• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Student
Title
Supervisor
Faculty
Educational Programme
Final Grade
Year of Graduation
Ekaterina Kovaleva
Machine Learning based Approach to Emotion Recognition for a Wearable EEG-device
9
2019
Author: Kovaleva, Ekaterina Alexandrovna, 2nd year master’s student at the IAUP 17-1 group at the Higher School of Economics-Perm. The topic of the master's thesis is the development of an approach to the identification of human emotions according to the data of a portable EEG device based on machine learning methods. This paper is devoted to the problem of identifying the signs important for the task of emotion recognition on a limited number of electrodes and the construction of the corresponding predictive model. To do this, compare different categories of features and methods for identifying the most relevant features for the task of predicting emotions, as well as various methods of machine learning. In this paper, it is shown that already on three electrodes one can obtain the accuracy of prediction of emotions of 75%.

The current study includes 3 chapters:

1. The theoretical aspects of the topic under study, the application of the EEG method for assessing the emotional state, the interpretation of brain signals and methods for their processing are considered.

2. Review of the applied component: methods for collecting, processing, analyzing and evaluating data.

3. Development of approaches based on pre-existing emotions for prediction and the choice of the approach that will show the best (from the point of view of the task of predicting emotions) on a fixed number of electrodes.

The number of pages - 71, the number of illustrations - 39, the number of tables - 3.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses