CN103945332B - A kind of received signal strength and multi-path information united NNs indoor orientation method - Google Patents
A kind of received signal strength and multi-path information united NNs indoor orientation method Download PDFInfo
- Publication number
- CN103945332B CN103945332B CN201410174502.6A CN201410174502A CN103945332B CN 103945332 B CN103945332 B CN 103945332B CN 201410174502 A CN201410174502 A CN 201410174502A CN 103945332 B CN103945332 B CN 103945332B
- Authority
- CN
- China
- Prior art keywords
- multipath
- rss
- neural network
- information
- received signal
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000000605 extraction Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000013528 artificial neural network Methods 0.000 claims description 60
- 238000010606 normalization Methods 0.000 claims description 20
- 238000005259 measurement Methods 0.000 claims description 3
- 235000002020 sage Nutrition 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 2
- 238000012545 processing Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000004807 localization Effects 0.000 abstract 1
- 230000007935 neutral effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 3
- 238000002474 experimental method Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 238000005315 distribution function Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Position Fixing By Use Of Radio Waves (AREA)
Abstract
The invention discloses a kind of received signal strength for belonging to field of locating technology and multi-path information united NNs indoor orientation method.Wherein localization method includes off-line phase and on-line stage.Off-line phase is to determine the reference point that is distributed in indoor environment according to the feature of indoor environment；Measure, obtained in signal of each reference point from diverse access point in each reference point selected；Go out received signal strength RSS and multipath characteristics parameter from the signal extraction received；The RSS of extraction and multipath characteristics parameter are normalized, on-line stage is signal of the real-time reception from each access point；From real-time reception to signal in extract RSS and multipath parameter；RSS and multipath parameter are normalized using offline normalized value；Using normalized parameter as the input of the neutral net of off-line training, output is obtained as the estimation to current location.This method can solve the problem of positioning precision is low, effectively improve positioning precision.
Description
Technical Field
The invention relates to the technical field of positioning, in particular to a method for positioning in a neural network room by combining received signal strength and multipath information.
Background
GPS location technology has a significant disadvantage in that location cannot be achieved in indoor environments, mainly due to lack of direct-view transmission in indoor environments.
Currently, indoor positioning is diversified, and most of the indoor positioning methods utilize existing infrastructure, such as Ultra Wideband (UWB), Wireless Local Area Network (WLAN), and the like. One of the positioning methods is an indoor positioning method based on Received Signal Strength (RSS) fingerprint. This method can locate a person or object in an indoor environment, but it also has some problems. Some studies indicate that many factors can have an effect on the accuracy of RSS. In order to improve the accuracy and precision of indoor positioning, more channel state information is needed for positioning. Meanwhile, with the development of wireless communication technology, mobile communication systems have been developed towards high frequency band and high bandwidth, and richer information of channels can be obtained by using parameter estimation algorithms such as SAGE (space-induced emission), and the like.
Disclosure of Invention
The invention aims to provide a received signal strength and multipath information combined neural network indoor positioning method, which is characterized by comprising the following positioning steps of an off-line stage and an on-line stage: the method comprises the following specific steps:
1) the off-line phase comprises the following steps: determining reference points distributed in the indoor environment according to the characteristics of the indoor environment; measuring each selected reference point to obtain signals from different access points at each reference point; extracting received signal strength RSS and multipath characteristic parameters from the received signal; on one hand, the normalization parameters are used for training a neural network of RSS and multipath combined positioning with position measurement parameters, and meanwhile, normalization values are input into an online stage by using offline data for normalization;
2) the online phase comprises the following steps: receiving signals from various access points in real time; extracting RSS and multipath parameters from a signal received in real time; normalizing the RSS and the multipath parameters by using an offline normalization value; and taking the normalization parameter as the input of the neural network for off-line training, and obtaining the output as the estimation of the current position through the neural network processing.
After the neural network parameters are trained in the off-line stage, the user receives signals from each access point in real time in the on-line stage, and RSS and multipath characteristic parameters can be extracted by using a channel parameter extraction algorithm. And normalizing the characteristic parameters of each dimension by using a normalization method in an off-line stage, and obtaining the estimation of the current position through a neural network. It should be noted that the normalization utilizes the maximum and minimum values for each dimension of the offline stage.
