Yacine Oussar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Yacine Oussar has a total of 53 co-authors. Here are the top co-authors by number of shared publications:
- Stéphane Holé
ESPCI, Paris, France
6 shared publications G. Dreyfus
5 shared publicationsGérard Dreyfus
Signal Processing and Machine Learning Laboratory, ESPCI - ParisTech
5 shared publications- Bruce Denby
Institut Langevin, ESPCI Paris, PSL University, CNRS, Sorbonne Université, 75005 Paris, France
3 shared publications Iness Ahriz
Signal Processing and Machine Learning Laboratory, ESPCI - ParisTech
3 shared publicationsJérôme Lucas
Laboratoire de Physique et d'Etude des Materiaux - LPEM (CNRS UMR 8213), PSL, Paris, Île-de-France, FRANCE
3 shared publications
Latest Publications
- 1 January 2020
- Published by Elsevier in Electric Power Systems Research
- Vol. 178
Feature extraction and ageing state recognition using partial discharges in cables under HVDC
- 1 January 2020
- Published by Elsevier in Electric Power Systems Research
- Vol. 178
Feature extraction and ageing state recognition using partial discharges in cables under HVDC
- 19 September 2019
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 30 (12) , 125108
A resonant half-wave antenna for moisture content assessment in wood chips
The production of heat via combustion of wood biomass is growing because of the urge of European institutions to increase the use of renewable energies. Calorific value depends directly on the moisture content of the wood chips. Moisture content varies considerably from the rough conditions of the forest up to the wood industry chain. This paper presents a sensor based on a resonant half-wave antenna as a new approach for moisture determination of wood chips in piles. There is, at the moment, no system able to determine the global moisture content in a large sample of chips in a pile or in a truck. The sensor has to be placed into the material under test and the behavior of the antenna is analyzed to measure the moisture content. This method is tested on a one cubic meter scale setup in laboratory conditions. Promising results support the extended implementation to a real-scale production system.
- 19 September 2019
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 30 (12) , 125108
A resonant half-wave antenna for moisture content assessment in wood chips
The production of heat via combustion of wood biomass is growing because of the urge of European institutions to increase the use of renewable energies. Calorific value depends directly on the moisture content of the wood chips. Moisture content varies considerably from the rough conditions of the forest up to the wood industry chain. This paper presents a sensor based on a resonant half-wave antenna as a new approach for moisture determination of wood chips in piles. There is, at the moment, no system able to determine the global moisture content in a large sample of chips in a pile or in a truck. The sensor has to be placed into the material under test and the behavior of the antenna is analyzed to measure the moisture content. This method is tested on a one cubic meter scale setup in laboratory conditions. Promising results support the extended implementation to a real-scale production system.
- 29 May 2018
- Published by Springer Nature in Wood Science and Technology
- Vol. 52 (5) , 1195-1211
Moisture content recognition for wood chips in pile using supervised classification
- 29 May 2018
- Published by Springer Nature in Wood Science and Technology
- Vol. 52 (5) , 1195-1211
Moisture content recognition for wood chips in pile using supervised classification
- Open Access
- 1 April 2018
- Published by Elsevier in Journal of Electrostatics
- Vol. 92, 45-53
A smart capacitive measurement system for fall detection
- 1 April 2018
- Published by Elsevier in Journal of Electrostatics
- Vol. 92, 45-53
Open AccessA smart capacitive measurement system for fall detection
- 1 May 2017
- Published by Elsevier in Neurocomputing
- Vol. 237, 79-91
Wood moisture content prediction using feature selection techniques and a kernel method
- 1 May 2017
- Published by Elsevier in Neurocomputing
- Vol. 237, 79-91
Wood moisture content prediction using feature selection techniques and a kernel method
- 18 April 2017
- Published by Wiley in International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
- Vol. 31 (2)
One or two circular shapes? A binary detection for electrical capacitance tomography sensors
Image reconstruction using engine electrical capacitance tomography sensors rises several drawbacks. Recently, the authors proposed a novel methodology dedicated to a fast detection of the configuration: size and position, of a single circular form using basic algebraic operations. However, this technique is efficient when a single form is present in the sensor cross‐section under interest. The present work proposes 2 different techniques that determine if the sensor cross‐section contains 1 or 2 circular shapes. Both methods are applied to simulated measurements. They operate much differently, and each comes with its own pros and cons. The first method considers that the sensor signal presents an axis of symmetry if a single circular object lies in the sensor. Otherwise, the symmetry is broken. It achieves a recognition rate of 73.9%. In the second method, machine‐learning techniques are used to perform a binary supervised classification. Promising rates of recognition over 99% are obtained. The present study also reveals that a 4‐electrode sensor leads to the best recognition rates with both methods. This result was also established by the authors in a different framework when dealing with physical limitations on spatial resolution in electrical capacitance tomography sensors.
