Thesis project; 30hp - Graph neural networks for anomaly detection.

Background
Scania is one of the world’s leading manufacturer of trucks and buses for heavy transports, as well as industrial and marine engines. Transport services and logistics services make up an increasing part of our business, which guarantees Scania’s customers cost-efficient transport solutions and high availability. Over a million Scania vehicles are in active use, in over 100 countries.
In the Connectivity section within Scania R&D, we develop new solutions for connected vehicles in our Internet of Things (IoT) platform, as part of Scania’s increasing focus on communication, services, and smart transport solutions. Advanced data analysis capabilities are a cornerstone enabler in this development. 

Target/scope
Deep learning (DL) and neural networks have demonstrated their versatility across various learning tasks. However, when applied to time series anomaly detection, DL models often overlook the relationships between variables (i.e. to use the knowledge about the system interactions). To address this issue, this thesis proposes utilizing interaction graphs to construct graph neural networks for anomaly detection. While there is existing work in this area [1], there is still room for improvement by incorporating predicted interaction graphs, contrastive learning and self-supervised approaches. Task for this thesis would be as follows.

1. Literature study on existing anomaly detection models.
2. Build a graph neural network methods for anomaly detection (time-series data).
3. Quantitative and qualitative evaluation measures on the method.

Student will be provided access to the computing infrastructure and to the dataset required for the task.
[1] Jin, Ming, et al. "A survey on graph neural networks for time series: Forecasting, classification, imputation, and anomaly detection." IEEE Transactions on Pattern Analysis and Machine Intelligence (2024).
What skill are for needed this thesis
-    Required
o  Knowledge on basic of Machine Learning ML 
o  Knowledge on basic of Neural networks (NN) e.g. back propagation, loss, supervised learning, convolution networks, recurrent networks
o  Knowledge on gradient based optimization.

-    Bonus
o   Knowledge about graph neural networks.

Education/line/direction
Area of education or direction: Masters programmes in Machine Learning, Data Science, Computational Mathematics, Complex Adaptive Systems, Computer Science or similar. 
Number of students: 1-2 
Start date for the Thesis project: January 2025
Estimated timescale: 20 weeks

Contact person and supervisor
Abhishek Srinivasan, Data Scientist, 08-553 816 96, abhishek.srinivasan@scania.com
Juan-Carlos Anderesen, Manager, 08-553 835 16, juan-carlos.anderesen@scania.com 

Application
Your application should contain the following: 
-   CV.
-   Personal letter. 
-   Copies of grades.
-   Optional: To propose tentative approach to the problem.
 
Date of publication,
Until 2024-11-05. Applicants will be assessed on a continuous basis until the position is filled. Do not wait until the last date to apply. 

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.     

Thesis Worker