What is the clinical evidence from this study?

Study design: Other. Population: Deceit (n=30). Intervention: Deep Neural Network (DNN) classifier on EEG P300 signals. Primary outcome: Classification accuracy.

June 3, 2021ACM Transactions on Management Information Systems

An Efficient Deep Learning Paradigm for Deceit Identification Test on EEG Signals

View Full Paper

Ask AI

Bookmark

Key result

A Deep Neural Network classifier analyzing EEG P300 signals achieved 95% accuracy in identifying deceit among 30 subjects.

Why the study?

The study was conducted to propose a novel Deceit Identification Test based on EEG signals to identify and classify P300 signals with good classification accuracy.

Population

30 subjects (15 guilty and 15 innocent)

Comparison

Guilty subjects vs innocent subjects

Design

Experimental validation study

Authors

DEDamodar Reddy EdlaNational Institute of Technology Goa SDShubham DodiaNational Institute of Technology Karnataka ABAnnushree BablaniSri Sri University

Discussion

Member takes

Implication

Hypothesis-generating for EEG-based deceit detection; leaves open validation in larger, diverse cohorts before any clinical use.

Structured PICO

Population

30 subjects (15 guilty and 15 innocent) evaluated for deceit identification using EEG signals.

Intervention

Deep Neural Network (DNN) with two autoencoders having 10 hidden layers each, using 'symlet' Wavelet Packet Transform (WPT) for feature extraction on P300 EEG signals

Outcome

Classification accuracy of P300 signals

A deep neural network using wavelet packet transform feature extraction achieved 95% accuracy in identifying deceit from P300 EEG signals.

Cite This Study

Edla et al. (2021) studied Deceit (n=30). Deep Neural Network (DNN) classifier on EEG P300 signals was evaluated on Classification accuracy. A Deep Neural Network classifier analyzing EEG P300 signals achieved 95% accuracy in identifying deceit among 30 subjects.

synapsesocial.com/papers/6a22af6d60296ba93ed2bff7 https://doi.org/10.1145/3458791

View Full Paper

Ask AI

Bookmark

June 3, 2021ACM Transactions on Management Information Systems

An Efficient Deep Learning Paradigm for Deceit Identification Test on EEG Signals

View Full Paper

Ask AI

Bookmark

Key result

A Deep Neural Network classifier analyzing EEG P300 signals achieved 95% accuracy in identifying deceit among 30 subjects.

Why the study?

The study was conducted to propose a novel Deceit Identification Test based on EEG signals to identify and classify P300 signals with good classification accuracy.

Population

30 subjects (15 guilty and 15 innocent)

Comparison

Guilty subjects vs innocent subjects

Design

Experimental validation study

Authors

DEDamodar Reddy EdlaNational Institute of Technology Goa SDShubham DodiaNational Institute of Technology Karnataka ABAnnushree BablaniSri Sri University

Discussion

Member takes

Implication

Hypothesis-generating for EEG-based deceit detection; leaves open validation in larger, diverse cohorts before any clinical use.

Structured PICO

Population

30 subjects (15 guilty and 15 innocent) evaluated for deceit identification using EEG signals.

Intervention

Deep Neural Network (DNN) with two autoencoders having 10 hidden layers each, using 'symlet' Wavelet Packet Transform (WPT) for feature extraction on P300 EEG signals

Outcome

Classification accuracy of P300 signals

A deep neural network using wavelet packet transform feature extraction achieved 95% accuracy in identifying deceit from P300 EEG signals.

Cite This Study

synapsesocial.com/papers/6a22af6d60296ba93ed2bff7 https://doi.org/10.1145/3458791

Also Consider

Synapse has enriched one closely related paper. Consider it for comparative context:

1Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion2010 · 4,114 citations

View Full Paper

Ask AI

Bookmark