Luminita Marmureanu - Academia.edu (original) (raw)

Uploads

Papers by Luminita Marmureanu

International Multidisciplinary Scientific GeoConference SGEM .., Jun 20, 2011

Pollen allergies are a growing concern for human health. This is why automated pollen monitoring ... more Pollen allergies are a growing concern for human health. This is why automated pollen monitoring is becoming an important area of research. Machine learning approaches show great promise for tackling this issue but these algorithms need large training data sets to perform well. This study introduces a new pollen data set, obtained using a Rapid-E particle analyzer, that is representative for the flora of Romania. Pollen, from thirteen species present in Romania, was used in developing this database with over 100 thousand samples measured. Our study shows performance similar to or above that of humans in the task of pollen classification on the newly introduced data set using a convolutional neural network.

Applied sciences, Dec 9, 2021

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

HAL (Le Centre pour la Communication Scientifique Directe), Aug 25, 2019

Atmospheric Environment, Mar 1, 2023

HAL (Le Centre pour la Communication Scientifique Directe), May 18, 2020

HAL (Le Centre pour la Communication Scientifique Directe), Apr 8, 2018

International audienc

Epj Web of Conferences, 2018

The purpose of the study is to analyze the seasonal variability, for the hot and cold seasons, of... more The purpose of the study is to analyze the seasonal variability, for the hot and cold seasons, of biomass burning aerosol observed over Romania using forward dispersion calculations based on FLEXPART model. The model was set up to use as input the MODIS fire data with a degree of confidence over 25% after transforming the emitted power in emission rate. The modelled aerosols in this setup was black carbon coated by organics. Distribution in the upper layers were compared to Calipso retrieval.

Physica D: Nonlinear Phenomena, May 1, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

EGU General Assembly Conference Abstracts, Apr 1, 2015

Sistemele Lidar de fluorescenţă sunt tehnici des utilizate în monitorizarea poluării din mediul a... more Sistemele Lidar de fluorescenţă sunt tehnici des utilizate în monitorizarea poluării din mediul acvatic, bazându-se pe identificarea semnăturii de fluorescenţă specifică fiecărui component. Principalul scop al acestei lucrări este de a analiza petele de petrol detectate în campania experimentală din august 2007 în zona românească a Mării Negre. Sunt analizate metodele de procesare prin regresie liniară şi prin relaţionare a canalelor, precum şi prin reţelele neuronale artificiale. S-a observat că pentru analiza distribuţiei de contaminanţi petrolieri de-a lungul unei traiectorii, cele mai potrivite metode sunt cea a relaţionării canalelor şi cea prin regresie liniară. Pentru determinarea tipului de petrol cea mai potrivită este reţeaua neuronală artificială. Fluorescence LIDAR is a useful tool in water pollution monitoring, based on the fluorescence signature of each contaminant. The main goal of this study is to analyze the oil spills detected in late 2007 summer campaign on the Romanian side of Black Sea. Artificial neural network (ANN), linear regression and channels relationship (CRM) methods are evaluated in order to identify the best option for oil spills detection and characterization. It was found that linear regression or channels relationship are suitable to use in order to reveal the distribution of oils on a sea path while ANN is suitable for identifying the type of oils.

Zenodo (CERN European Organization for Nuclear Research), Apr 1, 2017

DIGITAL.CSIC (Spanish National Research Council (CSIC)), May 18, 2020

Europe's ambient air quality is slowly improving, but fine particulate matter and nitrogen dioxid... more Europe's ambient air quality is slowly improving, but fine particulate matter and nitrogen dioxide in particular continue to cause serious impacts on health. Recent estimates point to more than 400.000 premature deaths in the EU each year (EEA, 2019). Air pollution remains the largest environmental health burden in Europe.

Pollen allergies are a cause of much suffering in an increasing number of individuals. Current po... more Pollen allergies are a cause of much suffering in an increasing number of individuals. Current pollen monitoring techniques are lacking due to their reliance on manual counting of pollen by human technicians. In this study, we present a neural network architecture capable of distinguishing pollen species using data from an automated particle measurement device. This study presents an improvement over the current state-of-the-art in the task of automated pollen classification using the fluorescence spectrum of aerosol particles.

