An Ultrasound Receiver ASIC with Slow-time Feedback for Transcranial Doppler Imaging

Transcranial Doppler ultrasound imaging is a crucial tool for both clinical and research applications. Despite its significance, its utility is constrained by the dynamic range limitations of the receiver system. Traditional methods, relying on high-dynamic-range front-end amplifiers and high-resolution ADCs, are often inefficient. These methods...

Project Journey Embassy: Foster the continuity of multidisciplinary collaboration in an IT consulting service towards problem-solving innovation

The application of multidisciplinary collaboration has become a trend to prevent knowledge isolation obstructing business development (Schaubroeck, Tarczewski, &amp; Theunissen, 2016), particularly in the IT industry as it pursue problem-solving innovation.<br/><br/>An IT service company is currently striving to transform into an IT innovation...

Unsupervised Wafer Map Failure Pattern Recognition with Contrastive Learning

This master’s thesis explores the application of Self-Supervised Contrastive Learning (SSCL), specifically the SimCLR algorithm, to enhance feature representation learning from Wafer Bin Maps (WBM) in the semiconductor manufacturing process. The motivation stems from the industry’s growing need for automated defect detection and root-cause...

Reconnecting: Multi-modal Transfer Station at Warsaw Street

In Berlin, the public transportation system is large and varied. Train (S-Bahn), tram, metro (U-Bahn), and bus consist of the main skeleton of the system. However, due to historical reasons, most U-bahn and tram lines are located only in the former West and East Berlin, respectively. Thus, lots of transfer stations are located in the area where...

Care and Nature: A Children’s Hospital in Berlin

This thesis is an exploration into architectural strategies that help build up the holistic care for children in paediatric facilities.

Integrate and store 3D roads and terrain for navigation purposes

Modern navigation heavily relies on Global Navigation Satellite Systems (GNSS) and digitized road network databases, but faces limitations in GNSS-denied areas and complex 2D road netowrks. This project addresses these challenges by developing a methodology to create and store a comprehensive 3D road and terrain dataset for enhanced navigation....

Federated Learning with Rebalanced Dataset

With the widespread application of artificial intelligence, centralized machine learning approaches, which require access to users' local data, have raised concerns about data privacy. In response, federated learning, an architecture that aggregates models trained locally with local data, has been proposed. This approach addresses the data...

Collaborative Payload Carrying with Multiple MAVs

The transportation of payloads utilizing multiple drones presents a promising application for lifting heavier loads that exceed the payload capacity of a single drone. However, the cable-suspended payload introduces significant challenges to the system, and this research area remains relatively unexplored. In this work, a novel solution for...

Development of a Patient-Specific Carotid Artery Fluid-Structure-Interaction Model

Background: <br/>Ischemic stroke is a major cause of death worldwide. Atherosclerosis in the carotid arteries is an established predictor of these events. FSI shows its advantage in simulating the hemodynamic environments due to involving the multiphysics coupling of fluid dynamics and structural mechanics regulations. Therefore, the aim of this...

Deep learning-based Image similarity estimation for geo-localization of Historical Aerial imagery

Historical aerial imagery serves as a valuable data source for observing Antarctica, facilitating an extended temporal scale of observation and enabling comparisons to deepen understanding of glacier dynamics. However, many historical aerial datasets, including the Antarctica Single Frames dataset utilized in this study, lack geo-referencing and...