Kumar
AU - Patel, Vanshita
AU - Gandhi, Manan
AU - Mohapatra, Rajesh Kumar
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024/1/1
Y1 - 2024/1/1
N2 - Sleep disorders are a common health concern affecting a significant portion of the global population. Early detection and intervention are crucial for preventing the detrimental impact of sleep disorders on an individual's physical and mental health. This study presents a comparative analysis of the effectiveness of machine and deep learning algorithms in the early detection of sleep disorders using brain signals. The research leverages electroencephalogram (EEG) data collected from individuals with varying sleep disorders. We extract relevant features from EEG signals, including spectral, temporal, and spatial features, which provide insight into the brain's activity during different sleep stages. These features serve as input to both machine learning and deep learning models. In the machine learning approach, we employ classical algorithms such as Support Vector Machines (SVM), Random Forest (RF), and K-nearest neighbors (KNN). In the deep learning approach, we use convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to process the EEG data. The study evaluates the performance of these algorithms in terms of accuracy, sensitivity, specificity, and precision while considering different sleep disorder categories, including insomnia, sleep apnea, and narcolepsy. Our findings indicate that deep learning models, particularly CNNs and RNNs, outperform traditional machine learning algorithms in accurately identifying sleep disorders. The deep learning models demonstrate the ability to capture intricate patterns and dependencies within EEG data, leading to more accurate and early detection.
AB - Sleep disorders are a common health concern affecting a significant portion of the global population. Early detection and intervention are crucial for preventing the detrimental impact of sleep disorders on an individual's physical and mental health. This study presents a comparative analysis of the effectiveness of machine and deep learning algorithms in the early detection of sleep disorders using brain signals. The research leverages electroencephalogram (EEG) data collected from individuals with varying sleep disorders. We extract relevant features from EEG signals, including spectral, temporal, and spatial features, which provide insight into the brain's activity during different sleep stages. These features serve as input to both machine learning and deep learning models. In the machine learning approach, we employ classical algorithms such as Support Vector Machines (SVM), Random Forest (RF), and K-nearest neighbors (KNN). In the deep learning approach, we use convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to process the EEG data. The study evaluates the performance of these algorithms in terms of accuracy, sensitivity, specificity, and precision while considering different sleep disorder categories, including insomnia, sleep apnea, and narcolepsy. Our findings indicate that deep learning models, particularly CNNs and RNNs, outperform traditional machine learning algorithms in accurately identifying sleep disorders. The deep learning models demonstrate the ability to capture intricate patterns and dependencies within EEG data, leading to more accurate and early detection.
KW - Deep Learning Algorithms
KW - Electroencephalogram (EEG)
KW - Machine Learning Algorithms
KW - Sleep stages
UR - http://www.scopus.com/inward/record.url?scp=85192256233&partnerID=8YFLogxK
U2 - 10.1109/IATMSI60426.2024.10503066
DO - 10.1109/IATMSI60426.2024.10503066
M3 - Conference contribution
AN - SCOPUS:85192256233
T3 - 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024
BT - 2024 IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024
PB - Institute of Electrical and Electronics Engineers
T2 - 2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024
Y2 - 14 March 2024 through 16 March 2024
ER -