TERMINET Open Call Winners!
TERMINET proudly announces the 4 winners of TERMINET-OC2022! On behalf of the TERMINET Open Call Project Committee, we would like to thank all the participants for submitting their proposals! In total 18 Open Call proposals were received from 9 countries.
Congratulations to the 4 winners!
Title: Privacy-Preserving Federated Learning Application for diagnosis of coMmunication disordErs iN Child development
Approach & Objectives:
The project aims to design and develop novel federated learning models, model architectures, algorithms, deployment strategies, and optimization techniques that can provide advanced and optimized FL solutions tailored to the environments and requirements described by TERMINET.
The FLAMENCO project will apply Federated Learning to an existing software application suite, which is used to diagnose communication skills development in children, detecting potential deficiencies timely and accurately. The software suite collects data from a child’s responses to an animation game, along with heart rate readings obtained from a smartwatch. The data is then sent and stored into a cloud data hub and analyzed using AI-based classification techniques. The outcome is a risk indicator that suggests the likelihood of a child developing any learning and communication disorders.
As the data collected is sensitive and personal, and the predictive model requires continuous and incremental training, more sophisticated techniques are required. The FLAMENCO project will employ several algorithms to ensure users’ privacy and prediction accuracy. First, the project will use Fully Homomorphic Encryption during the model aggregation step to protect user data from potential breaches. Second, client selection techniques will be utilized to remove users with corrupted or missing data to improve the model’s predictive accuracy. Third, state-of-the-art aggregators will manage data imbalance, ensuring that the Federated Learning model can converge effectively.
The project outcome will simulate a Federated Learning process using real-world data from IoT edge devices and incorporating the proposed extensions. The findings will demonstrate the potential of this approach to pave the way towards personalised healthcare solutions while respecting patient privacy.
Title: An Open API for Differential Privacy Systems
Approach & Objectives:
The rise of the Internet of Things (IoT) has led to an explosion of data, offering unprecedented opportunities for businesses and institutions to gain insights and make better-informed decisions. However, the collection, sharing, and analysis of data from IoT devices must be done in a way that respects privacy and protects the rights of individuals. In particular, the General Data Protection Regulation (GDPR) sets strict requirements for the collection and processing of personal data. As a result, businesses and institutions face a significant challenge in leveraging IoT data while ensuring compliance with privacy regulations. DPella’s proposed solution offers a way to tackle this challenge by providing an open API that interacts with tools based on Differential Privacy, a privacy-enhanced technology with strong mathematical guarantees developed through years of academic research. Currently, there is no standard API for interacting with Differential Privacy tools, which makes this technology difficult to access for many IoT data-driven companies. The proposed API will help make Differential Privacy technology more accessible and user-friendly, enabling businesses to leverage the power of IoT data while preserving the privacy of individuals involved in the datasets.
This project will also connect the open API with an open-source Differential Privacy tool to deliver a working prototype. This will help demonstrate the value of the proposed solution, as well as provide a practical and user-friendly interface for data sharing and discovery. This project aligns with the privacy and security goals and objectives of TERMINET, and it has the potential to make a significant impact in the field of IoT data analytics by providing a secure and privacy-preserving solution for data sharing and discovery.
Title: Secure immUtable System based on blockchAiN for water management smart coNtrActs
Approach & Objectives:
The project aims to design and develop a secure framework for smart device authentication and next generation Ricardian smart contracts, under to intention to ensure security and privacy and autonomy in all transactions carried out.
The project will create a permissioned blockchain architectural network, a Hyperledger Fabric, supporting smart contracts for the case of water utilisation management systems. Specifically, we will exploit current heavy IoT infrastructure and sensors in several Water Management Authorities in smart cities in Greece, and “transform” the current, traditional, way of collecting data from sensor readers and transmitting these to a central data hub, towards sharing, storing, accessing and analysing these data in a more secure and reliable way implemented through a blockchain architecture. In this way, any malicious acting or identity stealing actions will be prohibited, allowing a trustworthy, secure and reliable way of measuring water utilization as well as possible leaks in the water distribution network.
Smart data and trigger contracts will be supported to enable water meter information, utilization readings, as well as leaks, missing water meter or even exceeding limits types of data to be stored within a permissioned blockchain. Each node will be authorised to write specific information, whereas all anonymised information will be available to the nodes included in the blockchain network.
The project outcome can be a state-of-the art demo case for smart cities and smart home systems created upon a blockchain network architecture that promotes data privacy, reliability, integrity and accuracy.
Title: Next Generation PersonaLized EDGE-AI HealthCare
Acronym: Next Gen PLEDGE
Approach & Objectives:
During the last decade the digital revolution has accelerated the development of applications that enable a more efficient management of patients with chronic conditions, congestive heart failure, stroke or chronic obstructive pulmonary disease. More recently, the cross fertilization of ICT has allowed the development of advanced remote monitoring systems capable of providing continuous insight into the physiological condition and wellbeing of individuals. Such systems reduce hospitalizations, empower individuals and support their wellbeing, reduce negative impact of modern lifestyles, while significantly enhancing their arsenal combating societal changes with profound consequences on European citizens and healthcare systems.
In this landscape Next-Gen-PLEDGE innovative approach aims to develop and provide advanced remote monitoring systems, improving the capabilities of early detection of disease symptoms or pathology and respond to them in a timely manner, offering a solution that encompasses TERMINET’s framework for testing, validating, and demonstrating federated models and machine learning algorithms in a personalized healthcare scenario.
The proposed concept encompasses a personalized system consisting of a patch and wrist wearable that, in conjunction with a mobile device, is able to exploit the potential of Next Generation IoT through federated learning, by moving decisions closer to the end user. Next Gen PLEDGE is able to utilize raw data such as pulse waveforms, temperature data and electrocardiography (ECG) waveforms captured by the wearable sensors, build a personalized AI-model through on-device learning and convert them into measurements of actual precise health data such as, Respiratory Rate, Blood Oxygen Saturation, Body Temperature, Heart Rate and Heart Rate Variability, while taking personal physiological and behavioural user characteristics into account.
This unique proposition increases the relevance to the specific challenges of TERMINET and its innovation capacity, as well as the impact and importance of the use cases that this call is targeting.