Cross-modal intelligent sensing method for intelligent residential and commercial motor home

A business RV and intelligent perception technology, applied in the field of deep learning and intelligent perception technology, can solve the problems of asymmetric data acquisition, no bus, inconsistent interfaces, etc., to improve the efficiency of data input and output, ensure data diversification, and simplify connections structure effect

Active Publication Date: 2018-07-06
CHONGQING UNIV OF POSTS & TELECOMM
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the basic problem faced by the intelligent transformation of residential and commercial RVs is that there are many types of on-board equipment in the living area, but the interfaces are inconsistent, and there is no standard bu

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
  • Cross-modal intelligent sensing method for intelligent residential and commercial motor home
  • Cross-modal intelligent sensing method for intelligent residential and commercial motor home
  • Cross-modal intelligent sensing method for intelligent residential and commercial motor home

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0032] Hereinafter, the preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0033] The present invention includes the following steps:

[0034] 1. Sensor signal data transmission and collection based on CAN bus structure. It includes the following 3 steps:

[0035] 1. Build a CAN bus data acquisition platform.

[0036] 2. All digital communication signals.

[0037] 3. Unified interface function, program call port, interface verification and testing method

[0038] 2. Data coding design. Include the following 3 steps

[0039] 1. Use the data encoding method with deep self-encoding technology as the core.

[0040] 2. Construct a multilayer deep neural network structure.

[0041] 3. The autoencoder encodes the perception data by itself.

[0042] 3. Optimized deep autoencoder pruning. Include the following 3 steps.

[0043] 1. Neural network pruning technology.

[0044] 2. Optimize the neural network connection relationship. ...

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 relates to a cross-modal intelligent sensing method for an intelligent residential and commercial motor home. The method specifically comprises the following steps of S1, performing datacollection and transmission on a sensor signal based on a bus structure; S2, extracting sensed data with similarity in collected data via a depth self-coder, and simplifying data codes; and S3, optimizing a connection network structure by using a weight connection relation of the self-coder. Aiming at the problem that the data transmission load is large, the data coding technology using a depth self-coding technology as the core is adopted, so that the load balancing of data transmission is ensured and the data dimension is reduced while the data transmission quality is ensured. The method provided by the invention provides a sparse optimized neural network pruning technology, the connection structure is simplified after the weight of the connection relation is measured, and the data input/output efficiency and the operation efficiency of the coder are improved.

Description

technical field [0001] The invention belongs to the field of intelligent perception technology and deep learning technology, and relates to a cross-modal intelligent perception method for an intelligent sojourn commercial caravan. Background technique [0002] The smart business caravan is the product of the deep integration of intelligent networked cars and smart homes. It fully embodies the technical and social attributes of artificial intelligence, stimulates the great potential of artificial intelligence, strengthens the organic combination of innovation chain and industrial chain, and gives birth to the The interactive evolution of technology supply and market demand. The process of "intelligence" of business caravans mainly involves the collection, processing and output of sensory data in artificial intelligence technology. At the same time, a large number of embedded systems and smart components are used to further improve the online status monitoring and autonomy of ...

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
IPC IPC(8): H04L1/00H04L12/24H04L12/40G06N3/04
CPCH04L1/0006H04L12/40006H04L12/40169H04L41/044H04L41/12H04L2012/40273G06N3/045
Inventor 李嫄源张家昌李鹏华朱智勤米怡
Owner CHONGQING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap