• 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 the Korean Society of Physical Medicine
• /
• v.15 no.2
• /
• pp.23-30
• /
• 2020

PURPOSE: The purpose of this study was to examine the effects of dual-task training with cognitive tasks on cognitive functions and β-amyloid levels in the elderly with mild dementia. METHODS: The subjects were 36 elderly inpatients diagnosed with mild dementia at S Hospital located in Gyeongsangbuk-do, South Korea. The patients were randomly divided into a dual-task training group (DTG; n = 18) or a single-task training group (STG; n = 18). DTG performed dual-task training with cognitive tasks while STG performed only exercise tasks. These groups performed their respective exercises during a 30-minute session occurring three times a week over an 8-week period. MMSE-K and GDS were used to measure the subjects' cognitive function. To assess the subjects' dementia-related factors, their β-amyloid levels were measured by blood analysis. RESULTS: The results of the experiment were as follows: DTG showed statistically significant differences between their MMSE-K scores and β-amyloid levels before and after training (p < .05), whereas they exhibited no statistically significant differences in their GDS scores. MMSE-K scores and β-amyloid levels were significantly different between DTG and STG after training. CONCLUSION: The present study's overall results indicate that dual-task training with cognitive tasks is more effective than single-task training in improving cognitive functions and β-amyloid levels in the elderly with mild dementia. In other words, regular dual-task training can be considered as effective in improving cognitive function and dementia-related factors in the elderly with mild dementia and thus may be suggested as an effective exercise method for the treatment and early prevention of dementia.

• Journal of Oriental Neuropsychiatry
• /
• v.17 no.1
• /
• pp.79-105
• /
• 2006

Objective : This research aims to investigates the effects of CMT and HCMT on Dementia. and we also want to know the different effect of CMT, HCMT by drug types. Methods : The research is progressed by two types of experiment. one experiment is BV2 microglial cell line treated by LPS in vitro and another experiment is memory deficit mice induced by scopolamine in vivo. Results : The CMT and HCMT is effective in BV2 microglial cell line treated by LPS in vitro and in the serum of the memory deficit mice induced by scopolamine in vivo. But, there is no significant difference between CMT and HCMT extract&nano powder in experimental conclusion. Conclusions : These results suggest that the two drug types of CMT and HCMT may be effective for the prevention and treatment of Dementia. Investigation into the further study two drug types of the CMT and HCMT for Dementia is suggested for future research.

• Journal of Korean Academy of Nursing
• /
• v.43 no.2
• /
• pp.296-303
• /
• 2013

Purpose: The purpose of this study was to investigate the prevalence of depression and suicidal ideation in elders with dementia and to identify factors influencing their suicidal ideation. Methods: A descriptive and cross-sectional study was conducted from February to March, 2011. The participants were 298 older adults whose MMSE-KC score was 15 to 23. Collected Data were analyzed using t-test, ANOVA, Pearson correlation coefficients, and stepwise multiple regression. Results: According to the Geriatric Depression Scale (GDS) classification criteria, 86.2% of the elders in this study exhibited depression (GDS=5), and 31.5% manifested severe depression. The mean score of suicidal ideation was 5.70 (range 0-20). The risk factors for suicidal ideation were depression, suicidal attempt experience, present location for care, and activities of daily living. Conclusion: The results of this study can be utilized in the development of suicide prevention programs for older adults with dementia. In particular, depression should be screened and managed to reduce suicidal ideation of older adults with dementia.

• Journal of Sensor Science and Technology
• /
• v.28 no.6
• /
• pp.385-389
• /
• 2019

As we become an aging society, the number of dementia patients increases every year (an estimated 10% of the elderly, equating to 1.27 million in 30 years). In addition, 17,000 cases of missing people with disabilities and dementia are reported annually, indicating that more than one person per hour goes missing. More than 50% of those who are lost suffer injuries (some of which are fatal) within 24 hours after going missing. This is why measures are urgently required to ensure safety of the elderly. The core function of the disappearances prevention system proposed by this research group is to identify and respond early to deviations of dementia patients from their homes or facilities by identifying the location of the occurrence of disappearance, so that real-time notifications occur when a they leave the protected area. In addition, multiple receivers and public transportation integrated terminals share information when a patient leaves and uses public transportation to ensure their safe return. Most existing beacon-based positioning service models have fixed signal transmitters and are serviced in the form of transport receivers, but the proposed service model has users wearing the BLE beacon and receivers fixed.

