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

Multi-layer feed-forward artificial neural network parallel algorithm based on AI human body behaviors

An artificial neural network and parallel algorithm technology, applied in biological neural network models, neural learning methods, neural architectures, etc., can solve the problem of reducing the accuracy of the final human behavior recognition results, and cannot reflect the user's human behavior information and sensor data well. It does not meet the requirements of the database and other problems, and achieves the effects of rich dynamic effects, good user experience, and low response delay.

Pending Publication Date: 2022-04-01
南京市科小卫智能科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, the present invention provides a multi-layer feed-forward artificial neural network parallel algorithm based on AI human behavior, which solves the problem that the existing sensor data does not meet the requirements of the human sample behavior database to be constructed, and the data information is too complicated Or lack of integrity, unable to reflect the user's human behavior information well, the reliability is not high, reduce the accuracy of the final human behavior recognition result, and cannot use the previously constructed sample behavior recognition model to complete the technical problem of human behavior recognition tasks

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
  • Multi-layer feed-forward artificial neural network parallel algorithm based on AI human body behaviors
  • Multi-layer feed-forward artificial neural network parallel algorithm based on AI human body behaviors
  • Multi-layer feed-forward artificial neural network parallel algorithm based on AI human body behaviors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0026] see figure 1 , the embodiment of the present invention provides a kind of technical solution: a kind of multi-layer feed-forward artificial neural network parallel algorithm based on AI human behavior, including video characteristic code input layer, hidden layer, model excitation output layer and Spark bottom layer, described framework PANN is composed of a video feature code input layer, multiple hidden layers, and a model excitation output layer. The...

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 the technical field of AI behavior network algorithms, and discloses a multilayer feed-forward artificial neural network parallel algorithm based on AI human body behaviors, which comprises a video feature code input layer, hidden layers, a model excitation output layer and a Spark bottom layer, and is characterized in that a frame PANN is composed of one video feature code input layer, a plurality of hidden layers and one model excitation output layer, a backward propagation error adjustment formula is adopted, the video feature code input layer, the hidden layers and the model excitation output layer are connected through a one-way weight network, the Spark bottom layer is realized by a Scala language, and the depth of the neural network is related to the number of the hidden layers and the time length. According to the multi-layer feedforward artificial neural network parallel algorithm based on the AI human body behaviors, the task of human body behavior recognition is completed by adopting a neural network model method, the accuracy of human body sample behavior recognition is ensured, the ability of a system to complete the task of human body online behavior recognition is fully improved, and the system is smooth to operate.

Description

technical field [0001] The invention relates to the technical field of AI behavior network algorithms, in particular to a multi-layer feedforward artificial neural network parallel algorithm based on AI human behavior. Background technique [0002] Human behavior recognition can be divided into four levels according to the complexity of the research object: posture, individual behavior, interactive behavior and group behavior, where interactive behavior is an action completed by two or more people, and group behavior refers to an action completed by a group of people . At present, group behavior is affected by complex semantics and environment, and there are relatively few studies, most of which focus on posture and individual behavior. Human behavior pattern recognition has a huge market demand in the fields of security, education, and smart cities. Therefore, domestic and foreign R&D institutions and enterprises are focusing on and investing in technology development. ...

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 Applications(China)
IPC IPC(8): G06N3/04G06N3/08G06N3/10G06F8/30
Inventor 卢大伟李宁马君腾天龙
Owner 南京市科小卫智能科技有限公司
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com