Automated Classification of Airborne Pollen using Neural Networks

Schiele, J.; Rabe, Fabian; Schmitt, Maximilian; Glaser, Manuel; Häring, Franziska; Brunner, Jens O.; Bauer, Bernhard; Schuller, Björn; Traidl‐Hoffmann, Claudia; Damialis, Athanasios

doi:10.1109/embc.2019.8856910

Cited by 12 publications

(7 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, it is worth pointing out that the predictive models presented in this study are based on data provided by an innovative fully automated pollen monitor, which, being a novel device, is still undergoing improvements. Although the pollen monitoring has been reported to show a high accuracy of pollen determination (Oteros et al 2015), it has been documented already that a further improvement of the recognition algorithm is possible and that, consequently, there is still a lot of room for increasing the accuracy of pollen identification in near future (Schiele et al 2019). Therefore, we conclude that the key for reliable, shortterm pollen predictions, does not necessarily lie on the complexity and how sophisticated the applied statistical techniques are, but on the completeness of the toolkit used toward this purpose, as suggested below:…”

Section: Discussionmentioning

confidence: 99%

Forecasting Betula and Poaceae airborne pollen concentrations on a 3-hourly resolution in Augsburg, Germany: toward automatically generated, real-time predictions

et al. 2021

Self Cite

View full text Add to dashboard Cite

Airborne allergenic pollen impact the health of a great part of the global population. Under climate change conditions, the abundance of airborne pollen has been rising dramatically and so is the effect on sensitized individuals. The first line of allergy management is allergen avoidance, which, to date, is by rule achieved via forecasting of daily pollen concentrations. The aim of this study was to elaborate on 3-hourly predictive models, one of the very few to the best of our knowledge, attempting to forecast pollen concentration based on near-real-time automatic pollen measurements. The study was conducted in Augsburg, Germany, during four years (2016–2019) focusing on Betula and Poaceae pollen, the most abundant and allergenic in temperate climates. ARIMA and dynamic regression models were employed, as well as machine learning techniques, viz. artificial neural networks and neural network autoregression models. Air temperature, relative humidity, precipitation, air pressure, sunshine duration, diffuse radiation, and wind speed were additionally considered for the development of the models. It was found that air temperature and precipitation were the most significant variables for the prediction of airborne pollen concentrations. At such fine temporal resolution, our forecasting models performed well showing their ability to explain most of the variability of pollen concentrations for both taxa. However, predictive power of Betula forecasting model was higher achieving R2 up to 0.62, whereas Poaceae up to 0.55. Neural autoregression was superior in forecasting Betula pollen concentrations, whereas, for Poaceae, seasonal ARIMA performed best. The good performance of seasonal ARIMA in describing variability of pollen concentrations of both examined taxa suggests an important role of plants’ phenology in observed pollen abundance. The present study provides novel insight on per-hour forecasts to be used in real-time mobile apps by pollen allergic patients. Despite the huge need for real-time, short-term predictions for everyday clinical practice, extreme weather events, like in the year 2019 in our case, still comprise an obstacle toward highly performing forecasts at such fine timescales, highlighting that there is still a way to go to this direction.

show abstract

Section: Discussionmentioning

confidence: 99%

Forecasting Betula and Poaceae airborne pollen concentrations on a 3-hourly resolution in Augsburg, Germany: toward automatically generated, real-time predictions

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…Likewise, when it comes to identifying other bioaerosol types, namely fungal spores, the automatic system seems unable to perform efficiently. One of the main reasons seems to be that already highlighted by Schiele et al [ 42 ], viz. the cropping technique of acquired images is not accurate: cropping areas for image recognition are considered de facto to be round, so as to be efficient for the identification of the mostly round pollen grains, but then this filter is definitely not true for many other particles, including fungal spores, or deformed or broken pollen.…”

Section: Discussionmentioning

confidence: 99%

Detecting Airborne Pollen Using an Automatic, Real-Time Monitoring System: Evidence from Two Sites

