[iva] Postdoc and engineer positions at LITIS lab, Rouen, France

[alexandre.pauchet at insa-rouen.fr]

The LITIS lab at INSA Rouen Normandy, France is recruiting:

- 1 *post-doctoral* fellow for a period of 18 months
- 1 *engineer* for a period of 12 months

as part of the SICoPaD project (Interactive and Personalized Monitoring 
of Home Hospitalized Patients) funded by the Normandy region.


The 2 positions are to be filled from January 2019 (date may be 
postponed depending on the availability of the successful candidate).

*Context of the project:
*
The multiplication and diversification of connected devices that can be 
deployed at a reasonable cost in domestic environments opens up many 
perspectives on the monitoring of daily activities for assistance or 
supervision. In a medical context, the emergence of these Internet of 
Things has generated a strong interest in real-time patient monitoring, 
patient care, collection and exchange of information between patients 
and carers.... *The SICoPaD project is interested in the data analysis 
and processing provided by connected objects deployed in the patients 
home*. In this project, we will focus more specifically on oral 
chemotherapy, a therapeutic modality that is becoming increasingly 
common in the management of cancer patients. The patient becomes 
responsible for ensuring proper compliance with his or her treatment and 
for managing adverse reactions on a daily basis. To ensure adequate 
follow-up of cancer patients treated with oral chemotherapy at home, 
health professionals must have sufficient information at their disposal, 
such as the correct intake of treatment, nutritional status, the 
existence of a fever, and the maintenance of social activities.

The objective of the project is to provide models for the analysis and 
exploitation of data coming from heterogeneous sources. The project 
tasks will benefit from the scientific skills of the MIND/LITIS and 
MAD/GREYC groups in the fields of behaviour detection, decision theory 
and human-agent interaction, in complementarity with the Henri Becquerel 
Centre providing its medical expertise and access to data from objects 
deployed in real conditions.

The objectives of the project are as follows:

  * analysing the temporal evolution from different sources (connected
    objects, questionnaires completed by the patient) taken in isolation
    to define a normal behaviour model and a deviant situation detection
    mechanism;
  * proposing a model for integrating these data into a patient profile
    that allows them to be linked in order to extend the effectiveness
    of detection by combining weak signals;
  * defining an adaptive automatic decision-making system for alert
    removal, initialized with decision rules provided by health
    professional experts, and which will evolve according to previously
    detected situations to decide earlier on the actions to be taken;
  * developing an interactive virtual agent that substitutes forms used
    as questionnaires so that the feedback from the patient is
    facilitated and contextualized according to his or her situation;
  * implementing these models on the platform provided by the Henri
    Becquerel Centre to evaluate, validate and quantify the
    effectiveness of the system in patient follow-up.


*Missions and profile of the post-doctoral position:
*
The post-doctoral fellow will be recruited to contribute to a project 
workpackage entitled "Representation and detection of a patient's 
profile" whose objective is to precisely identify the data collected and 
to propose an integrative representation model characterizing the 
patient's activity and condition over a given period. Representation in 
the form of discrete dynamic systems will be preferred, possibly on 
different time scales if the heterogeneity of the values collected so 
requires. Comparative analysis by calculating distance with reference 
models will make it possible to identify abnormal situations, as can be 
done in the field of trust management for the detection of malicious 
actions/agents.

Candidates must have a PhD in computer science. Skills related to 
activity detection using discrete dynamic systems, automatic 
classification techniques and/or time series analysis are expected.

The contract is for a period of 18 months, starting in January 2019. The 
gross monthly salary is about 2800 euros.

*Missions and profile of the engineer's position:
*
The engineer will be recruited to contribute to the workpackages 
"Patient-Agent Interactions" and "Application to the follow-up of 
cancer patients treated with oral chemotherapy". Its role will be to 
develop the interaction and data collection environment necessary for 
the project. His/Her task will be to develop a conversational agent to 
interact with the patient using existing platforms and to integrate the 
data collected by different connected devices within a unified platform.

Candidates must have a MSc degree in computer science. The expected 
skills are mainly computer programming and web technologies. A 
desirable experience in networking for connected objects or in 
programming conversational agents is a plus.

The contract is for a period of 12 months, starting in January 2019. The 
gross monthly salary is about 2700 euros.

Applications must include a CV and a covering letter and must be sent by 
e-mail to Laurent.Vercouter at insa-rouen.fr 
<mailto:Laurent.Vercouter at insa-rouen.fr> by 31 December 2018 at the latest.

-- 
Alexandre Pauchet
Associate Professor HDR
INSA Rouen Normandie - ASI Department - LITIS Lab
Phone: +33(0)2 32 95 98 58
Web: http://asi.insa-rouen.fr/enseignants/~apauchet/

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.uni-bielefeld.de/mailman2/unibi/public/iva-list/attachments/20181214/8c562de1/attachment.html>