Constructing Health Indicators for Systems with Few Failure Instances Using Unsupervised Learning

Health indicators are crucial to assess the health of complex systems. In recent years, several studies have developed data-driven health indicators using supervised learning methods. However, due to preventive maintenance, there are often not enough failure instances to train a supervised learning model, i.e., the data is unlabelled with an...

Hybrid connection and host clustering for community detection in spatial-temporal network data

Network data clustering and sequential data mining are large<br/>fields of research, but how to combine them to analyze spatial-temporal<br/>network data remains a technical challenge. This study investigates a<br/>novel combination of two sequential similarity methods (Dynamic Time<br/>Warping and N-grams with Cosine distances), with two state...

Unsupervised anomaly detection in railway catenary condition monitoring using autoencoders

The condition monitoring of railway infrastructures is collecting big data for intelligent asset management. Making the most of the big data is a critical challenge facing the railway industry. This study focuses on one of the main railway infrastructures, namely the catenary (overhead line) system that transmits power to trains. To facilitate...

Automated Setting of Bus Schedule Coverage Using Unsupervised Machine Learning

The efficiency of Public Transportation (PT) Networks is a major goal of any urban area authority. Advances on both location and communication devices drastically increased the availability of the data generated by their operations. Adequate Machine Learning methods can thus be applied to identify patterns useful to improve the Schedule Plan. In...