Estimation of respiratory volume from thoracoabdominal breathing distances: comparison of two models of machine learning

Autor: Haitao Kang, Jacques Prioux, Alexis Le Faucheur, Hala Abdul Rahman, Remy Dumond, Steven Gastinger, Patrice Quinton

Publikováno v: European Journal of Applied Physiology
European Journal of Applied Physiology, Springer Verlag, 2017, 117 (8), pp.1533--1555. ⟨10.1007/s00421-017-3630-0⟩
European Journal of Applied Physiology, 2017, 117 (8), pp.1533--1555. ⟨10.1007/s00421-017-3630-0⟩

The purposes of this study were to both improve the accuracy of respiratory volume (V) estimates using the respiratory magnetometer plethysmography (RMP) technique and facilitate the use of this technique. We compared two models of machine learning (

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::50202205e9e4c5184be4ec0fb7566a3c
https://hal-univ-rennes1.archives-ouvertes.fr/hal-01585982

Circuits parallèles à l’Irisa dans les années 1980

Autor: Patrice Frison, Patrice Quinton

Publikováno v: Techniques et sciences informatiques. 31:959-968

From 1983 to 1990, the members of the parallel integrated architectures team (Api) of Irisa designed and developed several special-purpose parallel VLSI chips and invented some tools and methods to design these chips. We briefly present these researc

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e1ff344ef197ee1f8d8c56095e89df31
https://doi.org/10.3166/tsi.31.959-968

Combining execution pipelines to improve parallel implementation of HMMER on FPGA

Autor: Patrice Quinton, Dominique Lavenier, Alexandre Cornu, Sanjay Rajopadhye, Steven Derrien, Naeem Abbas

Publikováno v: Microprocessors and Microsystems: Embedded Hardware Design
Microprocessors and Microsystems: Embedded Hardware Design, 2015, 39, pp.457-470. ⟨10.1016/j.micpro.2015.06.006⟩
Microprocessors and Microsystems: Embedded Hardware Design (MICPRO)
Microprocessors and Microsystems: Embedded Hardware Design (MICPRO), Elsevier, 2015, 39, pp.457-470. ⟨10.1016/j.micpro.2015.06.006⟩

International audience; HMMER is a widely used tool in bioinformatic, based on the Profile Hidden Markov Models. The computation kernels of HMMER, namely MSV and P7Viterbi are very compute intensive, and their data dependencies if interpreted naively

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cba7d3de7681aa8cf90fa8dcc186b1d6
https://hal.inria.fr/hal-01235328

Component reuse methodology for multi-clock Data-Flow parallel embedded Systems

Autor: Steven Derrien, Anne Marie Chana, Patrice Quinton

Publikováno v: Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées
Revue Africaine de la Recherche en Informatique et Mathématiques Appliquées, INRIA, 2014, 18, pp.67-92
Revue Africaine de Recherche en Informatique et Mathématiques Appliquées
Revue Africaine de Recherche en Informatique et Mathématiques Appliquées, 2014, Volume 18, 2014, pp.67-92. ⟨10.46298/arima.1979⟩

The growing complexity of new chips and the time-to-market constraints require fundamental changes in the way systems are designed. Systems on Chip (SoC) based on reused components have become an absolute necessity to embedded systems companies that

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6f160728d7193e468e01dff50579dfe5
https://hal.inria.fr/hal-01300088

Polyhedral Bubble Insertion: A Method to Improve Nested Loop Pipelining for High-Level Synthesis

Autor: Antoine Morvan, Patrice Quinton, Steven Derrien

Publikováno v: IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2013, 32 (3), pp.339-352. ⟨10.1109/TCAD.2012.2228270⟩
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, IEEE, 2013, 32 (3), pp.339-352. ⟨10.1109/TCAD.2012.2228270⟩

International audience; High-level synthesis (HLS) allows hardware to be directly produced from behavioral description in C/C++, thus accelerating the design process. Loop pipelining is a key transformation of HLS, as it improves the throughput of th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d3dbd0a9b400f4d756a0fc00b929b309
https://hal.inria.fr/hal-00921424