+

CN113612555B - Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal - Google Patents

Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal Download PDF

Info

Publication number
CN113612555B
CN113612555B CN202110952490.5A CN202110952490A CN113612555B CN 113612555 B CN113612555 B CN 113612555B CN 202110952490 A CN202110952490 A CN 202110952490A CN 113612555 B CN113612555 B CN 113612555B
Authority
CN
China
Prior art keywords
calibration
mobile terminal
neural network
calibration model
model
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.)
Active
Application number
CN202110952490.5A
Other languages
Chinese (zh)
Other versions
CN113612555A (en
Inventor
余敏
吴璇
尧舒引
郭昊
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.)
Jiangxi Saibai Technology Co ltd
Jiangxi Normal University
Original Assignee
Jiangxi Saibai Technology Co ltd
Jiangxi Normal University
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 Jiangxi Saibai Technology Co ltd, Jiangxi Normal University filed Critical Jiangxi Saibai Technology Co ltd
Priority to CN202110952490.5A priority Critical patent/CN113612555B/en
Publication of CN113612555A publication Critical patent/CN113612555A/en
Application granted granted Critical
Publication of CN113612555B publication Critical patent/CN113612555B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/30—Monitoring; Testing of propagation channels
    • H04B17/309—Measuring or estimating channel quality parameters
    • H04B17/318—Received signal strength
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; 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 OR CALCULATING; 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
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/10—Monitoring; Testing of transmitters
    • H04B17/11—Monitoring; Testing of transmitters for calibration
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04B—TRANSMISSION
    • H04B17/00—Monitoring; Testing
    • H04B17/20—Monitoring; Testing of receivers
    • H04B17/21—Monitoring; Testing of receivers for calibration; for correcting measurements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30—Services specially adapted for particular environments, situations or purposes
    • H04W4/33—Services specially adapted for particular environments, situations or purposes for indoor environments, e.g. buildings
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W64/00—Locating users or terminals or network equipment for network management purposes, e.g. mobility management
    • H04W64/006—Locating users or terminals or network equipment for network management purposes, e.g. mobility management with additional information processing, e.g. for direction or speed determination
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00—Reducing energy consumption in communication networks
    • Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Biophysics (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Electromagnetism (AREA)
  • Quality & Reliability (AREA)
  • Monitoring And Testing Of Transmission In General (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

The invention provides an intelligent calibration method and system based on mobile terminal wireless radio frequency signal intensity, wherein a calibration model base is established according to an improved BP neural network calibration model obtained by a proposed nonlinear convergence factor, and the model number of a terminal and corresponding calibration model parameters are recorded and stored; judging whether the model of the mobile terminal is in a calibration model library, if not, taking the original RSSI observed values of all APs acquired by the standard mobile terminal at all acquisition points as standard sampling data, and taking the original RSSI observed values of all corresponding APs of the mobile terminal at corresponding acquisition points as test sampling data; and taking an original RSSI observation value received by the mobile terminal at any indoor position as a calibration model input, processing the original RSSI observation value by an improved BP neural network calibration model, and taking the final output as a calibration value. The invention can avoid the algorithm from falling into local optimum, has wide applicability, can finish the calibration work only by a handheld mobile terminal, and effectively eliminates the heterogeneous difference of software and hardware of different mobile terminals.

Description

基于移动终端无线射频信号强度的智能标定方法及系统Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal

技术领域technical field

本发明涉及无线射频信号强度观测值标定领域，特别涉及一种基于移动终端无线射频信号强度的智能标定算法及系统。The invention relates to the field of radio frequency signal strength observation value calibration, in particular to an intelligent calibration algorithm and system based on the radio frequency signal strength of a mobile terminal.

背景技术Background technique

在室内定位领域，可以利用移动终端无线射频信号传播的多路径效应进行环境感知，通过获取信号特征进行指纹定位。但是由于不同移动终端的软件、硬件都不相同，使得不同移动终端在同一位置接收到的射频信号强度观测值存在较大差异，导致指纹定位不可用。为了解决上述问题，需要对射频信号强度观测值进行标定，使得其他移动终端与标准移动终端在同一位置接收到的射频信号强度观测值趋于一致。In the field of indoor positioning, the multi-path effect of the wireless radio frequency signal propagation of the mobile terminal can be used for environmental perception, and the fingerprint positioning can be carried out by obtaining the signal characteristics. However, because the software and hardware of different mobile terminals are different, the observed values of radio frequency signal strengths received by different mobile terminals at the same location are quite different, resulting in unusable fingerprint positioning. In order to solve the above problem, it is necessary to calibrate the observed value of the radio frequency signal strength, so that the observed value of the radio frequency signal strength received by other mobile terminals and the standard mobile terminal at the same location tends to be consistent.

本发明提出一种基于移动终端无线射频信号强度的智能标定算法及系统，基于此，为了进一步加快标定算法的建立与优化，避免陷入局部最优，本发明还提出了一种非线性的收敛因子a得到改进的BP神经网络标定模型，使得其他移动终端与标准移动终端在同一位置接收到的射频信号强度观测值趋于一致。用户仅通过手持移动终端即可完成标定工作，有效消除了各移动终端的软硬件异构差异，操作简单，可提高对环境的适应性，可扩展性强，适用性广。The present invention proposes an intelligent calibration algorithm and system based on the strength of the radio frequency signal of the mobile terminal. Based on this, in order to further speed up the establishment and optimization of the calibration algorithm and avoid falling into local optimum, the present invention also proposes a nonlinear convergence factor a The improved BP neural network calibration model makes the observed values of RF signal strengths received by other mobile terminals and standard mobile terminals at the same location tend to be consistent. The user can complete the calibration work only by holding the mobile terminal, which effectively eliminates the heterogeneous differences in software and hardware of each mobile terminal. The operation is simple, and the adaptability to the environment can be improved.

发明内容SUMMARY OF THE INVENTION

本发明是为了解决现有技术中，由于各移动终端软硬件异构导致接收到的射频信号强度观测值存在较大差异，且传统标定方法步骤复杂，适应范围窄、可扩展性低的问题。The present invention is to solve the problems in the prior art that the received radio frequency signal strength observation values are quite different due to the heterogeneity of software and hardware of each mobile terminal, and the traditional calibration method has complex steps, narrow adaptability and low scalability.

为了解决这一技术问题，本发明提出一种基于移动终端无线射频信号强度的智能标定算法及系统，可对每个移动终端建立对应的改进的BP神经网络标定模型，其中，所述方法包括如下步骤：In order to solve this technical problem, the present invention proposes an intelligent calibration algorithm and system based on the strength of radio frequency signals of mobile terminals, which can establish a corresponding improved BP neural network calibration model for each mobile terminal, wherein the method includes the following step:

根据提出的非线性收敛因子得到改进的BP神经网络标定模型建立标定模型库，记录并保存终端型号及对应的标定模型参数；According to the proposed BP neural network calibration model with improved nonlinear convergence factor, a calibration model library is established, and the terminal model and the corresponding calibration model parameters are recorded and saved;

手持某个移动终端进行标定之前，判断该终端型号是否在标定模型库中；Before holding a mobile terminal for calibration, determine whether the terminal model is in the calibration model library;

若否，则以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以该移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；根据所述标准采样数据以及所述测试采样数据建立并训练得到改进的BP神经网络标定模型，记录并保存终端型号及对应的标定模型参数；If not, take all the original radio frequency signal strength observations of all APs at all collection points of the standard mobile terminal as the standard sampling data, and use all the original radio frequency signal strength observations of all corresponding APs at the corresponding collection points of the mobile terminal as the test Sampling data; establish and train an improved BP neural network calibration model according to the standard sampling data and the test sampling data, and record and save the terminal model and the corresponding calibration model parameters;

若是，则直接利用标定模型库对应的标定模型参数进行标定；If so, directly use the calibration model parameters corresponding to the calibration model library to calibrate;

手持该移动终端进行标定时以在室内任意位置接收到的原始射频信号强度观测值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。When holding the mobile terminal for calibration, the original RF signal strength observation value received at any position in the room is used as the input of the calibration model, and it is processed by the improved BP neural network calibration model, and the final output is used as the calibration value to complete the calibration model. Smart calibration of mobile terminals.

基于移动终端无线射频信号强度的智能标定算法，利用改进的BP神经网络标定模型建立标定模型库的方法，包括如下步骤：Based on the intelligent calibration algorithm of the wireless radio frequency signal strength of the mobile terminal, the method for establishing the calibration model library by using the improved BP neural network calibration model includes the following steps:

步骤1：在室内任意选择若干个采集点，标准手机在所有采集点上采集射频信号强 度，综合表示为初始标准采样数据，以移动终端在对应采集点上所有对应AP的所有原始射 频信号强度观测值作为测试采样数据，以所述测试采样数据为改进的BP神经网络标定模型 的真实输入值，以所述初始标准采样数据为改进的BP神经网络标定模型的真实输出值，随 机初始化神经网络的各层权值

Figure 207958DEST_PATH_IMAGE001
、阈值
Figure 390678DEST_PATH_IMAGE002
作为初始鲸鱼群位置向量
Figure 639257DEST_PATH_IMAGE003
，设置鲸鱼种群 大小N，当前鲸鱼种群迭代次数t=0，鲸鱼种群最大迭代数
Figure 237728DEST_PATH_IMAGE004
，当前BP神经网络迭代次数T，BP神经网络最大迭代次数T max ； Step 1: Select a number of collection points at random in the room. The standard mobile phone collects the RF signal strength at all the collection points, and comprehensively expresses it as the initial standard sampling data, and observes all the original RF signal strengths of all the corresponding APs at the corresponding collection point by the mobile terminal. The value is used as the test sampling data, and the test sampling data is the real input value of the improved BP neural network calibration model, and the initial standard sampling data is the real output value of the improved BP neural network calibration model. The weights of each layer
Figure 207958DEST_PATH_IMAGE001
, threshold
Figure 390678DEST_PATH_IMAGE002
as the initial whale swarm position vector
Figure 639257DEST_PATH_IMAGE003
, set the whale population size N , the current whale population iteration number t = 0, the maximum whale population iteration number
Figure 237728DEST_PATH_IMAGE004
, the current number of iterations of the BP neural network T, the maximum number of iterations of the BP neural network T max ;

步骤2：当鲸鱼种群迭代次数t小于鲸鱼种群最大迭代次数

Figure 520942DEST_PATH_IMAGE004
时，计算每只鲸鱼 的适应度值
Figure 61514DEST_PATH_IMAGE005
,找出最好的适应度及对应的最优鲸鱼位置
Figure 594126DEST_PATH_IMAGE006
； Step 2: When the number of whale population iterations t is less than the maximum number of whale population iterations
Figure 520942DEST_PATH_IMAGE004
When , calculate the fitness value of each whale
Figure 61514DEST_PATH_IMAGE005
, find the best fitness and the corresponding optimal whale position
Figure 594126DEST_PATH_IMAGE006
;

Figure 261868DEST_PATH_IMAGE007
(1)
Figure 261868DEST_PATH_IMAGE007
(1)

其中，

Figure 134009DEST_PATH_IMAGE008
为标准采样数据的第i个RSSI真实值，
Figure 596214DEST_PATH_IMAGE009
为测试采样数据的第i个RSSI 预测值，n为样本个数； in,
Figure 134009DEST_PATH_IMAGE008
is the ith RSSI real value of the standard sampled data,
Figure 596214DEST_PATH_IMAGE009
is the ith RSSI prediction value of the test sample data, and n is the number of samples;

步骤3：为了加快标定算法的建立与优化，更新迭代速度有所提升，提出了一种非 线性的收敛因子a模拟包围猎物的收缩行为，收敛因子

Figure 74512DEST_PATH_IMAGE010
只随着当前迭代次数
Figure 77103DEST_PATH_IMAGE011
动态变化， 可以较为有效避免陷入局部最优； Step 3: In order to speed up the establishment and optimization of the calibration algorithm and improve the update iteration speed, a nonlinear convergence factor a is proposed to simulate the shrinking behavior of surrounding prey, and the convergence factor
Figure 74512DEST_PATH_IMAGE010
only with the current number of iterations
Figure 77103DEST_PATH_IMAGE011
Dynamic changes can effectively avoid falling into local optimum;

Figure 69330DEST_PATH_IMAGE012
(2)
Figure 69330DEST_PATH_IMAGE012
(2)

其中, t为当前鲸鱼种群迭代次数，

Figure 968016DEST_PATH_IMAGE013
为鲸鱼种群最大迭代次数；更新鲸鱼位 置参数A、C； Among them, t is the number of iterations of the current whale population,
Figure 968016DEST_PATH_IMAGE013
is the maximum number of iterations for the whale population; update the whale position parameters A and C ;

Figure 412904DEST_PATH_IMAGE014
(3)
Figure 412904DEST_PATH_IMAGE014
(3)

Figure 406137DEST_PATH_IMAGE015
(4)
Figure 406137DEST_PATH_IMAGE015
(4)

其中, r是[0,1]的一个随机数；Among them, r is a random number in [0,1];

步骤4：随机产生概率p，判断p是否小于0.5，若

Figure 315187DEST_PATH_IMAGE016
，则进行收缩包围位置更 新： Step 4: Randomly generate probability p , and judge whether p is less than 0.5, if
Figure 315187DEST_PATH_IMAGE016
, then the shrink wrapping position update is performed:

Figure 119195DEST_PATH_IMAGE017
(5)
Figure 119195DEST_PATH_IMAGE017
(5)

其中,t为当前鲸鱼种群迭代次数；

Figure 316958DEST_PATH_IMAGE018
为最优鲸鱼位置；
Figure 599035DEST_PATH_IMAGE019
为当前鲸鱼位置；A 和C为步骤3所得出的系数向量；Among them, t is the iteration times of the current whale population;
Figure 316958DEST_PATH_IMAGE018
is the optimal whale position;
Figure 599035DEST_PATH_IMAGE019
is the current whale position; A and C are the coefficient vectors obtained in step 3;

若

Figure 815121DEST_PATH_IMAGE020
，且当
Figure 852347DEST_PATH_IMAGE021
时进行螺旋游走： like
Figure 815121DEST_PATH_IMAGE020
, and when
Figure 852347DEST_PATH_IMAGE021
When performing a spiral walk:

Figure 271827DEST_PATH_IMAGE022
(6)
Figure 271827DEST_PATH_IMAGE022
(6)

其中,

Figure 357595DEST_PATH_IMAGE023
表示当前鲸鱼与最优位置的距离；b为常数，定义对数螺旋线 形状；l为[-1,1]中随机数； in,
Figure 357595DEST_PATH_IMAGE023
Indicates the distance between the current whale and the optimal position; b is a constant, which defines the logarithmic spiral shape; l is a random number in [-1,1];

当

Figure 178920DEST_PATH_IMAGE024
时根据以下公式进行随机游走： when
Figure 178920DEST_PATH_IMAGE024
A random walk is performed according to the following formula:

Figure 839578DEST_PATH_IMAGE025
(7)
Figure 839578DEST_PATH_IMAGE025
(7)

其中,

Figure 543092DEST_PATH_IMAGE026
为随机选取的位置向量； in,
Figure 543092DEST_PATH_IMAGE026
is a randomly selected position vector;

步骤5：鲸鱼种群迭代次数t自增，根据步骤2比较更新最优位置；当到达鲸鱼种群 最大迭代次数

Figure 432550DEST_PATH_IMAGE027
时，输出
Figure 373961DEST_PATH_IMAGE028
即最优权值
Figure 690673DEST_PATH_IMAGE029
、阈值
Figure 334013DEST_PATH_IMAGE030
,并作为BP神经网络最优初始 参数； Step 5: The number of whale population iterations t increases automatically, and the optimal position is updated according to step 2; when the maximum number of iterations for the whale population is reached
Figure 432550DEST_PATH_IMAGE027
when the output
Figure 373961DEST_PATH_IMAGE028
the optimal weight
Figure 690673DEST_PATH_IMAGE029
, threshold
Figure 334013DEST_PATH_IMAGE030
, and as the optimal initial parameter of BP neural network;

步骤6：BP神经网络进行正向传播过程，通过神经元之间的连接权值

Figure 27163DEST_PATH_IMAGE031
和神经元 阈值
Figure 354239DEST_PATH_IMAGE030
进行数据加工，并采用非线性Sigmoid激活函数获得预测输出值。 Step 6: The BP neural network performs a forward propagation process, through the connection weights between neurons
Figure 27163DEST_PATH_IMAGE031
and neuron threshold
Figure 354239DEST_PATH_IMAGE030
Data processing is performed and a nonlinear sigmoid activation function is used to obtain predicted output values.

