Po-Yu has joined AESE group, Imperial College at the start of October 2011. He got his Ph.D. in 2016 and is currently looking at the topic of big data analytics in distributed systems such as Internet of Things (IoTs) and cyber-physical systems (CPS). His work focuses on the following topic:
- Anomaly detection in non-stationary time series.
- Feature extraction and dimensionality reduction techniques for large scale time-series data.
- Similarity search, correlation estimation, and pattern recognition between distrusted cross-discipline data streams.
He is currently responsible for WEFWEBs project (funded by EPSRC) in AESE. As our water, energy, food and waste systems are interconnected, and impacted by climate and demographic change, this nexus seeks to define the interdependencies between the different systems and improve our understanding and hence ability to effectively predict and manage them; The ultimate goal is to have some insights which help to ensure the overall water, energy and food security among the globe.
Before he joined AESE, Po-Yu has received his B.Sc. and M.Sc. degree in 2008 and 2010 from National Cheng-Kung University and National Taiwan University, respectively. During his undergraduate, he showed his interest in smart-home technologies and embedded systems. During his M.Sc. study, He has been involved in couple of practical wireless sensor network (WSN) related projects including:
- Long-distance marine aquaculture monitoring system
- A wireless medication system for chronic illnesses patients.
- Create smart-living space and improve environmental safety with an integrated public-subscribe system and wireless sensor networks.
- P-Y Chen , W. Yu, S. Yang , J. McCann, A General Solutoin to Summarise Time Series with Multiple Dimensionality-Reduced Features, (to appear soon).
- S. Yang , Y. Tahir , P-Y Chen , M. (2016), Distributed Optimization in Energy Harvesting Sensor Networks with Dynamic In-network Data, In Proc. IEEE INFOCOM.
- P-Y Chen , S. Yang, J. McCann, (2015), Distributed Real-Time Anomaly Detection in Networked Industrial Sensing Systems, IEEE Trans. Ind. Electron., Vol. 62, p.3832-3842.
- P-Y Chen, S. Yang , J. McCann, , (2015), Detection of False Data Injection Attacks in Smart-Grid Systems, IEEE Commun. Mag. , Vol. 53, p.206-213
A on-site low-power wireless sensor network
In order to capture the WEF nexus, Po-Yu designed and deployed a state-of-the-art wireless sensor system. 47 sensing devices and a PC-based base station have been deployed in the Ridgeview winery to capture the ambient information from Ridgeview since late 2016. A solar-powered device was also tested with the system to capture its own energy profile. This deployment can be regarded as an initial trail which helps us to establish a system that will capture the WEF information from both the in-door winery and our-door vineyards in 2017.