Automatic sleep staging can provide an aid to experts and it’s an important basis for assessing sleep quality and diagnosing sleep disorders. However, the complex non-stationary and non-linear characteristics of Electroencephalogram (EEG) signal make it difficult to use them directly for sleep staging, while existing EEG signal decomposition methods have drawbacks such as modal mixing and boundary effects. To address these issues, this paper decomposes single-channel EEG signal into sub-bands signal based on a new decomposition method, Empirical Fourier Decomposition (EFD). The time-domain, frequency-domain, and non-linear features of these sub-bands signal are then extracted. A ReliefF algorithm is then used for feature selection to obtain the feature subset with the optimal staging performance. The feature subset is input to the Random Forest (RF) to class, and the staging results of the proposed method are also compared with existing literature. The accuracy rates of the proposed algorithm in 2-6 classes of sleep staging are 97.79%, 95.35%, 94.33%, 93.35%, and 92.72%, respectively. Due to the portability of single-channel devices, the proposed method can effectively facilitate the research and application of home sleep monitoring devices.
KEYWORDS: Switching, Object detection, Signal filtering, Data modeling, Motion models, Education and training, Information visualization, Detection and tracking algorithms
Aiming at the problems of ID switching and tracking performance degradation caused by frequent occlusion and similar appearance of the tracked objects in dense scenes, a multi-object tracking method named TPFairMOT based on trajectory prediction and FairMOT is proposed in this paper. In the trajectory prediction branch, the object position of the future frame is predicted by using the object bounding box of the past frame and the velocity information learning network parameters, which overcomes the prediction failure caused by the uncertain motion state after the object is occluded in the tracking process. Secondly, the joint learning framework is used to combine the trajectory prediction branch with the detection and re-identification branch, and the tracking error caused by the high similarity between multiple objects in the tracking process is solved by integrating the appearance features and motion features of the tracked objects. Finally, MOTChallenge benchmarks (IDF1, IDs, MOTA, MT, and ML) are introduced to evaluate TPFairMOT, and different trajectory prediction strategies (FairMOT_KF and TPFairMOT_RNN) are used on FairMOT and TPFairMOT for comparative analysis. It is proved that the accuracy and ID switching times of trajectory prediction in this paper are better than other strategies. In addition, TPFairMOT, TPFairMOT_RNN, and FairMOT were compared on the public data sets MOT16, MOT17, and MOT20. The results show that TPFairMOT reduces the number of ID switching when the object is occluded, maintains the long-term validity of the identity information, and demonstrate good anti-occlusion performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.