Environmental Engineering and Management Journal, 2017

This study analyses the relationship between the scattering properties and the chemical compounds... more This study analyses the relationship between the scattering properties and the chemical compounds internal mixture of the aerosols near Bucharest, Romania. Several cases of local aerosols influenced by heating sources, like wood or fossil fuel, are characterized in order to retrieve the winter period specificity. Correlation between organic and inorganic aerosols composition from mass spectrometry measurements made with Compact Time (CT) of Flight Aerosol Mass Spectrometer (AMS) and scattering coefficient derived from Nephelometer measurements is highlighted. The scattering coefficient tendency can be assigned to some of the chemical components of the aerosols, exploiting the correlation coefficient with some fragments during the measurements period. High concentrations of organic markers specific for CO2 fragment (m/z 44) indicate the presence of oxygenated organic aerosols with low volatility. The aerosols aging process is emphasized by ratio between markers with different degrees of oxidation, as f44 and f43 (high oxidized marker, m/z 44 to total signal and low oxidized marker m/z 43 to total signal). Lower values are characteristic for the beginning of February and higher at the end of February and beginning of March. During winter, several aerosol sources were present, the m/z 57 marker being related to traffic. Strong correlations were revealed between m/z 43, 60 and 73 and the scattering coefficient.

Environmental Engineering and Management Journal, 2013

This study focuses on the local scale behavior of SO 2 emissions resulting from lignite-combustio... more This study focuses on the local scale behavior of SO 2 emissions resulting from lignite-combustion thermal power plants. The investigations aimed at monitoring the SO 2 emissions and imissions over a two week period in September 2010. One of the largest power plants from Eastern Europe was chosen for monitoring using different optoelectronic techniques. Rovinari power plant (44 o 54'45"N-23 o 09'44"E) is one of the largest electricity suppliers of Romania, having 4 groups of 330 MW each, with a total installed capacity of 1420 MW and is located in the Rovinari-Motru coal mining area This power plant along with similar facilities located in southwest of Romania is responsible for local and regional pollution problems concerning acid rain, formation of fine particulate matter, smog etc. Emissions from the stacks of Rovinari power plant were monitored with a UV camera that uses the strong absorption of SO 2 molecules between 280-320 nm. Images with UV camera were collected from distances ranging between 1 and 2 km. Immisions measurements were made simultaneously with a HORIBA SO 2 analyzer for continuous monitoring of atmospheric SO 2 imissions using UV fluorescence method. Within the two weeks of measurements the SO 2 immisions hourly limit of 350 μg/m 3 was exceeded two times, the highest measured concentration of 590 μg/m 3 occurring during stable meteorological conditions (very low wind speeds) inhibiting dispersion and favoring the accumulation of SO 2 on a local scale. At the stacks, SO 2 concentrations were constantly over 1000 ppm * m during the analyzed days.

International Multidisciplinary Scientific GeoConference SGEM .., Jun 20, 2011

Pollen allergies are a growing concern for human health. This is why automated pollen monitoring ... more Pollen allergies are a growing concern for human health. This is why automated pollen monitoring is becoming an important area of research. Machine learning approaches show great promise for tackling this issue but these algorithms need large training data sets to perform well. This study introduces a new pollen data set, obtained using a Rapid-E particle analyzer, that is representative for the flora of Romania. Pollen, from thirteen species present in Romania, was used in developing this database with over 100 thousand samples measured. Our study shows performance similar to or above that of humans in the task of pollen classification on the newly introduced data set using a convolutional neural network.

Applied sciences, Dec 9, 2021

This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY

HAL (Le Centre pour la Communication Scientifique Directe), Aug 25, 2019

Atmospheric Environment, Mar 1, 2023

HAL (Le Centre pour la Communication Scientifique Directe), May 18, 2020

HAL (Le Centre pour la Communication Scientifique Directe), Apr 8, 2018

International audienc

Epj Web of Conferences, 2018

The purpose of the study is to analyze the seasonal variability, for the hot and cold seasons, of... more The purpose of the study is to analyze the seasonal variability, for the hot and cold seasons, of biomass burning aerosol observed over Romania using forward dispersion calculations based on FLEXPART model. The model was set up to use as input the MODIS fire data with a degree of confidence over 25% after transforming the emitted power in emission rate. The modelled aerosols in this setup was black carbon coated by organics. Distribution in the upper layers were compared to Calipso retrieval.

Physica D: Nonlinear Phenomena, May 1, 2020

This is a PDF file of an article that has undergone enhancements after acceptance, such as the ad... more This is a PDF file of an article that has undergone enhancements after acceptance, such as the addition of a cover page and metadata, and formatting for readability, but it is not yet the definitive version of record. This version will undergo additional copyediting, typesetting and review before it is published in its final form, but we are providing this version to give early visibility of the article. Please note that, during the production process, errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

