Education‎ > ‎MSc theses‎ > ‎

Open topics

Below are some MBI thesis project ideas which I would find interesting to supervise. 

MS2017-04: Anomaly detection for industrial sensor data

posted Nov 27, 2017, 3:36 AM by Marco Spruit

With the advance of Internet of Things (IoTs), nowadays mechanical equipment, ranging from elevators, vehicles, to aircrafts and wind turbines, are typically instrumented with numerous sensors to constantly capture the behaviors and health of the machine. Those sensors have been used to create systems that monitor devices in real-time. Besides real-time monitoring systems, both researchers and practitioners are working on utilizing data collected by these sensors to profile the failures of devices. In some cases, even to build models to predict device failures. Due to the lack of labelled datasets, building predictive models with supervised learning is very difficult and time-consuming. Unsupervised anomaly detection becomes a better option in handling such data (Malhotra et al., 2015, Malhotra et al., 2016, Park et al., 2017).

The aim of this project is to explore the use of various anomaly detection techniques, including one-class SVM, PCA, LSTMs and etc., in industrial sensor data collected by Shell. The results of your anomaly detection will provide useful insights for maintenance and help create more efficient maintenance plans.

You will be working with a dedicated data science team in Shell (globally), and have the opportunities to solve real business problem with your advanced data techniques through an internship. To get an internship there, you need to pass their online recruitment test and a short phone interview. 

Contact Ian for more details.

References

  • Malhotra, P., Vig, L., Shroff, G., & Agarwal, P. (2015). Long short term memory networks for anomaly detection in time series. In Proceedings (p. 89). Presses universitaires de Louvain. Chicago 
  • Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., & Shroff, G. (2016). Lstm-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148. 
  • Park, D., Hoshi, Y., & Kemp, C. C. (2017). A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder. arXiv preprint arXiv:1711.00614. 
  • Luo, C., Yang, D., Huang, J., & Deng, Y. D. (2017). LSTM-Based Temperature Prediction for Hot-Axles of Locomotives. In ITM Web of Conferences (Vol. 12, p. 01013). EDP Sciences.

MS2016-12: Data Quality Improvement in Data Space Environments

posted Oct 26, 2016, 8:17 AM by Marco Spruit   [ updated Oct 27, 2016, 12:15 AM ]

The Research and Documentation Centre (WODC) of the Dutch Ministry of Security and Justice uses a lot of different, heterogeneous, data sets in their research. The need for integration depends strongly on the research being done, which is why the data sets are managed using a data space approach. In this approach, data integration and other data quality improvement are initiated by the need for it in specific research projects (pay-as-you-go). However, decentralizing data quality improvement is not always the most efficient way; when several projects encounter the same data quality issues collaboration on the improvement of these issues is desirable and the issues are also likely to become more urgent to solve. The WODC wants more insight in the impact of known data quality issues, and looks for solutions to determine which issues are better to solve in a more centralized way.

NB: Due to the Dutch data and documentation, understanding of written Dutch is preferable.

MS2016-11: Knowledge Provenance System for Data Space Architectures

posted Oct 26, 2016, 8:16 AM by Marco Spruit   [ updated Oct 27, 2016, 12:15 AM ]

The Research and Documentation Centre (WODC) of the Dutch Ministry of Security and Justice uses a lot of different, heterogeneous, data sets in their research. The need for integration depends strongly on the research being done, which is why the data sets are managed using a data space approach. In this approach, mappings are used to transform data sets such that they are useful for specific research projects and therefore volatile and highly flexible. Insight in these mappings and especially why they are performed is essential to understand the research data set. So, besides data provenance of the data itself, the WODC is also interested in storing the associated knowledge in a transparant yet maintainable way.

NB: Due to the Dutch data and documentation, understanding of written Dutch is preferable.

1-3 of 3