首页|Dicle University Reports Findings in Pain and Central Nervous System (Deep Insights into MCI Diagnosis: A Comparative Deep Learning Analysis of EEG Time Series)
Dicle University Reports Findings in Pain and Central Nervous System (Deep Insights into MCI Diagnosis: A Comparative Deep Learning Analysis of EEG Time Series)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Network Daily News - New research onPain and Central Nervous System is the subject of a report. According to news reporting from Diyarbakir,Turkey, by NewsRx journalists, research stated, “Individuals in the early stages of Alzheimer’s Disease(AD) are typically diagnosed with Mild Cognitive Impairment (MCI). MCI represents a transitional phasebetween normal cognitive function and AD.”The news correspondents obtained a quote from the research from Dicle University, “Electroencephalography(EEG) records carry valuable insights into cerebral cortex brain activities to analyze neuronal degeneration.To enhance the precision of dementia diagnosis, automatic and intelligent methods are requiredfor the analysis and processing of EEG signals. This paper aims to address the challenges associated withMCI diagnosis by leveraging EEG signals and deep learning techniques. The analysis in this study focuseson processing the information embedded within the sequence of raw EEG time series data. EEG recordingsare collected from 10 Healthy Controls (HC) and 10 MCI participants using 19 electrodes during a 30mineyes-closed session. EEG time series are transformed into 2 separate formats of input tensors and appliedto deep neural network architectures. Convolutional Neural Network (CNN) and ResNet from scratch areperformed with 2D time series with different segment lengths. Furthermore, EEGNet and DeepConvNetarchitectures are utilized for 1D time series. ResNet demonstrates superior effectiveness in detecting MCIwhen compared to CNN architecture. Complete discrimination is achieved using EEGNet and DeepConvNetfor noisy segments. ResNet has yielded a 3% higher accuracy rate compared to CNN. None of thearchitectures in the literature have achieved 100% accuracy except proposed EEGNet and DeepConvnet.”
DiyarbakirTurkeyEurasiaDiagnostics and ScreeningHealth and MedicineNetworksNeural NetworksPain and Central Nervous System
NETL
NSTL