EGU General Assembly Conference Abstracts, Apr 1, 2015

Sistemele Lidar de fluorescenţă sunt tehnici des utilizate în monitorizarea poluării din mediul a... more Sistemele Lidar de fluorescenţă sunt tehnici des utilizate în monitorizarea poluării din mediul acvatic, bazându-se pe identificarea semnăturii de fluorescenţă specifică fiecărui component. Principalul scop al acestei lucrări este de a analiza petele de petrol detectate în campania experimentală din august 2007 în zona românească a Mării Negre. Sunt analizate metodele de procesare prin regresie liniară şi prin relaţionare a canalelor, precum şi prin reţelele neuronale artificiale. S-a observat că pentru analiza distribuţiei de contaminanţi petrolieri de-a lungul unei traiectorii, cele mai potrivite metode sunt cea a relaţionării canalelor şi cea prin regresie liniară. Pentru determinarea tipului de petrol cea mai potrivită este reţeaua neuronală artificială. Fluorescence LIDAR is a useful tool in water pollution monitoring, based on the fluorescence signature of each contaminant. The main goal of this study is to analyze the oil spills detected in late 2007 summer campaign on the Romanian side of Black Sea. Artificial neural network (ANN), linear regression and channels relationship (CRM) methods are evaluated in order to identify the best option for oil spills detection and characterization. It was found that linear regression or channels relationship are suitable to use in order to reveal the distribution of oils on a sea path while ANN is suitable for identifying the type of oils.

Zenodo (CERN European Organization for Nuclear Research), Apr 1, 2017

DIGITAL.CSIC (Spanish National Research Council (CSIC)), May 18, 2020

Europe's ambient air quality is slowly improving, but fine particulate matter and nitrogen dioxid... more Europe's ambient air quality is slowly improving, but fine particulate matter and nitrogen dioxide in particular continue to cause serious impacts on health. Recent estimates point to more than 400.000 premature deaths in the EU each year (EEA, 2019). Air pollution remains the largest environmental health burden in Europe.

Pollen allergies are a cause of much suffering in an increasing number of individuals. Current po... more Pollen allergies are a cause of much suffering in an increasing number of individuals. Current pollen monitoring techniques are lacking due to their reliance on manual counting of pollen by human technicians. In this study, we present a neural network architecture capable of distinguishing pollen species using data from an automated particle measurement device. This study presents an improvement over the current state-of-the-art in the task of automated pollen classification using the fluorescence spectrum of aerosol particles.

Environmental Engineering and Management Journal, 2017

This study analyses the relationship between the scattering properties and the chemical compounds... more This study analyses the relationship between the scattering properties and the chemical compounds internal mixture of the aerosols near Bucharest, Romania. Several cases of local aerosols influenced by heating sources, like wood or fossil fuel, are characterized in order to retrieve the winter period specificity. Correlation between organic and inorganic aerosols composition from mass spectrometry measurements made with Compact Time (CT) of Flight Aerosol Mass Spectrometer (AMS) and scattering coefficient derived from Nephelometer measurements is highlighted. The scattering coefficient tendency can be assigned to some of the chemical components of the aerosols, exploiting the correlation coefficient with some fragments during the measurements period. High concentrations of organic markers specific for CO2 fragment (m/z 44) indicate the presence of oxygenated organic aerosols with low volatility. The aerosols aging process is emphasized by ratio between markers with different degrees of oxidation, as f44 and f43 (high oxidized marker, m/z 44 to total signal and low oxidized marker m/z 43 to total signal). Lower values are characteristic for the beginning of February and higher at the end of February and beginning of March. During winter, several aerosol sources were present, the m/z 57 marker being related to traffic. Strong correlations were revealed between m/z 43, 60 and 73 and the scattering coefficient.

Environmental Engineering and Management Journal, 2013

This study focuses on the local scale behavior of SO 2 emissions resulting from lignite-combustio... more This study focuses on the local scale behavior of SO 2 emissions resulting from lignite-combustion thermal power plants. The investigations aimed at monitoring the SO 2 emissions and imissions over a two week period in September 2010. One of the largest power plants from Eastern Europe was chosen for monitoring using different optoelectronic techniques. Rovinari power plant (44 o 54'45"N-23 o 09'44"E) is one of the largest electricity suppliers of Romania, having 4 groups of 330 MW each, with a total installed capacity of 1420 MW and is located in the Rovinari-Motru coal mining area This power plant along with similar facilities located in southwest of Romania is responsible for local and regional pollution problems concerning acid rain, formation of fine particulate matter, smog etc. Emissions from the stacks of Rovinari power plant were monitored with a UV camera that uses the strong absorption of SO 2 molecules between 280-320 nm. Images with UV camera were collected from distances ranging between 1 and 2 km. Immisions measurements were made simultaneously with a HORIBA SO 2 analyzer for continuous monitoring of atmospheric SO 2 imissions using UV fluorescence method. Within the two weeks of measurements the SO 2 immisions hourly limit of 350 μg/m 3 was exceeded two times, the highest measured concentration of 590 μg/m 3 occurring during stable meteorological conditions (very low wind speeds) inhibiting dispersion and favoring the accumulation of SO 2 on a local scale. At the stacks, SO 2 concentrations were constantly over 1000 ppm * m during the analyzed days.