Automated detection of schizophrenia using nonlinear signal processing methods
作者：
Highlights：
• Automated detection of schizophrenia is proposed.
• Nonlinear features are extracted from EEG signals.
• Obtained classification accuracy of 92.91% using SVM classifier.
• Developed model is kept in the cloud for fast and immediate diagnosis.
• Patient will be informed of the diagnosis after confirmation by the clinician.
摘要
•Automated detection of schizophrenia is proposed.•Nonlinear features are extracted from EEG signals.•Obtained classification accuracy of 92.91% using SVM classifier.•Developed model is kept in the cloud for fast and immediate diagnosis.•Patient will be informed of the diagnosis after confirmation by the clinician.
论文关键词：Schizophrenia,EEG signal,Series splitting,Non-linear feature extraction,SVM classifier,Performance evaluation and validation
论文评审过程：Received 15 May 2019, Revised 27 June 2019, Accepted 18 July 2019, Available online 20 July 2019, Version of Record 1 September 2019.
论文官网地址：https://doi.org/10.1016/j.artmed.2019.07.006
