Federated Transfer Learning with Multimodal Data Motivation
Federated Learning(FL) describes a Machine Learning (ML) technique in which a central ML model is trained using decentralized data. A well-known example of the application of FL is Google's Gboard keyboard on Android devices [1, 2].
Since the data remains on th... Theses in Progress Tutor: Wernet
Increasing vehicle’s perception in adverse conditions Motivation
Autonomous vehicles require a high level of environmental awareness. To detect and track objects, the vehicle first gathers data about the nearby surroundings using its onboard sensors (e.g., camera, lidar, radar). Then it preprocesses raw sensor data (e.g., size... Theses in Progress Tutor: Khalil
Mechanisms Coordination in Time-Sensitive Networking Motivation
Time-Sensitive Networking (TSN) is an evolving set of standards for reliable real-time ethernet communication.
It's possible to deploy current or future TSN mechanisms on hardware switching devices for reliable Ethernet communication. The Co-existence of multiple... Theses in Progress Tutor: Gärtner
Opportunistic Routing in Time-Critical Wireless Networks Motivation
A time-critical application of WSN is early warning of flash floods. In such a network, measurements must reach the sink within a certain deadline to be useful for early warning applications. Traditional routing is often based on single metrics, such as expected d... Theses in Progress Tutor: Becker
Learned Parallel Stream Processing using Zero-Shot Cost Models Motivation
In Distributed Stream Processing Systems (DSPS), queries are usually long-running. They typically deal with a very high workload of million or even billion of events per second. Under such scenarios, parallelism plays an important role in providing scalability for... Theses in Progress Tutor: Agnihotri