Predictive Compressive Sampling for Low-Traffic Sensor Networks

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional sensor networks face inefficiencies in data transmission and processing due to high network traffic, resource consumption, and delays caused by redundant data transmission and compression methods, which hinder advanced data analysis and time-critical applications.

Innovation Solution

An adaptive predictive compressive principal component model is implemented, shifting computationally intensive tasks to a server environment, allowing for optimal sparsifying transforms and subsampling parameters to be determined, and enabling efficient bandwidth use and reduced latency by separating frequency decomposition and sparsifying transformations between sensors and servers.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If conventional compression methods are used to reduce data size, then data transmission efficiency is improved, but processing time increases and resource consumption increases

Engineering Contradiction:
Improvedata sizeVSAvoidprocessing time
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent performs sparsifying transformation and subsampling at the sensor node before data transmission, preparing the data in advance for efficient compression. This preliminary action at the source eliminates the need for time-consuming compression operations at the gateway, resolving the contradiction between data size reduction and processing time.

Inventive Principle:
Principle #10Preliminary action

2Loss of energy

If compression is performed at the gateway to reduce bandwidth usage, then network resource efficiency is improved, but computational resource consumption increases

Engineering Contradiction:
Improvebandwidth usageVSAvoidcomputational resource consumption
Core Design Contradiction:
Loss of energyVSUse of energy by moving object

Solution Approach 1:

The patent segments the data processing workflow into two parts: sparsifying transformation performed at sensor nodes using local computational resources, and subsampling performed at the gateway using minimal computational resources. This segmentation distributes the computational burden, reducing both bandwidth usage and gateway computational resource consumption simultaneously.

Inventive Principle:
Principle #1Segmentation

3Quantity of substance

If adaptive sampling schemes are implemented to reduce redundant data transmission, then network traffic is reduced, but device complexity increases

Engineering Contradiction:
Improvenetwork trafficVSAvoidsampling scheme complexity
Core Design Contradiction:
Quantity of substanceVSDevice complexity

Solution Approach 1:

The patent changes the sampling parameters dynamically by adapting the sparsifying transformation basis and subsampling rate based on the actual characteristics of the sensed signal. This parameter adaptation enables the system to reduce network traffic effectively while keeping the underlying sampling mechanism relatively simple and manageable.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3398347B1Method and system for determining a sampling scheme for sensor data
Publication Date: 2020.04.29 TERAKI GMBH
  • EP3398347B1 patent drawingFigure 1
  • EP3398347B1 patent drawingFigure 2~3A
  • EP3398347B1 patent drawingFigure 3B

AI summary

A device and computer-executable method is provided for adaptively determining a sampling scheme to be applied at a first sensor from among a plurality of sensors for sampling sensor data values corresponding to a signal. A sparsifying transform for a subsequent sampling time window of the first sensor is predicted, wherein the sparsifying transform is determined based on a predictive model of the sparsity of the signal. Moreover, a subsampling parameter for the subsequent sampling time window is determined. The subsampling parameter corresponds to a number of sensor data values to be acquired within the sampling time window. This subsampling parameter is determined based on the predicted sparsifying transform. Further determined is a compressive sampling scheme for the subsequent sampling time window of the first sensor. The compressive sampling scheme is determined based on the predicted sparsifying transform.