COGNITIVE WORKLOAD RECOGNITION USING EEG SIGNALS AND MACHINE LEARNING A REVIEW

Abstract : Machine learning and its subfield deep learning techniques provide opportunities for the development of operator mental state monitoring, especially for cognitive workload recognition using electroencephalogram (EEG) signals. Although a variety of machine learning methods have been proposed for recognizing cognitive workload via EEG recently, there does not yet exist a review that covers in-depth the application of machine learning methods. To alleviate this gap, in this paper, we survey cognitive workload and machine learning literature to identify the approaches and highlight the primary advances

 EXISTING SYSTEM :

 ? In recent years, regardless of the task environments, the mean accuracies of existing methods to EEG workload recognition are almost over 80%, which seems acceptable for practical applications. ? Also, for code reproducibility, Roy et al. recommend that the published studies should clearly describe the architecture of models, the data used, or existing datasets used, whenever possible. Besides these, the studies should also include state-of-the-art baselines, and share code. ? In contrast to the intrinsic interpretable models, e.g., decision trees, many other existing machine learning approaches are non-interpretable black-box models

 DISADVANTAGE :

 ? Although a variety of machine learning methods have been proposed for recognizing cognitive workload via EEG recently, there does not yet exist a review that covers in-depth the application of machine learning methods ? In literature, various machine learning methods are proposed to handle those problems ? Several studies have used this dataset to validate their proposed machine learning models ? The frequency domain analysis is proposed to display the frequency information of EEG, with an assumption that EEG signals are stationary.

 PROPOSED SYSTEM :

 ? Although a variety of machine learning methods have been proposed for recognizing cognitive workload via EEG recently, there does not yet exist a review that covers in-depth the application of machine learning methods ? In literature, various machine learning methods are proposed to handle those problems ? Several studies have used this dataset to validate their proposed machine learning models ? The frequency domain analysis is proposed to display the frequency information of EEG, with an assumption that EEG signals are stationary.

 ADVANTAGE :

 ? Among them, EEG is one of the most widely used signals, due to its high temporal resolution, convenience, security, and cheapness. ? The commonly used physiological signals can be roughly divided into several categories, i.e., electroencephalogram (EEG), heart rate, eye movement, respiration, electromyogram, and skin The widely used paradigms to experience cognitive workload are performed either under controlled laboratory conditions, e.g., cognitive task, or operating machine in real or simulated environments. We then categorize the paradigms into cognitive-oriented and operate-oriented

Deep Learning Covid-19 outbreak

MACHINE LEARNING UNDERSTANDING DEPTH

MACHINE LEARNING UNDERSTANDING DEPTH

MACHINE LEARNING 3-D DECONVOLUTIONAL NETWORKS

MACHINE LEARNING INTER-TURN SHORT-CIRCUIT

MACHINE LEARNING BASED ON JOURNALING

MACHINE LEARNING FUSING SELL-SIDE ANALYST

MACHINE LEARNING FAIRNESS IN SEMI-SUPERVISED LEARNING

MACHINE LEARNING ENRICHING THE TRANSFER LEARNING

MACHINE LEARNING AUTOMATED SCREENING SYSTEM

MACHINE LEARNING AN ONLINE TRANSFER LEARNING

MACHINE LEARNING THE HIDDEN SEXUAL MINORITIES

MACHINE LEARNING DEPTH ESTIMATION

MACHINE LEARNING A SYSTEMATIC LITERATURE

MACHINE LEARNING FREEDOM IN MANUAL TEXT

MACHINE LEARNING A SYSTEMATIC REVIEW

MACHINE LEARNING key based security

MACHINE LEARNING Deep Learning

MACHINE LEARNING EMOJI TEXT

MACHINE LEARNING EDGE COMPUTING MULTI-OBJECTIVE