Plaza

Kolek

Leier-Wirtz

et al. 2022

IJERPH

Self Cite

View full text Add to dashboard Cite

Airborne pollen monitoring has been an arduous task, making ecological applications and allergy management virtually disconnected from everyday practice. Over the last decade, intensive research has been conducted worldwide to automate this task and to obtain real-time measurements. The aim of this study was to evaluate such an automated biomonitoring system vs. the conventional ‘gold-standard’ Hirst-type technique, attempting to assess which may more accurately provide the genuine exposure to airborne pollen. Airborne pollen was monitored in Augsburg since 2015 with two different methods, a novel automatic Bio-Aerosol Analyser, and with the conventional 7-day recording Hirst-type volumetric trap, in two different sites. The reliability, performance, accuracy, and comparability of the BAA500 Pollen Monitor (PoMo) vs. the conventional device were investigated, by use of approximately 2.5 million particles sampled during the study period. The observations made by the automated PoMo showed an average accuracy of approximately 85%. However, it also exhibited reliability problems, with information gaps within the main pollen season of between 17 to 19 days. The PoMo automated algorithm had identification issues, mainly confusing the taxa of Populus, Salix and Tilia. Hirst-type measurements consistently exhibited lower pollen abundances (median of annual pollen integral: 2080), however, seasonal traits were more comparable, with the PoMo pollen season starting slightly later (median: 3 days), peaking later (median: 5 days) but also ending later (median: 14 days). Daily pollen concentrations reported by Hirst-type traps vs. PoMo were significantly, but not closely, correlated (r = 0.53–0.55), even after manual classification. Automatic pollen monitoring has already shown signs of efficiency and accuracy, despite its young age; here it is suggested that automatic pollen monitoring systems may be more effective in capturing a larger proportion of the airborne pollen diversity. Even though reliability issues still exist, we expect that this new generation of automated bioaerosol monitoring will eventually change the aerobiological era, as known for almost 70 years now.

show abstract

“…Recent epidemiological studies have pointed toward a general increase in both the incidence and prevalence of respiratory diseases, such as allergic rhinitis (hay fever) and asthma ( 16 – 18 ). Over the last 60 years, there has been a rise in the epidemic prevalence of allergic disorders, which is expected to reach 4 billion in the 2050s ( 19 ).…”

Section: Prevalence Of Respiratory Disordersmentioning

confidence: 99%

“…The much-gained attention from the European and Mediterranean Plant Protection Organization is for the alien, invasive, and noxious plant species Ambrosia artemisiifolia L. (common ragweed) with a highly allergenic pollen ( 18 ). Ragweed, a native of North America, has been invading large areas of South America and Europe for the last few decades and has been identified as a major contributor to severe respiratory allergy diseases.…”

Section: Climate Change and Pollutants Affecting The Allergenicity Of...mentioning

confidence: 99%

Climate change and allergic diseases: An overview

Singh

Kumar

2022

Front. Allergy

View full text Add to dashboard Cite

Climate change has been regarded as a threat to the human species on the earth. Greenhouse gasses are leading to increased temperatures on Earth besides impacting the humanity. These atmospheric conditions have shown to alter the release pattern of pollens and can change the timing and magnitude of pollen release with flowering plants. As pollen is responsible for respiratory allergies in humans, so climate change can adversely affect human health in susceptible individuals. In this review, we highlight the association between climate change, increased prevalence and severity of asthma, and related allergic diseases. Increased air pollution can alter the production of local and regional pollen. This altered pattern depends on bioclimatic parameters. As simulated with a pollen-release model and future bioclimatic data, warmer temperatures lead to an increased pollen count in some specific locations and for longer periods. Thus, anticipation of a future allergic disease burden can help public health agencies in planning to develop strategies in mitigating the unprecedented health challenges expected in future years.

show abstract

Automated Classification of Airborne Pollen using Neural Networks

Cited by 12 publications

References 14 publications

Forecasting Betula and Poaceae airborne pollen concentrations on a 3-hourly resolution in Augsburg, Germany: toward automatically generated, real-time predictions

Forecasting Betula and Poaceae airborne pollen concentrations on a 3-hourly resolution in Augsburg, Germany: toward automatically generated, real-time predictions

Detecting Airborne Pollen Using an Automatic, Real-Time Monitoring System: Evidence from Two Sites

Climate change and allergic diseases: An overview

Contact Info

Product

Resources

About