skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Selective Sampling for Sensor Type Classification in Buildings

Conference · · 2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN)

A key barrier to applying any smart technology to a building is the requirement of locating and connecting to the necessary resources among the thousands of sensing and control points, i.e., the metadata mapping problem. Existing solutions depend on exhaustive manual annotation of sensor metadata --- a laborious, costly, and hardly scalable process. To reduce the amount of manual effort required, this paper presents a multi-oracle selective sampling framework to leverage noisy labels from information sources with unknown reliability such as existing buildings, which we refer to as weak oracles, for metadata mapping. This framework involves an interactive process, where a small set of sensor instances are progressively selected and labeled for it to learn how to aggregate the noisy labels as well as to predict sensor types. Two key challenges arise in designing the framework, namely, weak oracle reliability estimation and instance selection for querying. To address the first challenge, we develop a clustering-based approach for weak oracle reliability estimation to capitalize on the observation that weak oracles perform differently in different groups of instances. For the second challenge, we propose a disagreement-based query selection strategy to combine the potential effect of a labeled instance on both reducing classifier uncertainty and improving the quality of label aggregation. We evaluate our solution on a large collection of real-world building sensor data from 5 buildings with more than 11,000 sensors of 18 different types. The experiment results validate the effectiveness of our solution, which outperforms a set of state-of-the-art baselines.

Research Organization:
University of Virginia
Sponsoring Organization:
USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office
DOE Contract Number:
EE0008227
OSTI ID:
1822657
Report Number(s):
DOE-UVA-0008227-7
Journal Information:
2020 19th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), Conference: The 19th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN), Sydney, NSW, Australia, 21-24 April 2020
Country of Publication:
United States
Language:
English

References (32)

Active Learning with Statistical Models journal January 1996
Proactive learning conference January 2008
Plaster: an integration, benchmark, and development framework for metadata normalization methods
  • Koh, Jason; Hong, Dezhi; Gupta, Rajesh
  • BuildSys '18: The 5th ACM International Conference on Systems for Built Environments, Proceedings of the 5th Conference on Systems for Built Environments https://doi.org/10.1145/3276774.3276794
conference November 2018
Automated point mapping for building control systems: Recent advances and future research needs journal January 2018
Efficient crowdsourcing of unknown experts using bounded multi-armed bandits journal September 2014
Scrabble: transferrable semi-automated semantic metadata normalization using intermediate representation
  • Koh, Jason; Balaji, Bharathan; Sengupta, Dhiman
  • BuildSys '18: The 5th ACM International Conference on Systems for Built Environments, Proceedings of the 5th Conference on Systems for Built Environments https://doi.org/10.1145/3276774.3276795
conference November 2018
POEM: power-efficient occupancy-based energy management system
  • Erickson, Varick L.; Achleitner, Stefan; Cerpa, Alberto E.
  • Proceedings of the 12th international conference on Information processing in sensor networks - IPSN '13 https://doi.org/10.1145/2461381.2461407
conference January 2013
DeviceMien conference April 2019
Automated Metadata Construction to Support Portable Building Applications
  • Bhattacharya, Arka A.; Hong, Dezhi; Culler, David
  • Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys '15 https://doi.org/10.1145/2821650.2821667
conference January 2015
Sentinel: occupancy based HVAC actuation using existing WiFi infrastructure within commercial buildings conference January 2013
A Bayesian Framework for Modeling Human Evaluations conference June 2015
Active learning with confidence-based answers for crowdsourcing labeling tasks journal November 2018
Maximum Likelihood Estimation of Observer Error-Rates Using the EM Algorithm journal January 1979
A Data-driven Meta-data Inference Framework for Building Automation Systems
  • Gao, Jingkun; Ploennigs, Joern; Berges, Mario
  • Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys '15 https://doi.org/10.1145/2821650.2821670
conference January 2015
Clustering-based Active Learning on Sensor Type Classification in Buildings conference October 2015
Brick: Towards a Unified Metadata Schema For Buildings
  • Balaji, Bharathan; Agarwal, Yuvraj; Berges, Mario
  • Proceedings of the 3rd ACM International Conference on Systems for Energy-Efficient Built Environments - BuildSys '16 https://doi.org/10.1145/2993422.2993577
conference January 2016
Towards Automatic Spatial Verification of Sensor Placement in Buildings conference November 2013
Towards automating the deployment of energy saving approaches in buildings conference November 2014
On Information and Sufficiency journal March 1951
Online crowdsourcing: Rating annotators and obtaining cost-effective labels conference June 2010
Truth inference in crowdsourcing journal January 2017
Zodiac
  • Balaji, Bharathan; Verma, Chetan; Narayanaswamy, Balakrishnan
  • Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments https://doi.org/10.1145/2821650.2821674
conference November 2015
Mismatch string kernels for discriminative protein classification journal January 2004
A study of the effect of different types of noise on the precision of supervised learning techniques journal January 2010
Short Paper
  • Pritoni, Marco; Bhattacharya, Arka A.; Culler, David
  • Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments https://doi.org/10.1145/2821650.2821677
conference November 2015
A Bayesian Analysis of Some Nonparametric Problems journal March 1973
The Building Adapter: Towards Quickly Applying Building Analytics at Scale
  • Hong, Dezhi; Wang, Hongning; Ortiz, Jorge
  • Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments - BuildSys '15 https://doi.org/10.1145/2821650.2821657
conference January 2015
Efficiently learning the accuracy of labeling sources for selective sampling
  • Donmez, Pinar; Carbonell, Jaime G.; Schneider, Jeff
  • Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining - KDD '09 https://doi.org/10.1145/1557019.1557053
conference January 2009
Comparison of linear correlation and a statistical dependency measure for inferring spatial relation of temperature sensors in buildings conference November 2014
The wisdom of minority conference January 2014
Strip, bind, and search: a method for identifying abnormal energy consumption in buildings
  • Fontugne, Romain; Ortiz, Jorge; Tremblay, Nicolas
  • Proceedings of the 12th international conference on Information processing in sensor networks - IPSN '13 https://doi.org/10.1145/2461381.2461399
conference January 2013
Combining Crowd and Expert Labels Using Decision Theoretic Active Learning journal September 2015

Similar Records

Sequential Learning with Active Partial Labeling for Building Metadata
Conference · Wed Nov 13 00:00:00 EST 2019 · OSTI ID:1822657

Scalable Pattern Matching in Metadata Graphs via Constraint Checking
Journal Article · Mon Jan 04 00:00:00 EST 2021 · ACM Transactions on Parallel Computing · OSTI ID:1822657

The Building Adapter: Automatic Mapping of Commercial Buildings for Scalable Building Analytics
Technical Report · Tue Sep 28 00:00:00 EDT 2021 · OSTI ID:1822657