Dataset Information

Emotion Recognition Using Electroencephalography Signals of Older People for Reminiscence Therapy.

ABSTRACT: Objective: Numerous communication support systems based on reminiscence therapy have been developed. However, when using communication support systems, the emotional assessment of older people is generally conducted using verbal feedback or questionnaires. The purpose of this study is to investigate the feasibility of using Electroencephalography (EEG) signals for automatic emotion recognition during RT for older people. Participants: Eleven older people (mean 71.25, SD 4.66) and seven young people (mean 22.4, SD 1.51) participated in the experiment. Methods: Old public photographs were used as material for reminiscence therapy. The EEG signals of the older people were collected while the older people and young people were talking about the contents of the photos. Since emotions change slowly and responses are characterized by delayed effects in EEG, the depth models LSTM and Bi-LSTM were selected to extract complex emotional features from EEG signals for automatic recognition of emotions. Results: The EEG data of 8 channels were inputted into the LSTM and Bi-LSTM models to classify positive and negative emotions. The recognition highest accuracy rate of the two models were 90.8% and 95.8% respectively. The four-channel EEG data based Bi-LSTM also reached 94.4%. Conclusion: Since the Bi-LSTM model could tap into the influence of "past" and "future" emotional states on the current emotional state in the EEG signal, we found that it can help improve the ability to recognize positive and negative emotions in older people. In particular, it is feasible to use EEG signals without the necessity of multimodal physiological signals for emotion recognition in the communication support systems for reminiscence therapy when using this model.

SUBMITTER: Jiang L

PROVIDER: S-EPMC8777059 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Electroencephalography (EEG) is one of the most widely-used biosignal capturing technology for investigating brain activities, cognitive diseases, and affective disorders. To understand the underlying principles of brain activities and affective disorders using EEG data, one of the fundamental tasks is to accurately identify emotions from EEG signals, which has attracted huge attention in the field of affective computing. To improve the accuracy and effectiveness of emotion recognition based on EEG data, previous studies have successfully developed numerous feature extraction methods and classifiers. Among them, ensemble empirical mode decomposition (EEMD) is an efficient signal decomposition technique for extracting EEG features. It can alleviate the mode-mixing problem by adding white noise to the source signal. However, there remain some issues when applying this method to recognition tasks. As the added noise cannot be filtered completely, spurious modes are generated due to the residual noise. Therefore, it is crucial to perform intrinsic mode function (IMF) selection to find the most valuable IMF components that represent brain activities. Furthermore, the number of decomposed IMFs is various to different original signals, thus how to unify feature dimensions needs better solutions. To solve these issues, we propose a novel forecasting framework, named DEEMD-SPP, to identify emotions from EEG signals, based on the combination of denoising ensemble empirical mode decomposition (DEEMD) and Spatial Pyramid Pooling Network (SPP-Net). First, DEEMD is proposed to decompose the EEG signals, which effectively eliminates residual noise in the IMFs and selects the most valuable IMFs. Second, time-domain and frequency-domain features are extracted from the selected IMFs. Finally, SPP-net is employed as the classifier to recognize emotions, which can effectively transform various-sized feature maps into fixed-sized feature vectors through the pyramid pooling layer. The experimental results demonstrate that our proposed DEEMD-SPP framework can effectively reduce the effect of spike-in white noise, accurately extract EEG features, and significantly improve the performance of emotion recognition.

Project description:BACKGROUND:Reminiscence therapy (RT) can improve various dysfunctions in people with dementia (PWD), but it may not be a cost-effective intervention. Digital RT allows multiple users to participate in a therapy simultaneously. Moreover, digital RT offers convenience, such as for uploading personal materials and presenting individual triggers of personal memories. This pilot study aimed to evaluate the effect of digital RT through a comparison with conventional RT and to develop a strategy for designing larger RCTs. METHODS:An Android application and digital content were developed for digital RT. Overall, 49 PWD enrolled in nine daycare centers in Korea met the inclusion criteria. Eight sessions of digital RT in an intervention group (n?=?25) and storytelling in a control group (n?=?24) with no digital materials were performed over 4 weeks from February to June 2019. Cognition, depression, behavioral and psychological symptoms of dementia (BPSD), and engagement were measured as the primary outcomes to evaluate the effect of digital RT. All outcomes except for engagement were evaluated at baseline before the intervention (T0), post-intervention (T1), and 4 weeks after the intervention (T2). Engagement was measured at the first and last intervention sessions. Differences in cognition, depression and BPSD between groups and across time points (T0, T1, and T2) were analyzed by repeated measures ANOVA. Differences in engagement between the groups and time points (the first and last sessions) were analyzed by independent t-tests. This study adhered to the CONSORT guidelines. RESULTS:Depression (F?=?7.62, p?= .001, partial ?2?=?.17) was significantly decreased at T1 and T2, and engagement (t?=?-?2.71, p?=?.011) was significantly increased at the last session in the digital RT group compared to the control group. However, cognition (F?=?0.13, p?=?.821) and BPSD (F?=?0.67, p?=?.485) were not significantly different between groups and time points. CONCLUSIONS:Digital RT proved an innovative approach to manage PWD and will thus help PWD achieve a better mood and have more opportunities to engage in social interactions. TRIAL REGISTRATION:KCT0003446 in the Clinical Research Information Service. Registered 24 January 2019, https://cris.nih.go.kr/cris/search/search_result_st01.jsp?seq=14391.

Dataset Information

Emotion Recognition Using Electroencephalography Signals of Older People for Reminiscence Therapy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets