Supercharge Your Innovation With Domain-Expert AI Agents!

Deep learning method for garbage recognition classification and processing based on subconvolution hyper-correlation

A deep learning, recognition and classification technology, applied in character and pattern recognition, scientific instruments, analytical materials, etc., can solve the problems of interlayer overflow, high cost, high cost of gas waste disposal, and improve the time for deep learning and object recognition. reduced effect

Inactive Publication Date: 2019-07-26
南京康博智慧健康研究院有限公司
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] (1) The existing neural network misses the information in complex numbers in quantum computing, which can easily lead to interlayer overflow
[0008] (2) The existing solid waste treatment methods may produce violent reactions between different solids and generate additional toxic gases, causing damage to the human body and the environment
[0009] (3) The cost of the existing gas waste disposal method is very high, requiring professional chemical defense troops
[0010] Difficulty in solving the above technical problems: solid waste disposal will cause harm to human body and environment, and the cost of gas waste disposal is very high

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
  • Deep learning method for garbage recognition classification and processing based on subconvolution hyper-correlation
  • Deep learning method for garbage recognition classification and processing based on subconvolution hyper-correlation
  • Deep learning method for garbage recognition classification and processing based on subconvolution hyper-correlation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below in conjunction with the examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0062] The invention utilizes embedded technology, garbage positioning technology, signal processing and identification technology in the mine robot, and realizes the functions of automatic identification, classification and recycling of garbage by the robot. At the same time, it has the function of gas recovery and cooperation with multiple robots.

[0063] The application principle of the present invention will be described in detail below in conjunction with the accompanying drawings.

[0064] Such as Figure 1-Figure 4 As shown, the deep learning system for garbage identification and classification processing based on...

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 belongs to the technical field of electronic classification, and discloses a deep learning method for garbage recognition classification and processing based on subconvolution hyper-correlation, which comprises the following steps: deeply learning a group of sequences input by a convolutional layer, and obtaining a coefficient expressed by a gamma function of a generalized binomial of the sequence according to a generalized binomial formula; carrying out convolution on the input data and the weight matrix of the convolution layer after carrying out operation on the input data byusing the subconvolution; carrying out super-variance operation on the obtained corresponding output data; obtaining whether an object in the visual field of the camera is mine garbage or not, and knowing which kind of garbage the object is; and transmitting the obtained information to the control module, and enabling the control module to trigger the manipulator to recover the object, or the peripheral module cleans the object to complete the whole recovery or on-site treatment process. The deep learning method can be used in the sanitation cleaning system and can also be used in any dangerous occasion which cannot be reached by human beings.

Description

technical field [0001] The invention belongs to the technical field of electronic classification, and in particular relates to a deep learning method for garbage identification and classification processing based on sub-convolution super-correlation. Background technique [0002] Currently, the closest prior art: [0003] With the development of industrial production, the amount of industrial waste is increasing day by day. However, there are only a limited number of industrial wastes that have been utilized. For example, countries such as Japan have utilized fly ash and cinders, and countries such as the United States have utilized steel slag. Most industrial wastes are mainly stockpiled, and some hazardous solids are treated by incineration, landfill, chemical conversion and other methods. Coal is an important basic energy and an important raw material in China. In recent years, my country's coal industry has developed rapidly, but its safety and waste disposal problems ...

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): G06K9/62G06N3/04G01N33/00
CPCG01N33/0031G06N3/045G06F18/21355G06F18/24
Inventor 黄骏王洁徐童
Owner 南京康博智慧健康研究院有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More