IoT Sensor Data Correction Using Neighboring Anomaly Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In IoT networks, sensor data reliability is compromised due to malfunctioning sensors reporting incorrect values, which affects the accuracy and reliability of the gathered data, particularly in multi-sensor environments where inaccurate readings can lead to degraded system performance or loss of service.
Innovation Solution
The method involves employing anomaly detection techniques using additional sensor data from proximate sensors to identify and correct anomalous readings, leveraging machine learning and cross-sensor algorithms to predict and correct outlier data, thereby improving data quality and system reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If sensor data is collected from multiple sensors in an IoT network, then the quantity and coverage of data is improved, but the reliability and accuracy deteriorate due to malfunctioning sensors reporting incorrect values
Solution Approach 1:
The patent combines data from multiple sensors including the target sensor and neighboring sensors to detect anomalies. By merging sensor readings and comparing them against expected patterns derived from neighboring sensors, the system identifies malfunctioning sensors and corrects their data, thus maintaining reliability while utilizing multiple data sources.
Solution Approach 2:
The patent introduces an intermediary anomaly detection mechanism that mediates between raw sensor data and final processed data. This intermediary layer analyzes sensor readings against expected patterns and neighboring sensor data, identifying and correcting anomalies before the data is used for decision-making, thus preserving reliability.
2Measurement precision
If anomaly detection techniques are applied to correct sensor data, then the accuracy and reliability are improved, but the processing complexity increases
Solution Approach 1:
The patent applies anomaly detection locally by considering only neighboring sensors and local environmental context rather than processing all sensor data globally. This localized approach reduces computational complexity while maintaining accuracy by focusing on relevant comparative data from proximate sensors.
Solution Approach 2:
The patent establishes expected sensor value patterns in advance based on historical data and neighboring sensor readings. By pre-defining what normal sensor behavior should look like, the anomaly detection process becomes simpler as it only needs to compare current readings against these pre-established expectations rather than performing complex real-time analysis.
Data Source
AI summary
Techniques are provided for correcting sensor data in a multi-sensor environment. An exemplary method comprises obtaining sensor data from a first sensor; applying an anomaly detection technique to detect an anomaly in the sensor data from the first sensor based on additional sensor data from one or more of the first sensor and at least one additional sensor in proximity to the first sensor; and correcting the anomalous sensor data from the first sensor using additional sensor data from one or more of the first sensor and the at least one additional sensor. In some embodiments, additional sensor data from a plurality of neighboring sensors is used to predict the sensor data from the first sensor. The anomalous sensor data is optionally corrected substantially close in time to the detection of the anomaly in the sensor data.