Scientific direction Development of key enabling technologies
Transfer of knowledge to industry

PhD : selection by topics

Measurement of nuclear decay data for beta decay and electron capture using metallic magnetic calorimeters

DM2I (LIST)

Laboratoire de Métrologie de l'Activité

01-09-2019

SL-DRT-19-0643

matias.rodrigues@cea.fr

In the framework of ionizing radiation metrology, one of the tasks of the Laboratoire National Henri Becquerel (LNHB), the French national laboratory for ionizing radiation metrology, is the precise determination of nuclear decay data. During this PhD thesis, cryogenic detectors will be developed for the precise measurement of the shapes of beta spectra, photon emission probabilities and capture probabilities of radionuclides decaying via electron capture. These data are required in various fields of research and application, including nuclear medicine, nuclear energy and waste management, or neutrino physics research. The PhD student will conduct experiments comprising the conception and fabrication of cryogenic detectors, their operation in a complex cryogenic setup, work with highly specific electronics, Monte Carlo simulations, and data analysis using sophisticated methods. The measured data will be compared with theoretical calculations and help to improve nuclear data tables.

Explaining predicitive-model decisions: towards automatic interpretation of tree-ensemble models

DM2I (LIST)

Laboratoire d'Analyse des Données et d'Intelligence des Systèmes

01-09-2019

SL-DRT-19-0644

pierre.blanchart@cea.fr

Until recently, the focus in predictive modelling has mainly been set on improving model prediction accuracy. Many successful models scaling to big amounts of heterogeneous data have been proposed in the literature, and widely used implementations of these models are available. Unfortunately, these models generally do not intrinsically come with an easy way to explain their predictions, and are often presented as black-box tools performing complex and non-intuitive operations on their inputs. This can be an issue in many applications where the interpretation of the model decision may have a greater added-value than the decision itself. Examples include medical diagnosis where the interpretation would consist in identfying which combination(s) of characteristics presented by an individual contributes most to the diagnosis. In this thesis, we propose to add interpretability to a specific class of machine learning models known as tree-ensemble models, without impacting the performance of the model we want to interpret. In the continuation of the work already initiated in the laboratory, the objective is to analyze the combinations of input features along with their respective numerical values, so that each instance-level decision taken by the model can be explained by a set of input features having particular numerical values. Fault detection in connected manufacturing provides an interesting application for such approaches, and data as well as the fault detection models will be provided as a starting point for this thesis work.

Spintronic Wake-Up Radio

Département Architectures Conception et Logiciels Embarqués (LIST-LETI)

Laboratoire Architectures Intégrées Radiofréquences

01-09-2019

SL-DRT-19-0645

dominique.morche@cea.fr

The increasing number of wireless connected objects and smart sensors requires defining components and operational schemes that drastically reduce the power consumption. Within such communicating networks the RxTx modules are the most power consuming elements. The solution actively searched for is to switch off the main RxTx module when no communication is requested and to use a low power, degraded wake-up radio receiver WuRx that will switch on the main module when receiving an according wake-up signal. The realization of robust and ultralow power WuRx is an active field of research. The thesis proposes to explore RF spintronic devices as such a compact and low power solution. Magnetic tunnel junctions, which are the main spintronics building blocks, are capable to passively convert an RF signal into a DC signal, with frequency selectivity and at relatively high output signal levels. LETI/DACLE and INAC/SPINTEC work together on the realization of such spintroncis based WuRx and the PhD project will be at the interface of the two laboratories. While SPINTEC will realize the devices and optimize their sensitivity to low input signal levels, the thesis will be carried out at LETI/DACLE to realize the corresponding antenna networks and rf electronics. In order to establish the performance parameters the student will first spend some time at SPINTEC to get trained on the characterization of spintronic based rf components. The student will also be involved in the testing of the developed rf circuits with the spintronics components to iteratively optimize the electronic circuits and adapt it to the spintronics device performances.

