End-of-line Testing for Safety and Quality with Machine Learning

Safety-critical systems are pervasive throughout our society with everyday objects such as airplanes, cars, trains, or medical devices. The requested functionality and expectations from these systems are growing rapidly and consequently, they become more complex. The complexity is usually handled by breaking the system into manageable smaller components and parts. Factories then integrate these parts into the final product. However, while some complexity can be managed
by this divide & conquer strategy, the assembly is still a challenging task.

An Efficient Data Analysis Pipeline

The proposed research project targets computational performance improvements of an data analysis pipeline. The project has a duration of four months and aims to achieve two objectives: (1) to properly characterize the performance of individual stages of the existing data analysis pipeline in terms of execution time, memory, and I/O, and (2) to improve the performance of individual stages where possible. The intern will use methods learnt and developed during the masters research and apply them to a real-world system at Acerta Analytics Solutions.

Anomaly Detection using GAN

The proposed research project targets anomaly detection of event data. The project has a duration of four months and aims to achieve two objectives: (1) to evaluate the effectiveness of a novel approach on GAN for real-world data, and (2) compare it to alternative methods. The intern will use existing research resources, and will apply them to real-world data provided by the partner, Acerta Analytics Solutions, Inc. to evaluate the different methods.

Anomaly Detection in Event Data

The proposed research project targets anomaly detection of event data. The project has a duration of six months and aims to achieve two objectives: (1) to evaluate the effectiveness of a novel approach for real-world data, and (2) compare it to alternative methods. The intern will use existing research resources, and will apply them to real-world data provided by the partner, Acerta Analytics Solutions, Inc. to evaluate the different methods.