Activity Number:
|
215
- Contributed Poster Presentations: Section on Statistical Learning and Data Science
|
Type:
|
Contributed
|
Date/Time:
|
Tuesday, August 4, 2020 : 10:00 AM to 2:00 PM
|
Sponsor:
|
Section on Statistical Learning and Data Science
|
Abstract #313552
|
|
Title:
|
Anomaly Detection Methods for IoT Freeze Loss
|
Author(s):
|
Patrick Toman* and Ahmed Soliman and Nalini Ravishanker and Sanguthevar Rajasekaran and Nathan Lally and Yuchen Fama
|
Companies:
|
University of Connecticut - Department of Statistics and University of Connecticut and University of Connecticut and University of Connecticut and Hartford Steam Boiler and Hartford Steam Boiler
|
Keywords:
|
ARIMA/GARCH;
Ridesharing;
Transportation Network Companies;
Spatio-Temporal
|
Abstract:
|
With the advent of IoT, automated alert systems are being developed which will allow customers and insurance companies to monitor building infrastructure and help prevent mitigate freeze loss incidents. In this paper, the authors present a case study where time series anomaly detection methods are employed to improve Hartford Steam Boilers (HSB) IoT freeze loss alert system. The goal of the case study is to develop an online alert system capable of altering customers in real time of possible imminent freeze loss in their buildings.
|
Authors who are presenting talks have a * after their name.