Hybrid Hidden Markov Model for Marine Environment Monitoring. Rousseeuw, K., Caillault, É P., Lefebvre, A., & Hamad, D. 8(1):204–213. Number: 1doi abstract bibtex Phytoplankton is an important indicator of water quality assessment. To understand phytoplankton dynamics, many fixed buoys and ferry boxes were implemented, resulting in the generation of substantial data signals. Collected data are used as inputs of an effective monitoring system. The system, based on unsupervised hidden Markov model (HMM), is designed not only to detect phytoplancton blooms but also to understand their dynamics. HMM parameters are usually estimated by an iterative expectation-maximization (EM) approach. We propose to estimate HMM parameters by using spectral clustering algorithm. The monitoring system is assessed based on database signals from MAREL-Carnot station, Boulogne-sur-Mer, France. Experimental results show that the proposed system is efficient to detect environmental states such as phytoplankton productive and nonproductive periods without a priori knowledge. Furthermore, discovered states are consistent with biological interpretation.
@article{rousseeuw_hybrid_2015,
title = {Hybrid Hidden Markov Model for Marine Environment Monitoring},
volume = {8},
issn = {1939-1404},
doi = {10.1109/JSTARS.2014.2341219},
abstract = {Phytoplankton is an important indicator of water quality assessment. To understand phytoplankton dynamics, many fixed buoys and ferry boxes were implemented, resulting in the generation of substantial data signals. Collected data are used as inputs of an effective monitoring system. The system, based on unsupervised hidden Markov model ({HMM}), is designed not only to detect phytoplancton blooms but also to understand their dynamics. {HMM} parameters are usually estimated by an iterative expectation-maximization ({EM}) approach. We propose to estimate {HMM} parameters by using spectral clustering algorithm. The monitoring system is assessed based on database signals from {MAREL}-Carnot station, Boulogne-sur-Mer, France. Experimental results show that the proposed system is efficient to detect environmental states such as phytoplankton productive and nonproductive periods without a priori knowledge. Furthermore, discovered states are consistent with biological interpretation.},
pages = {204--213},
number = {1},
journaltitle = {{IEEE} Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
author = {Rousseeuw, K. and Caillault, É Poisson and Lefebvre, A. and Hamad, D.},
date = {2015-01},
note = {Number: 1},
keywords = {Monitoring, France, Clustering algorithms, oceanographic techniques, remote sensing, Boulogne-sur-Mer, Databases, environmental monitoring (geophysics), hidden Markov models, Hidden Markov models, hybrid hidden Markov model, Hybrid hidden Markov model ({HMM}), {MAREL}-Carnot station database, marine environment monitoring, marine water monitoring, microorganisms, phytoplankton blooms, phytoplankton dynamics, Remote sensing, Sensors, spectral clustering, spectral clustering algorithm, Support vector machines, water quality}
}
Downloads: 0
{"_id":"XQf5MsmC4RHjXpWxW","bibbaseid":"rousseeuw-caillault-lefebvre-hamad-hybridhiddenmarkovmodelformarineenvironmentmonitoring","authorIDs":[],"author_short":["Rousseeuw, K.","Caillault, É P.","Lefebvre, A.","Hamad, D."],"bibdata":{"bibtype":"article","type":"article","title":"Hybrid Hidden Markov Model for Marine Environment Monitoring","volume":"8","issn":"1939-1404","doi":"10.1109/JSTARS.2014.2341219","abstract":"Phytoplankton is an important indicator of water quality assessment. To understand phytoplankton dynamics, many fixed buoys and ferry boxes were implemented, resulting in the generation of substantial data signals. Collected data are used as inputs of an effective monitoring system. The system, based on unsupervised hidden Markov model (HMM), is designed not only to detect phytoplancton blooms but also to understand their dynamics. HMM parameters are usually estimated by an iterative expectation-maximization (EM) approach. We propose to estimate HMM parameters by using spectral clustering algorithm. The monitoring system is assessed based on database signals from MAREL-Carnot station, Boulogne-sur-Mer, France. Experimental results show that the proposed system is efficient to detect environmental states such as phytoplankton productive and nonproductive periods without a priori knowledge. Furthermore, discovered states are consistent with biological