Figure 107431DEST_PATH_IMAGE032
(8)
Figure 107431DEST_PATH_IMAGE032
(8)

Figure 723220DEST_PATH_IMAGE033
(9)
Figure 723220DEST_PATH_IMAGE033
(9)

其中，

Figure 469328DEST_PATH_IMAGE034
为神经元i到神经元j的连接权值；
Figure 916490DEST_PATH_IMAGE035
为神经元j阈值；
Figure 575004DEST_PATH_IMAGE036
为神经元j输入 值；
Figure 678090DEST_PATH_IMAGE037
为神经元j输出值；
Figure 713042DEST_PATH_IMAGE038
为神经元
Figure 732819DEST_PATH_IMAGE039
的输入值。 in,
Figure 469328DEST_PATH_IMAGE034
is the connection weight from neuron i to neuron j ;
Figure 916490DEST_PATH_IMAGE035
is the threshold of neuron j ;
Figure 575004DEST_PATH_IMAGE036
input value for neuron j;
Figure 678090DEST_PATH_IMAGE037
output value for neuron j ;
Figure 713042DEST_PATH_IMAGE038
for neurons
Figure 732819DEST_PATH_IMAGE039
the input value.

步骤7：BP神经网络进行误差反向传播过程，通过正向传播过程获得预测输出值， 根据智能设备的预测输出值与标准智能设备的真实输出值之间的差异得到当前迭代次数 的损失函数

Figure 358973DEST_PATH_IMAGE040
，将误差逆向传播至上一层神经元中得到该层误差，逐层传递直至最上层隐 藏层，基于梯度下降法对连接权值和阈值进行不断调整。 Step 7: The BP neural network performs the error back propagation process, obtains the predicted output value through the forward propagation process, and obtains the loss function of the current number of iterations according to the difference between the predicted output value of the smart device and the actual output value of the standard smart device
Figure 358973DEST_PATH_IMAGE040
, the error is back-propagated to the neurons of the previous layer to obtain the error of this layer, which is passed layer by layer to the top hidden layer, and the connection weights and thresholds are continuously adjusted based on the gradient descent method.

Figure 214933DEST_PATH_IMAGE041
(10)
Figure 214933DEST_PATH_IMAGE041
(10)

Figure 53576DEST_PATH_IMAGE042
(11)
Figure 53576DEST_PATH_IMAGE042
(11)

Figure 147434DEST_PATH_IMAGE043
(12)
Figure 147434DEST_PATH_IMAGE043
(12)

其中，

Figure 662598DEST_PATH_IMAGE044
为神经元j真实输出值；
Figure 537013DEST_PATH_IMAGE045
为输出层神经元j预测输出值；
Figure 179347DEST_PATH_IMAGE046
为更新后权值；
Figure 658870DEST_PATH_IMAGE047
为更新后阈值；
Figure 830088DEST_PATH_IMAGE048
为学习率，若其值偏大则收敛快但容易陷 入局部最优，若偏小则收敛慢但逼近全局最优。 in,
Figure 662598DEST_PATH_IMAGE044
is the real output value of neuron j ;
Figure 537013DEST_PATH_IMAGE045
Predict the output value for the output layer neuron j ;
Figure 179347DEST_PATH_IMAGE046
is the updated weight;
Figure 658870DEST_PATH_IMAGE047
is the updated threshold;
Figure 830088DEST_PATH_IMAGE048
is the learning rate. If the value is too large, the convergence will be fast but it is easy to fall into the local optimum. If the value is too small, the convergence will be slow but approach the global optimum.

步骤8：经过反复学习训练，当BP神经网络当前迭代次数T到达BP神经网络最大迭 代次数

Figure 638470DEST_PATH_IMAGE049
时，选取损失函数
Figure 615653DEST_PATH_IMAGE050
最小的BP神经网络作为最终标定模型，保存当前改进的 BP神经网络标定模型的参数。 Step 8: After repeated learning and training, when the current number of iterations T of the BP neural network reaches the maximum number of iterations of the BP neural network
Figure 638470DEST_PATH_IMAGE049
When , choose the loss function
Figure 615653DEST_PATH_IMAGE050
The smallest BP neural network is used as the final calibration model, and the parameters of the current improved BP neural network calibration model are saved.

步骤9：将多个移动终端重复步骤1至8，进而建立标定模型库。Step 9: Repeat steps 1 to 8 for multiple mobile terminals, and then establish a calibration model library.

本发明还提出了一种基于移动终端无线射频信号强度的智能标定系统，其中，所述系统包括：The present invention also proposes an intelligent calibration system based on the strength of the wireless radio frequency signal of the mobile terminal, wherein the system includes:

数据采集模块，以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以其他移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；The data acquisition module takes all the raw RF signal strength observations of all APs at all the collection points of the standard mobile terminal as the standard sampling data, and uses all the original RF signal strength observations of all the corresponding APs at the corresponding collection points of other mobile terminals as the test sampling data;

模型建立模块，根据所述标准采样数据以及所述测试采样数据建立并训练得到改进的BP神经网络标定模型，记录并保存终端型号及对应的标定模型参数；A model establishment module, establishes and trains an improved BP neural network calibration model according to the standard sampling data and the test sampling data, records and saves the terminal model and the corresponding calibration model parameters;

智能标定模块，以移动终端在室内任意位置接收到的射频信号值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。The intelligent calibration module takes the RF signal value received by the mobile terminal at any indoor position as the input of the calibration model, processes it through the improved BP neural network calibration model, and finally obtains the output as the calibration value to complete the intelligent calibration of the mobile terminal. Calibration.

与现有技术相比，本发明提出的一种基于移动终端无线射频信号强度的智能标定算法及系统，可避免算法陷入局部最优，提高对环境的适应性，可扩展性强，适用性广，可仅通过手持的移动终端即可完成标定工作，有效消除了不同移动终端的软硬件异构差异，操作简单。Compared with the prior art, an intelligent calibration algorithm and system based on the radio frequency signal strength of a mobile terminal proposed by the present invention can avoid the algorithm from falling into local optimum, improve the adaptability to the environment, and has strong scalability and wide applicability. , the calibration work can be completed only by the handheld mobile terminal, which effectively eliminates the software and hardware heterogeneous differences of different mobile terminals, and the operation is simple.

本发明的附加方面和优点将在下面的描述中部分给出，部分将从下面的描述中变得明显，或通过本发明的实践了解到。Additional aspects and advantages of the present invention will be set forth, in part, from the following description, and in part will be apparent from the following description, or may be learned by practice of the invention.

附图说明Description of drawings

图1为本发明实施例1的原理框架图；Fig. 1 is the principle frame diagram of Embodiment 1 of the present invention;

图2为本发明实施例1的流程图；2 is a flowchart of Embodiment 1 of the present invention;

图3为本发明实施例2的结构示意图。FIG. 3 is a schematic structural diagram of Embodiment 2 of the present invention.

具体实施方式Detailed ways

为了便于理解本发明，下面将参照相关附图对本发明进行更全面的描述。附图中给出了本发明的首选实施例。但是，本发明可以以许多不同的形式来实现，并不限于本文所描述的实施例。相反地，提供这些实施例的目的是使对本发明的公开内容更加透彻全面。In order to facilitate understanding of the present invention, the present invention will be described more fully hereinafter with reference to the related drawings. Preferred embodiments of the invention are shown in the drawings. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

除非另有定义，本文所使用的所有的技术和科学术语与属于本发明的技术领域的技术人员通常理解的含义相同。本文中在本发明的说明书中所使用的术语只是为了描述具体的实施例的目的，不是旨在于限制本发明。本文所使用的术语“及／或”包括一个或多个相关的所列项目的任意的和所有的组合。Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terms used herein in the description of the present invention are for the purpose of describing specific embodiments only, and are not intended to limit the present invention. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

实施例1Example 1

请参阅图1与图2，对于本发明提出第一实施例提出的一种基于移动终端无线射频信号强度的智能标定算法，其具体实施方式包括如下步骤：Referring to FIG. 1 and FIG. 2 , for an intelligent calibration algorithm based on the radio frequency signal strength of a mobile terminal proposed in the first embodiment of the present invention, the specific implementation method includes the following steps:

S101，根据提出的非线性收敛因子得到改进的BP神经网络标定模型建立标定模型库，记录并保存终端型号及对应的标定模型参数；S101, establishing a calibration model library according to the proposed BP neural network calibration model with an improved nonlinear convergence factor, and recording and saving the terminal model and the corresponding calibration model parameters;

S102，手持移动终端进行标定之前，判断该终端型号是否在标定模型库中，若否，则以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以该移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；S102, before carrying out the calibration of the handheld mobile terminal, determine whether the terminal model is in the calibration model library, if not, take all the original radio frequency signal strength observations of all APs at all the collection points of the standard mobile terminal as the standard sampling data, and use the All raw radio frequency signal strength observations of all corresponding APs on the mobile terminal at the corresponding collection point are used as test sampling data;

S103，以移动终端在室内任意位置接收到的原始射频信号强度观测值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。S103, take the original radio frequency signal strength observation value received by the mobile terminal at any indoor position as the input of the calibration model, process it through the improved BP neural network calibration model, and finally obtain the output as the calibration value to complete the calibration of the mobile terminal. Smart calibration.