The extraction process of the multipath characteristic parameters is as follows:
channel multipath information is obtained by using SAGE channel parameter extraction algorithm, the time delay and the amplitude of the channel multipath are shown in the following table,
TABLE 1 channel multipath
| Number of multipath | Time delay | Multipath amplitude |
| l＝1 | τ1 | a1 |
| l＝2 | τ2 | a2 |
| … | … | … |
| l＝n | τn | an |
After obtaining the multi-path parameter pair (tau)i,ai) Then, a method for extracting and describing multipath overall characteristic parameters is provided; first, the overall multipath energy is defined by:
where n is the number of multipaths, aiIs the amplitude of the ith multipath; the multipath time delay is regarded as a discrete probability distribution, and the probability value is the proportion of the energy of each multipath in the multipath energy G of the whole body; considering that the whole indoor environment is basically kept stable in indoor positioning, the probability distribution parameter of the multipath delay dispersion probability distribution is used as the description of the whole multipath characteristics of the current position, as follows:
that is, defined according to the above formulaAnd τrmsAnd uses them as the position fingerprint information of the multipath.
The RSS and multipath information joint neural network indoor positioning method obtains joint position fingerprint information of received signal strength RSS and multipath parameters; for two-dimensional indoor positioning, the number of access points AP in the indoor environment is set to n, and then for each reference point, the fingerprint information of the method is a (3n +2) -dimensional vector, as follows:
[Xpos,Ypos,RSS_AP1,RSS_AP2,…,RSS_APn,τrms_AP1,τrms_AP2,…,τrms_APn]where Xpos, Ypos are the position coordinates of the reference point, RSS _ AP1, RSS _ AP2, …, RSS _ APn are RSS fingerprints for n APs,τrms_AP1,τrms_AP2,…,τrmsAPn is the multipath fingerprint for n APs.
The structure of the off-line fingerprint database constructed by the RSS and multipath information combined neural network indoor positioning method is shown in the following table 2:
TABLE 1 TABLE 2 fingerprint database structure
Wherein, RP1To the RPMThe method is characterized by comprising the steps of selecting M reference points, wherein the information of each reference point comprises position information, RSS and multipath fingerprint information.
The RSS and multipath information joint neural network indoor positioning method is based on a fingerprint database obtained in an off-line stage, and indoor positioning is completed by utilizing an RSS and multipath joint neural network, wherein the structure of the neural network needs to be determined in advance, and the neural network with two hidden layers is used; after obtaining the fingerprint database in the off-line stage, the neural network normalizes the RSS and multipath parametersAs input, the coordinate position (x, y) is taken as output; the input of the joint neural network of the RSS and multipath information joint neural network indoor positioning method needs to be normalized before the neural network is trained, and the normalization method comprises the following steps:
assuming that the number of access points AP is n, fingerprint information of each reference point is as follows,
[Xpos,Ypos,RSS_AP1,RSS_AP2,…,RSS_APn,τrms_AP1,τrms_AP2,…,τrms_APn]；
the 3n dimensional inputs of the normalized neural network RSS _ AP1, RSS _ AP2, …, RSS _ APn, τrms_AP1,τrms_AP2,…,τrms_APn]each normalized to the interval [ -1,1](ii) a The normalization method utilizes the following formula:
where max and min refer to the maximum and minimum values of a dimension to all reference points.
The RSS and multipath information joint neural network indoor positioning method has the advantages that the RSS and specific multipath characteristic parameters are extracted from received signals. The method can solve the problem of low positioning accuracy and effectively improve the positioning accuracy.
Drawings
Fig. 1 is a flow chart of an indoor positioning method of a joint neural network of RSS and multipath information.
FIG. 2 is a schematic diagram of a federated neural network architecture with normalized RSS and multipath parameters As input, the coordinate position (x, y) is taken as output.
Fig. 3 is a diagram of an experimental indoor environment and AP deployment of an embodiment.
FIG. 4 is a cumulative distribution function of positioning error distances for different positioning methods of the experiments of the examples;
in the figure, rnn (RSS neural network positioning) is a method for positioning a neural network by simply using RSS information, KNN (K-nearest-neighbor algorithm) is a conventional RSS-based K-nearest neighbor indoor positioning method, and RMNN (RSS-multipath joint neural network) is an RSS and multipath information joint neural network indoor positioning method of the present invention.
Detailed Description
The invention provides a received signal strength and multipath information combined neural network indoor positioning method, which comprises positioning in an off-line stage and an on-line stage: embodiments of the invention are described in detail below with reference to the drawings, examples of which are illustrated in the drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used only for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and thus, are not to be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should be noted that, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
Fig. 1 is a flow chart of the RSS and multipath information joint neural network indoor positioning method of the present invention. As shown in fig. 1, the RSS and multipath information joint neural network indoor positioning method according to the embodiment of the present invention includes an offline stage and an online stage:
the off-line phase comprises the following steps: determining reference points distributed in the indoor environment according to the characteristics of the indoor environment; measuring at each selected reference point to obtain signals from different access points at each reference point; extracting received signal strength RSS and multipath characteristic parameters from the received signal; normalizing the extracted RSS and multipath characteristic parameters, and reserving a normalized value for online stage normalization; and training a neural network for RSS and multipath joint positioning by utilizing the normalized parameters, wherein the neural network is used for online stage positioning.
