004 Datenverarbeitung; Informatik
Refine
Has Fulltext
- yes (12)
Is part of the Bibliography
- yes (12)
Year of publication
- 2023 (12) (remove)
Document Type
- Journal article (12) (remove)
Language
- English (12)
Keywords
- Deep learning (2)
- 4D-GIS (1)
- BPM (1)
- BPMN (1)
- IT security (1)
- IoT (1)
- IoT-driven processes (1)
- Klima (1)
- Modell (1)
- Neuronales Netz (1)
- Structure-from-Motion (1)
- WhatsApp (1)
- anthropomorphism (1)
- availability (1)
- background knowledge (1)
- baseline detection (1)
- camera orientation (1)
- climate (1)
- communication models (1)
- communication networks (1)
- content-based image retrieval (1)
- data warehouse (1)
- decision support system (1)
- digital twin (1)
- eHealth (1)
- electronic health records (1)
- feature matching (1)
- fully convolutional neural networks (1)
- future energy grid exploration (1)
- group-based communication (1)
- historical document analysis (1)
- historical images (1)
- hospital data (1)
- human–computer interaction (1)
- informal education (1)
- information extraction (1)
- intelligent voice assistant (1)
- key-insight extraction (1)
- layout recognition (1)
- local energy system (1)
- long-term analysis (1)
- media analysis (1)
- medical records (1)
- misconceptions (1)
- mobile instant messaging (1)
- mobile messaging application (1)
- model output statistics (1)
- multiscale encoder (1)
- neural networks (1)
- ontology (1)
- performance (1)
- private chat groups (1)
- radiology (1)
- ransomware (1)
- scalability (1)
- sentinel (1)
- simulation (1)
- smart meter data utilization (1)
- smart speaker (1)
- social interaction (1)
- social relationship (1)
- social role (1)
- statistics and numerical data (1)
- surface model (1)
- table extraction (1)
- table understanding (1)
- text line detection (1)
An important but very time consuming part of the research process is literature review. An already large and nevertheless growing ground set of publications as well as a steadily increasing publication rate continue to worsen the situation. Consequently, automating this task as far as possible is desirable. Experimental results of systems are key-insights of high importance during literature review and usually represented in form of tables. Our pipeline KIETA exploits these tables to contribute to the endeavor of automation by extracting them and their contained knowledge from scientific publications. The pipeline is split into multiple steps to guarantee modularity as well as analyzability, and agnosticim regarding the specific scientific domain up until the knowledge extraction step, which is based upon an ontology. Additionally, a dataset of corresponding articles has been manually annotated with information regarding table and knowledge extraction. Experiments show promising results that signal the possibility of an automated system, while also indicating limits of extracting knowledge from tables without any context.
Climate models are the tool of choice for scientists researching climate change. Like all models they suffer from errors, particularly systematic and location-specific representation errors. One way to reduce these errors is model output statistics (MOS) where the model output is fitted to observational data with machine learning. In this work, we assess the use of convolutional Deep Learning climate MOS approaches and present the ConvMOS architecture which is specifically designed based on the observation that there are systematic and location-specific errors in the precipitation estimates of climate models. We apply ConvMOS models to the simulated precipitation of the regional climate model REMO, showing that a combination of per-location model parameters for reducing location-specific errors and global model parameters for reducing systematic errors is indeed beneficial for MOS performance. We find that ConvMOS models can reduce errors considerably and perform significantly better than three commonly used MOS approaches and plain ResNet and U-Net models in most cases. Our results show that non-linear MOS models underestimate the number of extreme precipitation events, which we alleviate by training models specialized towards extreme precipitation events with the imbalanced regression method DenseLoss. While we consider climate MOS, we argue that aspects of ConvMOS may also be beneficial in other domains with geospatial data, such as air pollution modeling or weather forecasts.