Key result
EEG-trained artificial neural network successfully classifies drunk versus non-drunk states.
Why the study?
The detection of alcohol-induced functional impairment is important as current breathalyzers measure alcohol amount but not loss of function, which varies between individuals.
Answers are grounded in this paper and cite their sources.
EEG data combined with Artificial Neural Networks can be used to detect alcohol impairment, potentially offering a functional assessment compared to standard breathalyzers.
Alcoholic beverages are widely used in many societies.People can maintain their everyday lives while using a certain amount of alcohol.However, when alcohol is used intensively, it prevents healthy thinking, undermines decision making and reflex functions.This decrease in reflexes brings increase in traffic and job accidents.In order to determine the capability of a person to do a job, the detection of alcohol level is important.Nowadays, breathalyzers are used for the purpose of such detection.These devices measure the amount of alcohol rather than loss of function caused by alcohol.But the amount of alcohol taken show different effects from person to person.In this study people were tested and determined whether they were alcoholic with the help of EEG data.Preprocessing was performed on the EEG data set before the process of detection, followed by the training of ANN (Artificial Neural Network) and its test.Based on the obtained best performance value, an interface was designed on MATLAB for users.
No takes yet. Share an insight, caveat, or question.
Eki et al. (2013) studied Alcohol intoxication. EEG data classification using Artificial Neural Network vs. Non-drunk individuals was evaluated on Classification of drunk vs non-drunk state. An Artificial Neural Network trained on EEG data was able to classify whether individuals were drunk or non-drunk, leading to the design of a MATLAB interface for users.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: