CN111311178A - Intelligent garbage classification transfer traceable system - Google Patents

Intelligent garbage classification transfer traceable system Download PDF

Info

Publication number
CN111311178A
CN111311178A CN202010077007.9A CN202010077007A CN111311178A CN 111311178 A CN111311178 A CN 111311178A CN 202010077007 A CN202010077007 A CN 202010077007A CN 111311178 A CN111311178 A CN 111311178A
Authority
CN
China
Prior art keywords
garbage
neurons
layer
unit
weight
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202010077007.9A
Other languages
Chinese (zh)
Inventor
王科炜
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Ruiyang Environmental Technology Co ltd
Original Assignee
Hangzhou Ruiyang Environmental Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Ruiyang Environmental Technology Co ltd filed Critical Hangzhou Ruiyang Environmental Technology Co ltd
Priority to CN202010077007.9A priority Critical patent/CN111311178A/en
Publication of CN111311178A publication Critical patent/CN111311178A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/10—Office automation; Time management
    • G06Q10/103—Workflow collaboration or project management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2323—Non-hierarchical techniques based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Business, Economics & Management (AREA)
  • Biophysics (AREA)
  • Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Human Resources & Organizations (AREA)
  • Molecular Biology (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • General Health & Medical Sciences (AREA)
  • Neurology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Computational Linguistics (AREA)
  • Computing Systems (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Microelectronics & Electronic Packaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Discrete Mathematics (AREA)
  • Evolutionary Biology (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention relates to an intelligent garbage classification transfer traceable system, which comprises a garbage throwing personnel identity information acquisition unit; the channel analysis unit is used for analyzing the channel of the acquisition unit; the allocation unit is used for confirming the identity according to the analysis result and allocating a unique code to the garbage throwing personnel; the garbage recording unit is used for recording the thrown garbage data; a data storage unit for storing the thrown-in garbage data; the background management unit is used for being communicated with the data storage unit; the system comprises a client, an operation end and a general server, wherein the client, the operation end and the general server are communicated with a background management unit. The system can trace the information of garbage throwing personnel, trace the garbage throwing region, judge the positivity of the garbage throwing in the region, quickly classify and distribute the unique codes through an intelligent algorithm, avoid error tracing, increase the comprehensiveness of data due to the fact that the collection form is not limited by the mode, the type and the number, manage all uploaded data in a centralized mode, and enhance the unified management performance.

