FR3090954B1 - Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices - Google Patents

Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices Download PDF

Info

Publication number
FR3090954B1
FR3090954B1 FR1873797A FR1873797A FR3090954B1 FR 3090954 B1 FR3090954 B1 FR 3090954B1 FR 1873797 A FR1873797 A FR 1873797A FR 1873797 A FR1873797 A FR 1873797A FR 3090954 B1 FR3090954 B1 FR 3090954B1
Authority
FR
France
Prior art keywords
property
determining
signal
neural network
associated devices
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
FR1873797A
Other languages
French (fr)
Other versions
FR3090954A1 (en
Inventor
Thomas Courtat
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Thales SA
Original Assignee
Thales SA
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Thales SA filed Critical Thales SA
Priority to FR1873797A priority Critical patent/FR3090954B1/en
Publication of FR3090954A1 publication Critical patent/FR3090954A1/en
Application granted granted Critical
Publication of FR3090954B1 publication Critical patent/FR3090954B1/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/045—Combinations of networks

Abstract

Procédé de détermination d’au moins une propriété d’un signal temporel, notamment un signal de télécommunication , et dispositifs associés La présente invention concerne un procédé de détermination d’au moins une propriété d’un signal temporel, le procédé étant mis en œuvre par ordinateur, le procédé comportant une optimisation d’un réseau de neurones à partir d’une base d’apprentissage, pour obtenir un réseau de neurones appris, le réseau de neurones comportant successivement des couches convolutionnelles, une couche de marginalisation et un classifieur, l’optimisation étant effectuée selon un critère de performance, la base d’apprentissage comprenant des signaux temporels présentant des propriétés connues, le réseau de neurones étant propre à classer selon au moins deux catégories, les signaux temporels échantillonnés en un nombre d’échantillons respectif, de préférence au moins deux nombres d’échantillons étant distincts, chaque catégorie correspondant à une propriété à déterminer. Figure pour l'abrégé : 2Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices The present invention relates to a method for determining at least one property of a time signal, the method being implemented by computer, the method comprising an optimization of a neural network from a learning base, to obtain a learned neural network, the neural network successively comprising convolutional layers, a marginalization layer and a classifier, the optimization being carried out according to a performance criterion, the learning base comprising time signals exhibiting known properties, the neural network being able to classify according to at least two categories, the time signals sampled into a respective number of samples , preferably at least two numbers of samples being distinct, each category corresponding to a property to be determined . Figure for abstract: 2

FR1873797A 2018-12-21 2018-12-21 Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices Active FR3090954B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
FR1873797A FR3090954B1 (en) 2018-12-21 2018-12-21 Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
FR1873797A FR3090954B1 (en) 2018-12-21 2018-12-21 Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices

Publications (2)

Publication Number Publication Date
FR3090954A1 FR3090954A1 (en) 2020-06-26
FR3090954B1 true FR3090954B1 (en) 2022-12-16

Family

ID=66867287

Family Applications (1)

Application Number Title Priority Date Filing Date
FR1873797A Active FR3090954B1 (en) 2018-12-21 2018-12-21 Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices

Country Status (1)

Country Link
FR (1) FR3090954B1 (en)

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
AU2017209028B2 (en) * 2016-01-18 2019-08-01 Viavi Solutions Inc. Method and apparatus for the detection of distortion or corruption of cellular communication signals

Also Published As

Publication number Publication date
FR3090954A1 (en) 2020-06-26

Similar Documents

Publication Publication Date Title
Raffi et al. Late Miocene calcareous nannofossil biostratigraphy and astrobiochronology for the Mediterranean region
McKenna et al. A parallel microfluidic flow cytometer for high-content screening
CN106597365B (en) A kind of sophisticated electronic signal time difference positioning method based on time domain cluster
CN106248621B (en) A kind of evaluation method and system
Suman et al. Label-free imaging to study phenotypic behavioural traits of cells in complex co-cultures
CN106372667A (en) Method for detecting adverse state of inclined sleeve part screws of high-speed train overhead line system
FR3077059B1 (en) METHOD FOR DETECTING ICING CONDITIONS FOR AN AIRCRAFT BY SUPERVISED AUTOMATIC LEARNING
FR3090954B1 (en) Method for determining at least one property of a time signal, in particular a telecommunications signal, and associated devices
Yeo et al. High-throughput quantification of early stages of phagocytosis
CN109685128A (en) A kind of MB-kmeans++ clustering method and the user conversation clustering method based on it
CN101751396A (en) Interest point information processing system
US10222315B2 (en) Machine-learning approach to holographic particle characterization
CN109032352A (en) Hand signal treating method and apparatus
FR2929411A1 (en) METHOD AND SYSTEM FOR TRACKING AND TRACKING TRANSMITTERS.
CN115278520A (en) 5G indoor positioning method based on fingerprint database migration reconstruction
Bassino et al. Globular cluster candidates within the Fornax Cluster: Intracluster globulars?
GB2588572A8 (en) Transition Detection
FR3091844B1 (en) Method for determining a confidence score of a target in a vehicle environment
FR3078804B1 (en) PROCESS FOR SELECTING SOLVENTS SUITABLE FOR FLUORINE POLYMERS
CN111578933B (en) Method for quickly identifying user entering specific geographic area
Wang et al. Specific emitter identification based on the multi‐discrepancy deep adaptation network
Jayawardena et al. Predicting clinical outcome of cardiac patients by six malnutrition screening tools
Lima et al. Human Mobility Support for Personalized Data Offloading
Zhou et al. Artificial intelligence for elections: the case of 2019 Argentina primary and presidential election
CN106845523B (en) A kind of data processing method blending geodata and sensor signal data

Legal Events

Date Code Title Description
PLFP Fee payment

Year of fee payment: 2

PLSC Publication of the preliminary search report

Effective date: 20200626

PLFP Fee payment

Year of fee payment: 3

PLFP Fee payment

Year of fee payment: 4

PLFP Fee payment

Year of fee payment: 5

PLFP Fee payment

Year of fee payment: 6