The online phase comprises the following steps: receiving signals from various access points in real time; extracting RSS and multipath parameters from a signal received in real time; normalizing the RSS and the multipath parameters by using an offline normalization value; and taking the normalization parameter as the input of the neural network for off-line training to obtain the output as the estimation of the current position.
The basic neural network structure is shown in figure 2. the RSS and multipath information joint neural network indoor positioning method is based on a fingerprint database obtained in an off-line stage, and indoor positioning is completed by using the RSS and multipath joint neural network. After obtaining the fingerprint database in the off-line stage, our inventive positioning method neural network uses normalized RSS and multipath parametersAs input, the coordinate position (x, y) is taken as output.
In order to verify the beneficial effect of the received signal strength and multipath information combined neural network indoor positioning method of the present invention, the following experiment was performed.
Fig. 3 is a diagram of an indoor environment and AP deployment of a laboratory in accordance with one embodiment of the present invention. We deploy 6 sender APs in a distributed manner in an environment of about 80m from west to east and 45m from north to south as in fig. 3. The MIMO measurement system works at 3.52GHz with a bandwidth of 40M. A mobile receiver measures the movement of signals received from different APs at different locations in the environment at each location.
Fig. 4 is a cumulative distribution function of positioning error distances of different positioning methods of the present experiment. Rnn (RSS neural network positioning) is a method for positioning a neural network by simply using RSS information, KNN (K-nearest-neighbor algorithm) is a conventional RSS-based K nearest neighbor indoor positioning method, and RMNN (RSS-multipath neural network) is an RSS and multipath information joint neural network indoor positioning method of the present invention.
In comparison with the results, it can be seen from the results that the positioning accuracy in the indoor environment can be significantly improved by the RSS and multipath information joint neural network indoor positioning method of the present invention.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made in the above embodiments by those of ordinary skill in the art without departing from the principle and spirit of the present invention.
Claims (4)
1. A method for positioning in a neural network room by combining received signal strength and multipath information comprises positioning in an off-line stage and an on-line stage: wherein,
1) the off-line phase comprises the following steps: determining reference points distributed in the indoor environment according to the characteristics of the indoor environment; measuring each selected reference point to obtain signals from different access points at each reference point; extracting received signal strength RSS and multipath characteristic parameters from the received signal; on one hand, the normalization parameters are used for training a neural network of RSS and multipath combined positioning with position measurement parameters, and meanwhile, normalization values are input into an online stage by utilizing offline data for normalization;
2) the online phase comprises the following steps: receiving signals from various access points in real time; extracting RSS and multipath parameters from a signal received in real time; normalizing the RSS and the multipath parameters by using an offline normalization value; taking the normalization parameter as the input of the neural network for off-line training, and outputting the normalization parameter as the estimation of the current position after the neural network processing;
the method is characterized in that the extraction process of the multipath characteristic parameters is as follows:
acquiring channel multipath information by using an SAGE channel parameter extraction algorithm, wherein the time delay and the amplitude of the channel multipath are shown in the following table 1;
TABLE 1 channel multipath
After obtaining the multi-path parameter pair (tau)i,ai) Then, a method for extracting and describing multipath overall characteristic parameters is provided; first, the overall multipath energy is defined by:
where n is the number of multipaths, aiIs the amplitude of the ith multipath; the multipath time delay is regarded as a discrete probability distribution, and the probability value is the proportion of the energy of each multipath in the multipath energy G of the whole body;
considering that the whole indoor environment is basically kept stable in indoor positioning, the probability distribution parameter of the multipath delay dispersion probability distribution is used as the description of the whole multipath characteristics of the current position, as follows:
that is, defined according to the above formulaAnd τrmsAnd uses them as the position fingerprint information of the multipath.
2. The indoor positioning method of the joint neural network of the received signal strength and the multipath information as claimed in claim 1, wherein the indoor positioning method of the joint neural network of the RSS and the multipath information obtains the joint position fingerprint information of the received signal strength RSS and the multipath parameter; for two-dimensional indoor positioning, the number of access points AP in the indoor environment is set to n, and then for each reference point, the fingerprint information of the method is a (3n +2) -dimensional vector, as follows:
where Xpos, Ypos are the location coordinates of the reference point, RSS _ AP1, RSS _ AP2, …, RSS _ APn are RSS fingerprints for n APs, is a multipath fingerprint for n APs.
