006 Spezielle Computerverfahren
Refine
H-BRS Bibliography
- yes (26) (remove)
Departments, institutes and facilities
- Fachbereich Informatik (26) (remove)
Document Type
- Conference Object (26) (remove)
Year of publication
Keywords
- Robotics (2)
- 450 MHz (1)
- Augmented Reality (1)
- Behaviour-Driven Development (1)
- Bioinformatics (1)
- Collaborating industrial robots (1)
- Compliant fingers (1)
- Concurrent repeated failure prognosis (1)
- Crossmedia (1)
- Data Fusion (1)
- Diagnostic bond graph-based online fault diagnosis (1)
- Embedded system (1)
- Forests (1)
- Functional safety (1)
- Games and Simulations for Learning (1)
- Higher education (1)
- Hyperspectral image (1)
- IEC 104 (1)
- IEC 61850 (1)
- Increasing fault magnitude (1)
- Inductive Logic Programming (1)
- Information Security (1)
- Intermittent faults (1)
- Knowledge Graphs (1)
- LTE-M (1)
- MQTT (1)
- Machine Learning (1)
- Model-driven engineering (1)
- NIR-point sensor (1)
- Natural Language Processing (1)
- Object-Based Image Analysis (OBIA) (1)
- Raman microscopy (1)
- Reasoning (1)
- Remaining Useful Life (RUL) estimates (1)
- Requirements (1)
- Review (1)
- Robust grasping (1)
- Serious Games (1)
- Skin detection (1)
- Slippage detection (1)
- Smart Grid (1)
- Smart InGaAs camera-system (1)
- Survey (1)
- Traffic Simulations (1)
- Transformers (1)
- Tree Stumps (1)
- Ultrasonic array (1)
- Unmanned Aerial Vehicle (UAV) (1)
- Virtual Agents (1)
- Virtual Reality (1)
- Vulnerable Groups (1)
- audio-tactile feedback (1)
- authoring tools (1)
- brightfield microscopy (1)
- component analyses (1)
- depth perception (1)
- guidance (1)
- image fusion (1)
- pansharpening (1)
- remote sensing (1)
ProtSTonKGs: A Sophisticated Transformer Trained on Protein Sequences, Text, and Knowledge Graphs
(2022)
While most approaches individually exploit unstructured data from the biomedical literature or structured data from biomedical knowledge graphs, their union can better exploit the advantages of such approaches, ultimately improving representations of biology. Using multimodal transformers for such purposes can improve performance on context dependent classication tasks, as demonstrated by our previous model, the Sophisticated Transformer Trained on Biomedical Text and Knowledge Graphs (STonKGs). In this work, we introduce ProtSTonKGs, a transformer aimed at learning all-encompassing representations of protein-protein interactions. ProtSTonKGs presents an extension to our previous work by adding textual protein descriptions and amino acid sequences (i.e., structural information) to the text- and knowledge graph-based input sequence used in STonKGs. We benchmark ProtSTonKGs against STonKGs, resulting in improved F1 scores by up to 0.066 (i.e., from 0.204 to 0.270) in several tasks such as predicting protein interactions in several contexts. Our work demonstrates how multimodal transformers can be used to integrate heterogeneous sources of information, paving the foundation for future approaches that use multiple modalities for biomedical applications.
Low-Cost In-Hand Slippage Detection and Avoidance for Robust Robotic Grasping with Compliant Fingers
(2021)