Hi everyone! Welcome to my blog, where you can find information such as human life, natural resource, forestry, agriculture, biotechnology, biodiversity, wood and non-wood materials.
Tuesday, 1 November 2016
Wood moisture content prediction using feature selection techniques and a kernel method
Published Date Available online 13 September 2016,doi:10.1016/j.neucom.2016.09.005 In Press, Corrected Proof —Note to users
Laboratoire de Physique et d'Étude des Matériaux (LPEM) PSL Research University, ESPCI-ParisTech Sorbonne Universités, UPMC Univ Paris 06 CNRS, UMR 8213, 10 rue Vauquelin, 75231 Paris Cedex 05, France
Received 11 January 2016. Revised 15 July 2016. Accepted 1 September 2016. Available online 13 September 2016. Communicated by Feiping Nie
The prediction of moisture content for two wood chips species using the wood dielectric property is studied.
Nonlinear models are built to predict the reflection coefficient values from frequencies.
Those reflection coefficients are used as input variables of a moisture content predictive model designed using Least Squares Support Vector Machines (LS-SVM) technique and feature selection methods.
Numerical experiments using real world data show the effectiveness of the proposed methodology that requires a limited computational power.
Wood is a renewable, abundant bio-energy and environment friendly resource. Woody biomass Moisture Content () is a key parameter for controlling the biofuel product qualities and properties. In this paper, we are interested in predictingfrom data. The input impedance of half-wave dipole antenna when buried in the wood pile varies according to the permittivity of wood. Hence, the measurement of reflection coefficient, that gives information about the input impedance, depends directly on theof wood. The relationship between the reflection coefficient measurements and theis studied. Based upon this relationship,predictive models that use machine learning techniques and feature selection methods are proposed. Numerical experiments using real world data show the relevance of the proposed approach that requires a limited computational power. Therefore, a real-time implementation for industrial processes is feasible.
Hela Daassi was born in Sousse, Tunisia, in 1976. She graduated from the engineering school Ecole Nationale d'Ingénieurs de Tunis in 1999 and obtained his Ph.D. in Computer Science in2006 from the University of Paris 5, France. She is Postdoctoral researcher at ESPCI since 2015. She has made many contributions to speech processing in mobile networks and Machine Learning applied to emotion recognition from speech. Currently she works for machine learning techniques and their applications in various domains of instrumentation. ESPCI/UPMC/CNRS-LPEM/UMR8213, 10 rue Vauquelin, 75005 Paris, France. (email: firstname.lastname@example.org).
Thierry Ditchi was born in Noisy le Sec, France, in 1959. He received his Ph.D. in electrical engineering in 1990 from the University Pierre et Marie Curie in association with the Ecole Supérieure de Physique et de Chimie Industrielles, Paris France. During his Ph.D. thesis, he studied electrical properties of insulating materials and developed instruments for measuring space charge buildup in insulators. He is currently Associate Professor at Sorbonne Universités-UPMC since 1991 where he teaches physics, electromagnetism, antennae and high frequency electronics. His research topics include instrumentation for the characterization of insulators, study of sensors and high frequency devices for several domains such as wood industry, automotive... UPMC/ESPCI/CNRS-LPEM/UMR8213, 10 rue Vauquelin, 75005 Paris, France. (email: email@example.com).
Emmanuel Géron was born in Saint-Maurice, France, in 1968. He graduated from the engineering school cole Supérieure de Physique et de Chimie Industrielles of the City of Paris in 1992 and obtained his Ph.D. in Electronics in 1997 from the University of Paris 6, France. He is Associate Professor at ESPCI since 1997. He obtained his Habilitation to lead researches (HDR) in 2013 from the University of Paris 6, Paris. He has made many contributions to Telecommunications and works currently for hyper-frequency circuits and propagation of electromagnetic waves in meta-materials, high resolution space charges systems, and more generally on instrumentation. ESPCI/UPMC/CNRS-LPEM/UMR8213, 10 rue Vauquelin, 75005 Paris, France. (email: firstname.lastname@example.org).
Stéphane Holé born in Pontoise, France, in 1968, studied electronics and instrumentation at Université Pierre et Marie Curie, Paris France. He joined Laboratoire d'Électricité Générale of École Supérieure de Physique et de Chimie Industrielles, Paris France, to study an instrument for measuring fast development of space charges in insulators under rapid voltage variations. It was the topic of his Ph.D. he received in 1996. Currently Professor at Sorbonne Universités-UPMC, he conducted his researches in Laboratoire des Instruments et Systémes d'Ile de France from 1997 to 2007 and leads the Instrumentation Group in Laboratoire de Physique et d'Étude des Materiaux since 2007. His research topics are various such as space charge in insulators and semiconductors (main topic), electrostatic, magnetostatic and ultrasonic sensors. He received the Jack Hollingum Award in 2002 and 2004, and obtained his Habilitation in 2007. He teaches solid state physics, electronics and sensor physics. He is coordinator of the sensors, instrumentation & measurement master at Pierre et Marie Curie University since 2009. His current address is: UPMC/ESPCI/CNRS-LPEM/UMR8213, 10 rue Vauquelin, 75005 Paris, France. (e-mail: email@example.com).
Yacine Oussar was born in Algiers, Algeria, in 1969. He graduated from the engineering school École Nationale Polytechnique d'Alger in 1993 and obtained his Ph.D. in Machine Learning in 1998 from the University of Paris 6, France. He is Associate Professor at ESPCI since 1998. He obtained his Habilitation to lead researches (HDR) in 2010 from the University of Paris 6, Paris. He has made many contributions to Machine Learning and works currently for electrostatics, electromagnetic waves, partial discharges, and more generally on applications of machine learning techniques for instrumentation. ESPCI/UPMC/CNRS-LPEM/UMR8213, 10 rue Vauquelin, 75005 Paris, France. (email: firstname.lastname@example.org).
Maria Merlan was born in Ferrol, Spain, in 1985. She holds a first degree in Telecommunication Engineering and a Master in Radio communication from the Electrical engineering school at the University of Vigo, Galicia 2011. She obtained her Ph.D. in Electronics in 2016 from the University Pierre et Marie Curie in Paris, France. She is specialized in RF antenna and instrumentation and currently working as a research engineer for hyper-frequency technologies in ENS Cachan, 61 Avenue du Président Wilson, (email: email@example.com).
Note to users:Corrected proofs are Articles in Press that contain the authors' corrections. Final citation details, e.g., volume/issue number, publication year and page numbers, still need to be added and the text might change before final publication.
Although corrected proofs do not have all bibliographic details available yet, they can already be cited using the year of online publication and the DOI , as follows: author(s), article title, journal (year), DOI. Please consult the journal's reference style for the exact appearance of these elements, abbreviation of journal names and use of punctuation.
When the final article is assigned to an issue of the journal, the Article in Press version will be removed and the final version will appear in the associated published issue of the journal. The date the article was first made available online will be carried over.
For further details log on website :