3. The indoor positioning method of the joint neural network based on the received signal strength and the multi-path information as claimed in claim 1, wherein the structure of the off-line fingerprint database constructed by the indoor positioning method of the joint neural network based on the RSS and the multi-path information is as follows:
TABLE 2 fingerprint database architecture
Wherein, RP1To the RPMThe method is characterized by comprising the steps of selecting M reference points, wherein the information of each reference point comprises position information, RSS and multipath fingerprint information.
4. The indoor positioning method of the joint neural network for received signal strength and multipath information according to claim 1, wherein the indoor positioning method of the joint neural network for RSS and multipath information is based on the fingerprint database obtained in the off-line stage, and uses the joint neural network for RSS and multipath to complete indoor positioning, wherein the structure of the neural network needs to be determined in advance, and a neural network with two hidden layers is used; after obtaining the fingerprint database in the off-line stage, the neural network takes normalized RSS and multipath parametersNumber ofAs input, the coordinate position (x, y) is taken as output; the input of the joint neural network of the RSS and multipath information joint neural network indoor positioning method needs to be normalized before the neural network is trained, and the normalization method comprises the following steps:
assuming that the number of access points AP is n, fingerprint information of each reference point is as follows,
3 n-dimensional input to a normalized neural network Each normalized to the interval [ -1,1 [ ]](ii) a The normalization method utilizes the following formula:
where max and min refer to the maximum and minimum values of a dimension to all reference points.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410174502.6A CN103945332B (en) | 2014-04-28 | 2014-04-28 | A kind of received signal strength and multi-path information united NNs indoor orientation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410174502.6A CN103945332B (en) | 2014-04-28 | 2014-04-28 | A kind of received signal strength and multi-path information united NNs indoor orientation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103945332A CN103945332A (en) | 2014-07-23 |
| CN103945332B true CN103945332B (en) | 2017-08-11 |
Family
ID=51192770
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410174502.6A Expired - Fee Related CN103945332B (en) | 2014-04-28 | 2014-04-28 | A kind of received signal strength and multi-path information united NNs indoor orientation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103945332B (en) |
Families Citing this family (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104954983B (en) * | 2015-05-14 | 2018-10-02 | 清华大学 | Dynamic base-station method of controlling switch based on fingerprint database and device |
| CN106879066A (en) * | 2015-12-14 | 2017-06-20 | 富士通株式会社 | Localization method and positioner |
| CN107135540B (en) * | 2016-02-29 | 2020-06-16 | 富士通株式会社 | Positioning device and method and electronic equipment |
| CN106100734B (en) * | 2016-08-15 | 2018-07-06 | 北京理工大学 | A kind of high-precision indoor visible light localization method based on artificial neural network |
| CN106792769A (en) * | 2016-11-22 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of WiFi localization methods and server and location model method for building up |
| CN106604392A (en) * | 2016-11-22 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Wifi positioning method based on bidirectional signal intensity data and server |
| CN106507477A (en) * | 2016-11-22 | 2017-03-15 | 上海斐讯数据通信技术有限公司 | A kind of outdoor positioning method and server based on humidity |
| CN106793066A (en) * | 2016-11-22 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of wifi localization methods and server based on two-way signaling intensity data |
| CN106792507A (en) * | 2016-11-22 | 2017-05-31 | 上海斐讯数据通信技术有限公司 | A kind of WiFi localization methods and server based on network data |
| CN106792552B (en) * | 2016-11-24 | 2020-03-31 | 南京邮电大学 | Wireless network self-adaptive authorization access method |
| CN107371164B (en) * | 2017-08-02 | 2020-05-19 | 西北大学 | Method for positioning pseudo AP (access point) based on fusion of sensor data and signal difference value |
| CN109756432B (en) * | 2017-11-01 | 2022-03-25 | 展讯通信（上海）有限公司 | OFDM channel estimation method and device |
| CN108303672B (en) * | 2017-12-26 | 2021-12-24 | 武汉创驰蓝天信息科技有限公司 | WLAN indoor positioning error correction method and system based on position fingerprint |
| CN109151995B (en) * | 2018-09-04 | 2020-12-01 | 电子科技大学 | Deep learning regression fusion positioning method based on signal intensity |
| US11079495B2 (en) * | 2018-10-31 | 2021-08-03 | Mitsubishi Electric Research Laboratories, Inc. | Position estimation under multipath transmission |
