Airborne pollen grain detection from partially labelled data utilising semi-supervised learning.

Airborne pollen monitoring has been conducted for more than a century now, as knowledge of the quantity and periodicity of airborne pollen has diverse use cases, like reconstructing historic climates and tracking current climate change, forensic applications, and up to warning those affected by pollen-induced respiratory allergies. Hence, related work on automation of pollen classification already exists. In contrast, detection of pollen is still conducted manually, and it is the gold standard for accuracy. So, here we used a new-generation, automated, near-real-time pollen monitoring sampler, the BAA500, and we used data consisting of both raw and synthesised microscope images. Apart from the automatically generated, commercially-labelled data of all pollen taxa, we additionally used manual corrections to the pollen taxa, as well as a manually created test set of bounding boxes and pollen taxa, so as to more accurately evaluate the real-life performance. For the pollen detection, we employed two-stage deep neural network object detectors. We explored a semi-supervised training scheme to remedy the partial labelling. Using a teacher-student approach, the model can add pseudo-labels to complete the labelling during training. To evaluate the performance of our deep learning algorithms and to compare them to the commercial algorithm of the BAA500, we created a manual test set, in which an expert aerobiologist corrected automatically annotated labels. For the novel manual test set, both the supervised and semi-supervised approaches clearly outperform the commercial algorithm with an F1 score of up to 76.9 % compared to 61.3 %. On an automatically created and partially labelled test dataset, we obtain a maximum mAP of 92.7 %. Additional experiments on raw microscope images show comparable performance for the best models, which potentially justifies reducing the complexity of the image generation process. Our results bring automatic pollen monitoring a step forward, as they close the gap in pollen detection performance between manual and automated procedure.

Towards automatic airborne pollen monitoring: From commercial devices to operational by mitigating class-imbalance in a deep learning approach.

Allergic diseases have been the epidemic of the century among chronic diseases. Particularly for pollen allergies, and in the context of climate change, as airborne pollen seasons have been shifting earlier and abundances have been becoming higher, pollen monitoring plays an important role in generating high-risk allergy alerts. However, this task requires labour-intensive and time-consuming manual classification via optical microscopy. Even new-generation, automatic, monitoring devices require manual pollen labelling to increase accuracy and to advance to genuinely operational devices. Deep Learning-based models have the potential to increase the accuracy of automated pollen monitoring systems. In the current research, transfer learning-based convolutional neural networks were employed to classify pollen grains from microscopic images. Given a high imbalance in the dataset, we incorporated class weighted loss, focal loss and weight vector normalisation for class balancing as well as data augmentation and weight penalties for regularisation. Airborne pollen has been routinely recorded by a Bio-Aerosol Analyzer (BAA500, Hund GmbH) located in Augsburg, Germany. Here we utilised a database referring to manually classified airborne pollen images of the whole pollen diversity throughout an annual pollen season. By using the cropped pollen images collected by this device, we achieved an unweighted average F1 score of 93.8% across 15 classes and an unweighted average F1 score of 75.9% across 31 classes. The majority of taxa (9 of 15), being also the most abundant and allergenic, showed a recall of at least 95%, reaching up to a remarkable 100% in pollen from Taxus and Urticaceae. The recent introduction of novel pollen monitoring devices worldwide has pointed to the necessity for real-time, automatic measurements of airborne pollen and fungal spores. Thus, we may improve everyday clinical practice and achieve the most efficient prophylaxis of allergic patients.

Typical vs. atypical: Combining auditory Gestalt perception and acoustic analysis of early vocalisations in Rett syndrome.

BACKGROUND: Early speech-language development of individuals with Rett syndrome (RTT) has been repeatedly characterised by a co-occurrence of apparently typical and atypical vocalisations. AIMS: To describe specific features of this intermittent character of typical versus atypical early RTT-associated vocalisations by combining auditory Gestalt perception and acoustic vocalisation analysis. METHODS AND PROCEDURES: We extracted N = 363 (pre-)linguistic vocalisations from home video recordings of an infant later diagnosed with RTT. In a listening experiment, all vocalisations were assessed for (a)typicality by five experts on early human development. Listeners' auditory concepts of (a)typicality were investigated in context of a comprehensive set of acoustic time-, spectral- and/or energy-related higher-order features extracted from the vocalisations. OUTCOMES AND RESULTS: More than half of the vocalisations were rated as 'atypical' by at least one listener. Atypicality was mainly related to the auditory attribute 'timbre', and to prosodic, spectral, and voice quality features in the acoustic domain. CONCLUSIONS AND IMPLICATIONS: Knowledge gained in our study shall contribute to the generation of an objective model of early vocalisation atypicality. Such a model might be used for increasing caregivers' and healthcare professionals' sensitivity to identify atypical vocalisation patterns, or even for a probabilistic approach to automatically detect RTT based on early vocalisations.