CN108737623A - The method for identifying ID of position and carrying mode is carried based on smart mobile phone - Google Patents
The method for identifying ID of position and carrying mode is carried based on smart mobile phone Download PDFInfo
- Publication number
- CN108737623A CN108737623A CN201810571596.9A CN201810571596A CN108737623A CN 108737623 A CN108737623 A CN 108737623A CN 201810571596 A CN201810571596 A CN 201810571596A CN 108737623 A CN108737623 A CN 108737623A
- Authority
- CN
- China
- Prior art keywords
- mobile phone
- data
- identification
- feature
- time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/66—Substation equipment, e.g. for use by subscribers with means for preventing unauthorised or fraudulent calling
- H04M1/667—Preventing unauthorised calls from a telephone set
- H04M1/67—Preventing unauthorised calls from a telephone set by electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/316—User authentication by observing the pattern of computer usage, e.g. typical user behaviour
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72454—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to context-related or environment-related conditions
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72457—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions according to geographic location
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/72—Mobile telephones; Cordless telephones, i.e. devices for establishing wireless links to base stations without route selection
- H04M1/724—User interfaces specially adapted for cordless or mobile telephones
- H04M1/72448—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions
- H04M1/72463—User interfaces specially adapted for cordless or mobile telephones with means for adapting the functionality of the device according to specific conditions to restrict the functionality of the device
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2250/00—Details of telephonic subscriber devices
- H04M2250/12—Details of telephonic subscriber devices including a sensor for measuring a physical value, e.g. temperature or motion
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Engineering & Computer Science (AREA)
- Computer Hardware Design (AREA)
- Environmental & Geological Engineering (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Telephone Function (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses the method for identifying ID that position and carrying mode are carried based on smart mobile phone, belong to mobile terminal control identification technology field.This method includes:First, sensing data of the acquisition mobile phone in different location;Sensing data is filtered using SavitzkyGolay filters;Acceleration time series is divided into data segment using gait cycle detection algorithm;Using statistical method the data after being divided into section are extracted with the feature of time domain and frequency domain;Secondly, the feature set of SFFS methods extraction out position identification is utilized;The specific location that the feature combination DT algorithms selected are worn user to mobile phone confirms;Finally, the encoded translated of the mobile phone wearing position that will identify that by One Hot Coding algorithms is feature vector, and the statistics feature of extraction and the user information trained is combined to carry out user identity identification using SVM algorithm.The method of user identity identification provided by the invention both provides a kind of lasting, safe and reliable personal identification method to mobile phone user and application manufacturers.
Description
Technical field
The present invention relates to a kind of mobile phone user's personal identification method, more particularly to carrying position based on smart mobile phone and take
The method for identifying ID of band model belongs to mobile terminal control identification technology field.
Technical background
As smart mobile phone is in the rapid growth of computing capability, perception etc., also companion while offering convenience to the mankind
With privacy risk, therefore, safety and lasting subscriber authentication mechanism are essential.
However, due to traditional numerical ciphers mechanism, many users are arranged too simple or are easy to pass into silence, this
It will lead to the insecurity such as individual privacy information leakage, therefore, the identification based on smart mobile phone is just come into being.It is existing
Identification be mostly based on including fingerprint recognition, recognition of face physiology identification, belong to the scope of initiative recognition, need
Want the high participation and fitness of user, and user's body of the present invention that position and carrying mode are carried based on smart mobile phone
Part identification, belongs to contactless passive discerning, is independently participated in without user, has compared to more traditional identification better
Convenience and concealment, it may have more preferably user experience.
Under the premise of based on this final goal of contactless identification, first, the prior art is mostly to solve certain
A application and generate, do not have extensively using property, that is, do not account for mobile phone in different levels, different users, different application
The various aspects factor such as program;Secondly, existing work is to be studied for fixed position and fixed-direction, but showing mostly
Grow directly from seeds in living, everyone has the custom that mobile phone is worn in different taking, and the identification based on fixed carrying mode is without practical significance.
In view of this, existing mode of operation is up for further improving.
Invention content
The user identity that the main object of the present invention is to provide for carrying position and carrying mode based on smart mobile phone is known
Other method, to solve the above-mentioned problems in the prior art.
The purpose of the present invention can reach by using following technical solution:
The method for identifying ID that position and carrying mode are carried based on smart mobile phone, is included the following steps:
Step S1:Flow starts;
Step S2:The pretreatment of sensing data acquires mobile phone sensor data, secondly to the sensor number of acquisition first
According to being filtered and dividing, the time domain of sensing data, frequecy characteristic after finally utilizing statistical method extraction to divide;
Step S3:The identification of mobile phone position information, extracts the feature set of position identification first, secondly confirms that user wears hand
The specific location of machine;
Step S4:The identification of mobile phone user's identity, using the encoded feature vector of location information is identified, in conjunction with front
Obtained time-domain and frequency-domain feature carries out authentication;
Step S5:Flow terminates.
Further, in the step S2, the pretreatment of sensing data includes the following steps:
Step S21:Flow starts;
Step S22:Sensing data obtain, using mobile phone inertial sensor (including accelerometer, gyroscope,
Magnetometer) obtain user different location mobile phone sensor data;
Step S23:Coordinate system is converted, and converts based on geodetic coordinates acceleration informations of the S22 based on mobile phone coordinate system to
Coefficient evidence;
Step S24:Data filtering is carried out using the mobile phone acceleration information that SavitzkyGolay filters obtain S23
Filtering, obtains true sensing data;
Step S25:Data are divided, by gait cycle detection algorithm in the wave crest and trough for obtaining accelerometer time series
Later, filtered sensing data is divided into segment according to the peaks and troughs data detected;
Step S26:Feature extraction carries out temporal signatures and frequency domain character using the data that statistical method obtains S25
Extraction, wherein temporal signatures include:Mean,Median,Standard Deviation,Range,Correlation,
Interquartile range, Kurtosis, Skewness, frequency domain character include:Energy,Entropy;
Step S27:Flow terminates.
Further, in the step S25, data segmentation is indicated using formula (1):
Wherein:
N is a fixed sliding window;
Be the time be t when acceleration;
Be the time be t+i when acceleration;
Be the time be t-i when acceleration;
Be the time be i when acceleration;
Be the time be i+1 when acceleration;
Be the time be i-1 when acceleration;
It is the set of the point of maximum value;
tpeakBe in the data set in sliding window N be more than threshold value;
tppIt is to be more than threshold value with the difference of previous valley or next valleyPoint set;
tslopeTo refer to compared with the point of this front N/2 the be point in the position risen, the point with the subsequent N/2 of the point
Compared to the set for being the point in down position:
Finally, it obtainstpp、tslopeIntersection be obtained wave crest point set.
Further, in the step S25, temporal signatures are indicated using formula (2), and frequency domain character uses formula (3) table
Show:Temporal signatures:
Wherein:
X is x-axis data;
Y is y-axis data;
Z is z-axis data;
M is space-time data,
xiIt is point in a period of time;
Frequency domain character:
Wherein:
energy:Refer to that integral obtains frequency domain energy after carrying out fast Fourier transform;
N:It refer to sample length;
m:It refer to some frequency width in sample;
entropy:It is the entropy in frequency domain;
n:It is some frequency width in sample.
Further, in the step S3, the identification of mobile phone position information includes the following steps:
Step S31:Flow starts;
Step S32:Feature selecting, the feature set obtained according to S25 utilize SFFS (Sequential Floating
Forward Selection) algorithm select in identification procedure have recognition effect good top n feature construction position
Recognition matrix recycles DT (Decision Tree) algorithms to carry out the foundation of position identification model to training set;
Step S33:Position identifies, the position model trained is combined to carry out the identification of user location using DT algorithms, can
The position of identification includes:Hand, left pocket of trousers, right pocket of trousers and waistband;
Step S34:Flow terminates.
Further, in the step S4, the identification of mobile phone user includes the following steps:
Step S41:Flow starts;
Step S42:One Hot Coding are believed using One Hot Coding modes by the position is known in step S33
Breath is encoded to a four-dimensional location matrix (because this experiment has used four positions, each position to use a matrix table
Show);
Step S43:Authentication, using the time-domain and frequency-domain feature extracted in step S26, the position obtained in conjunction with S42
The vector of information coding generates authentication training set, is combined and is generated using SVM (Support Vector Machine) algorithm
Training set, obtain the model of authenticating user identification;
Step S44:Flow terminates.
The advantageous effects of the present invention:The side of user identity identification according to the invention based on intelligent mobile phone sensor
Method, the method for the user identity identification provided by the invention based on intelligent mobile phone sensor, compared to traditional identification side
Formula has a wide range of application, and a kind of lasting, safe and reliable authenticating party is both provided to mobile phone user and application manufacturers
Method.Finally, design of the invention ensure that the authenticity of entire mechanism.
Description of the drawings
Fig. 1 is the excellent of the method for identifying ID according to the invention that position and carrying mode are carried based on smart mobile phone
Select the overall flow figure of embodiment;
Fig. 2 is the excellent of the method for identifying ID according to the invention that position and carrying mode are carried based on smart mobile phone
It can be embodiment identical with Fig. 1 to select the pretreated flow chart of the sensing data of embodiment, the embodiment, can also be with
Embodiments different Fig. 1;
Fig. 3 is the excellent of the method for identifying ID according to the invention that position and carrying mode are carried based on smart mobile phone
The flow chart for selecting the mobile phone position information of embodiment to identify, the embodiment can be embodiments identical with Fig. 1 or Fig. 2, also may be used
To be the embodiment different from Fig. 1 or Fig. 2;
Fig. 4 is the excellent of the method for identifying ID according to the invention that position and carrying mode are carried based on smart mobile phone
It can be embodiment identical with Fig. 1 or Fig. 2 or Fig. 3 to select the flow chart of mobile phone user's identification of embodiment, the embodiment,
Can also be the embodiment different from Fig. 1 or Fig. 2 or Fig. 3.
Specific implementation mode
To make the more clear and clear technical scheme of the present invention of those skilled in the art, with reference to embodiment and attached drawing
The present invention is described in further detail, and embodiments of the present invention are not limited thereto.
As shown in Figure 1, the user identity identification provided in this embodiment for carrying position and carrying mode based on smart mobile phone
Method includes the following steps:
Step S1:Flow starts;
Step S2:The pretreatment of sensing data acquires mobile phone sensor data, secondly to the sensor number of acquisition first
According to being filtered and dividing, the time domain of sensing data, frequecy characteristic after finally utilizing statistical method extraction to divide;
Step S3:The identification of mobile phone position information, extracts the feature set of position identification first, secondly confirms that user wears hand
The specific location of machine;
Step S4:The identification of mobile phone user's identity, using the encoded feature vector of location information is identified, in conjunction with front
Obtained time-domain and frequency-domain feature carries out authentication;
Step S5:Flow terminates.
Further, in the present embodiment, as shown in Fig. 2, in the step S2, the pretreatment of sensing data includes as follows
Step:
Step S21:Flow starts
Step S22:Sensing data obtain, using mobile phone inertial sensor (including accelerometer, gyroscope,
Magnetometer) obtain user different location mobile phone sensor data;
Step S23:Coordinate system is converted, and converts based on geodetic coordinates acceleration informations of the S22 based on mobile phone coordinate system to
Coefficient evidence;
Step S24:Data filtering is carried out using the mobile phone acceleration information that SavitzkyGolay filters obtain S23
Filtering, obtains true sensing data;
Step S25:Data are divided, by gait cycle detection algorithm in the wave crest and trough for obtaining accelerometer time series
Later, filtered sensing data is divided into segment according to the peaks and troughs data detected;
Step S26:Feature extraction carries out temporal signatures and frequency domain character using the data that statistical method obtains S25
Extraction, wherein temporal signatures include:Mean,Median,Standard Deviation,Range,Correlation,
Interquartile range, Kurtosis, Skewness, frequency domain character include:Energy,Entropy;
Step S27:Flow terminates
Further, in the present embodiment, in the step S25, data segmentation is indicated using formula (1):
Wherein:
N is a fixed sliding window;
Be the time be t when acceleration;
Be the time be t+i when acceleration;
Be the time be t-i when acceleration;
Be the time be i when acceleration;
Be the time be i+1 when acceleration;
Be the time be i-1 when acceleration;
It is the set of the point of maximum value;
tpeakBe in the data set in sliding window N be more than threshold value;
tppIt is to be more than threshold value with the difference of previous valley or next valleyPoint set;
tslopeTo refer to compared with the point of this front N/2 the be point in the position risen, the point with the subsequent N/2 of the point
Compared to the set for being the point in down position;
Finally, it obtainstpp、tslopeIntersection be obtained wave crest point set.
Further, in the present embodiment, in the step S25, temporal signatures are indicated using formula (2), frequency domain character
It is indicated using formula (3):
Temporal signatures:
Wherein:
X is x-axis data;
Y is y-axis data;
Z is z-axis data;
M is space-time data,
xiIt is point in a period of time;
Frequency domain character:
Wherein:
energy:Refer to that integral obtains frequency domain energy after carrying out fast Fourier transform;
N:It refer to sample length;
m:It refer to some frequency width in sample;
entropy:It is the entropy in frequency domain;
n:It is some frequency width in sample.
Further, in the present embodiment, as shown in figure 3, in the step S3, the identification of mobile phone position information includes such as
Lower step:
Step S31:Flow starts;
Step S32:Feature selecting, the feature set obtained according to S25 utilize SFFS (Sequential Floating
Forward Selection) algorithm select in identification procedure have recognition effect good top n feature construction position
Recognition matrix recycles DT (Decision Tree) algorithms to carry out the foundation of position identification model to training set;
Step S33:Position identifies, the position model trained is combined to carry out the identification of user location using DT algorithms, can
The position of identification includes:Hand, left pocket of trousers, right pocket of trousers and waistband;
Step S34:Flow terminates.
Further, in the present embodiment, as shown in figure 4, in the step S4, the identification of mobile phone user includes such as
Lower step:
Step S41:Flow starts;
Step S42:One Hot Coding are believed using One Hot Coding modes by the position is known in step S33
Breath is encoded to a four-dimensional location matrix (because this experiment has used four positions, each position to use a matrix table
Show);
Step S43:Authentication, using the time-domain and frequency-domain feature extracted in step S26, the position obtained in conjunction with S42
The vector of information coding generates authentication training set, is combined and is generated using SVM (Support Vector Machine) algorithm
Training set, obtain the model of authenticating user identification;
Step S44:Flow terminates.
Embodiment 1:
The present embodiment 1 provides a kind of method that user acquires in the mobile phone sensor data of different location, including as follows
Step:
Program is arranged to sample collection pattern by user first, from location options select one will collecting sample position
It sets, while mobile phone is positioned over corresponding position, direction can be free, freely walks on straight road substantially a few minutes
Distance more than (if any 7 minutes).During walking, ensure movement not opposite between mobile phone and body as possible,
The wearing mode for replacing mobile phone, the sample data that other wearing modes are re-started by above step acquire, and user completely may be used
To carry out self-defined wearing mode definition and identification according to human needs.
Embodiment 2:
The present embodiment 2 provides the example of mobile phone position information identification, mainly includes the following steps that:
By taking user places mobile phone in hand as an example, the sensing data being collected is filtered and is divided, is then used
SFFS algorithms extract the feature set of suitable position information identification, and position in the hand of these feature sets and user is corresponding, so
The model of DT algorithms training out position identification is used afterwards.Likewise, replace mobile phone placement location (such as:Jacket left side pocket,
Pocket on the right side of jacket, waist, left pocket of trousers, right pocket of trousers), the model training of other positions is re-started by above step.
