This project aims to develop an architecture that facilitates self-care for elderly individuals while enabling continuous health monitoring by healthcare professionals. This paper focuses on the initial phase of a larger project, emphasizing vital signs monitoring using FitBit Versa 4 and a cognitive decline management game. Wearable sensors track vital signs and compile historical data for analysis. Through continuous research and refinement, we aim to provide personalized and comprehensive care, improving the quality of life for elderly individuals.
The European Region is expected to have a larger population of individuals aged over 65
years than those under the age of 15, according to the World Health Organization (WHO)1.
This demographic shift presents new social, economic, and health challenges that require a
focus on healthy ageing to mitigate the impact of an ageing population. Assisting the elderly
population in efectively managing age-related conditions such as chronic illnesses and anxiety,
and maintaining their independence and self-suficiency as much as possible, is crucial for
improving their well-being and quality of life. Maintaining some level of quality of life is closely
associated with managing several forms of chronic conditions, including cardiovascular disease,
chronic respiratory disease, diabetes and mild cognitive impairment that are common with
age [
This research will also refer to the factor of dementia. Dementia is a loss of cognitive function
(i.e. thinking, remembering and reasoning) that afects a person’s daily life and activities 3.
Some people with dementia cannot control their emotions, and their personalities may change.
Dementia is predicted to afect 152 million people worldwide by 2050 [
The article [16] discusses the significant health risk posed by falls, especially among the elderly, where falls can be fatal. According to the authors, prevention and timely intervention are crucial in reducing this risk. Moreover, the authors in [17], consider the inactivity and medication reminders as a means to better control the elderly routine. They developed a tool for caregivers to assess patient vitality, with a focus on predicting falls. Other studies, focus their attention on monitor tracking through wearable sensor technologies. For example, in [18], the authors investigate the accuracy of wearable sensors in monitoring healthcare parameters for the elderly in smart home environments. The authors of [19] proposes a health detection system for smartwatches targeting the elderly, utilizing biosignal analysis to efectively monitor physiological parameters such as body temperature, pulse, and respiration. Through the analysis of Lipschitz exponent of maximum value column transform, the system achieves accurate health signal detection. It incorporates multiphysiological parameter acquisition and monitoring, ensuring 2E. La Montagna, ’Vital parameters: assessment and nursing responsibility (Parametri vitali: accertamento e responsabilità infermieristica)’, www.nurse24.it, published 08.11.16 and update 01.06.22, https://www.nurse24.it/infermiere/iparametri-vitali-accertemento-e-responsabilita-infermieristica-2.html, (03.02.2024). 3This content is provided by the NIH National Institute on Aging (NIA). NIA scientists and other experts review this content to ensure it is accurate and up to date., ’What Is Dementia? Symptoms, Types, and Diagnosis’, www.nia.nih.gov, Content reviewed: December 08, 2022, https://www.nia.nih.gov/health/alzheimers-and-dementia/what-dementia-symptoms-types-anddiagnosis#:˜:text=Dementia%20is%20the%20loss%20of,and%20their%20personalities%20may%20change. (03.02.2024). 4World Health Organization, 11 Oct 2023. UR: https://www.who.int/europe/news/item/11-10-2023-by-2024–the-65and-over-age-group-will-outnumber-the-youth-group–new-who-report-on-healthy-ageing continuous monitoring over extended periods. The system demonstrates high recognition rates, reaching up to 96.5%, and provides precise calibration accuracy and synchronization with national time standards, validating its efectiveness in extracting biosignal features and achieving high classification accuracy for elderly health detection.
Several studies have highlighted the pivotal role of various lifestyle factors in fostering cognitive plasticity [12, 13, 14, 15]. These factors encompass not only sleep levels but also encompass healthy nutrition, regular exercise, maintaining low stress levels, and adhering to prescribed drug therapy. Through a multidimensional approach encompassing these elements, individuals can potentially enhance their cognitive flexibility and adaptability. Figure 1 provides an overview of some of the most important aspects to be considered with regard to the cognitive plasticity of the elderly population.
The project aims to design an architecture that enables elderly individuals to care for themselves while also allowing doctors and caregivers to continuously monitor their health status. This paper discusses a section of our ongoing project, focusing on vital signs collected by wearable sensors and a game designed to control cognitive decline. Figure 2 illustrates how technology collaboration can enhance the monitoring of vital signs through the use of sensors. In the home environment, the elderly can maintain their independence while the technology passively assists them without the need for human intervention. Wearable sensors enable us to track the elderly’s vital signs and compile a historical record of measurements. Other relevant environments may include the caregiver’s home, the doctor’s surgery or the hospital. An application provide a comprehensive view of the data collected by the sensors, enabling them to gain insight into the well-being of the elderly. Moreover, a memory game has been developed to enhance the cognitive function of the elderly.