Advanced network management for controlling the real-time redeployment of a mobile network infrastructure under traffic performance constraints

Département Intelligence Ambiante et Systèmes Interactifs (LIST)

Laboratoire Systèmes Communiquants

01-10-2019

SL-DRT-19-0646

Michael.Boc@cea.fr

The digitization of industries introduces the need for providing high-speed wireless connectivity on industrial sites, which is extremely difficult due to the constraints imposed by these environments. To address them, this PhD thesis will investigate opportunities to increase real-time reconfiguration capabilities of the wireless infrastructure by means of an SDN-oriented management of the network. This network management will control the mobility of the infrastructure equipment as an additional degree of freedom in order to improve the performance of the data flows. This capability should provide two key benefits: 1) not having to rely on a lengthy and costly planning phase for network deployment, and 2) being able to implement new and more sophisticated network reconfiguration strategies to increase its overall performance level at any time. The mobility of the infrastructure could be provided by mobile robots that can be controlled through an SDN protocol and carrying some of the network equipment. In the case of a nuclear dismantling operation, for example, we could consider the wireless communication infrastructure as being composed of a fleet of mobile robots (terrestrial or aerial) whose mobility is managed by a network management system (SDN) in charge of ensuring the proper performance of the connectivity for dismantling robots remotely operated. The objective of the proposed thesis work is to define an advanced and centralized network management system for the control of the real-time redeployment of a mobile network infrastructure under performance constraints of data flows. This system should be able to 1) identify when a topological change becomes relevant considering the types of data flow performance problems and the limitations of existing network optimization solutions, 2) to define and pilot the redeployment of the network infrastructure in order to improve the performance of these data flows.

Machine learning based simulation of realistic signals for an enhanced automatic diagnostic in non-destructive testing applications

Département Imagerie Simulation pour le Contrôle (LIST)

Laboratoire Simulation et Modélisation en Electro-magnétisme

01-09-2019

SL-DRT-19-0657

roberto.miorelli@cea.fr

Model based solutions for automatic diagnostic in the field on non-destructive testing are currently a topic of great interest in both academic and industrial communities. Their ultimate objective is to provide a qualitative or quantitative evaluation of the inspected material state (sound, flawed, flawed with anomaly dimensions or criticality) in an industrial context like a production line. Such tools, providing inputs for real-time process control, contribute to the general trend in Europe that aims at modernizing Industry and services [1]. The CEA LIST institute is an internationally recognized research institution in the field of nondestructive testing. It develops the CIVA software [2], which offers multi-physics models and is considered as a leading product for simulation for NDT applications. Accurate models able to reproduce experimental signals prove very helpful in an inversion process aiming at classifying or characterizing flaws [3]. However, as they do not account for disturbances and parameters variability occurring during an experimental acquisition, simulated signals inherently look ?perfect? and are, for instance, easily distinguishable from experimental data. This PhD subject aims at improving the match between simulation and experimental data, by augmenting the simulation with another contribution on can generally refer to as ?noise?. The strategy proposed to obtain such noise contribution is to apply machine-learning techniques like dictionary learning to a set of representative experimental data. Alternatively, a deep learning model can be trained to analyze real data and then distinguish between contents (flaw signals) and style (the rest, which is not simulated by physical models). Afterwards, the augmented simulation tool will be able to reproduce closely experimental data, take into account specific discrepancies due to a particular environment and reproduce the variability observed experimentally. It will thus enhance the performance of model based tools developed at CEA LIST for sensibility analysis, management of uncertainty and diagnostic. REFERENCES [1] http://ec.europa.eu/research/participants/portal/desktop/en/opportunities/h2020/topics/dt-fof-08-2019.html [2] www.extende.com [3] M. Salucci et al., "Real-Time NDT-NDE Through an Innovative Adaptive Partial Least Squares SVR Inversion Approach," in IEEE Transactions on Geoscience and Remote Sensing, vol. 54, no. 11, pp. 6818-6832, Nov. 2016

Cyber-reasoning systems to the next level: bringing learning and deduction together

Département Ingénierie Logiciels et Systèmes (LIST)

Laboratoire pour la Sûreté du Logiciel

01-10-2019

SL-DRT-19-0658

sebastien.bardin@cea.fr

This PhD aims at understanding how deductive methods based on automatic reasoning (used in program analysis) can be combined with inductive methods based on machine learning (developed in Artificial Intelligence) in order to obtain new automatic methods for program analysis that could infer program behaviours in a precise and sound way. Then, these new methods will be applied on code security problems such as retro-engineering or code strengthening. We will focus on symbolic learning (constraint learning) and deductive methods based on symbolic execution and SMT solvers.

126 Results found (Page 13 of 21)
first   previous  11 - 12 - 13 - 14 - 15  next   last

Voir toutes nos offres