Sensor Data Analysis Using Reference Sensor Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In the Internet of Things, efficiently analyzing massive sensor data in real-time is challenging due to the high computational demands of anomaly detection, especially when relying solely on cloud computing, which can lead to delayed or inadequate detection of abnormal sensor readings.
Innovation Solution
A method and device for data analysis that determines reference sensors based on location and temporal proximity to a target sensor, using historical data from these reference sensors to estimate target sensor data and detect anomalies, thereby reducing computational requirements and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Power
If cloud computing is used for sensor data analysis, then computational power is sufficient, but detection speed is slow and real-time monitoring is inadequate
Solution Approach 1:
The patent segments the sensor network into multiple clusters, each with a cluster head that performs local data processing and anomaly detection. This distributed segmentation allows parallel processing across clusters, improving detection speed while maintaining sufficient computational power through collective processing capability.
Solution Approach 2:
The patent introduces a hierarchical dimension to the computing architecture, with edge devices performing preliminary processing and cloud providing supplementary computation. This dimensional addition allows real-time detection at the edge while maintaining overall computational adequacy through cloud resources.
2Measurement precision
If all sensor data is processed centrally, then detection accuracy is high, but computational load is excessive and efficiency is low
Solution Approach 1:
The patent implements local quality by enabling each cluster head to perform anomaly detection using data from its local cluster members. This localized processing maintains detection accuracy for local events while improving overall processing efficiency by distributing the computational load across multiple nodes rather than concentrating it centrally.
Solution Approach 2:
The patent introduces cluster heads as intermediary nodes between individual sensors and the central cloud system. These intermediaries perform preliminary data processing and anomaly detection, reducing the computational burden on central systems while maintaining detection accuracy through hierarchical processing.
3Measurement precision
If more computational resources are allocated to anomaly detection, then detection accuracy improves, but system complexity and energy consumption increase
Solution Approach 1:
The patent segments the computational workload across multiple cluster heads rather than concentrating it in a single complex central system. Each cluster head implements simplified anomaly detection algorithms for its local cluster, reducing individual device complexity while maintaining overall detection accuracy through distributed processing.
Solution Approach 2:
The patent enables cluster heads to autonomously perform anomaly detection on their own cluster data without requiring complex centralized control. This self-service capability reduces system complexity by distributing intelligence to edge nodes while maintaining detection accuracy through local autonomous decision-making.
Data Source
AI summary
Methods, devices and computer program products for data analysis are provided. For example, a method comprises: in response to receiving target data from a target sensor at a first time, determining one or more reference sensors based on location information of a neighbor sensor adjacent to the target sensor and a second time of receiving the latest data from the neighbor sensor; determining reference estimation data of the one or more reference sensors at the first time based on historical sensor data obtained from the one or more reference sensors; determining target estimation data of the target sensor at the first time based on the reference estimation data; and detecting abnormity of the target data based on the target data and the target estimation data. In this way, abnormity of the sensor data may be detected efficiently and accurately.