Emotions recognizing using lognnet neural network and Keystroke dynamics dataset

The development of methods for assessing the emotional state of a person in modern society plays an important role not only in order to increase the efficiency of labor in the workplace or office, but also socially to prevent conflict situations and improve the standard of living. This study present...

Full description

Saved in:
Bibliographic Details
Main Authors: Velichko, A., Izotov, Yu
Format: Conference Proceeding
Language:English
Subjects:
Datasets
Emotional factors
Emotions
Internet of Things
Keyboards
Neural networks
Recognition
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The development of methods for assessing the emotional state of a person in modern society plays an important role not only in order to increase the efficiency of labor in the workplace or office, but also socially to prevent conflict situations and improve the standard of living. This study presents a method for recognizing human emotions using LogNNet neural network and keystroke dynamics dataset. Two types of training sets were investigated, with 10 and 15 features compiled on the basis of the Emosurv database, an assessment of recognition metrics was given (accuracy, Precision, Recall and F1). It is shown that the accuracy of recognition of one emotion out of 5 (happy, sad, angry, calm, neutral state) reaches 33.4% when using 10 features read only from the keyboard. Such a neural network can be placed on 'Internet of Things' edge devices with low computing resources and RAM up to 3 kB, as well as built into the keyboard using inexpensive controllers such as Arduino.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0162572