scholarly journals Application of decision tree algorithms for discriminating among woody plant taxa based on the pollen season characteristics

2015 ◽  
Vol 67 (4) ◽  
pp. 1127-1135 ◽  
Author(s):  
Agnieszka Kubik-Komar ◽  
Elżbieta Kubera ◽  
Krystyna Piotrowska-Weryszko ◽  
Elżbieta Weryszko-Chmielewska
Keyword(s):  
Decision Tree ◽  
Pollen Season ◽  
Airborne Pollen ◽  
Classification Tree ◽  
Pollen Grains ◽  
Pollen Concentration ◽  
Pollen Types ◽  
Tree Algorithms ◽  
Atmospheric Pollen ◽  
Parameter Ranges

The aim of this study was to verify whether and which parameters of the atmospheric pollen season can distinguish between pollen types, the ranges of parameter values that delineate classes of taxa, and finally which taxa are similar to others within the domain of these parameter ranges. Decision tree algorithms were applied and the best tree was chosen to describe the rules of pollen classification. The study material consisted of airborne pollen grains of the following eight taxa: Alnus, Betula, Carpinus, Corylus, Cupressaceae, Fraxinus, Populus and Ulmus. Research was conducted in Lublin in eastern Poland during 2001-2013. The following six atmospheric pollen season parameters were analyzed: season start and end, duration, maximum daily pollen concentration, date of maximum pollen concentration, and the Seasonal Pollen Index (SPI). Four algorithms were used in data analysis and the J4.8 algorithm was chosen as the best for taxa classification, date of the end of season and the SPI value belonging to characteristics that served most to discriminate between pollen types. Based on the classification tree, the following four groups of taxa were identified: (i) Ulmus; (ii) Corylus, Alnus, Populus; (iii) Betula; and (iv) Carpinus, Fraxinus, Cupressaceae.

scholarly journals The late flowering of invasive species contributes to the increase of Artemisia allergenic pollen in autumn: an analysis of 25 years of aerobiological data (1995–2019) in Trentino-Alto Adige (Northern Italy)

Aerobiologia ◽  
2020 ◽  
Vol 36 (4) ◽  
pp. 669-682 ◽  
Author(s):  
Antonella Cristofori ◽  
Edith Bucher ◽  
Michele Rossi ◽  
Fabiana Cristofolini ◽  
Veronika Kofler ◽  
...  
Keyword(s):  
Invasive Species ◽  
Pollen Season ◽  
Airborne Pollen ◽  
Pollen Grains ◽  
Late Summer ◽  
Natura 2000 ◽  
Allergenic Pollen ◽  
Pollen Concentration ◽  
Pollen Concentrations ◽  
Negative Impacts

AbstractArtemisia pollen is an important aeroallergen in late summer, especially in central and eastern Europe where distinct anemophilous Artemisia spp. produce high amounts of pollen grains. The study aims at: (i) analyzing the temporal pattern of and changes in the Artemisia spp. pollen season; (ii) identifying the Artemisia species responsible for the local airborne pollen load.Daily pollen concentration of Artemisia spp. was analyzed at two sites (BZ and SM) in Trentino-Alto Adige, North Italy, from 1995 to 2019.The analysis of airborne Artemisia pollen concentrations evidences the presence of a bimodal curve, with two peaks, in August and September, respectively. The magnitude of peak concentrations varies across the studied time span for both sites: the maximum concentration at the September peak increases significantly for both the BZ (p < 0.05) and SM (p < 0.001) site. The first peak in the pollen calendar is attributable to native Artemisia species, with A. vulgaris as the most abundant; the second peak is mostly represented by the invasive species A. annua and A. verlotiorum (in constant proportion along the years), which are causing a considerable increase in pollen concentration in the late pollen season in recent years.. The spread of these species can affect human health, increasing the length and severity of allergenic pollen exposure in autumn, as well as plant biodiversity in both natural and cultivated areas, with negative impacts on, e.g., Natura 2000 protected sites and crops.

scholarly journals Flowering Phenology of Selected Linden (Tilia L.) Taxa in Relation to Pollen Seasons