Description

Intelligent garbage classification transfer traceable system
Technical Field
The invention relates to an intelligent garbage classification transfer traceable system, and belongs to the technical field of intelligent garbage cans.
Background
In the modern times, along with the continuous improvement of living standard of people, more and more garbage is generated in life. The dustbin on the market belongs to ordinary dustbin at present, and in the use, no matter park, campus or on the road, the intelligent garbage bin has begun to use, especially in the aspect of the garbage classification, not only the classification diversified, such as paper, glass, metal, fabric, harmful rubbish, recoverable rubbish and unrecoverable rubbish etc. appear. Under the development background, the utilization rate of the garbage is higher and higher, the recovered garbage can be changed into valuable things, the method is beneficial to recovering the valuable garbage for safely and reliably recovering paper, metal and fabric, and a system capable of tracing back to the information of a collector is developed.
Disclosure of Invention
In order to overcome the defects, the invention aims to provide an intelligent garbage classification transit traceability system which can quickly and effectively trace back the source.
In order to achieve the above object, the present invention adopts a technical solution comprising:
an intelligent garbage classification transfer traceable system comprises a garbage throwing personnel identity information acquisition unit; the channel analysis unit is used for analyzing the channel of the acquisition unit; the allocation unit is used for confirming the identity according to the analysis result and allocating a unique code to the garbage throwing personnel; the garbage recording unit is used for recording the thrown garbage data; a data storage unit for storing the thrown-in garbage data; the background management unit is used for being communicated with the data storage unit; and the client, the operation end and the general service end are communicated with the background management unit.
Further, the identity information acquisition unit of the garbage throwing personnel is at least one of code scanning identification, face identification, identity card identification, IC card identification and garbage automatic identification.
The channel analysis unit comprises an input layer, a competition layer and an output layer of the neurons, wherein the competition layer is provided with m neurons, the input layer is provided with n neurons, and the two layers are completely connected; each neuron of the output layer is only connected with one group of neurons in the competition layer, the connection weight is fixed to be 1, the weight between the input layer and the competition layer is gradually adjusted to be a clustering center in the training process through the LVQ network learning algorithm, when a sample is input into the LVQ network, the neurons of the competition layer generate winning neurons through a winner-king learning rule, the output of the winning neurons is allowed to be 1, and the output of other neurons is allowed to be 0. The neuron output of the output layer connected to the group where the winning neuron is located is 1, and the neurons of the other output layers are 0, thereby giving the pattern class of the current input sample, the class learned by the competition layer is a subclass, and the class learned by the output layer is a target class.
And the sample set in the LVQ network learning algorithm is { (xi, di) }, wherein di is I dimension, only one component of the L neurons corresponding to the output layer is 1, and other components are 0, so that a weight data matrix from the competition layer to the output layer is formed.
Further, the specific process of the LVQ network learning algorithm is as follows:
(1) initialization: randomly assigning small random numbers to weight vectors of each neuron of the competition layer, and determining initial learning rate and training times;
(2) inputting a sample vector;
(3) searching for a winning neuron;
(4) and (3) adjusting the weight of the winning neuron according to whether the classification is correct: when the network classification result is informed to the teacher
When the numbers are consistent, adjusting the weight to the input sample direction:
Figure BDA0002378727630000021
when the network classification result is inconsistent with the teacher signal, the weight is adjusted in the opposite direction of the input sample:
Figure BDA0002378727630000022
the weights of the other non-winning neurons remain unchanged,
wherein η (t, N) is a function of training time t and topological distance N between jth and winning neurons in the neighborhood, wij(t +1) is the weight of the winning neuron, wij(t) is the non-winning neuron weight,
Figure BDA0002378727630000023
is a sample parameter value;
(5) updating the learning rate:
Figure BDA0002378727630000024
and (3) when the training times do not reach the set times, switching to the step (2) to input a next sample, and repeating the steps until the set training times, wherein in the training process, η (t) is ensured to be a monotone decreasing function.
The invention has the beneficial effects that: the system can trace the information of garbage throwing personnel, trace the garbage throwing region, judge the positivity of the garbage throwing in the region, quickly classify and distribute the unique codes through an intelligent algorithm, avoid error tracing, further increase the comprehensiveness and the tracing breadth of data due to the fact that the input collection form is not limited in mode, type and quantity, and can manage all uploaded data in a centralized mode and enhance the unified management performance.
Drawings
FIG. 1 is a schematic flow diagram of a system according to the present invention;
FIG. 2 is a schematic diagram of the structure of a learning vector quantization neural network according to the present invention;
fig. 3 is a schematic diagram of the LVQ network learning algorithm principle according to the present invention.
Detailed Description
For a better understanding of the present invention, the following examples and drawings are included to further illustrate the present invention, but the present invention is not limited to the following embodiments.
The terms referred to in the following examples are labeled with their meanings:
learning Vectorization (LVQ);
lossy compression techniques based on vector quantization: vector quantization, dividing the high-dimensional input space into a plurality of different regions, determining a central vector for each region as the center of a cluster, and representing the input vector in the same region by the central vector, thereby forming a point set taking each central vector as the center of the cluster. In the field of image processing, the encoding of the center point (vector) of each region is commonly used to replace the point in the region for storage or transmission.
Voronoi diagram: the distribution of the central vectors represented on the two-dimensional input plane is called Voronoi diagram.
The winner-in-the-king learning rule (only the competitive winning neuron can adjust the weight vector, and any other neuron has no weight to adjust the weight vector, so that the inhibition of all the peripheral neurons by the winner-in-the-go learning rule is in a 'blocking' mode) and the SOFM competitive learning algorithm are vector quantization algorithms.
And (4) quantizing the learning vector, adopting a supervision mechanism, adding a teacher signal (the specific content is the category of the input sample) as classification information in training to fine-tune the weight, and pre-assigning the category of the output neuron.
In this embodiment, the intelligent garbage classification transit traceable system comprises a garbage throwing person identity information acquisition unit; the channel analysis unit is used for analyzing the channel of the acquisition unit; the allocation unit is used for confirming the identity according to the analysis result and allocating a unique code to the garbage throwing personnel; the garbage recording unit is used for recording the thrown garbage data; a data storage unit for storing the thrown-in garbage data; the background management unit is used for being communicated with the data storage unit; and the client, the operation end and the general service end are communicated with the background management unit.
FIG. 1 is a schematic flow diagram of a system according to the present invention.
As shown in fig. 1: the operation flow of the intelligent garbage classification transfer traceable system is as follows:
(1) collecting identity information of garbage throwing personnel: collecting identity information of a garbage throwing person by using any form of code scanning identification, face identification, identity card identification, IC card identification, garbage automatic identification and the like;
(2) channel analysis:
FIG. 2 is a schematic diagram of the structure of the learning vector quantization neural network according to the present invention.
As shown in fig. 2: the channel analysis unit comprises an input layer, a competition layer and an output layer of the neurons, wherein the competition layer is provided with m neurons, the input layer is provided with n neurons, and the two layers are completely connected; each neuron of the output layer is only connected with one group of neurons in the competition layer, the connection weight is fixed to be 1, the weight between the input layer and the competition layer is gradually adjusted to be a clustering center in the training process through the LVQ network learning algorithm, when a sample is input into the LVQ network, the neurons of the competition layer generate winning neurons through a winner-king learning rule, the output of the winning neurons is allowed to be 1, and the output of other neurons is allowed to be 0. The neuron output of the output layer connected to the group where the winning neuron is located is 1, and the neurons of the other output layers are 0, thereby giving the pattern class of the current input sample, the class learned by the competition layer is a subclass, and the class learned by the output layer is a target class.
The LVQ network learning algorithm combines a competitive learning rule and instructor learning, a sample set is { (xi, di) } the sample set in the LVQ network learning algorithm is { (xi, di) }, wherein di is I dimension, corresponding to L neurons of an output layer, only one component of the L neurons is 1, other components are 0, each neuron of the competitive layer is assigned to one output neuron, and the corresponding weight is 1, so that the weight of the output layer is obtained, and finally a weight data matrix from the competitive layer to the output layer is formed.
Such as: the LVQ network has 6 neurons in competition layer and 3 neurons in output layer, and represents 3 classes. If 1, 3 of the competition layer is designated as the first output neuron, 2, 5 is designated as the second output neuron, and 3, 6 is designated as the third output neuron. The weight matrix from the competition layer to the output layer is:
Figure BDA0002378727630000041
fig. 3 is a schematic diagram of the LVQ network learning algorithm principle according to the present invention.
As shown in fig. 3: the weights from the competition layer to the output layer are predefined before training, so that the class of the output neuron is specified, the output neuron is not changed during training, the learning of the network is carried out by changing the weights from the input layer to the competition layer, whether the current classification is correct or not can be judged according to the class of the input sample and the class of the winning neuron, if the classification is correct, the weight vector of the winning neuron is adjusted towards the direction of the input vector, and if the classification is wrong, the weight vector of the winning neuron is adjusted towards the opposite direction.
The specific process of the LVQ network learning algorithm is as follows:
(1) initialization: randomly assigning small random numbers to weight vectors of each neuron of the competition layer, and determining initial learning rate and training times;
(2) inputting a sample vector;
(3) searching for a winning neuron;
(4) and (3) adjusting the weight of the winning neuron according to whether the classification is correct: when the network classification result is informed to the teacher
When the numbers are consistent, adjusting the weight to the input sample direction:
Figure BDA0002378727630000051
when the network classification result is inconsistent with the teacher signal, the weight is adjusted in the opposite direction of the input sample:
Figure BDA0002378727630000052
the weights of the other non-winning neurons remain unchanged,
wherein η (t, N) is a function of training time t and topological distance N between jth and winning neurons in the neighborhood, wij(t +1) is the weight of the winning neuron, wij(t) is the non-winning neuron weight,
Figure BDA0002378727630000053
is a sample parameter value;
(5) updating the learning rate:
Figure BDA0002378727630000054
when the training frequency does not reach the set frequency, the next sample is input in the step (2), and the steps are repeated until the training frequency is set, wherein in the training process, η (t) is ensured to be a monotone decreasing function.
(3) And (3) confirming the identity: confirming the identity according to the analysis result;
(4) assigning a unique code: the allocation unit allocates a unique code to the garbage throwing personnel;
(5) data matrix recording: the garbage recording unit records the thrown garbage data, such as identity information of a person throwing the garbage, the garbage quality, the garbage type, the garbage position information and the like;
(6) data storage: the thrown garbage data, the identity information of the thrower and the like are stored in a data storage unit;
(7) background management: the data management, the scheduling and the like are carried out through the background management unit, and the data management, the scheduling and the like can be specifically distributed to a next-level client, an operation end, a main server and the like, so that the real-time monitoring, the tracing and the like are realized.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.

Claims (6)

1. An intelligent garbage classification transfer traceable system is characterized by comprising a garbage throwing personnel identity information acquisition unit; the channel analysis unit is used for analyzing the channel of the acquisition unit; the allocation unit is used for confirming the identity according to the analysis result and allocating a unique code to the garbage throwing personnel; the garbage recording unit is used for recording the thrown garbage data; a data storage unit for storing the thrown-in garbage data; the background management unit is used for being communicated with the data storage unit; and the client, the operation end and the general service end are communicated with the background management unit.
2. The intelligent garbage classification transit traceability system of claim 1, wherein the garbage throwing person identity information acquisition unit is at least one of code scanning recognition, face recognition, identification card recognition, IC card recognition and garbage automatic recognition.
3. The intelligent garbage classification transit traceable system according to claim 1, wherein the channel analysis unit comprises an input layer, a competition layer and an output layer of neurons, the competition layer comprises m neurons, the input layer comprises n neurons, and the two layers are completely connected; each neuron of the output layer is only connected with one group of neurons in the competition layer, the connection weight is fixed to be 1, the weight between the input layer and the competition layer is gradually adjusted to be a clustering center in the training process through the LVQ network learning algorithm, when a sample is input into the LVQ network, the neurons of the competition layer generate winning neurons through a winner-king learning rule, the output of the winning neurons is allowed to be 1, and the output of other neurons is allowed to be 0. The neuron output of the output layer connected to the group where the winning neuron is located is 1, and the neurons of the other output layers are 0, thereby giving the pattern class of the current input sample, the class learned by the competition layer is a subclass, and the class learned by the output layer is a target class.
4. The intelligent system of claim 3, wherein the sample set in the LVQ learning algorithm is { (xi, di) }, where di is the I dimension, corresponding to L neurons in the output layer, and only one component of which is 1, and the other components are 0, thereby forming a weight data matrix from the competition layer to the output layer.
5. The intelligent garbage classification transit traceable system according to claim 3 or 4, wherein the specific process of the LVQ network learning algorithm is as follows:
(1) initialization: randomly assigning small random numbers to weight vectors of each neuron of the competition layer, and determining initial learning rate and training times;
(2) inputting a sample vector;
(3) searching for a winning neuron;
(4) and (3) adjusting the weight of the winning neuron according to whether the classification is correct: when the network classification result is consistent with the teacher signal, the weight is adjusted towards the input sample direction:
Figure FDA0002378727620000021
when the network classification result is inconsistent with the teacher signal, the weight is adjusted in the opposite direction of the input sample:
Figure FDA0002378727620000022
the weights of the other non-winning neurons remain unchanged,
where η (t, N) is a function of training time t and the topological distance N between the jth and winning neurons in the neighborhood, ωij(t +1) is the weight of the winning neuron, ωij(t) is the non-winning neuron weight,
Figure FDA0002378727620000023
is a sample parameter value;
(5) updating the learning rate:
Figure FDA0002378727620000024
when the training frequency does not reach the set frequency, the next sample is input in the step (2), and the steps are repeated until the training frequency is set, wherein in the training process, η (t) is ensured to be a monotone decreasing function.
6. The intelligent system according to claim 1, wherein the garbage data comprises: identity information of personnel throwing the garbage, the garbage quality, the garbage type and the garbage position information.
CN202010077007.9A 2020-01-23 2020-01-23 Intelligent garbage classification transfer traceable system Pending CN111311178A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010077007.9A CN111311178A (en) 2020-01-23 2020-01-23 Intelligent garbage classification transfer traceable system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010077007.9A CN111311178A (en) 2020-01-23 2020-01-23 Intelligent garbage classification transfer traceable system