Embodiment 3:
The present embodiment 3 provides the example of mobile phone user's identification, mainly includes the following steps that:
We can go to identify the mobile phone wearing mode of user with higher accuracy rate in example 2.But still have
There is the probability centainly to malfunction, in order to solve this problem, in the model training of authentication, we can be stamped ourselves using
The data of location tags carry out the model training of position identification.Simultaneously in true environment, the wearing mode of everyone mobile phone
With prodigious difference, and our system can also be determined it is several with that in specific operational process by user oneself
Position carries out authentication:As party A-subscriber carrys out carrying mobile phone commonly using trouser pocket and mobile phone, therefore in position identification and identity
The data that corresponding position need to be only trained in verification process, solve the personalized wearing mode of each user well.Most
This patent uses traditional machine learning model SVM afterwards, but other machine learning models are reaching higher discrimination
Under the premise of be also that can use.Such as BP (neural network), logistic regression and Bayes etc..
In conclusion in the present embodiment, the use according to the invention that position and carrying mode are carried based on smart mobile phone
Family personal identification method, the method for identifying ID provided by the invention that position and carrying mode are carried based on smart mobile phone,
Have a wide range of application compared to traditional identification mode, one kind is both provided to mobile phone user and application manufacturers
Continue, safe and reliable identity identifying method.Finally, design of the invention ensure that the authenticity of entire mechanism.
The above, further embodiment only of the present invention, but scope of protection of the present invention is not limited thereto, and it is any
Within the scope of the present disclosure, according to the technique and scheme of the present invention and its design adds those familiar with the art
With equivalent substitution or change, protection scope of the present invention is belonged to.
Claims (6)
1. carrying the method for identifying ID of position and carrying mode based on smart mobile phone, which is characterized in that including walking as follows
Suddenly:
Step S1:Flow starts;
Step S2:The pretreatment of sensing data acquires mobile phone sensor data first, secondly to the sensing data of acquisition into
Row filtering and segmentation, the time domain of sensing data, frequecy characteristic after finally statistical method being utilized to extract segmentation;
Step S3:The identification of mobile phone position information, extracts the feature set of position identification first, secondly confirms that user wears mobile phone
Specific location;
Step S4:The identification of mobile phone user's identity, using identifying the encoded feature vector of location information, in conjunction with being previously obtained
Time-domain and frequency-domain feature carry out authentication;
Step S5:Flow terminates.
2. the method for identifying ID according to claim 1 that position and carrying mode are carried based on smart mobile phone,
It is characterized in that, in the step S2, the pretreatment of sensing data includes the following steps:
Step S21:Flow starts;
Step S22:Sensing data obtains, and uses inertial sensor (including accelerometer, gyroscope, the earth magnetism of mobile phone
Instrument) obtain user different location mobile phone sensor data;
Step S23:Coordinate system is converted, and converts based on geodetic coordinates coefficient acceleration informations of the S22 based on mobile phone coordinate system to
According to;
Step S24:Data filtering was carried out the mobile phone acceleration information that S23 is obtained using SavitzkyGolay filters
Filter, obtains more true sensing data;
Step S25:Data divide, by gait cycle detection algorithm obtain accelerometer time series wave crest and trough it
Afterwards, filtered acceleration transducer data are divided into segment according to the peaks and troughs data detected;
Step S26:Data that S25 is obtained are carried out carrying for temporal signatures and frequency domain character by feature extraction using statistical method
It takes, wherein temporal signatures include:Mean,Median,Standard Deviation,Range,Correlation,
Interquartile range, Kurtosis, Skewness, frequency domain character include:Energy,Entropy;
Step S27:Flow terminates.
3. the method for identifying ID according to claim 2 that position and carrying mode are carried based on smart mobile phone,
It is characterized in that, in the step S25, data segmentation is indicated using formula (1):
tstep=tpeak∩tpp∩tslope (1)
Wherein:
N is a fixed sliding window;
Be the time be t when acceleration;
Be the time be t+i when acceleration;
Be the time be t-i when acceleration;
Be the time be i when acceleration;
Be the time be i+1 when acceleration;
Be the time be i-1 when acceleration;
It is the set of the point of maximum value;
tpeakBe in the data set in sliding window N be more than threshold value;
tppIt is to be more than threshold value with the difference of previous valley or next valleyPoint set;
tslopeTo refer to compared with the point of this front N/2 the be point in the position risen, compared with the point of the subsequent N/2 of the point
It is the set of the point in down position;
Finally, it obtainstpp、tslopeIntersection be obtained wave crest point set.
