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

Reminiscence and conversation between older adults and younger volunteers using past photographs are very effective in improving the emotional state of older adults and alleviating depression. However, we need to evaluate the emotional state of the older adult while conversing on the past photographs. While electroencephalogram (EEG) has a significantly stronger association with emotion than other physiological signals, the challenge is to eliminate muscle artifacts in the EEG during speech as well as to reduce the number of dry electrodes to improve user comfort while maintaining high emotion recognition accuracy. Therefore, we proposed the CTA-CNN-Bi-LSTM emotion recognition framework. EEG signals of eight channels (P3, P4, F3, F4, F7, F8, T7, and T8) were first implemented in the MEMD-CCA method on three brain regions separately (Frontal, Temporal, Parietal) to remove the muscle artifacts then were fed into the Channel-Temporal attention module to get the weights of channels and temporal points most relevant to the positive, negative and neutral emotions to recode the EEG data. A Convolutional Neural Networks (CNNs) module then extracted the spatial information in the new EEG data to obtain the spatial feature maps which were then sequentially inputted into a Bi-LSTM module to learn the bi-directional temporal information for emotion recognition. Finally, we designed four group experiments to demonstrate that the proposed CTA-CNN-Bi-LSTM framework outperforms the previous works. And the highest average recognition accuracy of the positive, negative, and neutral emotions achieved 98.75%.

A Library of Old Photos Supporting Conversation of Two Generations Serving Reminiscence Therapy.

In Japan, a shift in family patterns has led to a sense of social isolation among older people, which increases the risk of major neurocognitive disorder. Interventions for them using old photos to implement reminiscence therapy (RT) have been proved to be effective. A super-aged society has in turn led to a shortage of medical resources and older people prefer home care over institutional care. Therefore, there is an urgent need for volunteers to help in RT. However, the age of volunteers tends to be increasingly younger. The lack of knowledge and experience of the past for the young volunteers makes it difficult for them to select appropriate stimulated materials. To improve this situation, a library of old photos for RT was developed to support conversation between the two generations. A two-factor experiment and emotion assessment scales were designed to explore the effect of different old photo types on the fluency of conversation between the two generations and their emotion. It was found that the types of old photos have little effect on older people and that conversations were almost pleasant. However, the pleasantness of older people was enhanced when using photos that they wanted to talk about (P = 0.006). Meanwhile, pleasure in conversation of the older people increased with the attention of the young people to the topic (R = 0.304, p < 0.001). Conversely, photo type has a strong impact on young people. When photos are selected that older people do not want to talk about or photos that young people do not know the content and are not interested in, concern for the topic of young people drops dramatically. Therefore, when RT, it is important to avoid using the types of photos above that cause a drop in younger people's attention.

Heart sound recognition technology based on convolutional neural network.

The mortality rate of heart disease continues to rise each year: developing mechanisms to reduce mortality from heart disease is a top concern in today's society. Heart sound auscultation is a crucial skill used to detect and diagnose heart disease. In this study, we propose a heart sound signal classification algorithm based on a convolutional neural network. The algorithm is based on heart sound data collected in the clinic and from medical books. The heart sound signals were first preprocessed into a grayscale image of 5 seconds. The training samples were then used to train and optimize the convolutional neural network; obtaining a training result with an accuracy of 95.17% and a loss value of 0.23. Finally, the convolutional neural network was used to test the test set samples. The results showed an accuracy of 94.80%, sensitivity of 94.29%, specificity of 95.54%, precision of 93.44%, F1_score of 93.84%, and an AUC of 0.943. Compared with other algorithms, the accuracy and sensitivity of the algorithms were improved. This shows that the method used in this study can effectively classify heart sound signals and could prove useful in assisting heart sound auscultation.

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

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.

Fabrication of Two Polyester Nanofiber Types Containing the Biobased Monomer Isosorbide: Poly (Ethylene Glycol 1,4-Cyclohexane Dimethylene Isosorbide Terephthalate) and Poly (1,4-Cyclohexane Dimethylene Isosorbide Terephthalate).

The thermal and mechanical properties of two types of polyester nanofiber, poly (1,4-cyclohexanedimethylene isosorbide terephthalate) (PICT) copolymers and the terpolyester of isosorbide, ethylene glycol, 1,4-cyclohexane dimethanol, and terephthalic acid (PEICT), were investigated. This is the first attempt to fabricate PICT nanofiber via the electrospinning method; comparison with PEICT nanofiber could give greater understanding of eco-friendly nanofibers containing biomass monomers. The nanofibers fabricated from each polymer show similar smooth and thin-and-long morphologies. On the other hand, the polymers exhibited significantly different mechanical and thermal properties; in particular, a higher tensile strength was observed for PICT nanofiber mat than for that of PEICT. We hypothesized that PICT has more trans-configuration than PEICT, resulting in enhancement of its tensile strength, and demonstrated this by Fourier transform infrared spectroscopy. In addition, PICT nanofibers showed clear crystallization behavior upon increased temperature, while PEICT nanofibers showed completely amorphous structure. Both nanofibers have better tensile properties and thermal stability than the typical polyester polymer, implying that they can be utilized in various industrial applications.