- 18 April 2017
- Published by Wiley in International Journal of Numerical Modelling: Electronic Networks, Devices and Fields
- Vol. 31 (2)
One or two circular shapes? A binary detection for electrical capacitance tomography sensors
Image reconstruction using engine electrical capacitance tomography sensors rises several drawbacks. Recently, the authors proposed a novel methodology dedicated to a fast detection of the configuration: size and position, of a single circular form using basic algebraic operations. However, this technique is efficient when a single form is present in the sensor cross‐section under interest. The present work proposes 2 different techniques that determine if the sensor cross‐section contains 1 or 2 circular shapes. Both methods are applied to simulated measurements. They operate much differently, and each comes with its own pros and cons. The first method considers that the sensor signal presents an axis of symmetry if a single circular object lies in the sensor. Otherwise, the symmetry is broken. It achieves a recognition rate of 73.9%. In the second method, machine‐learning techniques are used to perform a binary supervised classification. Promising rates of recognition over 99% are obtained. The present study also reveals that a 4‐electrode sensor leads to the best recognition rates with both methods. This result was also established by the authors in a different framework when dealing with physical limitations on spatial resolution in electrical capacitance tomography sensors.
- 3 January 2017
- Published by Emerald Publishing in COMPEL - The international journal for computation and mathematics in electrical and electronic engineering
- Vol. 36 (1) , 2-17
Fast circular shapes detection in cylindrical ECT sensors by design selection and nonlinear black-box modeling
Purpose: Within the framework of image reconstruction in cylindrical electrical capacitance tomography (ECT) sensors, the purpose of this study is to select the structure of a sensor in terms of number and size of the electrodes, to predict the radius and the position of a single circular shape lying in the cross-section defined by the sensor electrodes. Design/methodology/approach: Nonlinear black-box models using a set of physically independent capacitances and least-square support vector machines models selected with a sophisticated validation method are implemented. Findings: The coordinates of circular shapes are well estimated in fixed and variable permittivity environments even with noisy data. Various numerical experiments are presented and discussed. Sensors formed by three or four electrodes covering 50 per cent of the sensor perimeter provide the best prediction performances. Research limitations/implications: The proposed method is limited to the detection of a single circular shape in a cylindrical ECT sensor. Practical implications: This method can be advantageously implemented in real-time applications, as it is numerically cost-effective and necessitates a small amount of measurements. Originality/value: The contribution is two-fold: a fast computation of a circular shape position and radius with a satisfactory precision compared to the sensor size, and the determination of a cylindrical ECT sensor architecture that allows the most efficient predictions.
- 3 January 2017
- Published by Emerald Publishing in COMPEL - The international journal for computation and mathematics in electrical and electronic engineering
- Vol. 36 (1) , 2-17
Fast circular shapes detection in cylindrical ECT sensors by design selection and nonlinear black-box modeling
Purpose: Within the framework of image reconstruction in cylindrical electrical capacitance tomography (ECT) sensors, the purpose of this study is to select the structure of a sensor in terms of number and size of the electrodes, to predict the radius and the position of a single circular shape lying in the cross-section defined by the sensor electrodes. Design/methodology/approach: Nonlinear black-box models using a set of physically independent capacitances and least-square support vector machines models selected with a sophisticated validation method are implemented. Findings: The coordinates of circular shapes are well estimated in fixed and variable permittivity environments even with noisy data. Various numerical experiments are presented and discussed. Sensors formed by three or four electrodes covering 50 per cent of the sensor perimeter provide the best prediction performances. Research limitations/implications: The proposed method is limited to the detection of a single circular shape in a cylindrical ECT sensor. Practical implications: This method can be advantageously implemented in real-time applications, as it is numerically cost-effective and necessitates a small amount of measurements. Originality/value: The contribution is two-fold: a fast computation of a circular shape position and radius with a satisfactory precision compared to the sensor size, and the determination of a cylindrical ECT sensor architecture that allows the most efficient predictions.
- 12 November 2015
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 26 (12) , 125105
Physical limitations on spatial resolution in electrical capacitance tomography
Electrical capacitance tomography (ECT) is an imaging technique providing the distribution of permittivity in a medium by means of electrodes. As for any imaging systems, the accessible spatial resolution is a key parameter. In this paper the physical limitations on the spatial resolution of ECT sensors are analysed in terms of the accuracy of an object’s position and of the ability to distinguish between two close objects for any sensor geometry. Cylindrical geometry sensors are particularly studied and the example of a square geometry sensor is used to show how to apply the calculations to any other geometries. In cylindrical geometries, it is shown that a 50% gap between electrodes is a good compromise and that increasing the number of electrodes improves the spatial resolution near the electrodes but decreases the spatial resolution in the centre. The best spatial resolution at the centre of the sensor is obtained with 3 or 4 electrodes. In the square geometry studied, it is shown that a better distribution of the spatial resolution is obtained when there are electrodes in the corners.
- 12 November 2015
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 26 (12) , 125105
Physical limitations on spatial resolution in electrical capacitance tomography
Electrical capacitance tomography (ECT) is an imaging technique providing the distribution of permittivity in a medium by means of electrodes. As for any imaging systems, the accessible spatial resolution is a key parameter. In this paper the physical limitations on the spatial resolution of ECT sensors are analysed in terms of the accuracy of an object’s position and of the ability to distinguish between two close objects for any sensor geometry. Cylindrical geometry sensors are particularly studied and the example of a square geometry sensor is used to show how to apply the calculations to any other geometries. In cylindrical geometries, it is shown that a 50% gap between electrodes is a good compromise and that increasing the number of electrodes improves the spatial resolution near the electrodes but decreases the spatial resolution in the centre. The best spatial resolution at the centre of the sensor is obtained with 3 or 4 electrodes. In the square geometry studied, it is shown that a better distribution of the spatial resolution is obtained when there are electrodes in the corners.
- Open Access
- 4 March 2015
- Published by Copernicus GmbH in Atmospheric Measurement Techniques
- Vol. 8 (3) , 1055-1071
A layer-averaged relative humidity profile retrieval for microwave observations: design and results for the Megha-Tropiques payload
A statistical method trained and optimized to retrieve seven-layer relative humidity (RH) profiles is presented and evaluated with measurements from radiosondes. The method makes use of the microwave payload of the Megha-Tropiques platform, namely the SAPHIR sounder and the MADRAS imager. The approach, based on a generalized additive model (GAM), embeds both the physical and statistical characteristics of the inverse problem in the training phase, and no explicit thermodynamical constraint – such as a temperature profile or an integrated water vapor content – is provided to the model at the stage of retrieval. The model is built for cloud-free conditions in order to avoid the cases of scattering of the microwave radiation in the 18.7–183.31 GHz range covered by the payload. Two instrumental configurations are tested: a SAPHIR-MADRAS scheme and a SAPHIR-only scheme to deal with the stop of data acquisition of MADRAS in January 2013 for technical reasons. A comparison to learning machine algorithms (artificial neural network and support-vector machine) shows equivalent performance over a large realistic set, promising low errors (biases < 2.2%RH) and scatters (correlations > 0.8) throughout the troposphere (150–900 hPa). A comparison to radiosonde measurements performed during the international field experiment CINDY/DYNAMO/AMIE (winter 2011–2012) confirms these results for the mid-tropospheric layers (correlations between 0.6 and 0.92), with an expected degradation of the quality of the estimates at the surface and top layers. Finally a rapid insight of the estimated large-scale RH field from Megha-Tropiques is presented and compared to ERA-Interim.
- 4 March 2015
- Published by Copernicus GmbH in Atmospheric Measurement Techniques
- Vol. 8 (3) , 1055-1071
Open AccessA layer-averaged relative humidity profile retrieval for microwave observations: design and results for the Megha-Tropiques payload
A statistical method trained and optimized to retrieve seven-layer relative humidity (RH) profiles is presented and evaluated with measurements from radiosondes. The method makes use of the microwave payload of the Megha-Tropiques platform, namely the SAPHIR sounder and the MADRAS imager. The approach, based on a generalized additive model (GAM), embeds both the physical and statistical characteristics of the inverse problem in the training phase, and no explicit thermodynamical constraint – such as a temperature profile or an integrated water vapor content – is provided to the model at the stage of retrieval. The model is built for cloud-free conditions in order to avoid the cases of scattering of the microwave radiation in the 18.7–183.31 GHz range covered by the payload. Two instrumental configurations are tested: a SAPHIR-MADRAS scheme and a SAPHIR-only scheme to deal with the stop of data acquisition of MADRAS in January 2013 for technical reasons. A comparison to learning machine algorithms (artificial neural network and support-vector machine) shows equivalent performance over a large realistic set, promising low errors (biases < 2.2%RH) and scatters (correlations > 0.8) throughout the troposphere (150–900 hPa). A comparison to radiosonde measurements performed during the international field experiment CINDY/DYNAMO/AMIE (winter 2011–2012) confirms these results for the mid-tropospheric layers (correlations between 0.6 and 0.92), with an expected degradation of the quality of the estimates at the surface and top layers. Finally a rapid insight of the estimated large-scale RH field from Megha-Tropiques is presented and compared to ERA-Interim.
- 1 January 2015
- Published by Czech Technical University in Prague - Central Library in Neural Network World
- Vol. 25 (1) , 75-91
EXTERNAL VS. INTERNAL SVM-RFE: THE SVM-RFE METHOD REVISITED AND APPLIED TO EMOTION RECOGNITION
- 1 January 2015
- Published by Czech Technical University in Prague - Central Library in Neural Network World
- Vol. 25 (1) , 75-91
EXTERNAL VS. INTERNAL SVM-RFE: THE SVM-RFE METHOD REVISITED AND APPLIED TO EMOTION RECOGNITION