4. the method for identifying ID according to claim 2 that position and carrying mode are carried based on smart mobile phone,
It is characterized in that, in the step S25, temporal signatures are indicated using formula (2), and frequency domain character is indicated using formula (3):
Temporal signatures:
Mean:
Standard Deviation:
Range:Range=Max (M)-Min (M)
Correlation:
Kurtoisis:
Skewness:
Wherein:
X is x-axis data;
Y is y-axis data;
Z is z-axis data;
M is space-time data,
xiIt is point in a period of time;
Frequency domain character:
Wherein:
energy:Refer to that integral obtains frequency domain energy after carrying out fast Fourier transform;
N:It refer to sample length;
m:It refer to some frequency width in sample;
entropy:It is the entropy in frequency domain;
n:It is some frequency width in sample.
5. the method for identifying ID according to claim 1 that position and carrying mode are carried based on smart mobile phone,
It is characterized in that, in the step S3, the identification of mobile phone position information includes the following steps:
Step S31:Flow starts;
Step S32:Feature selecting, the feature set obtained according to S25 utilize SFFS (Sequential Floating Forward
Selection) algorithm, which is selected, in identification procedure there is recognition effect good top n feature construction position to identify square
Battle array recycles DT (Decision Tree) algorithms to carry out the foundation of position identification model to training set;
Step S33:Position identifies, combines the position model trained to carry out the identification of user location using DT algorithms, can recognize that
Position include:Hand, left pocket of trousers, right pocket of trousers and waistband;
Step S34:Flow terminates.
6. the method for identifying ID according to claim 1 that position and carrying mode are carried based on smart mobile phone,
It is characterized in that, in the step S4, the identification of mobile phone user includes the following steps:
Step S41:Flow starts;
Step S42:One Hot Coding are compiled using One Hot Coding modes by the location information is known in step S33
Code is a four-dimensional location matrix (because this experiment has used four positions, each position to be indicated using a matrix);
Step S43:Authentication, using the time-domain and frequency-domain feature extracted in step S26, the location information obtained in conjunction with S42
The vector of coding generates authentication training set, and the instruction generated is combined using SVM (Support Vector Machine) algorithm
Practice collection, obtains the model of user identity identification;
Step S44:Flow terminates.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810571596.9A CN108737623A (en) | 2018-05-31 | 2018-05-31 | The method for identifying ID of position and carrying mode is carried based on smart mobile phone |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810571596.9A CN108737623A (en) | 2018-05-31 | 2018-05-31 | The method for identifying ID of position and carrying mode is carried based on smart mobile phone |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108737623A true CN108737623A (en) | 2018-11-02 |
Family
ID=63932035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810571596.9A Pending CN108737623A (en) | 2018-05-31 | 2018-05-31 | The method for identifying ID of position and carrying mode is carried based on smart mobile phone |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108737623A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109684812A (en) * | 2018-12-29 | 2019-04-26 | 西安电子科技大学 | A kind of lasting identity identifying method of mobile device acquisition user movement behavior |
CN109893137A (en) * | 2019-03-07 | 2019-06-18 | 山东科技大学 | Improve the method for gait detection under different carrying positions based on mobile terminal |
CN113159288A (en) * | 2019-12-09 | 2021-07-23 | 支付宝(杭州)信息技术有限公司 | Coding model training method and device for preventing private data leakage |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106406516A (en) * | 2016-08-26 | 2017-02-15 | 兰州理工大学 | Local real-time movement trajectory characteristic extraction and identification method for smartphone |
CN106971203A (en) * | 2017-03-31 | 2017-07-21 | 中国科学技术大学苏州研究院 | Personal identification method based on characteristic on foot |
