CN111724495A - Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network - Google Patents

Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network Download PDF

Info

Publication number
CN111724495A
CN111724495A CN202010363977.5A CN202010363977A CN111724495A CN 111724495 A CN111724495 A CN 111724495A CN 202010363977 A CN202010363977 A CN 202010363977A CN 111724495 A CN111724495 A CN 111724495A
Authority
CN
China
Prior art keywords
attendance
gateway
cloud
neural network
data
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
CN202010363977.5A
Other languages
Chinese (zh)
Inventor
牛俊彬
吕智民
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 Renlian Technology Co ltd
Original Assignee
Hangzhou Renlian 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 Renlian Technology Co ltd filed Critical Hangzhou Renlian Technology Co ltd
Priority to CN202010363977.5A priority Critical patent/CN111724495A/en
Publication of CN111724495A publication Critical patent/CN111724495A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/10—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people together with the recording, indicating or registering of other data, e.g. of signs of identity
    • 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • 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
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00—Data switching networks
    • H04L12/66—Arrangements for connecting between networks having differing types of switching systems, e.g. gateways
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/01—Protocols
    • H04L67/10—Protocols in which an application is distributed across nodes in the network
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00—Network arrangements or protocols for supporting network services or applications
    • H04L67/50—Network services
    • H04L67/55—Push-based network services
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/80—Services using short range communication, e.g. near-field communication [NFC], radio-frequency identification [RFID] or low energy communication

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Time Recorders, Dirve Recorders, Access Control (AREA)

Abstract

The invention provides a non-inductive attendance system based on a bi-directional gateway, an RFID (radio frequency identification) and a BP (back propagation) neural network, which is characterized by comprising an outdoor directional gateway, an indoor directional gateway, an active RFID tag, a router, a cloud server, cloud attendance data receiving and processing software, cloud kafka message queue software, a cloud database, cloud attendance notification push software, BP neural network data analysis software, and a terminal or application software for receiving attendance notifications. Compared with the prior art, the active RFID signals are collected by adopting the dual-directional gateways of the outdoor directional gateway and the indoor directional gateway, so that the card-punching missing probability can be obviously reduced, and the in-and-out direction of a user can be accurately judged; in a high concurrency scene, the performance is stable and efficient, and the detection is timely and accurate; the accuracy of classified prediction of attendance checking in and out is improved, the method can adapt to more complex field environment, and the application of the active RFID technology in the field of automatic noninductive attendance checking is effectively promoted.

Description

Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network
Technical Field
The invention relates to the technical field of artificial intelligence in the internet technology, in particular to a non-inductive attendance system and a method based on a dual-orientation gateway, an RFID and a BP neural network.
Background
With the rapid development and popularization of the internet of things technology, the Radio Frequency Identification Device (RFID) technology is widely applied to numerous fields such as logistics transportation, supply chains, industrial automation and the like, the enterprise management and operation efficiency is greatly improved, and the enterprise operation cost is greatly reduced.
At present, an automatic personnel attendance system based on Radio Frequency Identification (RFID), communication and internet technologies is gradually applied to communities, schools, factories, enterprises and public institutions due to the advantages of low cost, low power consumption, long distance, no perception, batch acquisition and the like.
Attendance systems based on RFID automatic identification technology mostly adopt the technical scheme of RFID gateway + active RFID label. The scheme has the advantages of simple installation and deployment, remote automatic identification, large-batch centralized collection, high access efficiency, no manual queuing and card punching, automatic generation of attendance reports and the like. However, this solution also has the following disadvantages: the access direction of the user cannot be accurately judged, and the RFID label is easily shielded by a human body or interfered by the field environment, so that the card punching can be missed with a high probability. These problems cause great troubles to the popularization and application of automatic noninductive attendance based on the active RFID technology.
Disclosure of Invention
Aiming at the defects in the prior art, the invention provides a non-inductive attendance system and a method based on a dual-orientation gateway, an RFID and a BP neural network, wherein the non-inductive attendance system comprises the following steps:
the technical scheme of the invention is realized as follows:
a non-inductive attendance system based on a dual directional gateway, an RFID and a BP neural network comprises an outdoor directional gateway, an indoor directional gateway, an active RFID tag, a router, a cloud server, cloud attendance data receiving and processing software, cloud kafka message queue software, a cloud database, cloud attendance notification pushing software, BP neural network data analysis software, and a terminal or application software for receiving attendance notifications, wherein the BP neural network data analysis software, the cloud kafka message queue software, the cloud attendance pushing notification software and the cloud attendance data receiving and processing software run on the cloud server, the outdoor directional gateway and the indoor directional gateway are connected with the router through network cables, the router is connected with the Internet through the network cables, the active RFID tag is carried by a user, the outdoor directional gateway and the indoor directional gateway are connected with the Internet through the router and are kept in long connection with the cloud server in a TCP protocol mode, and the outdoor directional gateway and the indoor directional gateway are provided with directional antennas.
Preferably, the router has a POE power supply function.
Preferably, the terminal or the application software comprises a short message, a WeChat public number and an attendance application APP.
The invention also provides a non-inductive attendance checking method, which comprises the following steps;
s1: an active RFID tag that transmits a wireless signal at a certain frequency;
s2: the outdoor directional gateway and the indoor directional gateway are responsible for acquiring signals sent by the active RFID label in the step S1 in the coverage range of the gateway, encrypting the acquired attendance data with time sequence at corresponding frequency and sending the encrypted attendance data to the cloud server;
s3: cloud attendance data receiving and processing software, which is responsible for receiving the original time sequence attendance data sent in the step S2, decrypting the original time sequence attendance data, storing the decrypted original time sequence attendance data into a cloud database, recording the first and last signal time of the active RFID tags, performing overtime detection on a plurality of active RFID tags through an annular timing queue, generating a record containing the active RFID tags, the starting time and the ending time by the overtime active RFID tags, and storing the record into a kafka message queue S3;
s4: BP neural network data analysis software subscribes to a kafka message queue s3, when data are generated, active RFID tag attendance time sequence data received by two directional base stations are respectively inquired from a cloud database according to the starting time and the ending time of an active RFID tag, two sections of time sequence data are further subjected to drying reduction treatment respectively, then the noise-reduced data are input into a trained attendance data classification prediction model, two user attendance access results are obtained after the analysis of the classification prediction model, the user access direction is obtained according to access direction judgment rules, and the results are stored in a kafka message queue s 4;
s5: and cloud attendance notification push software is responsible for taking out the active RFID tag attendance record from the kafka message queue s4 and issuing an attendance notification to user terminal equipment in a short message, WeChat public number and attendance application APP mode.
Preferably, in step S4, the processing for reducing two pieces of time series data includes: detecting deviation, and filtering abnormal fluctuation signals according to a preset deviation threshold value of a system; the entry/exit direction determination rule includes: (1) if the front of the gateway outside the door passes through or is close to the front of the gateway and the back of the gateway inside the door passes through or is far away from the front of the gateway, the user is considered to enter; (2) and if the front side of the gateway inside the door passes through or is close to the front side of the gateway outside the door and the back side of the gateway outside the door passes through or is far away from the front side of the gateway outside the door, the user is considered to go out.
Preferably, the circular timing queue specifically includes a data structure, a circular queue algorithm, a circular queue operation flow when an active RFID tag signal is received, and a circular queue timeout detection method.
Preferably, in step S4, the attendance data classification prediction model obtained through training of the BP neural network data analysis software classifies the prediction result of the active RFID tag attendance data into six categories: the front surface is close to, the front surface is far away from, the front surface passes through, the back surface is close to, the back surface is far away from and the back surface passes through.
Preferably, the BP neural network comprises an input layer, a hidden layer, and an output layer.
Preferably, the BP neural network comprises an attendance data classification algorithm, comprising: BP neural network construction, BP neural network training and BP neural network testing.
Compared with the prior art, the invention has the following beneficial effects:
according to the non-inductive attendance system and method based on the bi-directional gateway, the RFID and the BP neural network, the bi-directional gateways of the outside-door directional gateway and the inside-door directional gateway are adopted to collect active RFID signals, the probability of missed card punching can be obviously reduced, and the in-and-out direction of a user can be accurately obtained through signal characteristic comparison of the bi-directional gateways. The RFID tag is subjected to overtime detection by adopting an annular queue algorithm, and the performance is stable and efficient in a high concurrency scene, and the detection is timely and accurate; a set of complete attendance classification prediction model is established, the accuracy of attendance classification prediction can be obviously improved, the method can adapt to more complex field environment, and the application of the active RFID technology in the field of automatic non-inductive attendance is effectively promoted.
Drawings
Fig. 1 is a diagram of a non-inductive attendance system architecture based on a bi-directional gateway, an RFID and a BP neural network;
FIG. 2 is a schematic diagram of a circular timing monitoring queue;
FIG. 3 is a classification prediction model of attendance data;
FIG. 4 is a BP neural network structure;
fig. 5 is an attendance data classification algorithm based on a BP neural network.
Detailed Description
The present invention will now be described more fully hereinafter with reference to the accompanying drawings, in which embodiments of the invention are shown.
As shown in fig. 1, a non-inductive attendance system based on bi-directional gateway, RFID and BP neural network comprises an outdoor directional gateway, an indoor directional gateway, an active RFID tag, a router, a cloud server, cloud attendance data receiving and processing software, cloud kafka message queue software, a cloud database, cloud attendance notification push software, BP neural network data analysis software, and a terminal or application software for receiving attendance notification, wherein the BP neural network data analysis software, the cloud kafka message queue software, the cloud attendance push notification software, and the cloud attendance data receiving and processing software are run on the cloud server, the outdoor directional gateway and the indoor directional gateway are connected with the router through a network cable, the router is connected to the internet through a network cable, the active RFID tag is carried by a user, the outdoor directional gateway, the cloud server, the cloud attendance notification push software, the cloud attendance data receiving and processing software are run on the cloud server, the outdoor directional gateway and the indoor directional gateway are connected with the router through, The indoor directional gateway is accessed to the Internet through the router and is in long connection with the cloud server in a TCP protocol mode, and the outdoor directional gateway and the indoor directional gateway are both provided with directional antennas. The router has a POE power supply function. The terminal or the application software comprises a short message, a WeChat public number and an attendance application APP.
The invention also comprises a non-inductive attendance checking method, and the attendance checking data acquisition method comprises the following processes:
s1: an active RFID tag that transmits a radio signal (e.g., 10Hz) at a certain frequency;
s2: the two RFID gateways (an outdoor directional gateway and an indoor directional gateway) with directional antennas are responsible for acquiring signals sent by the active RFID label in the step S1 in the coverage range of the gateway, encrypting the acquired attendance data with time sequence at a certain frequency (for example, 1Hz) and sending the encrypted attendance data to the cloud server;
s3: cloud attendance data receiving and processing software, which is responsible for receiving the original time sequence attendance data sent in the step S2, decrypting the original time sequence attendance data, storing the decrypted original time sequence attendance data into a cloud database, recording the first time and last time signal time of the RFID tags, carrying out overtime detection on a plurality of RFID tags through an annular timing queue, generating a record containing the RFID tags, the starting time and the ending time by the overtime RFID tags, and storing the record into a kafka message queue S3;
s4: BP neural network data analysis software subscribes to a kafka message queue s3, when data are generated, according to the starting time and the ending time of an RFID label, RFID label attendance time sequence data received by two directional base stations are respectively inquired from a cloud database, two sections of time sequence data are further subjected to drying reduction treatment respectively, then the noise-reduced data are input into a trained attendance data classification prediction model, after the analysis of the classification prediction model, two user attendance access results are obtained, the user access direction is obtained according to access direction judgment rules, and the results are stored into a kafka message queue s 4;
s5: cloud attendance notification push software which is responsible for taking out RFID tag attendance records from the kafka message queue S4 and issuing attendance notifications to user terminal equipment in the modes of short messages, WeChat public numbers, attendance application APPs and the like;
further, the step S4:
s41: the time series data reduction processing comprises the following steps: detecting deviation, and filtering abnormal fluctuation signals according to a preset deviation threshold value of a system;
s42: attendance entry and exit direction judgment rule: (1) if the front of the gateway outside the door passes through or is close to the front of the gateway and the back of the gateway inside the door passes through or is far away from the front of the gateway, the user is considered to enter; (3) if the front side of the gateway inside the door passes through or is close to the front side of the gateway outside the door and the back side of the gateway outside the door passes through or is far away from the front side of the gateway outside the door, the user is considered to go out;
as shown in fig. 2, the ring-shaped timing monitoring queue specifically includes:
(1) the circular timing queue contains three data structures:
first, assuming a timeout of T, a ring queue with index from 0 to T
Per slot on the ring is a Set < RFID > Set
Thirdly, a Map < RFID, index > records the position of each RFID on the ring;
(2) the circular queue algorithm:
firstly, starting a timer, and moving one grid, 0- >1- >2- >3, in a circular queue every 1 s;
secondly, a Current Index pointer is used for identifying the slot which is just detected;
(3) when receiving the RFID label signal, the circular queue operation flow:
finding out the slot in which the RFID is stored from a Map structure;
deleting the RFID from the Set structure of the slot;
adding the RFID label into a new slot again, namely the last slot pointed by the Current Index pointer, wherein the whole slot can be scanned by the timer after T seconds;
fourthly, updating the index value of the slot corresponding to the RFID label in the Map;
(4) the ring queue timeout detection method comprises the following steps:
the Current Index moves one slot per second, and all RFID tags in Set < RFID > corresponding to the slot are subjected to collective timeout processing;
as shown in fig. 3, the attendance data classification prediction model obtained through the BP neural network training classifies the prediction result of the RFID tag attendance data into six categories: the front surface is close to, the front surface is far away from, the front surface passes through, the back surface is close to, the back surface is far away from and the back surface passes through;
as shown in fig. 4, the BP neural network structure specifically includes:
inputting a layer: each neuron is responsible for receiving input information from the outside and transmitting the input information to each neuron in the middle layer;
hiding the layer: the internal information processing layer is responsible for information transformation and can be designed into a single-hidden layer or multi-hidden layer structure according to the requirement of information change capability; the empirical formula of the number of nodes of the hidden layer is as follows: s ═ 1+ [ m (n +2) ]1/2, where S is the number of nodes in the hidden layer, m is the number of input nodes, and n is the number of output nodes.
Output layer: the information transmitted to each neuron of the output layer by the last hidden layer is further processed to finish a forward propagation processing process of learning once, and an information processing result is output to the outside by the output layer;
and fourthly, for the neural network output layer, a mathematical model is as follows:
ok＝f(netk) (1)
Figure RE-GDA0002642314090000071
for the neural network hidden layer, the mathematical model is as follows:
yj＝f(netj),j＝1,2,...,m (3)
Figure RE-GDA0002642314090000072
as shown in fig. 5, the attendance data classification algorithm based on the BP neural network specifically includes:
(1) constructing a BP neural network:
sample data acquisition, namely, sample data acquisition in 6 modes, wherein each mode comprises 1000 groups of labeled data and 256 data in each group;
giving the initial weight of the neuron between the hidden layer and the input layer at random;
(2) BP neural network training:
firstly, collecting training samples, and randomly taking 800 groups of data as training samples and 200 groups of data as test samples in each mode according to a twenty-eight principle;
inputting the sample into a neural network, and calculating the actual output of the hidden layer;
calculating the weight between the output layer and the hidden layer, taking the r-th neuron of the output layer as an object, and establishing an equation by taking a given output target value as a polynomial value of the equation;
fourthly, the weights of m neurons of the output layer can be obtained by repeating the third step, and the unknown weights are obtained by solving a linear equation set by using a Gaussian elimination method;
(3) BP neural network test:
firstly, inputting a test sample into a neural network by using a model obtained by training, and verifying the accuracy of a model prediction result;
and secondly, after the test prediction is achieved, storing the training model for actual attendance data classification prediction.
According to the system and the attendance checking method, the non-inductive attendance checking system and the method based on the bi-directional gateway, the RFID and the BP neural network are integrated, the bi-directional gateways of the outdoor directional gateway and the indoor directional gateway are adopted to collect active RFID signals, the missed card-punching probability can be obviously reduced, and the in-and-out direction of a user can be accurately obtained through signal characteristic comparison of the bi-directional gateways. The RFID tag is subjected to overtime detection by adopting an annular queue algorithm, and the performance is stable and efficient in a high concurrency scene, and the detection is timely and accurate; a set of complete attendance classification prediction model is established, the accuracy of attendance classification prediction can be obviously improved, the method can adapt to more complex field environment, and the application of the active RFID technology in the field of automatic non-inductive attendance is effectively promoted.

Claims (9)

1. A non-inductive attendance system based on a dual directional gateway, an RFID and a BP neural network is characterized by comprising an outdoor directional gateway, an indoor directional gateway, an active RFID tag, a router, a cloud server, cloud attendance data receiving and processing software, cloud kafka message queue software, a cloud database, cloud attendance notification pushing software, BP neural network data analysis software and a terminal or application software for receiving attendance notifications, wherein the BP neural network data analysis software, the cloud kafka message queue software, the cloud attendance pushing notification software and the cloud attendance data receiving and processing software run on the cloud server, the outdoor directional gateway and the indoor directional gateway are connected with the router through network cables, the router is accessed to the Internet through the network cables, the active RFID tag is carried by a user, and the outdoor directional gateway, the cloud attendance notification pushing notification software and the cloud attendance data receiving and processing software run on the cloud server, The indoor directional gateway is accessed to the Internet through the router and is in long connection with the cloud server in a TCP protocol mode, and the outdoor directional gateway and the indoor directional gateway are both provided with directional antennas.
2. The dual orientation gateway, active RFID, and BP neural network based non-inductive attendance system of claim 1, wherein the router has POE power on function.
3. The dual orientation gateway, active RFID, and BP neural network based non-inductive attendance system of claim 1, wherein the terminal or application software comprises a short message, a wechat public number, and an attendance application APP.
4. A non-inductive attendance checking method which adopts any one of the non-inductive attendance checking systems of claims 1 to 3 and is characterized by comprising the following steps;
s1: an active RFID tag that transmits a wireless signal at a certain frequency;
s2: the outdoor directional gateway and the indoor directional gateway are responsible for acquiring signals sent by the active RFID label in the step S1 in the coverage range of the gateway, encrypting the acquired attendance data with time sequence at corresponding frequency and sending the encrypted attendance data to the cloud server;
s3: cloud attendance data receiving and processing software, which is responsible for receiving the original time sequence attendance data sent in the step S2, decrypting the original time sequence attendance data, storing the decrypted original time sequence attendance data into a cloud database, recording the first and last signal time of the active RFID tags, performing overtime detection on a plurality of active RFID tags through an annular timing queue, generating a record containing the active RFID tags, the starting time and the ending time by the overtime active RFID tags, and storing the record into a kafka message queue S3;
s4: BP neural network data analysis software subscribes to a kafka message queue s3, when data are generated, active RFID tag attendance time sequence data received by two directional base stations are respectively inquired from a cloud database according to the starting time and the ending time of an active RFID tag, two sections of time sequence data are further subjected to drying reduction treatment respectively, then the noise-reduced data are input into a trained attendance data classification prediction model, two user attendance access results are obtained after the analysis of the classification prediction model, the user access direction is obtained according to access direction judgment rules, and the results are stored in a kafka message queue s 4;
s5: and cloud attendance notification push software is responsible for taking out the active RFID tag attendance record from the kafka message queue s4 and issuing an attendance notification to user terminal equipment in a short message, WeChat public number and attendance application APP mode.
5. The method for attendance checking according to claim 4, wherein in step S4, the drying process for the two pieces of time series data comprises: detecting deviation, and filtering abnormal fluctuation signals according to a preset deviation threshold value of a system; the entry/exit direction determination rule includes: (1) if the front of the gateway outside the door passes through or is close to the front of the gateway and the back of the gateway inside the door passes through or is far away from the front of the gateway, the user is considered to enter; (2) and if the front side of the gateway inside the door passes through or is close to the front side of the gateway outside the door and the back side of the gateway outside the door passes through or is far away from the front side of the gateway outside the door, the user is considered to go out.
6. The method for noninductive attendance checking according to claim 5, wherein the circular timing queue specifically comprises a data structure, a circular queue algorithm, a circular queue operation flow when an active RFID tag signal is received, and a circular queue timeout detection method.
7. The noninductive attendance method of claim 5 or 6, wherein in step S4, the attendance data classification prediction model obtained through training of BP neural network data analysis software classifies the prediction results of active RFID tag attendance data into six categories: the front surface is close to, the front surface is far away from, the front surface passes through, the back surface is close to, the back surface is far away from and the back surface passes through.
8. The sensorless attendance method of claim 5 or 6 wherein the BP neural network comprises an input layer, a hidden layer, and an output layer.
9. The sensorless attendance method of claim 8, wherein the BP neural network comprises an attendance data classification algorithm comprising: BP neural network construction, BP neural network training and BP neural network testing.
CN202010363977.5A 2020-04-30 2020-04-30 Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network Pending CN111724495A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010363977.5A CN111724495A (en) 2020-04-30 2020-04-30 Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010363977.5A CN111724495A (en) 2020-04-30 2020-04-30 Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network

Publications (1)

Publication Number Publication Date
CN111724495A true CN111724495A (en) 2020-09-29

Family

ID=72563724

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010363977.5A Pending CN111724495A (en) 2020-04-30 2020-04-30 Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network

Country Status (1)

Country Link
CN (1) CN111724495A (en)