2016 ◽  
Vol 60 (2) ◽  
pp. 193-208
Author(s):  
Agnieszka Dąbrowska ◽  
Krystyna Piotrowska-Weryszko ◽  
Elżbieta Weryszko-Chmielewska ◽  
Ryszard Sawicki
Keyword(s):  
Pollen Season ◽  
Airborne Pollen ◽  
Average Length ◽  
Pollen Grains ◽  
Flowering Phenology ◽  
Flowering Period ◽  
Growing Seasons ◽  
Time Period ◽  
Relative Air Humidity ◽  
Atmospheric Pollen

Abstract All lindens provide Apidae insects with nectar, pollen, and honeydew. Lindens are important melliferous trees in Poland. The first purpose of the study was to carry out phenological observations of the flowering in ten linden taxa. The second aim was to analyse the content of linden pollen grains in the air of Lublin. A correlation between the parameters of the pollen season and meteorological factors was also determined. This study was conducted in the city of Lublin located in the central-eastern part of Poland. The flowering phenophases were analysed, using the method developed by Łukasiewicz, during the growing seasons of 2012-2015. Aerobiological monitoring, which was based on the volumetric method, was carried out over the 2001-2014 time period. As shown in the study, the flowering period of all the analysed linden taxa lasted 7 weeks, on average, from June 7 to July 24. The average length of the flowering period of the investigated taxa and hybrids was in the range of 12-17 days. Their flowering periods overlapped. The atmospheric pollen season lasted, on average, from mid-June to the second 10-day period of July. The highest concentration of airborne pollen was noted at the end of June. The pollen season pattern was significantly affected by temperature and relative air humidity as well as by rainfall in May and June. The investigations indicate a 9-day acceleration of the pollen season, which may be associated with global warming.

scholarly journals Airborne pollen observations using a multi-wavelength Raman polarization lidar in Finland: characterization of pure pollen types

2020 ◽  
Author(s):  
Xiaoxia Shang ◽  
Elina Giannakaki ◽  
Stephanie Bohlmann ◽  
Maria Filioglou ◽  
Annika Saarto ◽  
...  
Keyword(s):  
Optical Properties ◽  
Airborne Pollen ◽  
Pollen Grains ◽  
Wavelength Dependence ◽  
Depolarization Ratio ◽  
Mean Values ◽  
Pollen Types ◽  
Pine Pollen ◽  
Significant Wavelength ◽  
532 Nm

Abstract. We present a novel algorithm for characterizing the optical properties of pure pollen particles, based on the depolarization values obtained in lidar measurements. The algorithm was first tested and validated through a simulator, and then applied to the lidar observations during a four-month pollen campaign from May to August 2016 at the European Aerosol Research Lidar Network (EARLINET) station in Kuopio (62°44′ N, 27°33′ E), in Eastern Finland. Twenty types of pollen were observed and identified from concurrent measurements with Burkard sampler; Birch (Betula), pine (Pinus), spruce (Picea) and nettle (Urtica) pollen were most abundant, contributing more than 90 % of total pollen load, regarding number concentrations. Mean values of lidar-derived optical properties in the pollen layer were retrieved for four intense pollination periods (IPPs). Lidar ratios at both 355 and 532 nm ranged from 55 to 70 sr for all pollen types, without significant wavelength-dependence. Enhanced depolarization ratio was found when there were pollen grains in the atmosphere, and even higher depolarization ratio (with mean values of 25 % or 14 %) was observed with presence of the more non-spherical spruce or pine pollen. The depolarization ratio at 532 nm of pure pollen particles was assessed, resulting to 24 ± 3 % and 36 ± 5 % for birch and pine pollen, respectively. Pollen optical properties at 1064 nm and 355 nm were also estimated. The backscatter-related Ångström exponent between 532 and 1064 nm was assessed as ~ 0.8 (~ 0.5) for pure birch (pine) pollen, thus the longer wavelength would be better choice to trace pollen in the air. The pollen depolarization ratio at 355 nm of 17 % and 30 % were found for birch and pine pollen, respectively. The depolarization values show a wavelength dependence for pollen. This can be the key parameter for pollen detection and characterization.

scholarly journals Near-Optimal Sparse Neural Trees for Supervised Learning

2021 ◽  
Author(s):  
Tanujit Chakraborty
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Decision Tree ◽  
Classification Tree ◽  
Mathematical Formulation ◽  
Machine Learning Algorithms ◽  
Optimal Decision ◽  
Feed Forward ◽  
Feed Forward Network ◽  
Tree Algorithms

Decision tree algorithms have been among the most popular algorithms for interpretable (transparent) machine learning since the early 1980s. On the other hand, deep learning methods have boosted the capacity of machine learning algorithms and are now being used for non-trivial applications in various applied domains. But training a fully-connected deep feed-forward network by gradient-descent backpropagation is slow and requires arbitrary choices regarding the number of hidden units and layers. In this paper, we propose near-optimal neural regression trees, intending to make it much faster than deep feed-forward networks and for which it is not essential to specify the number of hidden units in the hidden layers of the neural network in advance. The key idea is to construct a decision tree and then simulate the decision tree with a neural network. This work aims to build a mathematical formulation of neural trees and gain the complementary benefits of both sparse optimal decision trees and neural trees. We propose near-optimal sparse neural trees (NSNT) that is shown to be asymptotically consistent and robust in nature. Additionally, the proposed NSNT model obtain a fast rate of convergence which is near-optimal up to some logarithmic factor. We comprehensively benchmark the proposed method on a sample of 80 datasets (40 classification datasets and 40 regression datasets) from the UCI machine learning repository. We establish that the proposed method is likely to outperform the current state-of-the-art methods (random forest, XGBoost, optimal classification tree, and near-optimal nonlinear trees) for the majority of the datasets.

Seasonal pollen distribution in the atmosphere of Hobart, Tasmania: preliminary observations and congruence with flowering phenology

2010 ◽  
Vol 58 (6) ◽  
pp. 440 ◽  
Author(s):  
D. Y. P. Tng ◽  
F. Hopf ◽  
S. G. Haberle ◽  
D. M. J. S. Bowman
Keyword(s):  
Native Plants ◽  
Airborne Pollen ◽  
Flowering Phenology ◽  
Sampling Location ◽  
Minor Role ◽  
Sampling Effort ◽  
Pollen Load ◽  
Flowering Duration ◽  
Pollen Types ◽  
Atmospheric Pollen

The atmospheric pollen loads of Hobart, Tasmania, Australia, were monitored between September 2007 and July 2009. To examine the match of the airborne pollen composition with the flowering duration of their contributing plants, the phenology of native and non-native plants in various habitats near the pollen-trapping site was undertaken between August 2008 and July 2009. The pollen load was found to have a strong seasonal component associated with the start of spring in September. This is incongruent with the peak flowering season of the total taxa in October. In most taxa, atmospheric pollen signatures appeared before flowering was observed in the field. The presence of most pollen types in the atmosphere also exceeded the observed flowering duration of potential pollen-source taxa. Reasons for this may be related to the sampling effort of phenological monitoring, pollen blown in from earlier flowering populations outside of the sampling area, the ability of pollen to be reworked, and the large pollen production of some wind-pollinated taxa. In 2007–2008, 15 pollen types dominated the atmosphere, accounting for 90% of the airborne pollen load. The top six pollen types belonged to Betula, Cupressaceae, Myrtaceae, Salix, Poaceae and Ulmus. Comparatively, the annual pollen load of Hobart is lower than in most other Australian cities; however, the pollen signal of Betula is inordinately high. Native plants play a minor role as pollen contributors, despite the proximity of native habitats to the pollen-sampling location. The implications of the aerobiological observations are discussed in relation to public health.

scholarly journals Oak pollen concentration in the air of selected Polish cities in 2020