• Dementia and Neurocognitive Disorders
• /
• v.21 no.2
• /
• pp.45-58
• /
• 2022

Recently, aducanumab, a beta amyloid targeted immunotherapy, has been approved by the US Food and Drug Administration for the treatment of Alzheimer's dementia (AD). Although many questions need to be answered, this approval provides a promising hope for the development of AD drugs that could be supported by new biomarkers such as blood-based ones and composite neuropsychological tests that can confirm pathologic changes in early stages of AD. It is important to elucidate the complexity of AD which is known to be associated with other factors such as vascular etiologies and neuro-inflammation. Through the second international conference of the Korean Dementia Association (KDA), researchers from all over the world have participated in the exchange of opinions with KDA members on the most up-to-date topics. The Academic Committee of the KDA summarizes lectures to provide the depth of the conference as well as discussions. This will be an important milestone to widen the latest knowledge in the research of AD's diagnosis, therapeutics, pathogenesis that can lead to the establishment of future directions.

• Journal of Digital Contents Society
• /
• v.19 no.2
• /
• pp.319-325
• /
• 2018

The general public's interest in dementia has increased recently as dementia has become a social issue due to its rapid aging. Several dementia prevention and rehabilitation programs are being carried out at the dementia rehabilitation center and at the old welfare center depending on the number of dementia patients. In this paper, a 3 dimensional finger and motion search of the leap motion is utilized and combined with dementia preventive and cognitive rehabilitation programs at various facilities. We suggest technologies that can provide both fun and effective treatment and rehabilitation content for rehabilitation therapists. A variety of cognitive enhancement content is designed using finger tracking and configured to be recorded in the database for rehabilitation programmes to increase the effectiveness of management.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.01a
• /
• pp.55-56
• /
• 2020

본 논문에서는 키넥트 센서 기반의 노인 건강 관리 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 체조하기 모드와 두뇌 게임 모드로 구성한다. 체조하기 모드는 모션 인식 기능을 활용하여 스트레칭을 비롯한 다양한 체조 동작을 반복적으로 따라 함으로써 사용자의 건강을 관리할 수 있는 기능을 제공한다. 두뇌게임 모드는 사용자의 기억력을 증진함으로써 치매를 예방할 수 있는 기능을 제공한다. 또한, Unity의 핸드트래킹 기술을 이용하여 두뇌 게임을 하는 동시에 자연스레 팔과 어깨의 운동을 할 수 있도록 게임 화면을 구성한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.151-152
• /
• 2022

본 논문에서는 키넥트 센서 기반의 치매 예방 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 치매 예방을 위해 노년층의 인지기능을 높이고, 팔 동작을 활성화할 수 있는 청기 백기 게임의 기능을 구현한다. 청기 백기 게임은 키넥트 센서 기반으로 모션 인식 기능을 활용하여 화면의 텍스트와 음성에 따른 행동을 취함으로써 점수를 획득할 수 있다. 청기 백기 게임은 사용자들이 애플리케이션의 지시에 집중하고, 기억하는 능력과 자기 조절력을 향상함으로써 치매를 예방할 수 있는 기능을 제공한다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.229-230
• /
• 2024

본 논문에서는 키넥트 센서 기반의 치매 예방 애플리케이션을 설계하고 구현한다. 이 애플리케이션은 노년층의 치매 예방을 위해 기억력을 향상시키고 간단한 동작으로 운동을 촉진할 수 있는 햄버거 만들기 게임을 구현한다. 햄버거 만들기 게임은 키넥트 센서 기반으로 조인트와 스켈레톤 기능을 활용하여 하늘에서 떨어지는 재료들을 순서에 맞게 획득하여 햄버거를 완성함으로써 점수를 얻는다. 사용자들은 제한 시간이 끝날 때까지 계속 진행하며 순서를 기억해 내는 과정을 통해 기억력을 향상시키고, 재료를 잡기 위한 활동적인 움직임으로 치매 예방에 도움이 되는 운동 기능을 제공한다.