Truth Identification from EEG Signal by using Convolution neural network: Lie Detection

2020 ◽  
Author(s):  
Neeraj Baghel ◽  
Divyanshu Singh ◽  
Malay Kishore Dutta ◽  
Radim Burget ◽  
Vojtech Myska
Keyword(s):  
Neural Network ◽  
Lie Detection ◽  
Convolution Neural Network ◽  
Eeg Signal

scholarly journals A Novel Time-Incremental End-to-End Shared Neural Network with Attention-Based Feature Fusion for Multiclass Motor Imagery Recognition

2021 ◽  
Vol 2021 ◽  
pp. 1-16
Author(s):  
Shidong Lian ◽  
Jialin Xu ◽  
Guokun Zuo ◽  
Xia Wei ◽  
Huilin Zhou
Keyword(s):  
Neural Network ◽  
Motor Imagery ◽  
Classification Accuracy ◽  
Feature Fusion ◽  
Spatial Domain ◽  
Convolution Neural Network ◽  
Eeg Signal ◽  
Signal Recognition ◽  
Eeg Signals ◽  
End To End

In the research of motor imagery brain-computer interface (MI-BCI), traditional electroencephalogram (EEG) signal recognition algorithms appear to be inefficient in extracting EEG signal features and improving classification accuracy. In this paper, we discuss a solution to this problem based on a novel step-by-step method of feature extraction and pattern classification for multiclass MI-EEG signals. First, the training data from all subjects is merged and enlarged through autoencoder to meet the need for massive amounts of data while reducing the bad effect on signal recognition because of randomness, instability, and individual variability of EEG data. Second, an end-to-end sharing structure with attention-based time-incremental shallow convolution neural network is proposed. Shallow convolution neural network (SCNN) and bidirectional long short-term memory (BiLSTM) network are used to extract frequency-spatial domain features and time-series features of EEG signals, respectively. Then, the attention model is introduced into the feature fusion layer to dynamically weight these extracted temporal-frequency-spatial domain features, which greatly contributes to the reduction of feature redundancy and the improvement of classification accuracy. At last, validation tests using BCI Competition IV 2a data sets show that classification accuracy and kappa coefficient have reached 82.7 ± 5.57% and 0.78 ± 0.074, which can strongly prove its advantages in improving classification accuracy and reducing individual difference among different subjects from the same network.

scholarly journals Automatic Classification of Autism using Fusion of EEG and 4D FMRI

2019 ◽  
Vol 9 (2S4) ◽  
pp. 656-659
Keyword(s):  
Neural Network ◽  
Neuropsychiatric Disorders ◽  
Automatic Classification ◽  
Independent Component ◽  
Convolution Neural Network ◽  
Fmri Data ◽  
Eeg Signal ◽  
Individual Basis ◽  
Feature Projection

The identification and classification of diseased networks in fMRI is very difficult mastermind in people with big running autism has demonstrated to have diminished integration beyond field of renewal regulated by fMRI. When looking at the resting essential structure of people with independent and rule individuals coordinated for dotage and knowledge result, the outcome demonstrate that those pairs have a quiet essential structure that is fundamentally same as together in amount and in constitution, but in solitary this grid is extra unfined related. The exact forecast of general neuropsychiatric issues, on an individual basis, using rs-fMRI is a challenging task of incredible clinical noteworthiness. By developing a system which process and classify the fMRI data, it can be easily predicted whether the neuropsychiatric disorders especially autism is present or not. The fusion of features of EEG signal and the features obtained from independent component of fMRI are utilized for the automatic classification of Autism disorder. It can also be used to identify the diseased network and to automatically classify the different components of diseased networks. A classifier is constructed by k-means on a 2D feature projection space, with groupwise normalization for the classification of HC and Autism subjects with EEG and Rs-fMRI 4D dataset and compared with Convolution Neural network(CNN).

The Convolution Neural Network Combined with the HT Person Fit Statistic to Develop an APP for Detecting Dengue Fever in Children: Development and Usability Study (Preprint)

2019 ◽  
Author(s):  
CHIEN WEI ◽  
Chi Chow Julie ◽  
Chou Willy
Keyword(s):  
Neural Network ◽  
Dengue Fever ◽  
Prediction Accuracy ◽  
Early Stage ◽  
Family Members ◽  
Convolution Neural Network ◽  
Public Health Issue ◽  
Person Fit ◽  
Model Accuracy ◽  
Comparison Results

UNSTRUCTURED Backgrounds: Dengue fever (DF) is an important public health issue in Asia. However, the disease is extremely hard to detect using traditional dichotomous (i.e., absent vs. present) evaluations of symptoms. Convolution neural network (CNN), a well-established deep learning method, can improve prediction accuracy on account of its usage of a large number of parameters for modeling. Whether the HT person fit statistic can be combined with CNN to increase the prediction accuracy of the model and develop an application (APP) to detect DF in children remains unknown. Objectives: The aim of this study is to build a model for the automatic detection and classification of DF with symptoms to help patients, family members, and clinicians identify the disease at an early stage. Methods: We extracted 19 feature variables of DF-related symptoms from 177 pediatric patients (69 diagnosed with DF) using CNN to predict DF risk. The accuracy of two sets of characteristics (19 symptoms and four other variables, including person mean, standard deviation, and two HT-related statistics matched to DF+ and DF−) for predicting DF, were then compared. Data were separated into training and testing sets, and the former was used to predict the latter. We calculated the sensitivity (Sens), specificity (Spec), and area under the receiver operating characteristic curve (AUC) across studies for comparison. Results: We observed that (1) the 23-item model yields a higher accuracy rate (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90) based on the 177-case training set; (2) the Sens values are almost higher than the corresponding Spec values (90% in 10 scenarios) for predicting DF; (3) the Sens and Spec values of the 23-item model are consistently higher than those of the 19-item model. An APP was subsequently designed to detect DF in children. Conclusion: The 23-item model yielded higher accuracy rates (0.95) and AUC (0.94) than the 19-item model (accuracy = 0.92, AUC = 0.90). An APP could be developed to help patients, family members, and clinicians discriminate DF from other febrile illnesses at an early stage.

Sign in / Sign up

Export Citation Format

Share Document