Refine
Document Type
- Article (2)
- Part of a Book (1)
- Doctoral Thesis (1)
- Report (1)
Is part of the Bibliography
- yes (5) (remove)
Keywords
- automation (5) (remove)
In a warming Arctic, permafrost-related disturbances, such as retrogressive thaw slumps (RTS), are becoming more abundant and dynamic, with serious implications for permafrost stability and bio-geochemical cycles on local to regional scales. Despite recent advances in the field of earth observation, many of these have remained undetected as RTS are highly dynamic, small, and scattered across the remote permafrost region. Here, we assessed the potential strengths and limitations of using deep learning for the automatic segmentation of RTS using PlanetScope satellite imagery, ArcticDEM and auxiliary datasets. We analyzed the transferability and potential for pan-Arctic upscaling and regional cross-validation, with independent training and validation regions, in six different thaw slump-affected regions in Canada and Russia. We further tested state-of-the-art model architectures (UNet, UNet++, DeepLabv3) and encoder networks to find optimal model configurations for potential upscaling to continental scales. The best deep learning models achieved mixed results from good to very good agreement in four of the six regions (maxIoU: 0.39 to 0.58; Lena River, Horton Delta, Herschel Island, Kolguev Island), while they failed in two regions (Banks Island, Tuktoyaktuk). Of the tested architectures, UNet++ performed the best. The large variance in regional performance highlights the requirement for a sufficient quantity, quality and spatial variability in the training data used for segmenting RTS across diverse permafrost landscapes, in varying environmental conditions. With our highly automated and configurable workflow, we see great potential for the transfer to active RTS clusters (e.g., Peel Plateau) and upscaling to much larger regions.
It’s personal
(2021)
The new technologies of the Fourth Industrial Revolution (4IR) are disrupting traditional models of work and learning. While the impact of digitalization on education was already a point of serious deliberation, the COVID-19 pandemic has expedited ongoing transitions. With 90% of the world’s student population having been impacted by national lockdowns—online learning has gone from being a luxury to a necessity, in a context where around 3.6 billion people are offline. As the impacts of the 4IR unfold alongside the current crisis, it is not enough for future policy pathways to prioritize educational attainment in the traditional sense; it is essential to reimagine education itself as well as its delivery entirely. Future policy narratives will need to evaluate the very process of learning and identify the ways in which technology can help reduce existing disparities and enhance digital access, literacy and fluency in a scalable manner. In this context, this chapter analyses the status quo of online learning in India and Germany. Drawing on the experiences of these two economies with distinct trajectories of digitalization, the chapter explores how new technologies intersect with traditional education and local sociocultural conditions. Further, the limitations and opportunities presented by dominant ed-tech models is critically analyzed against the ongoing COVID-19 pandemic.
We and AI
(2021)
Robotic Process Automation (RPA) steht für die softwareunterstützte Bedienung von Softwarelösungen über deren Benutzeroberfläche. Das primäre Ziel, das mit RPA erreicht werden soll, ist die automatisierte Ausführung von Routineaufgaben, die bisher einen menschlichen Eingriff erforderten. Das Potenzial von RPA, Prozesse langfristig zu verbessern, ist allerdings stark begrenzt. Die Automatisierung von Prozessen und die Überbrückung von Medienbrüchen auf der Front-End-Ebene führt zu einer Vielzahl von Abhängigkeiten und Bedingungen, die in diesem Beitrag zusammengefasst werden. Der Weg zu einer nachhaltigen Unternehmensarchitektur (bestehend aus Prozessen und Systemen) erfordert offene, adaptive Systeme mit moderner Architektur, die sich durch ein hohes Maß an Interoperabilität auf verschiedenen Ebenen auszeichnen.
Self-adaptive data quality
(2017)
Carrying out business processes successfully is closely linked to the quality of the data inventory in an organization. Lacks in data quality lead to problems: Incorrect address data prevents (timely) shipments to customers. Erroneous orders lead to returns and thus to unnecessary effort. Wrong pricing forces companies to miss out on revenues or to impair customer satisfaction. If orders or customer records cannot be retrieved, complaint management takes longer. Due to erroneous inventories, too few or too much supplies might be reordered.
A special problem with data quality and the reason for many of the issues mentioned above are duplicates in databases. Duplicates are different representations of same real-world objects in a dataset. However, these representations differ from each other and are for that reason hard to match by a computer. Moreover, the number of required comparisons to find those duplicates grows with the square of the dataset size. To cleanse the data, these duplicates must be detected and removed. Duplicate detection is a very laborious process. To achieve satisfactory results, appropriate software must be created and configured (similarity measures, partitioning keys, thresholds, etc.). Both requires much manual effort and experience.
This thesis addresses automation of parameter selection for duplicate detection and presents several novel approaches that eliminate the need for human experience in parts of the duplicate detection process.
A pre-processing step is introduced that analyzes the datasets in question and classifies their attributes semantically. Not only do these annotations help understanding the respective datasets, but they also facilitate subsequent steps, for example, by selecting appropriate similarity measures or normalizing the data upfront. This approach works without schema information.
Following that, we show a partitioning technique that strongly reduces the number of pair comparisons for the duplicate detection process. The approach automatically finds particularly suitable partitioning keys that simultaneously allow for effective and efficient duplicate retrieval. By means of a user study, we demonstrate that this technique finds partitioning keys that outperform expert suggestions and additionally does not need manual configuration. Furthermore, this approach can be applied independently of the attribute types.
To measure the success of a duplicate detection process and to execute the described partitioning approach, a gold standard is required that provides information about the actual duplicates in a training dataset. This thesis presents a technique that uses existing duplicate detection results and crowdsourcing to create a near gold standard that can be used for the purposes above. Another part of the thesis describes and evaluates strategies how to reduce these crowdsourcing costs and to achieve a consensus with less effort.