本申请的标定算法是为了建立标准移动终端和其他移动终端之间的标定模型，一个移动终端最终只有一个对应的标定模型，与采集点没有直接关系，即标定模型的采样数据既可以是在一个采集点采集的，也可以是在很多采集点采集的，并且射频信号指的是WiFi、蓝牙等。标准采样数据和测试采样数据中采集点是一一对应的，且AP及其所有RSSI也是一一对应的。The calibration algorithm of the present application is to establish a calibration model between a standard mobile terminal and other mobile terminals. In the end, a mobile terminal has only one corresponding calibration model, which is not directly related to the collection point, that is, the sampling data of the calibration model can be in a The collection point can also be collected at many collection points, and the radio frequency signal refers to WiFi, Bluetooth, and so on. There is a one-to-one correspondence between the collection points in the standard sampling data and the test sampling data, and the AP and all its RSSIs are also in a one-to-one correspondence.

在S102中，对其他移动终端是否存在该型号的标定模型分两种情况讨论：In S102, whether other mobile terminals have calibration models of the model are discussed in two cases:

a、若存在该移动终端型号的标定模型，则跳转至步骤S103，在对移动终端进行标定之前，当判断出该终端型号存在标定库中，则可使用该移动终端在室内任意位置接收到的原始射频信号强度观测值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定；a. If there is a calibration model of the mobile terminal model, then jump to step S103. Before calibrating the mobile terminal, when it is judged that the terminal model exists in the calibration library, the mobile terminal can be used to receive any location in the room. The observed value of the original RF signal strength is used as the input of the calibration model, which is processed by the improved BP neural network calibration model, and the final output is used as the calibration value to complete the intelligent calibration of the mobile terminal;

b、若终端型号不在标定库中，则以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以该终端在对应采集点上所有AP的所有原始射频信号强度观测值作为测试采样数据，再跳转至步骤S101，也即根据所述标准采样数据以及所述测试采样数据建立并训练得到改进的BP神经网络标定模型，记录并保存终端型号及对应的标定模型参数，最后跳转至步骤S103完成移动终端智能标定。b. If the terminal model is not in the calibration library, use all the original radio frequency signal strength observations of all APs at all acquisition points of the standard mobile terminal as the standard sampling data, and use all the original radio frequency signals of all APs at the corresponding acquisition points of the terminal as the standard sampling data. The intensity observation value is used as the test sampling data, and then jumps to step S101, that is, an improved BP neural network calibration model is established and trained according to the standard sampling data and the test sampling data, and the terminal model and the corresponding calibration model are recorded and saved. model parameters, and finally jump to step S103 to complete the intelligent calibration of the mobile terminal.

在此需要指出的是，采集到的射频信号是室内环境中早已存在的信号源，不需要再次特意布设AP。It should be pointed out here that the collected radio frequency signal is a signal source that already exists in the indoor environment, and there is no need to deploy APs again.

此外，为了保证标准采样数据和测试采样数据是稳定可靠的，设置在每个采集点采样时间为10分钟，采样频率为5秒。In addition, in order to ensure that the standard sampling data and test sampling data are stable and reliable, the sampling time at each collection point is set to 10 minutes, and the sampling frequency is 5 seconds.

进一步地，从所述标准移动终端获取的所述标准采样数据或从所述其他移动终端获取的所述测试采样数据的原始数据发送格式为：Further, the original data sending format of the standard sampling data obtained from the standard mobile terminal or the test sampling data obtained from the other mobile terminals is:

Figure 152945DEST_PATH_IMAGE051
Figure 152945DEST_PATH_IMAGE051

其中，P i 为第i个采集点位置，i=1,2,...,j, j为采集点个数，AP in 为在P i 采集点上接收到的第n个AP，RSSI k 为采集到的第k次原始射频信号强度观测值。Among them, Pi is the position of the ith collection point, i =1,2,..., j, j is the number of collection points, AP in is the nth AP received at the collection point Pi , RSSI k is the acquired kth original RF signal strength observation value.

S101，基于根据提出的非线性收敛因子得到改进的BP神经网络标定模型建立标定模型库，记录并保存终端型号及对应的标定模型参数。S101 , a calibration model library is established based on the BP neural network calibration model improved according to the proposed nonlinear convergence factor, and the terminal model and corresponding calibration model parameters are recorded and saved.

在本步骤中，其具体实施过程如下：In this step, its specific implementation process is as follows:

步骤1：在室内任意选择若干个采集点（如果室内中有多个环境，比如走廊、房间、楼梯间等，在每个场景下都会选几个采集点代表这个场景，综合下来就表示该室内环境），以标准手机在所有采集点上采集射频信号强度，综合表示为初始标准采样数据（比如在a点采了n1条数据，b点采了n2条数据，综合就是n1+n2条数据），以移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；Step 1: Select a number of collection points at will in the room (if there are multiple environments in the room, such as corridors, rooms, stairwells, etc., in each scene, several collection points will be selected to represent this scene. environment), use a standard mobile phone to collect RF signal strength at all collection points, and comprehensively express it as the initial standard sampling data (for example, if n1 pieces of data are collected at point a, and n2 pieces of data are collected at point b, the synthesis is n1+n2 pieces of data) , and use all the original radio frequency signal strength observations of all corresponding APs at the corresponding collection point of the mobile terminal as the test sampling data;

以所述测试采样数据为改进的BP神经网络标定模型的真实输入值，以所述初始标 准采样数据为改进的BP神经网络标定模型的真实输出值，随机初始化神经网络的各层权值

Figure 557382DEST_PATH_IMAGE052
、阈值
Figure 609651DEST_PATH_IMAGE053
作为初始鲸鱼群位置向量
Figure 311897DEST_PATH_IMAGE054
，设置鲸鱼种群大小N，当前鲸鱼种群迭代次数t= 0，鲸鱼种群最大迭代次数
Figure 766012DEST_PATH_IMAGE055
，当前BP神经网络迭代次数T，BP神经网络最大迭代次数T max ； Taking the test sampling data as the real input value of the improved BP neural network calibration model, using the initial standard sampling data as the real output value of the improved BP neural network calibration model, and randomly initializing the weights of each layer of the neural network
Figure 557382DEST_PATH_IMAGE052
, threshold
Figure 609651DEST_PATH_IMAGE053
as the initial whale swarm position vector
Figure 311897DEST_PATH_IMAGE054
, set the whale population size N , the current whale population iteration number t = 0, the maximum whale population iteration number
Figure 766012DEST_PATH_IMAGE055
, the current number of BP neural network iterations T , the maximum number of BP neural network iterations T max ;

步骤2：计算每只鲸鱼的适应度值

Figure 544612DEST_PATH_IMAGE056
,找出最好的适应度及对应的最优鲸鱼位 置
Figure 880915DEST_PATH_IMAGE057
； Step 2: Calculate the fitness value of each whale
Figure 544612DEST_PATH_IMAGE056
, find the best fitness and the corresponding optimal whale position
Figure 880915DEST_PATH_IMAGE057
;

Figure 403164DEST_PATH_IMAGE058
(1)
Figure 403164DEST_PATH_IMAGE058
(1)

其中，

Figure 961053DEST_PATH_IMAGE059
为标准采样数据的第i个RSSI真实值，
Figure 644975DEST_PATH_IMAGE060
为测试采样数据的第i个RSSI预 测值，n为样本个数； in,
Figure 961053DEST_PATH_IMAGE059
is the ith RSSI real value of the standard sampled data,
Figure 644975DEST_PATH_IMAGE060
is the ith RSSI prediction value of the test sample data, and n is the number of samples;

步骤3：为了加快标定算法的建立与优化，更新迭代速度有所提升，提出了一种非 线性的收敛因子a模拟包围猎物的收缩行为，收敛因子

Figure 406258DEST_PATH_IMAGE061
只随着当前迭代次数
Figure 732197DEST_PATH_IMAGE062
动态变化， 可以较为有效避免陷入局部最优，更新鲸鱼位置参数a、A、C： Step 3: In order to speed up the establishment and optimization of the calibration algorithm and improve the update iteration speed, a nonlinear convergence factor a is proposed to simulate the shrinking behavior of surrounding prey, and the convergence factor
Figure 406258DEST_PATH_IMAGE061
only with the current number of iterations
Figure 732197DEST_PATH_IMAGE062
Dynamic changes can effectively avoid falling into local optimum, and update the whale position parameters a , A, and C :