Alergoprofil ◽  
2020 ◽  
Vol 16 (4) ◽  
pp. 15-20
Author(s):  
Anna Rapiejko ◽  
Małgorzata Malkiewicz ◽  
Monika Ziemianin ◽  
Aneta Sulborska ◽  
Kazimiera Chłopek ◽  
...  
Keyword(s):  
Pollen Season ◽  
Pollen Grains ◽  
Volumetric Method ◽  
Pollen Concentration ◽  
Total Catch ◽  
Pollen Concentrations ◽  
Oak Pollen ◽  
Annual Total ◽  
High Concentrations

The study aims to compare the oak pollen season in selected Polish cities; Bialystok, Bydgoszcz, Cracow, Katowice, Piotrkow Trybunalski, Lublin, Olsztyn, Opole, Szczecin, Warsaw, and Wroclaw in 2020. Measurements were made using the volumetric method, with a Hirst-type sampler. Oak pollen season, defined as the period with 98% of the annual total catch, started between 14 (in Opole) and 25 April (in Lublin). The season ended on 1 June at the latest;  in Sosnowiec, Bydgoszcz, Olsztyn, and Bialystok. It lasted from 30 to 47 days  (37 days on average). The maximum daily oak pollen concentrations were observed between 24 April and 11 May. The highest annual sum of oak pollen grains (SPI) was recorded in Lublin, while the lowest in Bialystok. The highest concentrations of 596 oak pollen grains/m3 were noted in Lublin on 28 April. The longest exposure to high concentrations of oak pollen (>91 grains/m3), lasting 12-13 days, was recorded in Lublin, Opole, and Wroclaw.

scholarly journals Flowering and airborne pollen - a novel statistical approach

2012 ◽  
Vol 60 (2) ◽  
pp. 51-55 ◽  
Author(s):  
Idalia Kasprzyk ◽  
Adam Walanus
Keyword(s):  
Pollen Season ◽  
Statistical Approach ◽  
Airborne Pollen ◽  
Pollen Grains ◽  
Weather Conditions ◽  
Time Pattern ◽  
Se Poland ◽  
Full Flowering ◽  
High Concentrations ◽  
Intensive Growth

The time pattern of flowering significantly affects the pollen season, its beginning, length and the concentration of pollen grains in air. The forecasting models used in aerobiological studies were chiefly based on the elements of weather conditions; however, recently the phenology of pollen shedding has been taken into consideration in these models more and more frequently. The aim of the presented investigations was to determine to what extent the flowering and the occurrence of allergenic pollen grains in air coincided in time. The investigation was carried out in Rzeszów (SE Poland) in the years 2003-2004. The flowering of 19 allergenic plant species was observed and seven phenophases were distinguished. Aerobiological monitoring was based on the volumetric method. In the case of most herbaceous plants, the flowering period overlapped the pollen season, high concentrations of pollen being recorded throughout several phenophases. In general, the pollen of trees occurred during very short periods, frequently during one phenophase, while the investigated phenomena were missing each other. The most intensive growth of inflorescences of alder, hazel and birch was observed at the beginning of full fl owering or towards the end of full flowering.

scholarly journals Decision Tree Ensemble Techniques To Predict Thyroid Disease

2019 ◽  
Vol 8 (3) ◽  
pp. 8242-8246 ◽  
Keyword(s):  
Decision Tree ◽  
Classification Tree ◽  
Real Data ◽  
Classification Algorithm ◽  
Ensemble Method ◽  
Batch Size ◽  
Classification Algorithms ◽  
Ensemble Techniques ◽  
Tree Algorithms ◽  
Experimental Values

Decision tree provides help in making decision for very complex and large dataset. Decision tree techniques are used for gathering knowledge. Classification tree algorithms predict the experimental values of women thyroid dataset. The objective of this research paper observation is to determine hyperthyroidism, hypothyroidism and euthyroidism participation in hormones can be good predictor of the final result of laboratories and to examination whether the propose ensemble approach can be similar accuracy to other single classification algorithm. In the proposed experiment real data from 499 thyroid patients were used classifications algorithms in predicting whether thyroid detected or not detected on the basis of T3, T4 and TSH experimental values. The results show that the expectation of maximization classification tree algorithms in those of the best classification algorithm especially when using only a group of selected attributes. Finally we predict batch size, tree confidential factor, min number of observation, num folds, seed, accuracy and time build model with different classes of thyroid sickness. Different classification algorithms are analyzed using thyroid dataset. The results obtained by individual classification algorithms like J48, Random Tree and Hoeffding gives accuracy 99.12%, 97.59% and 92.37 respectively. Then we developed a new ensemble method and apply again on the same dataset, which gives a better accuracy of 99.2% and sensitivity of 99.36%. This new proposed ensemble method can be used for better classification of thyroid patients.

