Postdoc Position: Digital Twin for real-time monitoring and anomaly detection of complex systems
The objective is a monitoring tool for complex mechanic systems that detects precursors of potential failure mechanisms, and proposes the safest set of actions to avoid failure in real time with the minimum necessary number of probes. The idea of this project is to establish a very fast digital twin of the tested machine that captures all the relevant physical phenomena and their links by combining mathematically-based and data-driven surrogate models. The digital twin will then be used for real-time assessment of new data collected during operation of the machine and their deviation from the predicted behavior. Your mission is the development, implementation and testing of this digital twin. Start date : As soon as possible
Postdoc Position: “Edge AI Devices for DigiPredict, Exposome and Beyond”
The successful candidate will lead innovative research projects in a stimulating, open, and international research environment with a highly talented and motivated team, embedded in a strong network of academic and industrial collaborators.
The candidate will work in collaboration with 3 labs on program co-funded by the EPFL Center for Intelligent Systems (CIS): David Atienza (STI), head of the Embedded Systems Laboratory (ESL), Adrian Ionescu (STI), head of The Nanoelectronic Devices Laboratory (NANOLAB), Martin Jaggi (IC), head of Machine Learning and Optimization Laboratory (MLO).
This Postdoc will be affiliated by to two of these EPFL laboratories (NANOLAB and ESL), and will work in cooperation with additional international medical partners. The topic to be developed in this post-doctoral position is multidisciplinary and includes the linking between Nanolab and ESL through the development of edge AI systems from the software mapping and architecture to the inclusion of new sensors and technologies. Start date : The starting date is flexible, but an earlier start date is preferred.
The Collaborative Research on Science and Society (CROSS) Program encourages interdisciplinary projects that deal with current issues in society and technology, and that are carried out as a collaboration between researchers from EPFL (École polytechnique fédérale de Lausanne) and UNIL (Université de Lausanne). Through an annual call for projects, CROSS provides competitive grants to support the preparatory phase of new research endeavors with a view to obtaining major funding.
The CROSS 2022 theme is Responsible Innovation. Deadline for submission: Submissions are received until 20 August, 2021. Selected projects will be notified in October, 2021.
Research, PhD and Postdoc: ELISE Mobility Programs
1. Mobility program for experienced researchers The goal of the ELISE Mobility Program for Experienced Researchers is to bring ELISE/ELLIS Fellows, Scholars, and Members together by supporting their short and long-term scientific visits to initiate collaboration within the ELISE/ELLIS community. More information and application
2. Mobility program for phds and postdocs The PhD and Postdoc mobility program is aimed at existing PhD students and postdocs in the network who want to initiate a collaboration with a Fellow or Member at another site. Young researchers can give their careers a head start by gaining international experience and exchanging ideas with the best labs in Europe. The Mobility Award covers travel costs of up to 2,500 EUR per researcher over the duration of their PhD or postdoc.
A series of student projects associated to the CIS Collaboration Grant on Intelligent Assistive Robotics are now open! These projects aim to address additional research topics within the project or to implement related technological bricks. Several labs and research groups are typically involved in the supervision of these project, which allows students to gain multidisciplinary experience in research and development.
Interpretable Deep Learning towards cardiovascular disease prediction
Cardiovascular disease (CVD) is the leading cause of death in most European countries and is responsible for more than one in three of all potential years of life lost. Myocardial ischemia and infarction are most often the result of obstructive coronary artery disease (CAD), and their early detection is of prime importance. This could be developed based on data such as coronary angiography (CA), which is an X-ray based imaging technique used to assess the coronary arteries. However, such prediction is a non-trivial task, as i) data is typically noisy and of small volume, and ii) CVDs typically result from the complex interplay of local and systemic factors ranging from cellular signaling to vascular wall histology and fluid hemodynamics. The goal of this project is to apply advanced machine learning techniques, and in particular deep learning, in order to detect culprit lesions from CA images, and eventually predict myocardial infarction. Incorporating domain specific constraints to existing learning algorithms might be needed.