To evaluate the well-being of elderly individuals, we use the Fitbit Versa 45, a cutting-edge wearable device equipped with advanced health monitoring technology. The Fitbit Versa 4 includes features such as continuous heart rate tracking, sleep analysis, activity monitoring, and SpO2 monitoring, providing comprehensive insights into the individual’s health status. This device detects anomalies in vital signs, allowing for prompt intervention when necessary to ensure the health and safety of the elderly. Its sophisticated capabilities are leveraged for our purpose. We also use Postman6, a powerful tool for testing and debugging Application Programming Interface (API) in collaboration with Swagger UI7. To design the interfaces, we employ Android Studio, a comprehensive Integrated Development Environment (IDE) specifically tailored for Android app development.
We use the resources available on the Fitbit developer website, combined with Swagger UI, to generate a token through Postman. This token was a key component in our process, enabling us to eficiently generate APIs and send requests directly from Android Studio 8. Based on the data 5iftbit is a smartwatch powered by Google. Oficial website https://www.fitbit.com. Developers website: https://dev.fitbit.com/ 6https://www.postman.com 7https://swagger.io/tools/swaggerhub/?utm_source=aw&utm_medium=ppcg&utm_campaign=SEM_SwaggerHub_PR _EMEA_ENG_EXT_Prospecting_Tier2&utm_term=swagger%20ui&utm_content=665457100541&gad_source=1&gclid =CjwKCAjwoa2xBhACEiwA1sb1BK7Um8IrSGUSMbLwkRoe6ldg6AXxKAw1ToNiSkFP-tGlE1IHzKVQxoCVdEQAvD_BwE&gclsrc=aw.ds 8https://developer.android.com/studio?hl=it collected with FitBit, we have designed three distinct interfaces to ensure that users can interact with the data seamlessly, gain meaningful insights, and facilitate informed decision-making processes.
The data collected by the sensors should be viewed on an interface by the doctors and caregivers. We design various tablet interfaces (see Figure 3), tailored to specific end users. These evolutionary prototypes (see Figure 4) of the application are a basic framework for testing and validating the integration of FitBit technology into our system. The future aim will be to customize the evolutionary prototypes, to create interfaces that are well structured for the specific user. For instance, doctors require a comprehensive overview of the data collected by the sensor, while carers only need a quick overview of the elderly person’s health. Additionally, older individuals can exercise their minds by playing games on the tablet.
The project aims to support the elderly population and address the challenges associated with aging. Vital sign monitoring is one of the key components of our eforts, but it is only one facet of our multi-faceted approach. In the future, we plan to integrate additional devices into the home environment to comprehensively monitor not only physical health but also the mental and emotional well-being of the elderly. A social robot is planned to be introduced within this architecture to enhance communication skills among the elderly and improve situational control. Furthermore, our future work will focus on refining and customizing the interfaces to meet the unique needs of each stakeholder within the system. This iterative approach will ensure that our interfaces not only meet generic requirements, but also provide optimized functionality and a user experience tailored to individual roles and preferences. Our goal is to ofer comprehensive care and improve the overall quality of life for the elderly community. We accomplish this by providing support throughout their daily lives. We consistently improve our services to meet their changing needs through ongoing research. [12] M. Kivipelto, A. Solomon, S. Ahtiluoto, T. Ngandu, J. Lehtisalo, R. Antikainen, L. Bäckman, T. Hänninen, A. Jula, T. Laatikainen, J. Lindström, F. Mangialasche, A. Nissinen, T. Paajanen, S. Pajala, M. Peltonen, R. Rauramaa, A. Stigsdotter-Neely, T. Strandberg, J. Tuomilehto, H. Soininen, The finnish geriatric intervention study to prevent cognitive impairment and disability (finger): Study design and progress, Alzheimer’s & Dementia 9 (2013) 657–665. URL: https://www.sciencedirect.com/science/article/pii/S155252601202523X. doi:https: //doi.org/10.1016/j.jalz.2012.09.012. [13] N. Schneider, C. Yvon, A review of multidomain interventions to support healthy cognitive ageing, The journal of nutrition, health & aging 17 (2013) 252–257. doi:10.1007/ s12603-012-0402-8. [14] G. Schechter, G. K. Azad, R. Rao, A. McKeany, M. Matulaitis, D. M. Kalos, B. K. Kennedy, A comprehensive, multi-modal strategy to mitigate alzheimer’s disease risk factors improves aspects of metabolism and ofsets cognitive decline in individuals with cognitive impairment, J. Alzheimers Dis. Rep. 4 (2020) 223–230. [15] E. Guglielman, The ageing brain: Neuroplasticity and lifelong learning, eLearning Papers 29 (2012) 1–7. [16] E. A. SAĞBAŞ, S. BALLI, Elderly fall detection using autoencoder based dimensionality reduction and smartwatch based wearable motion detectors, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi 23 (2023) 1150–1159. [17] M. Deutsch, H. Burgsteiner, A smartwatch-based assistance system for the elderly performing fall detection, unusual inactivity recognition and medication reminding., in: eHealth, 2016, pp. 259–266. [18] A. Alsadoon, G. Al-Naymat, O. D. Jerew, An architectural framework of elderly healthcare monitoring and tracking through wearable sensor technologies, Multimedia Tools and Applications (2024) 1–46. [19] Z. Zhu, P. Wang, F. Wang, Design of health detection system for elderly smart watch based on biosignal acquisition, Journal of Sensors 2022 (2022).