REFLEXION aims to position the European high-tech industry at the forefront of personalized smart machines by enhancing quality and stability during early product roll-out. The project enables rapid and cost-effective responses to unforeseen issues and emerging needs by integrating advanced data sensing and analytics. This allows for the identification of ‘missed’ or ‘misunderstood’ end-customer requirements, the detection of problems that escape standard product release testing, and the identification of items requiring maintenance or service. The insights gained are used to enhance product quality continuously.
By optimizing the full end-to-end product development lifecycle and maintenance processes, REFLEXION brings analytics into play to automate and enhance expert knowledge. It facilitates predictive maintenance on a larger industrial scale while reducing product evolution cycles.
Orise’s involvement in the project focuses on all aspects of anomaly detection through machine learning, specifically applied to log-based and time-series data analytics.
The Active@Work project focuses on developing and implementing a web-based solution designed to support senior employees in their roles within organizations. The project provides services to facilitate their integration and responsibilities, ensuring a more inclusive work environment.
To achieve this, advanced IoT wearable multi-sensors will be deployed to monitor individual health status. The project will explore ways to improve compliance with wearable monitoring devices to generate valuable health insights in the workplace. By involving end-users early in the project, Active@Work seeks to overcome limitations of existing market solutions and ensure the prototype aligns with real-world needs.
Two pilot deployments will be conducted in diverse organizational environments, covering both local and mobile work settings. A broad range of users will be included to refine the solution and ensure its effectiveness for the end users.
Orise AI’s role in the project encompasses anomaly detection through machine learning applied to IoT sensor data, including smartwatches, activity trackers, environmental sensors, and position sensors.
30/09/2016