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146547A (en) * 2006-12-13 2008-06-26 Ntt Comware Corp Entrance and exit detection system, entrance and exit detection method, and entrance and exit detection program
CN101782652A (en) * 2010-02-08 2010-07-21 上海和为科技有限公司 Indoor positioning system based on RFID technology
CN104537722A (en) * 2015-01-26 2015-04-22 深圳市天星通科技有限公司 Method and equipment capable of simultaneously checking attendance of multiple persons
CN104599389A (en) * 2015-02-11 2015-05-06 深圳市小卫星移动网络科技有限公司 School entering and leaving judgment method of intelligent electronic student identity card
CN104915999A (en) * 2015-07-11 2015-09-16 安庆状元郎电子科技有限公司 Schoolyard remote attendance system
CN107403477A (en) * 2017-08-11 2017-11-28 北京启迪时代科技有限公司 The method that discrepancy judgement is carried out using wireless signal Time-distribution
CN109284189A (en) * 2018-09-06 2019-01-29 福建星瑞格软件有限公司 A kind of batch tasks overtime efficiently triggering method and system
CN109444813A (en) * 2018-10-26 2019-03-08 南京邮电大学 A kind of RFID indoor orientation method based on BP and DNN amphineura network
CN110166352A (en) * 2019-04-25 2019-08-23 浙江天地人科技有限公司 The multidirectional orientation gateway of one kind enters and leaves angle detecting system and enters and leaves direction detection method

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008146547A (en) * 2006-12-13 2008-06-26 Ntt Comware Corp Entrance and exit detection system, entrance and exit detection method, and entrance and exit detection program
CN101782652A (en) * 2010-02-08 2010-07-21 上海和为科技有限公司 Indoor positioning system based on RFID technology
CN104537722A (en) * 2015-01-26 2015-04-22 深圳市天星通科技有限公司 Method and equipment capable of simultaneously checking attendance of multiple persons
CN104599389A (en) * 2015-02-11 2015-05-06 深圳市小卫星移动网络科技有限公司 School entering and leaving judgment method of intelligent electronic student identity card
CN104915999A (en) * 2015-07-11 2015-09-16 安庆状元郎电子科技有限公司 Schoolyard remote attendance system
CN107403477A (en) * 2017-08-11 2017-11-28 北京启迪时代科技有限公司 The method that discrepancy judgement is carried out using wireless signal Time-distribution
CN109284189A (en) * 2018-09-06 2019-01-29 福建星瑞格软件有限公司 A kind of batch tasks overtime efficiently triggering method and system
CN109444813A (en) * 2018-10-26 2019-03-08 南京邮电大学 A kind of RFID indoor orientation method based on BP and DNN amphineura network
CN110166352A (en) * 2019-04-25 2019-08-23 浙江天地人科技有限公司 The multidirectional orientation gateway of one kind enters and leaves angle detecting system and enters and leaves direction detection method

Similar Documents

Publication Publication Date Title
Lau et al. Sensor fusion for public space utilization monitoring in a smart city
Ibrahim et al. CNN based indoor localization using RSS time-series
US10812761B2 (en) Complex hardware-based system for video surveillance tracking
Abdalzaher et al. A deep learning model for earthquake parameters observation in IoT system-based earthquake early warning
CN104820072B (en) Based on the monitoring method of the Electronic Nose air-quality monitoring system of cloud computing
CN109543992A (en) Intelligent polling method, device, intelligent terminal and server
Kamelia et al. Real-time online attendance system based on fingerprint and GPS in the smartphone
Cartwright et al. SONYC-UST-V2: An urban sound tagging dataset with spatiotemporal context
CN107170065A (en) Intelligent movable Work attendance method, device and system
CN112770265B (en) Pedestrian identity information acquisition method, system, server and storage medium
CN104483462A (en) Water sampling method and system for environmental monitoring
Portelli et al. Leveraging edge computing through collaborative machine learning
CN112087444B (en) Account identification method and device, storage medium and electronic equipment
CN111461231A (en) Short message sending control method, device and storage medium
Kovelan et al. Automated attendance monitoring system using iot
Jaikumar et al. Fingerprint based student attendance system with SMS alert to parents
CN116828433A (en) Intelligent patrol management system and method based on Bluetooth beacon
CN113572757A (en) Server access risk monitoring method and device
CN111724495A (en) Non-inductive attendance system and method based on dual-orientation gateway, RFID and BP neural network
CN209087002U (en) Inspection device based on two dimensional code and wireless location
CN115291184B (en) Attitude monitoring method combining millimeter wave radar and deep learning
Andrijašević et al. Lid Opening Detection in Manholes using RNN
CN113074718B (en) Positioning method, device, equipment and storage medium
Meghana et al. Smart attendance management system using radio frequency identification
Saimounika et al. Real time locating system using RFID for Internet of Things

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200929

RJ01 Rejection of invention patent application after publication