Category: Decentralised AI
End-to-End Prototype using AffectLog’s Privacy-Preserving Mental Health Digital Twin Platform
•
Introduction Integrating personal health data with clinical records can greatly improve the prediction and management of mental health conditions. In this prototype, we design a privacy-preserving mental health digital twin platform that unifies data from iPhone sensors, doctor’s notes, and electronic health records (EHR) to create a dynamic digital representation…
AL360°: Redefining Trust and Access in the Private Data Economy
•
In a data-centric world marked by surging digital footprints and ever-tightening regulatory frameworks, enterprises, researchers, and policymakers face a critical dilemma: how to responsibly access and utilise sensitive, private data without breaching trust, security, or legal boundaries. This challenge is particularly pronounced in domains like healthcare, financial services, education, and…
PersonaCore: A Federated Neuromorphic Edge AI Platform for Privacy-Preserving Affective Digital Twins
•
Abstract Affective Digital Twins (ADT) are virtual replicas of human emotional and cognitive states, enabling simulation and personalized AI interactions in human-centric applications. This paper presents AffectLog PersonaCore, a technical framework for implementing ADTs via a federated, privacy-preserving, neuromorphic computing platform. We detail how PersonaCore innovates on-device federated neuromorphic processing…
Federated Learning within the leading American Hospital Network: How AffectLog Sets a New Standard in Secure Data Aggregation for the Mental Health Monitoring of the Frontline Health workers
•
In today’s data-driven landscape, healthcare data is a treasure trove of insights waiting to be unlocked—especially for large hospital networks. From predictive analytics in oncology to AI-based radiology, the potential for machine learning (ML) to enhance patient care is immense. Yet concerns around data privacy, complex regulatory requirements, and the…
