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.

Electroencephalogram signals emotion recognition based on convolutional neural network-recurrent neural network framework with channel-temporal attention mechanism for older adults

“…Our experiments were conducted on the dataset from the previous study ( Jiang et al, 2022 ). Eleven older adults (six males and five females) and seven younger adults (five males and two females) were randomly pair-matched into 11 groups, and each group engaged in 36 photo conversations.…”

“…Electroencephalogram signals used a 1–45 Hz bandpass filter (removal of the line interference) and a Chebyshev I high-pass filter to remove baseline drift ( Jiang et al, 2022 ).…”

Editorial for advances in human-centred dementia technology

“…Studies have shown that the use of novel technologies for reminiscence therapy is more effective than traditional methods (Hayhurst, 2018). More recently, novel research has started to look into recognising emotional elicitation in older adults during reminiscence therapy using physiological signals; aiming to provide in-depth insights beyond PwDs' verbal feedback, which could lend a lens to therapy administers especially for PwD who face barriers with verbal communication (Jiang et al, 2022b(Jiang et al, , 2022d.…”

“…Finally, difficulties in the areas of language and communication is a common symptom in PwD; it can be challenging for PwD to share their thoughts or express their emotions (Banovic et al, 2018). As such, it is imperative that tools, solutions, interventions, and technologies developed are based on sound human-centred principles, and sensitive to the needs of this population in a bid to design more user-friendly, highly engaging, and effective solutions (Tabbaa et al, 2020), which can also help PwD and those around them understand their emotions through means beyond verbal communication (Jiang et al, 2022a(Jiang et al, , 2022cTabbaa et al, 2021;Zeng et al, 2020aZeng et al, , 2020b.…”

Topical Cellular/Tissue and Molecular Aspects Regarding Nonpharmacological Interventions in Alzheimer’s Disease—A Systematic Review

“…An important biomedical link has been reported between RT and feeding; the former encourages persons with dementia to enjoy meals specific to the origin culture and remote experiences from their childhood, including participating in traditional related gastronomic events and involvement in cooking, using their tastes and customs, established before becoming mentally ill [10]. Moreover, through "electroencephalography (EEG) signals for automatic emotion recognition" one can see the objective effects of RT; in addition, "the pleasure level of RT and the (o. n.: eu-)stress level of the conversation is more conducive to the emotion classification of older people in the communication support systems" [193]. Hence, RT "can help improve communication, feelings of belonging..., mood, wellbeing", with beneficial intellective actions; further, with the aid of the impressive actual development and expansion of artificial intelligence (AI), there can be related digital progress: re-configuring RT in a customized paradigm, resembling the features provided by a human health professional (skilled/licensed carer or respectively, therapist), targeting thereby an "intangible cultural heritage", including "facial expression analysis and reinforcement learning techniques".…”