Industrial Internet Consortium Releases Deep Learning Testbed Results
December 03, 2018
The Testbed detected unusual activity from air conditioning equipment in a kitchen, revealing that kitchen staff had closed air intake ducts to reduce odors.
BOSTON, MA. The Industrial Internet Consortium (IIC) has released results from its Deep Learning Facility Testbed in Kawasaki, Japan, which explored deep learning neural networks within an IoT platform and how they optimized asset utilization in an office building. Based on an application developed by Toshiba and Dell EMC, the Testbed analyzes 35,000 measured data points per minute, applying artificial intelligence (AI) to detect anomalies, automate temperature and lighting, and prioritize elevator schedules.
The Testbed application works by learning normal conditions based on data aggregated from sensors at the facility. This allows the AI-powered platform to recognize unusual conditions, identify the related device(s), and inform a team to check the accuracy of the inference.
For instance, the Testbed detected unusual activity from air conditioning equipment in a kitchen, revealing that kitchen staff had closed air intake ducts to reduce odors.
“The deployment of an IoT system for a smart building will maximize the value of big data collection through deep learning analytics,” says Dr. Said Tabet, IIC Deep Learning Testbed lead, and Lead Technologist for IoT Strategy, Dell EMC. “A smart building will improve operational efficiency, reduce maintenance costs, and maximize the use of assets.”
For more information on the Deep Learning Testbed, email [email protected].