Figure 144592DEST_PATH_IMAGE063
(2)
Figure 144592DEST_PATH_IMAGE063
(2)

Figure 61733DEST_PATH_IMAGE064
(3)
Figure 61733DEST_PATH_IMAGE064
(3)

Figure 575891DEST_PATH_IMAGE065
(4)
Figure 575891DEST_PATH_IMAGE065
(4)

其中, t为当前鲸鱼种群迭代次数，

Figure 174362DEST_PATH_IMAGE066
为最大迭代数，r是[0,1]的一个随机数； Among them, t is the number of iterations of the current whale population,
Figure 174362DEST_PATH_IMAGE066
is the maximum number of iterations, r is a random number in [0,1];

步骤4：随机产生概率p，判断p是否小于0.5，若

Figure 191997DEST_PATH_IMAGE067
，则进行收缩包围位置更 新： Step 4: Randomly generate probability p , and judge whether p is less than 0.5, if
Figure 191997DEST_PATH_IMAGE067
, then the shrink wrapping position update is performed:

Figure 998148DEST_PATH_IMAGE068
(5)
Figure 998148DEST_PATH_IMAGE068
(5)

其中,t为当前鲸鱼种群迭代次数；

Figure 530760DEST_PATH_IMAGE069
为最优鲸鱼位置；
Figure 198502DEST_PATH_IMAGE070
为当前鲸鱼位置；A 和C为步骤3所得出的系数向量； Among them, t is the iteration times of the current whale population;
Figure 530760DEST_PATH_IMAGE069
is the optimal whale position;
Figure 198502DEST_PATH_IMAGE070
is the current whale position; A and C are the coefficient vectors obtained in step 3;

若

Figure 70643DEST_PATH_IMAGE071
，且当
Figure 532848DEST_PATH_IMAGE021
时进行螺旋游走： like
Figure 70643DEST_PATH_IMAGE071
, and when
Figure 532848DEST_PATH_IMAGE021
When performing a spiral walk:

Figure 552757DEST_PATH_IMAGE072
(6)
Figure 552757DEST_PATH_IMAGE072
(6)

其中,

Figure 7878DEST_PATH_IMAGE073
表示当前鲸鱼与最优位置的距离；b为常数，定义对数螺旋线 形状；l为[-1,1]中随机数； in,
Figure 7878DEST_PATH_IMAGE073
Indicates the distance between the current whale and the optimal position; b is a constant, which defines the logarithmic spiral shape; l is a random number in [-1,1];

当

Figure 105DEST_PATH_IMAGE074
时根据以下公式进行随机游走： when
Figure 105DEST_PATH_IMAGE074
A random walk is performed according to the following formula:

Figure 633211DEST_PATH_IMAGE075
(7)
Figure 633211DEST_PATH_IMAGE075
(7)

其中,

Figure 78099DEST_PATH_IMAGE076
为随机选取的位置向量； in,
Figure 78099DEST_PATH_IMAGE076
is a randomly selected position vector;

步骤5：鲸鱼种群迭代次数t自增，根据步骤2比较更新最优位置；当到达鲸鱼种群 最大迭代次数

Figure 336911DEST_PATH_IMAGE077
时，输出
Figure 449224DEST_PATH_IMAGE078
即最优权值
Figure 49969DEST_PATH_IMAGE079
、阈值
Figure 247732DEST_PATH_IMAGE030
,并作为BP神经网络最优初始 参数； Step 5: The number of whale population iterations t increases automatically, and the optimal position is updated according to step 2; when the maximum number of iterations for the whale population is reached
Figure 336911DEST_PATH_IMAGE077
when the output
Figure 449224DEST_PATH_IMAGE078
the optimal weight
Figure 49969DEST_PATH_IMAGE079
, threshold
Figure 247732DEST_PATH_IMAGE030
, and as the optimal initial parameter of BP neural network;

步骤6：BP神经网络进行正向传播过程，通过神经元之间的连接权值

Figure 529809DEST_PATH_IMAGE080
和神经元 阈值
Figure 745896DEST_PATH_IMAGE081
进行数据加工，并采用非线性Sigmoid激活函数获得预测输出值。 Step 6: The BP neural network performs a forward propagation process, through the connection weights between neurons
Figure 529809DEST_PATH_IMAGE080
and neuron threshold
Figure 745896DEST_PATH_IMAGE081
Data processing is performed and a nonlinear sigmoid activation function is used to obtain predicted output values.

Figure 517543DEST_PATH_IMAGE082
(8)
Figure 517543DEST_PATH_IMAGE082
(8)

Figure 202602DEST_PATH_IMAGE083
(9)
Figure 202602DEST_PATH_IMAGE083
(9)

其中，

Figure 553949DEST_PATH_IMAGE084
为神经元i到神经元j的连接权值；
Figure 109695DEST_PATH_IMAGE085
为神经元j阈值；
Figure 776212DEST_PATH_IMAGE086
为神经元j输 入值；
Figure 682988DEST_PATH_IMAGE087
为神经元j输出值；
Figure 369184DEST_PATH_IMAGE088
为神经元
Figure 310595DEST_PATH_IMAGE089
的输入值。in,
Figure 553949DEST_PATH_IMAGE084
is the connection weight from neuron i to neuron j ;
Figure 109695DEST_PATH_IMAGE085
is the threshold of neuron j ;
Figure 776212DEST_PATH_IMAGE086
input value for neuron j ;
Figure 682988DEST_PATH_IMAGE087
output value for neuron j ;
Figure 369184DEST_PATH_IMAGE088
for neurons
Figure 310595DEST_PATH_IMAGE089
the input value.

步骤7：BP神经网络进行误差反向传播过程，通过正向传播过程获得预测输出值， 根据智能设备的预测输出值与标准智能设备的真实输出值之间的差异得到当前迭代次数 的损失函数

Figure 361728DEST_PATH_IMAGE090
，将误差逆向传播至上一层神经元中得到该层误差，逐层传递直至最上层隐 藏层，基于梯度下降法对连接权值和阈值进行不断调整。 Step 7: The BP neural network performs the error back propagation process, obtains the predicted output value through the forward propagation process, and obtains the loss function of the current number of iterations according to the difference between the predicted output value of the smart device and the actual output value of the standard smart device
Figure 361728DEST_PATH_IMAGE090
, the error is back-propagated to the neurons of the previous layer to obtain the error of this layer, which is passed layer by layer to the top hidden layer, and the connection weights and thresholds are continuously adjusted based on the gradient descent method.

Figure 5068DEST_PATH_IMAGE091
(10)
Figure 5068DEST_PATH_IMAGE091
(10)

Figure 698217DEST_PATH_IMAGE092
(11)
Figure 698217DEST_PATH_IMAGE092
(11)

Figure 494135DEST_PATH_IMAGE093
(12)
Figure 494135DEST_PATH_IMAGE093
(12)

其中，

Figure 44065DEST_PATH_IMAGE094
为神经元j真实输出值；
Figure 925433DEST_PATH_IMAGE095
为输出层神经元j预测输出值；
Figure 405962DEST_PATH_IMAGE096
为更新后权值；
Figure 790807DEST_PATH_IMAGE097
为更新后阈值；
Figure 714901DEST_PATH_IMAGE098
为学习率，若其值偏大则收敛快但容易陷 入局部最优，若偏小则收敛慢但逼近全局最优。 in,
Figure 44065DEST_PATH_IMAGE094
is the real output value of neuron j;
Figure 925433DEST_PATH_IMAGE095
Predict the output value for the output layer neuron j;
Figure 405962DEST_PATH_IMAGE096
is the updated weight;
Figure 790807DEST_PATH_IMAGE097
is the updated threshold;
Figure 714901DEST_PATH_IMAGE098
is the learning rate. If the value is too large, the convergence will be fast but it is easy to fall into the local optimum. If the value is too small, the convergence will be slow but approach the global optimum.