| CN109600711B (en) * | 2018-12-10 | 2020-07-28 | 西安交通大学 | Indoor positioning method based on channel response frequency domain and spatial domain combined processing |
| CN109587627B (en) * | 2018-12-12 | 2021-04-06 | 嘉兴学院 | Indoor positioning method for improving terminal heterogeneity problem based on RSSI |
| CN110395207A (en) * | 2019-07-15 | 2019-11-01 | 东北大学 | A kind of mine car avoiding collision and device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101815308A (en) * | 2009-11-20 | 2010-08-25 | 哈尔滨工业大学 | WLAN indoor positioning method for neural network regional training |
| CN102711245A (en) * | 2012-06-26 | 2012-10-03 | 中国科学技术大学苏州研究院 | Two-stage matching and positioning method in WLAN (Wireless Local Area Network) area in indoor environment |
| CN103237344A (en) * | 2013-04-08 | 2013-08-07 | 北京航空航天大学 | Indoor antenna sensor network positioning method based on received signal strength indication |
| JP5291618B2 (en) * | 2006-05-08 | 2013-09-18 | スカイフック ワイヤレス，インク． | Method for classifying access points of WLAN positioning system |
| CN103501538A (en) * | 2013-10-12 | 2014-01-08 | 清华大学 | Indoor positioning method based on multipath energy fingerprints |
-
2014
- 2014-04-28 CN CN201410174502.6A patent/CN103945332B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5291618B2 (en) * | 2006-05-08 | 2013-09-18 | スカイフック ワイヤレス，インク． | Method for classifying access points of WLAN positioning system |
| CN101815308A (en) * | 2009-11-20 | 2010-08-25 | 哈尔滨工业大学 | WLAN indoor positioning method for neural network regional training |
| CN102711245A (en) * | 2012-06-26 | 2012-10-03 | 中国科学技术大学苏州研究院 | Two-stage matching and positioning method in WLAN (Wireless Local Area Network) area in indoor environment |
| CN103237344A (en) * | 2013-04-08 | 2013-08-07 | 北京航空航天大学 | Indoor antenna sensor network positioning method based on received signal strength indication |
| CN103501538A (en) * | 2013-10-12 | 2014-01-08 | 清华大学 | Indoor positioning method based on multipath energy fingerprints |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103945332A (en) | 2014-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103945332B (en) | A kind of received signal strength and multi-path information united NNs indoor orientation method | |
| Hu et al. | Experimental Analysis on Weight ${K} $-nearest neighbor indoor fingerprint positioning | |
| CN107769828B (en) | CSI-MIMO indoor positioning method and system based on characteristic value extraction | |
| CN110446940A (en) | Indoor positioning based on WIFI multiband fingerprint | |
| CN109275095B (en) | Bluetooth-based indoor positioning system, positioning equipment and positioning method | |
| CN107347210B (en) | A kind of precision target localization method based on channel state information | |
| Shrestha et al. | Deconvolution-based indoor localization with WLAN signals and unknown access point locations | |
| CN109672973B (en) | Indoor positioning fusion method based on strongest AP | |
| CN104869636B (en) | Indoor orientation method based on ranging information fusion | |
| CN109490826B (en) | Ranging and position positioning method based on radio wave field intensity RSSI | |
| CN109640262B (en) | Positioning method, system, equipment and storage medium based on mixed fingerprints | |
| Li et al. | Location estimation in large indoor multi-floor buildings using hybrid networks | |
| CN111918388A (en) | CSI fingerprint passive positioning method based on depth separable convolution | |
| CN104965189B (en) | Indoor occupant localization method based on maximal possibility estimation | |
| CN105487072A (en) | Method and system of joint location based on T2/R time difference and Doppler shift | |
| CN105554882A (en) | 60GHz non-line of sight (NLOS) identification and wireless fingerprint positioning method based on energy detection | |
| CN105611629A (en) | 60GHz millimeter wave non-line of sight identification and wireless fingerprint positioning method based on energy detection | |
| CN103698740A (en) | Weighted value selecting-based WIFI (wireless fidelity) indoor positioning method | |
| Chen et al. | CSI-based probabilistic indoor position determination: An entropy solution | |
| Zhu | Indoor Localization Based on Optimized KNN. | |
| CN105589063B (en) | Impulse radio 60GHz distance-finding methods based on the degree of bias | |
| Das et al. | TDOA based localization architecture for M2M communications over cellular networks | |
| CN105738866B (en) | A kind of identification of 60GHz non line of sight and wireless fingerprint positioning method based on energy measuring | |
| Han et al. | DFF-EDR: An indoor fingerprint location technology using dynamic fusion features of channel state information and improved edit distance on real sequence | |
| Xu et al. | Variance-based fingerprint distance adjustment algorithm for indoor localization |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170811 Termination date: 20180428 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |