• Journal of Multimedia Information System
• /
• v.6 no.1
• /
• pp.31-35
• /
• 2019

The Socialist Republic of Vietnam has become one of the top ten nations with the highest aging rate. The proportion of their aging population increased from 7.2% to 10.95% from 1989 to 2017 and entered into the aging society six years earlier than what had been anticipated in 2011. The main issues in such a society are the problems associated with the elderly living by themselves and their solitary deaths. This study attempts to find a solution which would mitigate the burdens of aging or aged population who are living in a lonely and solitary living condition focusing on the system used for the purpose of managing or monitoring of their daily lives to prevent any undesirable outcomes including solitary deaths. The study also discusses the possibility of introducing the system into Vietnam.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.5
• /
• pp.177-182
• /
• 2024

This study proposes a big data-based analytical method to detect high-risk areas for solitary deaths among the elderly in Seoul. The study categorizes and analyzes the risk factors of solitary deaths into demographic, health, economic, and socio-environmental factors. Using data collected from the Seoul Open Data Plaza and Public Data Portal, variables were generated and scatter plots were created using K-means clustering, followed by visual implementation through map creation. The analysis identified Jungnang-gu, Gangbuk-gu, Nowon-gu, Eunpyeong-gu, Gangseo-gu, and Gwanak-gu as the highest-risk areas. This study addresses the limitations of previous survey-based research through big data analysis. The findings are expected to enhance the efficiency of solitary death prevention programs and serve as a basis for informed decision-making in budget allocation across districts.

• Journal of Internet Computing and Services
• /
• v.25 no.5
• /
• pp.13-22
• /
• 2024

This study proposes a Korean model for a smart home telehealth service, utilizing advanced ICT technologies such as 5G, artificial intelligence, blockchain, and big data, to effectively manage and treat chronic diseases and mental health-related illnesses in an aging society. By improving the existing telehealth system, which is limited to phone consultations and prescription deliveries, this model integrates various health data, mental health information, and emergency detection data, and includes functions for prescription drug management and welfare counseling, creating an all-in-one system. This model is expected to enhance accessibility for vulnerable populations, reduce medical costs, and increase the efficiency of health management, and contribute to the prevention of solitary deaths.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.10
• /
• pp.6019-6023
• /
• 2013

Lung cancer, one of the leading causes of cancer-related deaths, usually appears as solitary pulmonary nodules (SPNs) which are hard to diagnose using the naked eye. In this paper, curvelet-based textural features and clinical parameters are used with three prediction models [a multilevel model, a least absolute shrinkage and selection operator (LASSO) regression method, and a support vector machine (SVM)] to improve the diagnosis of benign and malignant SPNs. Dimensionality reduction of the original curvelet-based textural features was achieved using principal component analysis. In addition, non-conditional logistical regression was used to find clinical predictors among demographic parameters and morphological features. The results showed that, combined with 11 clinical predictors, the accuracy rates using 12 principal components were higher than those using the original curvelet-based textural features. To evaluate the models, 10-fold cross validation and back substitution were applied. The results obtained, respectively, were 0.8549 and 0.9221 for the LASSO method, 0.9443 and 0.9831 for SVM, and 0.8722 and 0.9722 for the multilevel model. All in all, it was found that using curvelet-based textural features after dimensionality reduction and using clinical predictors, the highest accuracy rate was achieved with SVM. The method may be used as an auxiliary tool to differentiate between benign and malignant SPNs in CT images.