Current

Inferring Sensor Meta-Data to Create Portable Software Applications for Buildings

Mario Bergés

Jingkun Gao

Project Description

In modern buildings, thousands of sensors and instruments need to be installed and configured. However, manual work to record meta data information(e.g., location, functionality, sensor type and etc.) of those devices is time-consuming and error-prone. Yet such information is often required by software and hardware in building infrastructure system. The purpose of this project is to automatically infer such meta data information from measurements themselves, which can be further used to crete portable software applications for buildings. An intuitive example could be that we want to infer whether some sensors are placed in the same location just by the analyzing the data streams coming out of them.

In a simple framework, the inputs are data streams from different measurements and the outputs are the relationships among those measurements. Such relationship could be the group information from the result of clustering algorithms, or a dynamic graphical model indicating the dependency between each data stream. A data-driven approach utilizing machine learning and statistical methods will be developed to tackle this problem.

• 01/1970

Selected Publications

1. J. Gao, J. Ploennigs, and M. Berg'es, "A Data-driven Meta-data Inference Framework for Building Automation Systems," in Proceedings of the 2nd ACM Conference on Embedded Systems for Energy-Efficient Buildings, New York, NY, USA, 2015.
bibtex
@inproceedings{Gao-automap, author = {Gao, Jingkun and Ploennigs, Joern and Berg{'e}s, Mario},  title = {A Data-driven Meta-data Inference Framework for Building Automation Systems},  booktitle = {Proceedings of the 2nd ACM Conference on Embedded Systems for Energy-Efficient Buildings},  series = {BuildSys '15},  year = {2015},  isbn = {978-1-4503-3981-0},  location = {Seoul, South Korea},  url = {http://dx.doi.org/10.1145/2821650.2821670},  doi = {10.1145/2821650.2821670},  publisher = {ACM},  address = {New York, NY, USA}, }
2. J. Gao, E. C. Kara, S. Giri, and M. Berges, "A feasibility study of automated plug-load identification from high-frequency measurements," in Signal and Information Processing (GlobalSIP), 2015 IEEE Global Conference on, 2015.
bibtex
@INPROCEEDINGS{high-freq, author={Gao, J. and Kara, E.C. and Giri, S. and Berges, M.},  booktitle={Signal and Information Processing (GlobalSIP), 2015 IEEE Global Conference on},  title={A feasibility study of automated plug-load identification from high-frequency measurements},  year={2015}, }
3. J. Gao, S. Giri, E. C. Kara, and M. Berg'es, "PLAID: A Public Dataset of High-resolution Electrical Appliance Measurements for Load Identification Research: Demo Abstract," in Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, New York, NY, USA, 2014, pp. 198-199.
bibtex
@inproceedings{Gao:2014:PPD:2674061.2675032, author = {Gao, Jingkun and Giri, Suman and Kara, Emre Can and Berg{'e}s, Mario},  title = {PLAID: A Public Dataset of High-resolution Electrical Appliance Measurements for Load Identification Research: Demo Abstract},  booktitle = {Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings},  series = {BuildSys '14},  year = {2014},  isbn = {978-1-4503-3144-9},  location = {Memphis, Tennessee},  pages = {198--199},  numpages = {2},  url = {http://doi.acm.org/10.1145/2674061.2675032},  doi = {10.1145/2674061.2675032},  acmid = {2675032},  publisher = {ACM},  address = {New York, NY, USA}, }