interpretation.","pages":"204–213","number":"1","journaltitle":"IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing","author":[{"propositions":[],"lastnames":["Rousseeuw"],"firstnames":["K."],"suffixes":[]},{"propositions":[],"lastnames":["Caillault"],"firstnames":["É","Poisson"],"suffixes":[]},{"propositions":[],"lastnames":["Lefebvre"],"firstnames":["A."],"suffixes":[]},{"propositions":[],"lastnames":["Hamad"],"firstnames":["D."],"suffixes":[]}],"date":"2015-01","note":"Number: 1","keywords":"Monitoring, France, Clustering algorithms, oceanographic techniques, remote sensing, Boulogne-sur-Mer, Databases, environmental monitoring (geophysics), hidden Markov models, Hidden Markov models, hybrid hidden Markov model, Hybrid hidden Markov model (HMM), MAREL-Carnot station database, marine environment monitoring, marine water monitoring, microorganisms, phytoplankton blooms, phytoplankton dynamics, Remote sensing, Sensors, spectral clustering, spectral clustering algorithm, Support vector machines, water quality","bibtex":"@article{rousseeuw_hybrid_2015,\n\ttitle = {Hybrid Hidden Markov Model for Marine Environment Monitoring},\n\tvolume = {8},\n\tissn = {1939-1404},\n\tdoi = {10.1109/JSTARS.2014.2341219},\n\tabstract = {Phytoplankton is an important indicator of water quality assessment. To understand phytoplankton dynamics, many fixed buoys and ferry boxes were implemented, resulting in the generation of substantial data signals. Collected data are used as inputs of an effective monitoring system. The system, based on unsupervised hidden Markov model ({HMM}), is designed not only to detect phytoplancton blooms but also to understand their dynamics. {HMM} parameters are usually estimated by an iterative expectation-maximization ({EM}) approach. We propose to estimate {HMM} parameters by using spectral clustering algorithm. The monitoring system is assessed based on database signals from {MAREL}-Carnot station, Boulogne-sur-Mer, France. Experimental results show that the proposed system is efficient to detect environmental states such as phytoplankton productive and nonproductive periods without a priori knowledge. Furthermore, discovered states are consistent with biological interpretation.},\n\tpages = {204--213},\n\tnumber = {1},\n\tjournaltitle = {{IEEE} Journal of Selected Topics in Applied Earth Observations and Remote Sensing},\n\tauthor = {Rousseeuw, K. and Caillault, É Poisson and Lefebvre, A. and Hamad, D.},\n\tdate = {2015-01},\n\tnote = {Number: 1},\n\tkeywords = {Monitoring, France, Clustering algorithms, oceanographic techniques, remote sensing, Boulogne-sur-Mer, Databases, environmental monitoring (geophysics), hidden Markov models, Hidden Markov models, hybrid hidden Markov model, Hybrid hidden Markov model ({HMM}), {MAREL}-Carnot station database, marine environment monitoring, marine water monitoring, microorganisms, phytoplankton blooms, phytoplankton dynamics, Remote sensing, Sensors, spectral clustering, spectral clustering algorithm, Support vector machines, water quality}\n}\n\n","author_short":["Rousseeuw, K.","Caillault, É P.","Lefebvre, A.","Hamad, D."],"key":"rousseeuw_hybrid_2015","id":"rousseeuw_hybrid_2015","bibbaseid":"rousseeuw-caillault-lefebvre-hamad-hybridhiddenmarkovmodelformarineenvironmentmonitoring","role":"author","urls":{},"keyword":["Monitoring","France","Clustering algorithms","oceanographic techniques","remote sensing","Boulogne-sur-Mer","Databases","environmental monitoring (geophysics)","hidden Markov models","Hidden Markov models","hybrid hidden Markov model","Hybrid hidden Markov model (HMM)","MAREL-Carnot station database","marine environment monitoring","marine water monitoring","microorganisms","phytoplankton blooms","phytoplankton dynamics","Remote sensing","Sensors","spectral clustering","spectral clustering algorithm","Support vector machines","water quality"],"downloads":0,"html":""},"bibtype":"article","biburl":"https://cloud.ifremer.fr/index.php/s/N5RUrxe0NmktYhq/download","creationDate":"2021-02-02T15:18:06.008Z","downloads":0,"keywords":["monitoring","france","clustering algorithms","oceanographic techniques","remote sensing","boulogne-sur-mer","databases","environmental monitoring (geophysics)","hidden markov models","hidden markov models","hybrid hidden markov model","hybrid hidden markov model (hmm)","marel-carnot station database","marine environment monitoring","marine water monitoring","microorganisms","phytoplankton blooms","phytoplankton dynamics","remote sensing","sensors","spectral clustering","spectral clustering algorithm","support vector machines","water quality"],"search_terms":["hybrid","hidden","markov","model","marine","environment","monitoring","rousseeuw","caillault","lefebvre","hamad"],"title":"Hybrid Hidden Markov Model for Marine Environment Monitoring","year":null,"dataSources":["HRywGBFdy4ALvsWmW"]}