Publications (1)

Publication Number Publication Date
CN111311178A true CN111311178A (en) 2020-06-19

Family

ID=71146902

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010077007.9A Pending CN111311178A (en) 2020-01-23 2020-01-23 Intelligent garbage classification transfer traceable system

Country Status (1)

Country Link
CN (1) CN111311178A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112215147A (en) * 2020-10-12 2021-01-12 平安国际智慧城市科技股份有限公司 Tracing method, device, equipment and storage medium for garbage throwing position

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110386385A (en) * 2019-07-30 2019-10-29 东莞弓叶互联科技有限公司 A kind of acquisition of rubbish impression information and retroactive method for intelligent garbage bin
CN110473130A (en) * 2019-07-30 2019-11-19 五邑大学 A kind of garbage classification evaluation method, device and storage medium based on deep learning

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110386385A (en) * 2019-07-30 2019-10-29 东莞弓叶互联科技有限公司 A kind of acquisition of rubbish impression information and retroactive method for intelligent garbage bin
CN110473130A (en) * 2019-07-30 2019-11-19 五邑大学 A kind of garbage classification evaluation method, device and storage medium based on deep learning

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
梁娜等: "基于学习矢量量化(LVQ)神经网络的高校毕业生学位评审预测", 《甘肃科学学报》 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112215147A (en) * 2020-10-12 2021-01-12 平安国际智慧城市科技股份有限公司 Tracing method, device, equipment and storage medium for garbage throwing position

Similar Documents

Publication Publication Date Title
CN103116766B (en) A kind of image classification method of encoding based on Increment Artificial Neural Network and subgraph
Zhou et al. Extracting symbolic rules from trained neural network ensembles
CN111181939A (en) Network intrusion detection method and device based on ensemble learning
CN103279392B (en) A kind of load sorting technique run on virtual machine under cloud computing environment
CN108304427A (en) A kind of user visitor's heap sort method and apparatus
CN109409400A (en) Merge density peaks clustering method, image segmentation system based on k nearest neighbor and multiclass
KR20190123372A (en) Apparatus and method for robust face recognition via hierarchical collaborative representation
CN110414376B (en) Method for updating face recognition model, face recognition camera and server
CN110245783B (en) Short-term load prediction method based on C-means clustering fuzzy rough set
CN102324038A (en) A kind of floristics recognition methods based on digital picture
CN109960808A (en) A kind of text recognition method, device, equipment and computer readable storage medium
CN109858518A (en) A kind of large data clustering method based on MapReduce
CN111186656A (en) Target garbage classification method and intelligent garbage can
CN109711473A (en) Item identification method, equipment and system
CN108375729B (en) Degenerate state appraisal procedure is clustered based on the motor SOM that Fisher differentiates
CN116028838B (en) Clustering algorithm-based energy data processing method and device and terminal equipment
CN107577994A (en) A kind of pedestrian based on deep learning, the identification of vehicle auxiliary product and search method
CN113255617B (en) Image recognition method and device, electronic equipment and computer-readable storage medium
CN108333468A (en) The recognition methods of bad data and device under a kind of active power distribution network
Rahman et al. Serial combination of multiple experts: A unified evaluation
Mookkaiah et al. Design and development of smart Internet of Things–based solid waste management system using computer vision
CN112734037A (en) Memory-guidance-based weakly supervised learning method, computer device and storage medium
CN111311178A (en) Intelligent garbage classification transfer traceable system
CN114359632A (en) Point cloud target classification method based on improved PointNet + + neural network
CN110597792A (en) Multistage redundant data fusion method and device based on synchronous line loss data fusion

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination