Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Region monitoring method based on multi-instance multi-label learning in wireless sensor networks

A technology of wireless sensor network and multi-label learning, which is applied in wireless communication, network topology, data exchange network, etc., and can solve the problems of mass sensor data compression, etc.

Active Publication Date: 2019-05-24
NANJING UNIV OF POSTS & TELECOMM
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0013] In order to solve the technical problems raised by the above-mentioned background technology, the present invention aims to provide an area monitoring method based on multi-instance and multi-label learning in wireless sensor networks, which solves the problems of massive sensor data compression and information mining in wireless sensor networks, and further Utilizing the mined information to solve the problem of real-time assessment of the state of the monitoring area

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Region monitoring method based on multi-instance multi-label learning in wireless sensor networks
  • Region monitoring method based on multi-instance multi-label learning in wireless sensor networks
  • Region monitoring method based on multi-instance multi-label learning in wireless sensor networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The technical solutions of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0065] Such as figure 1 The overall flowchart of the present invention is shown, and the present invention includes three processes: data collection, model training / updating, and network state prediction.

[0066] First, it is necessary to train a prediction model through the collected data, such as figure 2 As shown, the steps are as follows:

[0067] Step 1: Collect sensor network data at T moments to form a data set D o ={(N t ,Y t ), t=1,2,...,T}, N t ={s t,1 ,s t,2 ,...,S t,i ,...,S t,M} represents the data collected by the sensor network at time t, s t,i Indicates the data collected by the i-th sensor at time t, M is the total number of sensors in the entire sensor network, Y t ={y t,1 ,y t,2 ,...,y t,l ,...,y t,L} represents the state vector of the sensor network at time t, Y t There are L states y that need to be mo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an area monitoring method based on multi-instance and multi-label learning in a wireless sensor network, and utilizes Fisher Kernel to compress data of multiple sensor nodes at the same time. After compression, at a certain moment, the entire wireless sensor network corresponds to a single-instance data instead of multi-instance data. Use MMD to compress historical package data, select the most representative package data, and form a data subset. The training on the compressed data and the evaluation of the state of the monitoring area are completed using a fast multi-instance multi-label algorithm. The invention builds a sensor network state prediction model on the two-layer compressed sensor data set, and can realize rapid network state prediction.

Description

technical field [0001] The invention belongs to the field of wireless sensor network technology and machine learning technology, and in particular relates to an area monitoring method based on multi-instance multi-label learning. Background technique [0002] As an emerging technology that can have a profound impact on the future life of human beings, Wireless Sensor Networks (WSNs) technology has received widespread attention in recent years. The application of WSNs technology involves many fields, including national defense technology, Internet of Things technology, environmental monitoring, remote control, interstellar exploration, etc. The research on WSNs is of great significance. [0003] An important source of data in the era of big data is the sensor network. The task of the sensor network is to help people monitor the situation of the monitoring object in a certain area, rather than the situation of a specific node. The nodes in the sensor network are meaningless ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04L12/24H04W84/18G06K9/62G06K9/66G06F16/28
CPCH04L41/142H04L41/145H04L41/147H04W84/18G06F16/285G06V30/194G06F18/24G06F18/214
Inventor 胡海峰唐川吴建盛
Owner NANJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products