scholarly journals Seasonal variation in diurnal atmospheric grass pollen concentration profiles

2013 ◽  
Vol 10 (9) ◽  
pp. 14627-14656 ◽  
Author(s):  
R. G. Peel ◽  
P. V. &amp;Oslash;rby ◽  
C. A. Skj&amp;oslash;th ◽  
R. Kennedy ◽  
V. Schlünssen ◽  
...  
Keyword(s):  
Grass Pollen ◽  
Pollen Season ◽  
Meteorological Factors ◽  
Time Of Day ◽  
Grass Species ◽  
Pollen Concentration ◽  
Late Season ◽  
Pollen Loads ◽  
Pollen Concentrations ◽  
Atmospheric Pollen

Abstract. In this study, the diurnal atmospheric grass pollen concentration profile within the Danish city of Aarhus was shown to change in a systematic manner as the season progressed. Although diurnal grass pollen profiles can differ greatly from day-to-day, it is common practice to establish the time of day when peak concentrations are most likely to occur using seasonally-averaged diurnal profiles. Atmospheric pollen loads are highly dependent upon emissions, and different species of grass are known to flower and emit pollen at different times of the day and during different periods of the pollen season. Pollen concentrations are also influenced by meteorological factors – directly through those parameters that govern pollen dispersion and transport, and indirectly through the weather-driven flowering process. We found that three different profiles dominated the grass pollen season in Aarhus – a twin peak profile in the early season, a single evening profile in the mid-season, and a single midday peak in the late season. Whilst this variation could not be explained by meteorological factors, no inconsistencies were found with the theory that the variation was driven by a succession of different grass species with different diurnal flowering patterns dominating atmospheric pollen loads as the season progressed. The potential for exposure was found to be significantly greater during the late season period than during either the early or mid season periods.

scholarly journals Seasonal variation in diurnal atmospheric grass pollen concentration profiles

2014 ◽  
Vol 11 (3) ◽  
pp. 821-832 ◽  
Author(s):  
R. G. Peel ◽  
P. V. Ørby ◽  
C. A. Skjøth ◽  
R. Kennedy ◽  
V. Schlünssen ◽  
...  
Keyword(s):  
Grass Pollen ◽  
Pollen Season ◽  
Meteorological Factors ◽  
Time Of Day ◽  
Grass Species ◽  
Pollen Concentration ◽  
Late Season ◽  
Pollen Loads ◽  
Pollen Concentrations ◽  
Atmospheric Pollen

Abstract. In this study, the diurnal atmospheric grass pollen concentration profile within the Danish city of Aarhus was shown to change in a systematic manner as the pollen season progressed. Although diurnal grass pollen profiles can differ greatly from day-to-day, it is common practice to establish the time of day when peak concentrations are most likely to occur using seasonally averaged diurnal profiles. Atmospheric pollen loads are highly dependent upon emissions, and different species of grass are known to flower and emit pollen at different times of the day and during different periods of the pollen season. Pollen concentrations are also influenced by meteorological factors – directly through those parameters that govern pollen dispersion and transport, and indirectly through the weather-driven flowering process. We found that three different profiles dominated the grass pollen season in Aarhus – a twin peak profile during the early season, a single evening profile during the middle of the season, and a single midday peak during the late season. Whilst this variation could not be explained by meteorological factors, no inconsistencies were found with the theory that it was driven by a succession of different grass species with different diurnal flowering patterns dominating atmospheric pollen loads as the season progressed. The potential for exposure was found to be significantly greater during the late-season period than during either the early- or mid-season periods.

Sign in / Sign up

Export Citation Format

Share Document