Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data
The development of objective methods for assessing stress levels is an important task of applied neuroscience. Analysis of EEG recorded as part of a behavioral self-control program can serve as the basis for the development of test methods that allow classifying people by stress level. It is well kn...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Siberian Branch of the Russian Academy of Sciences, Federal Research Center Institute of Cytology and Genetics, The Vavilov Society of Geneticists and Breeders
2023-12-01
|
| Series: | Вавиловский журнал генетики и селекции |
| Subjects: | |
| Online Access: | https://vavilov.elpub.ru/jour/article/view/3985 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575046281854976 |
|---|---|
| author | X. Fu S. S. Tamozhnikov A. E. Saprygin N. A. Istomina A. N. Klemeshova A. N. Savostyanov |
| author_facet | X. Fu S. S. Tamozhnikov A. E. Saprygin N. A. Istomina A. N. Klemeshova A. N. Savostyanov |
| author_sort | X. Fu |
| collection | DOAJ |
| description | The development of objective methods for assessing stress levels is an important task of applied neuroscience. Analysis of EEG recorded as part of a behavioral self-control program can serve as the basis for the development of test methods that allow classifying people by stress level. It is well known that participation in meditation practices leads to the development of skills of voluntary self-control over the individual’s mental state due to an increased concentration of attention to themselves. As a consequence of meditation practices, participants can reduce overall anxiety and stress levels. The aim of our study was to develop, train and test a convolutional neural network capable of classifying individuals into groups of practitioners and non-practitioners of meditation by analysis of eventrelated brain potentials recorded during stop-signal paradigm. Four non-deep convolutional network architectures were developed, trained and tested on samples of 100 people (51 meditators and 49 non-meditators). Subsequently, all structures were additionally tested on an independent sample of 25 people. It was found that a structure using a one-dimensional convolutional layer combining the layer and a two-layer fully connected network showed the best performance in simulation tests. However, this model was often subject to overfitting due to the limitation of the display size of the data set. The phenomenon of overfitting was mitigated by changing the structure and scale of the model, initialization network parameters, regularization, random deactivation (dropout) and hyperparameters of cross-validation screening. The resulting model showed 82 % accuracy in classifying people into subgroups. The use of such models can be expected to be effective in assessing stress levels and inclination to anxiety and depression disorders in other groups of subjects. |
| format | Article |
| id | doaj-art-cb45ddabfe414713bb3eadd72bcdeb97 |
| institution | Kabale University |
| issn | 2500-3259 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | Siberian Branch of the Russian Academy of Sciences, Federal Research Center Institute of Cytology and Genetics, The Vavilov Society of Geneticists and Breeders |
| record_format | Article |
| series | Вавиловский журнал генетики и селекции |
| spelling | doaj-art-cb45ddabfe414713bb3eadd72bcdeb972025-02-01T09:58:12ZengSiberian Branch of the Russian Academy of Sciences, Federal Research Center Institute of Cytology and Genetics, The Vavilov Society of Geneticists and BreedersВавиловский журнал генетики и селекции2500-32592023-12-0127785185810.18699/VJGB-23-981413Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG dataX. Fu0S. S. Tamozhnikov1A. E. Saprygin2N. A. Istomina3A. N. Klemeshova4A. N. Savostyanov5Novosibirsk State UniversityScientific Research Institute of Neurosciences and MedicineScientific Research Institute of Neurosciences and Medicine; Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of SciencesNovosibirsk State UniversityInstitute of Cytology and Genetics of the Siberian Branch of the Russian Academy of SciencesNovosibirsk State University; Scientific Research Institute of Neurosciences and Medicine; Institute of Cytology and Genetics of the Siberian Branch of the Russian Academy of SciencesThe development of objective methods for assessing stress levels is an important task of applied neuroscience. Analysis of EEG recorded as part of a behavioral self-control program can serve as the basis for the development of test methods that allow classifying people by stress level. It is well known that participation in meditation practices leads to the development of skills of voluntary self-control over the individual’s mental state due to an increased concentration of attention to themselves. As a consequence of meditation practices, participants can reduce overall anxiety and stress levels. The aim of our study was to develop, train and test a convolutional neural network capable of classifying individuals into groups of practitioners and non-practitioners of meditation by analysis of eventrelated brain potentials recorded during stop-signal paradigm. Four non-deep convolutional network architectures were developed, trained and tested on samples of 100 people (51 meditators and 49 non-meditators). Subsequently, all structures were additionally tested on an independent sample of 25 people. It was found that a structure using a one-dimensional convolutional layer combining the layer and a two-layer fully connected network showed the best performance in simulation tests. However, this model was often subject to overfitting due to the limitation of the display size of the data set. The phenomenon of overfitting was mitigated by changing the structure and scale of the model, initialization network parameters, regularization, random deactivation (dropout) and hyperparameters of cross-validation screening. The resulting model showed 82 % accuracy in classifying people into subgroups. The use of such models can be expected to be effective in assessing stress levels and inclination to anxiety and depression disorders in other groups of subjects.https://vavilov.elpub.ru/jour/article/view/3985convolutional neural networkseegevent-related brain potentialsmeditationstop-signal paradigm |
| spellingShingle | X. Fu S. S. Tamozhnikov A. E. Saprygin N. A. Istomina A. N. Klemeshova A. N. Savostyanov Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data Вавиловский журнал генетики и селекции convolutional neural networks eeg event-related brain potentials meditation stop-signal paradigm |
| title | Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data |
| title_full | Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data |
| title_fullStr | Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data |
| title_full_unstemmed | Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data |
| title_short | Convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the EEG data |
| title_sort | convolutional neural networks for classifying healthy individuals practicing or not practicing meditation according to the eeg data |
| topic | convolutional neural networks eeg event-related brain potentials meditation stop-signal paradigm |
| url | https://vavilov.elpub.ru/jour/article/view/3985 |
| work_keys_str_mv | AT xfu convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata AT sstamozhnikov convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata AT aesaprygin convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata AT naistomina convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata AT anklemeshova convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata AT ansavostyanov convolutionalneuralnetworksforclassifyinghealthyindividualspracticingornotpracticingmeditationaccordingtotheeegdata |