python

Federated learning (FL) enables multiple devices to collaboratively train a global model while maintaining data on local servers. Each device trains the model on its local server and shares only the model updates (i.e., gradient weights) during the aggregation step. A significant challenge in FL is managing the feature distribution of novel, unbalanced data across devices. In this paper, we propose an FL approach using few-shot learning and aggregation of the model weights on a global server. We introduce a dynamic early stopping method to balance out-of-distribution classes based on representation learning, specifically utilizing the maximum mean discrepancy of feature embeddings between local and global models. An exemplary application of FL is orchestrating machine learning models along highways for interference classification based on snapshots from global navigation satellite system (GNSS) receivers. Extensive experiments on four GNSS datasets from two real-world highways and controlled environments demonstrate that our FL method surpasses state-of-the-art techniques in adapting to both novel interference classes and multipath scenarios.

This is the code developed by Dr.-Ing. Dominique Koster and contributed to by Dr. Mariam R. Rizkallah for the workshop "Data Reconciliation: Integration of Electrochemical Data and Optical Sensor Data for Health Diagnostics of Lithium-Ion Batteries" https://www.bremen-research.de/data-train/courses/course-details?event_id=88

Sensor Software Setup Solution for Microcontrollers by Eric Kondratenko

Heat pump control testing framework

A suggested template for recording and assessing time sheets in Obsidian vaults (e.g. using daily notes).

A publicly accessible knowledge base for everybody. Accompanies the IIS Confluence Knowledge Base.