Electroencephalography(EEG)analysis extracts critical information from brain signals,enabling brain disease diagnosis and providing fundamental support for brain–computer interfaces.However,performing an artificial i...Electroencephalography(EEG)analysis extracts critical information from brain signals,enabling brain disease diagnosis and providing fundamental support for brain–computer interfaces.However,performing an artificial intelligence analysis of EEG signals with high energy efficiency poses significant challenges for electronic processors on edge computing devices,especially with large neural network models.Herein,we propose an EEG opto-processor based on diffractive photonic computing units(DPUs)to process extracranial and intracranial EEG signals effectively and to detect epileptic seizures.The signals of the EEG channels within a second-time window are optically encoded as inputs to the constructed diffractive neural networks for classification,which monitors the brain state to identify symptoms of an epileptic seizure.We developed both free-space and integrated DPUs as edge computing systems and demonstrated their applications for real-time epileptic seizure detection using benchmark datasets,that is,the Children’s Hospital Boston(CHB)–Massachusetts Institute of Technology(MIT)extracranial and Epilepsy-iEEG-Multicenter intracranial EEG datasets,with excellent computing performance results.Along with the channel selection mechanism,both numerical evaluations and experimental results validated the sufficiently high classification accuracies of the proposed opto-processors for supervising clinical diagnosis.Our study opens a new research direction for utilizing photonic computing techniques to process large-scale EEG signals and promote broader applications.展开更多
Cluster analysis is a method often used in pattern recognition. With the aid of the signal processing and the learning of the computer, disfferent samples can be classifeid and recognized in a dimension reduction spac...Cluster analysis is a method often used in pattern recognition. With the aid of the signal processing and the learning of the computer, disfferent samples can be classifeid and recognized in a dimension reduction space of the characteristics because of the differences of their character -istics. To realize dimension reduction transformation, a nonlinear mapping method was discussed in this paper. To prove that the cluster analysis is suitable for quite different fields of samples, in this paper some ship noises and some EEG as the samples belong to two different fields are classified and shown. And it is worthy to point out that an adaptive step size expression of adaptive iteration deduced here will also be effective if it is applied to speed adaptive algorithm convergence of general signal processing.展开更多
基金supported by the National Major Science and Technology Projects of China(2021ZD0109902 and 2020AA0105500)the National Natural Science Fundation of China(62275139 and 62088102)the Tsinghua University Initiative Scientific Research Program.
文摘Electroencephalography(EEG)analysis extracts critical information from brain signals,enabling brain disease diagnosis and providing fundamental support for brain–computer interfaces.However,performing an artificial intelligence analysis of EEG signals with high energy efficiency poses significant challenges for electronic processors on edge computing devices,especially with large neural network models.Herein,we propose an EEG opto-processor based on diffractive photonic computing units(DPUs)to process extracranial and intracranial EEG signals effectively and to detect epileptic seizures.The signals of the EEG channels within a second-time window are optically encoded as inputs to the constructed diffractive neural networks for classification,which monitors the brain state to identify symptoms of an epileptic seizure.We developed both free-space and integrated DPUs as edge computing systems and demonstrated their applications for real-time epileptic seizure detection using benchmark datasets,that is,the Children’s Hospital Boston(CHB)–Massachusetts Institute of Technology(MIT)extracranial and Epilepsy-iEEG-Multicenter intracranial EEG datasets,with excellent computing performance results.Along with the channel selection mechanism,both numerical evaluations and experimental results validated the sufficiently high classification accuracies of the proposed opto-processors for supervising clinical diagnosis.Our study opens a new research direction for utilizing photonic computing techniques to process large-scale EEG signals and promote broader applications.
基金The project supported by National Natural Science Foundation of China
文摘Cluster analysis is a method often used in pattern recognition. With the aid of the signal processing and the learning of the computer, disfferent samples can be classifeid and recognized in a dimension reduction space of the characteristics because of the differences of their character -istics. To realize dimension reduction transformation, a nonlinear mapping method was discussed in this paper. To prove that the cluster analysis is suitable for quite different fields of samples, in this paper some ship noises and some EEG as the samples belong to two different fields are classified and shown. And it is worthy to point out that an adaptive step size expression of adaptive iteration deduced here will also be effective if it is applied to speed adaptive algorithm convergence of general signal processing.
