• Dementia and Neurocognitive Disorders
• /
• v.23 no.3
• /
• pp.146-160
• /
• 2024

Background and Purpose: The emotions of people at various stages of dementia need to be effectively utilized for prevention, early intervention, and care planning. With technology available for understanding and addressing the emotional needs of people, this study aims to develop speech emotion recognition (SER) technology to classify emotions for people at high risk of dementia. Methods: Speech samples from people at high risk of dementia were categorized into distinct emotions via human auditory assessment, the outcomes of which were annotated for guided deep-learning method. The architecture incorporated convolutional neural network, long short-term memory, attention layers, and Wav2Vec2, a novel feature extractor to develop automated speech-emotion recognition. Results: Twenty-seven kinds of Emotions were found in the speech of the participants. These emotions were grouped into 6 detailed emotions: happiness, interest, sadness, frustration, anger, and neutrality, and further into 3 basic emotions: positive, negative, and neutral. To improve algorithmic performance, multiple learning approaches were applied using different data sources-voice and text-and varying the number of emotions. Ultimately, a 2-stage algorithm-initial text-based classification followed by voice-based analysis-achieved the highest accuracy, reaching 70%. Conclusions: The diverse emotions identified in this study were attributed to the characteristics of the participants and the method of data collection. The speech of people at high risk of dementia to companion robots also explains the relatively low performance of the SER algorithm. Accordingly, this study suggests the systematic and comprehensive construction of a dataset from people with dementia.

• Journal of People, Plants, and Environment
• /
• v.24 no.1
• /
• pp.107-117
• /
• 2021

Background and objective: The purpose of this study is to investigate the effect of a forest healing program in terms of depression, neuropsychological and physiological benefits for the elderly. Methods: For this purpose, we developed a forest therapy program for the elderly who are vulnerable to dementia and conducted a total of 11 sessions of forest therapy activities in a forest once a week. We measured the changes in depression, resting-state Electroencephalography(EEG) and heart rate variability (HRV) before and after the program. There were 60 subjects aged over 65 yesrs old. 30 subjects participated in the forest therapy program, and the other were in the control group. The Geriatric Depression Scale was used to measure the level of depression, neuroNicle FX2 (Laxtha, Korea) was used to measure the resting-state EEG, and photoplethymogram (ubpulse T1, Laxtha, Korea) was used to measure the HRV. Results: The results showed that the depression index of the experimental group improved with statistical significance after the program (experiment group = 3.267 decrease of the mean). In the EEG measurement, the alpha-peak frequency at rest (experimental group = 0.227 Hz increase of the mean) was improved (mean increase = 0.23 in the experimental group, p < .05). The high frequency of HRV, which represents the parasympathetic nerve activity of the body's autonomous response, was also significantly improved (mean increase = 0.396 in the experimental group, p < .05). Conclusion: The results suggest that the forest therapy program can reduce the cognitive, psychological and physical risk factors of dementia for the elderly at risk of cognitive decline. Therefore, forest therapy activities may be suitable for the prevention of dementia in the elderly.

• Journal of the Korean Dietetic Association
• /
• v.27 no.4
• /
• pp.248-262
• /
• 2021

This study examined the effect of the Mediterranean-DASH Intervention for Neurodegenerative Delay (MIND) diet of the Korean multi-domain dementia prevention program on the cognitive functions of the elderly with dementia risk factors. We developed the program including nutrition, exercise, cognitive training, vascular disease prevention, and motivation. One- hundred and fifty-three participants aged 60~79 years with at least 1 dementia risk factor were randomly assigned in a 1:1:1 ratio to the facility-based intervention (FMI), home-based intervention (HMI), and the control group. The nutrition education program consisted of 10 classes over 24 weeks: the FMI received 7 group sessions and three 1:1 sessions, the HMI received 4 group sessions and three 1:1 sessions with 3 homework sessions. The Nutrition Quotient for Elderly (NQ-E) and the Mini Nutritional Assessment (MNA) were used to evaluate nutritional status. The Repeatable Battery for the Assessment Neuropsychological Status (RBANS), Korean Mini-Mental State Examination (K-MMSE), and the Cognitive Complaint Interview (CCI) were used to evaluate cognitive functions. A total of 136 people completed the program with an 11.1% dropout rate. The NQ-E (P=0.009) and RBANS (P=0.001) scores significantly increased in the FMI (N=45) and HMI (N=49) groups compared to the control group (N=42) after the study. The changes in the score of MNA and CCI did not differ significantly between groups. In conclusion, the nutritional intervention which focused on the MIND diet as a part of a multi-domain intervention program had a positive effect on the improvement of healthy eating habits and cognitive function scores in the high-risk dementia group.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.26 no.3
• /
• pp.399-407
• /
• 2012

To evaluate age and gender differences in the relation of cardiovascular risk factors, cognitive impairment, and subclinical carotid atherosclerosis from aged people using by a cross sectional method. Sixty-nine healthy elders living in the community who had not previously undergone carotid ultrasonography were included. We conducted life style surveys, and cognitive function tests including Korean-mini-mental state examination (K-MMSE) and clinical dementia rating-Korean. Various biomarkers from blood were assessed; fasting insulin-like growth factor-1, lipid-profile, high sensitivity C-reactive protein, total homocysteine, glucose, insulin, Homeostasis model assessment (HOMA) for insulin resistance index, vitamin B12, and folate level. Carotid intima-media thickness (C-IMT), and plaques were measured using carotid ultrasonography and aortic ultrasonography, a valid index of atherosclerosis. For the elderly subjects (aged 65-82 years), cognition impairment was more prevalent in females while subclinical atherosclerosis was more prevalentin males. Increased C-IMT has been kept in males, and C-IMT shows increasing trend and the peak at about 80 year-old in females with increasing age. The significant correlations between C-IMT and many vascular risk factors including age, triglyceride, abnormal homocysteinein male, and K-MMSE, insulin, HOMA index and abnormal aortic ultrasonography in female were different in each gender, with the exception of homocysteine (p<0.05). This data suggests that there were differences of age and gender characteristics in terms of subclinical atherosclerosis, cognitive impairment and vascular risk factors in community-living elders. Further larger and longitudinal studies across entire age are required to better understand the effects of risk factors on subclinical atherosclerosis.