Edge4iwelli – Edge computing to support the iwelli ecosystem of services for smart home care and independent living
Idea and relation to VEDLIoT
Edge4iwelli addresses the challenges of integrating edge computing systems in a smart home environment to generate home care services for health and wellbeing. Within the realm of the project, we will embed in the existing iwelli IoT care package (eg. www.iwelli.com/, https://clinic.iwelli.com/) edge computing systems and some more advanced AI modules and we will create a more secure and more efficient IoT care platform for proofs-of-concept in edge computing, optimization, and machine learning in home contexts. The new tools (the health smart mirror for healthcare monitoring) and application libraries that will be developed, will enable the VEDLIoT project to manage the diverse and growing capabilities of AI and edge computing and the practical utilization of these technologies in the context of the smart home for home care services.
Edge4iwelli will contribute to the VEDLIoT ecosystem extension with mainly 3 aspects:
- Extending the application of the VEDLIoT platform to an extensive set of new and relevant use cases. More specifically the Edge4iwelli project intends to utilize (deploy, test, and validate) the VEDLIoT technology to strengthen the iwelli IoT care package application in the areas of smart home and home care for better health and wellness.
- Providing results and recommendations of how to simplify smart home services for healthcare in home and will try to prove that the application of edge computing can accelerate and increase the security of the monitoring devices.
- Leveraging VEDLIoT technologies to its iwelli IoT care package broadening the VEDLIoT use-case basis and help making the overall concept more robust.
Objectives
- Design the next generation for the iwelli IoT architecture for home care and assisted living services
- Minimize the utilization of cloud services by distributing our AI models in house.
- Increase the iwelli IoT network security by adopting the VEDLIoT’s security mechanisms like the Secure IoT Gateway, something that we expect to enhance iwelli home care applications’ security trustworthiness and safety.
- Update the iwelli health smart mirror device and by adopting the architecture of the VEDLIoT mirror use-case. For that we will use the VEDLIoT toolchain and interface our AI software to hardware in a comprehensive fashion leveraging and building on existing open-source components of the mirror. Validate the new health smart mirror in the Leykiposs technological park.
Approach
Global strategies to reduce the overall cost of healthcare include the promotion of care at home rather than in hospital. There are many cases where citizens are unable to easily access to healthcare services, healthcare professionals that need to manage their patients form distance and cares that need decision support tools while caring their patients. More specifically there are populations with chronic conditions that are unable to frequently visit their doctors because they are older people with mobility difficulties, or they are living in rural areas and others. Recently the initial reaction in many countries in this pandemic was for healthcare facilities to reduce or even cease many clinical services, including closure of clinics and postponement of medical appointments or elective surgeries. However, such strategies cannot be sustained indefinitely if the COVID-19 pandemic extends beyond few months.
The utilization of various AI-based triage and screening systems can potentially alleviate the clinical load of physicians. An online medical symptom checker, a mobile card like ECG monitoring device supported by prediction AI models or an intelligent chat bot supported by state-of-the-art home care tools could help patients recognize early symptoms, educate people on the importance of their hygiene and refer people for medical treatment should symptoms worsen. Additionally, AI software that detects and records patients’ data (e.g., daily vitals and symptoms) may prevent unnecessary hospital consultations for patients with mild flu-like symptoms and chronic diseases. These data could also be developed into AI algorithms for the detection and prevention not only of infectious diseases but also for preventing chronic diseases like diabetes, cardiac diseases, skin cancer and stroke.
Within this realm studies compare the performance of deep learning in detecting diseases from medical imaging versus that of healthcare professionals while the constant mutating of diseases and viruses makes it difficult to avoid using artificial intelligence, machine learning algorithms and new tools like lowcost IR cameras and others, creating new applications that are able to screen and diagnose not only infectious diseases but also chronic diseases. Within this realm the need to provide access to secure, accurate and low-cost tests for the diagnosis of diseases is a challenge.
The role of iwelli IoT care package such as the health smart mirror, is to:
- provide users, registered in the system, an easy way to remotely record crucial health data, using wireless health sensors
- keep an eye on users’ medical folder in cooperation with their doctors through visualization of their health data,
- remind users for important things like medications, doctor’s appointments etc.,
- allow users to communicate with their doctors and their family members.
Patients, professionals, social cares, unofficial cares are able to get registered in the platform through the same interface. Proprietary technology (a health smart mirror, IoT home gateway) and proprietary software applications (are under validation in running pilot trials) and have been uploaded in Android store. Specific attention has been paid to the respect of privacy, to data protection. Security, interoperability, minimal invasiveness, low-cost and user-friendliness, are keywords that will guide us all through the development process.
Expected Impact
The Edge4iwelli project will validate the technological choice to adopt edge computing versus cloud-based computing in smart home for home care services, to evaluate the sustainability and replicability of the adopted architecture and the interoperability properties and highlight the key characteristics of the VEDLIoT architecture that are suitable for the Edge4iwelli use cases such as security and simplification of AI models within home environment.