Publikationsserver der Technischen Hochschule Augsburg
Not a member yet
2118 research outputs found
Sort by
Ganzheitliches Risikomanagement im Einkauf – Strategien zur Integration von Umwelt-, Sozial- und Governance-Kriterien
No full textThermal Analysis of Glulam for the Development of New Reduction Factors for Strength and Stiffness in Fire
No full text
Context-Aware NILM: Disaggregating Electrical Load Profiles with Multimodal Co-Learning and Textual Metadata
No full textNon-Intrusive Load Monitoring (NILM) uses machine learning to predict the power consumption of individual electrical consumers from an aggregate source of power data, removing the need for costly sensor hardware. This thesis introduces a multimodal co-learning approach that integrates consumer-specific textual metadata as an additional modality for NILM models. Specifically, metadata are encoded into fixed-length text embeddings, which are fused with the aggregate power data sequence in a Transformer-based deep learning model. This additional input specifies which consumer’s power consumption to predict, allowing one model to be trained to disaggregate arbitrary consumers. Representing consumer names and types as word embeddings allows the multimodal NILM model to identify the target consumer and achieve disaggregation performance comparable to models trained individually for each consumer. However, encoding additional contextual information into consumer representations did not improve performance. Future work on adapting the training strategy to better exploit the textual modality could increase the model’s ability to utilize contextual information, enabling more generalizable NILM models with better applicability in real-world energy monitoring
The Trust–NPS Correlation: The Role of Trust in Promoting Customer Loyalty in Swiss Financial Institutions
No full textImproved Machinability of Pockets in a Liquid-Silicon-Infiltrated Silicon Carbide Composite Using Ultrasonic Assistance
No full text
