18049362. DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)
Contents
- 1 DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS
Organization Name
INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor(s)
Andrew C. M. Hicks of Highland NY (US)
Michael Terrence Cohoon of Fishkill NY (US)
DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18049362 titled 'DRIFT DETECTION IN EDGE DEVICES VIA MULTI-ALGORITHMIC DELTAS
Simplified Explanation
The patent application relates to data drift detection in an edge device without network connectivity.
- Verification component to verify accuracy of models
- Computation component to compute ratios based on model accuracy
- Analysis component to determine performance degradation due to data drift
Potential Applications
This technology can be applied in various industries such as IoT, manufacturing, and healthcare where edge devices are deployed without constant network connectivity.
Problems Solved
1. Detecting data drift in edge devices without network connectivity 2. Ensuring accuracy and performance of machine learning models in edge devices
Benefits
1. Improved reliability of edge devices 2. Early detection of data drift for timely corrective actions
Potential Commercial Applications
Optimizing performance of edge devices in remote locations
Possible Prior Art
Prior art may include methods for monitoring data drift in centralized systems, but not specifically tailored for edge devices without network connectivity.
Unanswered Questions
== How does this technology handle real-time data drift detection in edge devices? This article does not provide details on the real-time capabilities of the system for detecting data drift in edge devices.
== What are the specific metrics used to determine the accuracy of the machine learning models? The article does not specify the exact metrics or criteria used to assess the accuracy of the machine learning models in detecting data drift.
Original Abstract Submitted
One or more systems, devices, computer program products and/or computer-implemented methods provided herein relate to data drift detection in an edge device. A system can comprise a memory configured to store computer executable components; and a processor configured to execute the computer executable components stored in the memory, wherein the computer executable components can comprise a verification component that can verify accuracy of a first model and accuracy of a second model to detect data drift associated with an edge device that is deployed without network connectivity; a computation component that can compute at least a first ratio based on the accuracy of the first model and the accuracy of the second model; and an analysis component that can use the at least the first ratio to determine whether performance degradation of at least one of the first model or the second model is a function of the data drift.