步骤8：经过反复学习训练，当BP神经网络迭代次数T到达BP神经网络最大迭代次 数

Figure 83565DEST_PATH_IMAGE099
时，选取损失函数
Figure 915255DEST_PATH_IMAGE100
最小的BP神经网络作为最终标定模型，保存当前改进的BP神 经网络标定模型的参数。 Step 8: After repeated learning and training, when the number of iterations T of the BP neural network reaches the maximum number of iterations of the BP neural network
Figure 83565DEST_PATH_IMAGE099
When , choose the loss function
Figure 915255DEST_PATH_IMAGE100
The smallest BP neural network is used as the final calibration model, and the parameters of the current improved BP neural network calibration model are saved.

步骤9：将多个移动终端重复步骤1至8，进而建立标定模型库。Step 9: Repeat steps 1 to 8 for multiple mobile terminals, and then establish a calibration model library.

当行人手持移动终端需要进行标定时，首先系统会自动在服务器的标定数据库中匹配该终端型号，若存在，则可手持移动终端在室内任意位置对接收到的射频信号强度观测值进行标定，否则要先在采集点采集测试采样数据，建立该终端型号的改进的BP神经网络标定模型后再进行标定。When a pedestrian needs to calibrate a handheld mobile terminal, the system will automatically match the terminal model in the calibration database of the server. If it exists, the mobile terminal can be used to calibrate the received RF signal strength observation value at any location in the room. The test sampling data should be collected at the collection point first, and the improved BP neural network calibration model of the terminal model should be established before calibration.

在此需要补充的是，室内任意位置可以是采样数据的采集点，也可以是其他位置，在任意位置上移动终端接收到所有AP的原始射频信号强度观测值会即时进行标定。What needs to be added here is that any location in the room can be the collection point of the sampling data, or it can be another location. At any location, the mobile terminal receives the raw RF signal strength observations of all APs and will perform calibration in real time.

实施例2Example 2

请参阅图3，对于本发明第二实施例提出的一种基于移动终端无线射频信号强度的智能标定系统，包括依次连接的数据采集模块11、模型建立模块12以及智能标定模块13；Referring to FIG. 3 , an intelligent calibration system based on the strength of a wireless radio frequency signal of a mobile terminal proposed by the second embodiment of the present invention includes a data acquisition module 11 , a model establishment module 12 and an intelligent calibration module 13 connected in sequence;

其中所述数据采集模块11具体用于：The data acquisition module 11 is specifically used for:

以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；All raw radio frequency signal strength observations of all APs at all collection points of the standard mobile terminal are used as standard sampling data, and all original radio frequency signal strength observations of all corresponding APs at corresponding collection points by the mobile terminal are used as test sampling data;

其中所述模型建立模块12具体用于：The model building module 12 is specifically used for:

根据所述标准采样数据以及所述测试采样数据建立并训练得到改进的BP神经网络标定模型，记录并保存终端型号及对应的标定模型参数；Establish and train an improved BP neural network calibration model according to the standard sampling data and the test sampling data, and record and save the terminal model and the corresponding calibration model parameters;

其中所述智能标定模块13具体用于：The intelligent calibration module 13 is specifically used for:

以移动终端在室内任意位置接收到的射频信号值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。The radio frequency signal value received by the mobile terminal at any indoor position is used as the input of the calibration model, which is processed by the improved BP neural network calibration model, and the final output is used as the calibration value to complete the intelligent calibration of the mobile terminal.

本领域普通技术人员可以理解实现上述实施例方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成。所述的程序可以存储于一计算机可读取存储介质中。该程序在执行时，包括上述方法所述的步骤。所述的存储介质，包括：ROM/RAM、磁碟、光盘等。Those skilled in the art can understand that all or part of the steps in the method of the above embodiments can be implemented by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, the steps described in the above method are included. The storage medium includes: ROM/RAM, magnetic disk, optical disk and so on.

以上所述实施例仅表达了本发明的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本发明专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变形和改进，这些都属于本发明的保护范围。因此，本发明专利的保护范围应以所附权利要求为准。The above-mentioned embodiments only represent several embodiments of the present invention, and the descriptions thereof are specific and detailed, but should not be construed as a limitation on the scope of the patent of the present invention. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can also be made, which all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims (2)

1.基于移动终端无线射频信号强度的智能标定方法，其特征在于：所述标定方法对每个移动终端建立对应的改进的BP神经网络标定模型，包括如下步骤：1. the intelligent calibration method based on the radio frequency signal strength of mobile terminal, is characterized in that: described calibration method establishes corresponding improved BP neural network calibration model to each mobile terminal, comprises the steps: S1、根据提出的非线性收敛因子得到改进的BP神经网络标定模型建立标定模型库，记录并保存终端型号及对应的标定模型参数；S1. Establish a calibration model library according to the BP neural network calibration model with the improved nonlinear convergence factor proposed, and record and save the terminal model and the corresponding calibration model parameters; 所述根据提出的非线性收敛因子得到改进的BP神经网络标定模型建立标定模型库的方法包括如下步骤：The method for establishing a calibration model library according to the BP neural network calibration model with an improved nonlinear convergence factor proposed includes the following steps: S1-1：在室内任意选择若干个采集点，标准移动终端在所有采集点上采集射频信号强度，综合表示为初始标准采样数据，以移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据，以所述测试采样数据为改进的BP神经网络标定模型的真实输入值，以所述初始标准采样数据为改进的BP神经网络标定模型的真实输出值；随机初始化神经网络的各层权值
Figure DEST_PATH_IMAGE001
、阈值
Figure 300529DEST_PATH_IMAGE002
作为初始鲸鱼群位置向量
Figure DEST_PATH_IMAGE003
，设置鲸鱼种群大小N，当前鲸鱼种群迭代次数t=0，鲸鱼种群最大迭代次数
Figure 421194DEST_PATH_IMAGE004
，当前BP神经网络迭代次数T，BP神经网络最大迭代次数T max ；S1-1: Select several collection points at random in the room, the standard mobile terminal collects the RF signal strength at all collection points, and comprehensively expresses it as the initial standard sampling data, using all the original RF signals of all corresponding APs at the corresponding collection point by the mobile terminal The intensity observation value is used as the test sample data, and the test sample data is used as the real input value of the improved BP neural network calibration model, and the initial standard sample data is used as the real output value of the improved BP neural network calibration model; random initialization neural network The weights of each layer of the network
Figure DEST_PATH_IMAGE001
, threshold
Figure 300529DEST_PATH_IMAGE002
as the initial whale swarm position vector
Figure DEST_PATH_IMAGE003
, set the whale population size N , the current whale population iteration number t = 0, the maximum whale population iteration number
Figure 421194DEST_PATH_IMAGE004
, the current number of iterations of the BP neural network T, the maximum number of iterations of the BP neural network T max ; S1-2：当鲸鱼种群当前迭代次数t小于鲸鱼种群最大迭代次数
Figure DEST_PATH_IMAGE005
时，计算每只鲸鱼的适应度值
Figure 750544DEST_PATH_IMAGE006
,找出最好的适应度及对应的最优鲸鱼位置
Figure DEST_PATH_IMAGE007
：S1-2: When the current iteration number t of the whale population is less than the maximum iteration number of the whale population
Figure DEST_PATH_IMAGE005
When , calculate the fitness value of each whale
Figure 750544DEST_PATH_IMAGE006
, find the best fitness and the corresponding optimal whale position
Figure DEST_PATH_IMAGE007
:
Figure 683865DEST_PATH_IMAGE008
(1)
Figure 683865DEST_PATH_IMAGE008
(1) 式中，
Figure DEST_PATH_IMAGE009
为标准采样数据的第i个RSSI真实值，
Figure 149481DEST_PATH_IMAGE010
为测试采样数据的第i个RSSI预测值，n为样本个数；In the formula,
Figure DEST_PATH_IMAGE009
is the ith RSSI real value of the standard sampled data,
Figure 149481DEST_PATH_IMAGE010
is the ith RSSI prediction value of the test sample data, and n is the number of samples; S1-3：为了加快标定方法的建立与优化，更新迭代速度有所提升，提出了一种非线性的收敛因子a模拟包围猎物的收缩行为，收敛因子
Figure DEST_PATH_IMAGE011
只随着当前迭代次数
Figure 205162DEST_PATH_IMAGE012
动态变化，可以有效避免算法陷入局部最优，非线性的收敛因子a的计算公式为：S1-3: In order to speed up the establishment and optimization of the calibration method and improve the update iteration speed, a nonlinear convergence factor a is proposed to simulate the shrinking behavior of surrounding prey, and the convergence factor
Figure DEST_PATH_IMAGE011
only with the current number of iterations
Figure 205162DEST_PATH_IMAGE012
The dynamic change can effectively avoid the algorithm from falling into local optimum. The calculation formula of the nonlinear convergence factor a is:
Figure DEST_PATH_IMAGE013
(2)
Figure DEST_PATH_IMAGE013
(2) 式中，t为当前鲸鱼种群迭代次数，
Figure 317081DEST_PATH_IMAGE014
为鲸鱼种群最大迭代次数；更新鲸鱼位置参数A、C，公式如下：where t is the number of iterations of the current whale population,
Figure 317081DEST_PATH_IMAGE014
is the maximum number of iterations for the whale population; to update the whale position parameters A and C, the formula is as follows:
Figure DEST_PATH_IMAGE015
(3)
Figure DEST_PATH_IMAGE015
(3)
Figure 116410DEST_PATH_IMAGE016
(4)
Figure 116410DEST_PATH_IMAGE016
(4) 式中， r是[0,1]的一个随机数；where r is a random number in [0,1]; S1-4：随机产生概率p，判断p是否小于0.5，若
Figure DEST_PATH_IMAGE017
，则进行收缩包围位置更新：S1-4: Randomly generate probability p , determine whether p is less than 0.5, if
Figure DEST_PATH_IMAGE017
, then the shrink wrapping position update is performed:
Figure 436533DEST_PATH_IMAGE018
(5)
Figure 436533DEST_PATH_IMAGE018
(5) 式中，t为当前鲸鱼种群迭代次数；
Figure DEST_PATH_IMAGE019
为最优鲸鱼位置；
Figure 600798DEST_PATH_IMAGE020
为当前鲸鱼位置；A和C为所述步骤S1-3所得出的系数向量；In the formula, t is the number of iterations of the current whale population;
Figure DEST_PATH_IMAGE019
is the optimal whale position;
Figure 600798DEST_PATH_IMAGE020
is the current whale position; A and C are the coefficient vectors obtained in the step S1-3; 若
Figure DEST_PATH_IMAGE021
，且当
Figure 639161DEST_PATH_IMAGE022
时进行螺旋游走：like
Figure DEST_PATH_IMAGE021
, and when
Figure 639161DEST_PATH_IMAGE022
When performing a spiral walk:
Figure DEST_PATH_IMAGE023
(6)
Figure DEST_PATH_IMAGE023
(6) 式中，
Figure 274804DEST_PATH_IMAGE024
表示当前鲸鱼与最优位置的距离；b为常数，定义对数螺旋线形状；l为[-1,1]中随机数；In the formula,
Figure 274804DEST_PATH_IMAGE024
Indicates the distance between the current whale and the optimal position; b is a constant, which defines the logarithmic spiral shape; l is a random number in [-1,1]; 当
Figure DEST_PATH_IMAGE025
时根据公式（7）进行随机游走：when
Figure DEST_PATH_IMAGE025
When the random walk is performed according to formula (7):
Figure 980592DEST_PATH_IMAGE026
(7)
Figure 980592DEST_PATH_IMAGE026
(7) 式中，
Figure DEST_PATH_IMAGE027
为随机选取的位置向量；In the formula,
Figure DEST_PATH_IMAGE027
is a randomly selected position vector; S1-5：鲸鱼种群迭代次数t自增，根据步骤S1-2比较更新最优位置；当到达鲸鱼种群最大迭代次数
Figure 112496DEST_PATH_IMAGE028
时，输出
Figure DEST_PATH_IMAGE029
即最优权值
Figure 575838DEST_PATH_IMAGE030
、阈值
Figure DEST_PATH_IMAGE031
,并作为BP神经网络最优初始参数；S1-5: The number of iterations t of the whale population increases automatically, and the optimal position is updated according to step S1-2; when the maximum number of iterations for the whale population is reached
Figure 112496DEST_PATH_IMAGE028
when the output
Figure DEST_PATH_IMAGE029
the optimal weight
Figure 575838DEST_PATH_IMAGE030
, threshold
Figure DEST_PATH_IMAGE031
, and as the optimal initial parameter of BP neural network; S1-6：BP神经网络进行正向传播过程，通过神经元之间的连接权值
Figure 451391DEST_PATH_IMAGE032
和神经元阈值
Figure DEST_PATH_IMAGE033
进行数据加工，并采用非线性Sigmoid激活函数获得预测输出值：S1-6: BP neural network performs forward propagation process, through the connection weights between neurons
Figure 451391DEST_PATH_IMAGE032
and neuron threshold
Figure DEST_PATH_IMAGE033
Perform data processing and use a nonlinear sigmoid activation function to obtain predicted output values:
Figure 510220DEST_PATH_IMAGE034
(8)
Figure 510220DEST_PATH_IMAGE034
(8)
Figure DEST_PATH_IMAGE035
(9)
Figure DEST_PATH_IMAGE035
(9) 式中，
Figure 140921DEST_PATH_IMAGE036
为神经元i到神经元j的连接权值；
Figure DEST_PATH_IMAGE037
为神经元j阈值；
Figure 888298DEST_PATH_IMAGE038
为神经元j输入值；
Figure DEST_PATH_IMAGE039
为神经元j输出值；
Figure 505224DEST_PATH_IMAGE040
为神经元
Figure DEST_PATH_IMAGE041
的输入值；In the formula,
Figure 140921DEST_PATH_IMAGE036
is the connection weight from neuron i to neuron j ;
Figure DEST_PATH_IMAGE037
is the threshold of neuron j ;
Figure 888298DEST_PATH_IMAGE038
input value for neuron j;
Figure DEST_PATH_IMAGE039
output value for neuron j ;
Figure 505224DEST_PATH_IMAGE040
for neurons
Figure DEST_PATH_IMAGE041
the input value of ; S1-7：BP神经网络进行误差反向传播过程，通过正向传播过程获得预测输出值，根据智能设备的预测输出值与标准智能设备的真实输出值之间的差异得到当前迭代次数的损失函数
Figure 920025DEST_PATH_IMAGE042
，将误差逆向传播至上一层神经元中得到该层误差，逐层传递直至最上层隐藏层，基于梯度下降法对连接权值和阈值进行不断调整：S1-7: The BP neural network performs the error back propagation process, obtains the predicted output value through the forward propagation process, and obtains the loss function of the current iteration number according to the difference between the predicted output value of the smart device and the actual output value of the standard smart device
Figure 920025DEST_PATH_IMAGE042
, the error is back-propagated to the neurons of the previous layer to obtain the layer error, which is passed layer by layer to the top hidden layer, and the connection weights and thresholds are continuously adjusted based on the gradient descent method:
Figure DEST_PATH_IMAGE043
(10)
Figure DEST_PATH_IMAGE043
(10)
Figure 160775DEST_PATH_IMAGE044
(11)
Figure 160775DEST_PATH_IMAGE044
(11)
Figure DEST_PATH_IMAGE045
(12)
Figure DEST_PATH_IMAGE045
(12) 式中，
Figure 457764DEST_PATH_IMAGE046
为神经元j真实输出值；
Figure DEST_PATH_IMAGE047
为输出层神经元j预测输出值；
Figure 675119DEST_PATH_IMAGE048
为更新后权值；
Figure DEST_PATH_IMAGE049
为更新后阈值；
Figure 210006DEST_PATH_IMAGE050
为学习率，若其值偏大则收敛快但容易陷入局部最优，若偏小则收敛慢但逼近全局最优；In the formula,
Figure 457764DEST_PATH_IMAGE046
is the real output value of neuron j ;
Figure DEST_PATH_IMAGE047
Predict the output value for the output layer neuron j ;
Figure 675119DEST_PATH_IMAGE048
is the updated weight;
Figure DEST_PATH_IMAGE049
is the updated threshold;
Figure 210006DEST_PATH_IMAGE050
is the learning rate, if the value is too large, the convergence will be fast but it is easy to fall into the local optimum; if it is too small, the convergence will be slow but approach the global optimum; S1-8：经过反复学习训练，当BP神经网络迭代次数T到达BP神经网络最大迭代次数
Figure DEST_PATH_IMAGE051
时，选取损失函数
Figure 57876DEST_PATH_IMAGE052
最小的BP神经网络作为最终标定模型，保存当前改进的BP神经网络标定模型的参数以及对应的移动终端型号；S1-8: After repeated learning and training, when the number of iterations T of the BP neural network reaches the maximum number of iterations of the BP neural network
Figure DEST_PATH_IMAGE051
When , choose the loss function
Figure 57876DEST_PATH_IMAGE052
The smallest BP neural network is used as the final calibration model, and the parameters of the current improved BP neural network calibration model and the corresponding mobile terminal model are saved; S1-9：将多个移动终端重复步骤S1-1至S1-8，进而建立标定模型库；S1-9: Repeat steps S1-1 to S1-8 for multiple mobile terminals, and then establish a calibration model library; S2、手持某个移动终端进行标定之前，判断该终端型号是否在标定模型库中；S2, before holding a mobile terminal for calibration, determine whether the terminal model is in the calibration model library; 若否，则以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，以该移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据，以所述测试采样数据为改进的BP神经网络标定模型的真实输入值，以所述标准采样数据为改进的BP神经网络标定模型的真实输出值，重复步骤S1建立并训练得到该终端型号在所述改进的BP神经网络标定模型中的标定模型参数，再进入步骤S3中；If not, take all the original radio frequency signal strength observations of all APs at all collection points of the standard mobile terminal as the standard sampling data, and use all the original radio frequency signal strength observations of all corresponding APs at the corresponding collection points of the mobile terminal as the test Sampling data, taking the test sampling data as the real input value of the improved BP neural network calibration model, taking the standard sampling data as the real output value of the improved BP neural network calibration model, repeating step S1 to establish and train to obtain the terminal The calibration model parameters of the model in the improved BP neural network calibration model, and then enter step S3; 若是，则直接进入步骤S3中利用标定模型库对应的标定模型参数进行标定；If yes, then directly enter step S3 to perform calibration using the calibration model parameters corresponding to the calibration model library; S3、手持该移动终端进行标定时以在室内任意位置接收到的原始射频信号强度观测值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。S3. When holding the mobile terminal for calibration, the original RF signal strength observation value received at any position in the room is used as the input of the calibration model, and the improved BP neural network calibration model is processed, and the final output is used as the calibration value to complete Intelligent calibration of the mobile terminal. 2.基于移动终端无线射频信号强度的智能标定系统，其特征在于：所述智能标定系统执行权利要求1所述的基于移动终端无线射频信号强度的智能标定方法，所述标定系统包括数据采集模块、模型建立模块和智能标定模块；2. The intelligent calibration system based on the strength of the radio frequency signal of the mobile terminal, is characterized in that: the intelligent calibration system executes the intelligent calibration method based on the strength of the radio frequency signal of the mobile terminal according to claim 1, and the calibration system comprises a data acquisition module , model building module and intelligent calibration module; 所述数据采集模块，用于以标准移动终端在所有采集点上所有AP的所有原始射频信号强度观测值作为标准采样数据，和以其他移动终端在对应采集点上所有对应AP的所有原始射频信号强度观测值作为测试采样数据；The data acquisition module is used to use all the original radio frequency signal strength observations of all APs at all acquisition points of the standard mobile terminal as standard sampling data, and use all the original radio frequency signals of all corresponding APs at the corresponding acquisition points of other mobile terminals as the standard sampling data. Intensity observations are used as test sampling data; 所述模型建立模块，用于根据所述标准采样数据以及所述测试采样数据建立并训练得到改进的BP神经网络标定模型，记录并保存终端型号及对应的标定模型参数；The model establishment module is used to establish and train an improved BP neural network calibration model according to the standard sampling data and the test sampling data, and record and save the terminal model and the corresponding calibration model parameters; 所述智能标定模块，用于以移动终端在室内任意位置接收到的射频信号值作为标定模型输入，将其经过改进的BP神经网络标定模型进行处理，最终得到的输出作为标定值以完成对该移动终端的智能标定。The intelligent calibration module is used to use the radio frequency signal value received by the mobile terminal at any indoor position as the input of the calibration model, process it through the improved BP neural network calibration model, and finally obtain the output as the calibration value to complete the calibration model. Smart calibration of mobile terminals.
CN202110952490.5A 2021-08-19 2021-08-19 Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal Active CN113612555B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110952490.5A CN113612555B (en) 2021-08-19 2021-08-19 Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110952490.5A CN113612555B (en) 2021-08-19 2021-08-19 Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal

Publications (2)

Publication Number Publication Date
CN113612555A CN113612555A (en) 2021-11-05
CN113612555B true CN113612555B (en) 2022-06-07

Family

ID=78341189

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110952490.5A Active CN113612555B (en) 2021-08-19 2021-08-19 Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal

Country Status (1)

Country Link
CN (1) CN113612555B (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109948791A (en) * 2017-12-21 2019-06-28 河北科技大学 A method of optimizing BP neural network by genetic algorithm and its application in localization
US10655971B1 (en) * 2019-05-01 2020-05-19 Mapsted Corp. Maintaining a trained neural network for mobile device RSS fingerprint based indoor navigation
CN112333652A (en) * 2019-07-16 2021-02-05 中国移动通信集团浙江有限公司 WLAN indoor positioning method and device and electronic equipment
CN112700060A (en) * 2021-01-08 2021-04-23 佳源科技股份有限公司 Station terminal load prediction method and prediction device
CN113163484A (en) * 2021-01-08 2021-07-23 广东工业大学 Indoor positioning method

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9239990B2 (en) * 2011-06-24 2016-01-19 Zos Communications, Llc Hybrid location using pattern recognition of location readings and signal strengths of wireless access points
US10555192B2 (en) * 2017-11-15 2020-02-04 Futurewei Technologies, Inc. Predicting received signal strength in a telecommunication network using deep neural networks
WO2021007812A1 (en) * 2019-07-17 2021-01-21 深圳大学 Deep neural network hyperparameter optimization method, electronic device and storage medium
US11057118B2 (en) * 2020-04-29 2021-07-06 Intel Corporation Indoor localization with beacon technology based on signal strength distribution and deep learning techniques

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109948791A (en) * 2017-12-21 2019-06-28 河北科技大学 A method of optimizing BP neural network by genetic algorithm and its application in localization
US10655971B1 (en) * 2019-05-01 2020-05-19 Mapsted Corp. Maintaining a trained neural network for mobile device RSS fingerprint based indoor navigation
CN112333652A (en) * 2019-07-16 2021-02-05 中国移动通信集团浙江有限公司 WLAN indoor positioning method and device and electronic equipment
CN112700060A (en) * 2021-01-08 2021-04-23 佳源科技股份有限公司 Station terminal load prediction method and prediction device
CN113163484A (en) * 2021-01-08 2021-07-23 广东工业大学 Indoor positioning method

Also Published As

Publication number Publication date
CN113612555A (en) 2021-11-05

Similar Documents

Publication Publication Date Title
US9542938B2 (en) Scene recognition method, device and mobile terminal based on ambient sound
CN110166154B (en) Software radio frequency spectrum monitoring and identifying method based on neural network
CN109769280B (en) A WIFI intelligent predictive switching method based on machine learning
CN111512178B (en) Motion detection based on machine learning of wireless signal properties
CN107832834B (en) Method for constructing WIFI indoor positioning fingerprint database based on generation countermeasure network
US20130172006A1 (en) Hybrid location using a weighted average of location readings and signal strengths of wireless access points
CN112153616B (en) Power control method in millimeter wave communication system based on deep learning
WO2016165459A1 (en) Method and device for indoor positioning
CN107992882A (en) A kind of occupancy statistical method based on WiFi channel condition informations and support vector machines
CN111930336A (en) Volume adjusting method and device of audio device and storage medium
CN106572228A (en) Volume adjusting method, volume adjusting device and mobile terminal
Cui et al. Improved genetic algorithm to optimize the Wi-Fi indoor positioning based on artificial neural network
CN118861992A (en) A multimodal data processing method, device, equipment and medium for intelligent manufacturing
CN110969240A (en) Pruning method, device, equipment and medium for deep convolutional neural network
Mallik et al. EME-Net: A U-net-based indoor EMF exposure map reconstruction method
CN110956265A (en) Model training method and related device
CN113612555B (en) Intelligent calibration method and system based on wireless radio frequency signal strength of mobile terminal
CN107832848B (en) Application management method and device, storage medium and electronic equipment
CN108414970B (en) indoor positioning method
CN110290466A (en) Floor discrimination method, device, equipment and computer storage medium
CN118230751A (en) A method, terminal and server for adaptive noise reduction based on scene perception
CN118861585A (en) Method and device for identifying drones based on infrared temperature measurement
Liu et al. Combining auto-encoder with LSTM for WiFi-based fingerprint positioning
CN110049442B (en) Automatic calibration method and system for indoor WiFi fingerprint positioning based on smart phone
CN111880568A (en) Optimization training method, device and equipment for automatic control of unmanned aerial vehicle and storage medium

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
GR01 Patent grant
GR01 Patent grant
点击 这是indexloc提供的php浏览器服务，不要输入任何密码和下载