CN107103297A (en) * | 2017-04-20 | 2017-08-29 | 武汉理工大学 | Gait identification method and system based on mobile phone acceleration sensor |
US20180078179A1 (en) * | 2014-09-25 | 2018-03-22 | Bae Systems Information And Electronic Systems Integration Inc. | Gait authentication system and method thereof |
-
2018
- 2018-05-31 CN CN201810571596.9A patent/CN108737623A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20180078179A1 (en) * | 2014-09-25 | 2018-03-22 | Bae Systems Information And Electronic Systems Integration Inc. | Gait authentication system and method thereof |
CN106406516A (en) * | 2016-08-26 | 2017-02-15 | 兰州理工大学 | Local real-time movement trajectory characteristic extraction and identification method for smartphone |
CN106971203A (en) * | 2017-03-31 | 2017-07-21 | 中国科学技术大学苏州研究院 | Personal identification method based on characteristic on foot |
CN107103297A (en) * | 2017-04-20 | 2017-08-29 | 武汉理工大学 | Gait identification method and system based on mobile phone acceleration sensor |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109684812A (en) * | 2018-12-29 | 2019-04-26 | 西安电子科技大学 | A kind of lasting identity identifying method of mobile device acquisition user movement behavior |
CN109684812B (en) * | 2018-12-29 | 2021-09-03 | 西安电子科技大学 | Continuous identity authentication method for mobile equipment to acquire user motion behaviors |
CN109893137A (en) * | 2019-03-07 | 2019-06-18 | 山东科技大学 | Improve the method for gait detection under different carrying positions based on mobile terminal |
CN109893137B (en) * | 2019-03-07 | 2021-09-03 | 山东科技大学 | Method for improving gait detection based on mobile terminal at different carrying positions |
CN113159288A (en) * | 2019-12-09 | 2021-07-23 | 支付宝(杭州)信息技术有限公司 | Coding model training method and device for preventing private data leakage |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sun et al. | Accelerometer-based speed-adaptive gait authentication method for wearable IoT devices | |
CN104573458B (en) | A kind of personal identification method based on electrocardiosignal, apparatus and system | |
WO2018040757A1 (en) | Wearable device and method of using same to monitor motion state | |
WO2019192253A1 (en) | Mobile device-based user identity authentication method and system | |
CN108737623A (en) | The method for identifying ID of position and carrying mode is carried based on smart mobile phone | |
CN107103297A (en) | Gait identification method and system based on mobile phone acceleration sensor | |
US20140089673A1 (en) | Biometric identification method and apparatus to authenticate identity of a user of a wearable device that includes sensors | |
CN105989694A (en) | Human body falling-down detection method based on three-axis acceleration sensor | |
CN108629167A (en) | A kind of more smart machine identity identifying methods of combination wearable device | |
CN110705454A (en) | Face recognition method with living body detection function | |
CN110276189A (en) | A kind of method for authenticating user identity based on gait information | |
Geng | Research on athlete’s action recognition based on acceleration sensor and deep learning | |
Cola et al. | Personalized gait detection using a wrist-worn accelerometer | |
Tanviruzzaman et al. | Your phone knows you: Almost transparent authentication for smartphones | |
Li et al. | Multi-resolution Fusion Convolutional Network for Open Set Human Activity Recognition | |
Lee et al. | Gait-based continuous authentication using a novel sensor compensation algorithm and geometric features extracted from wearable sensors | |
CN108563939B (en) | Human body identity recognition based on gait track curve characteristics | |
CN109302532B (en) | Identity authentication method based on smart phone acceleration sensor | |
Jiang et al. | Rf-gait: Gait-based person identification with cots rfid | |
Li et al. | Intelligent walk authentication: implicit authentication when you walk with smartphone | |
Chakraborty et al. | An approach for designing low cost deep neural network based biometric authentication model for smartphone user | |
CN112990261B (en) | Intelligent watch user identification method based on knocking rhythm | |
CN109846496B (en) | Hardware implementation method and combination of emotion perception function of intelligent wearable device | |
Chen et al. | Modeling interactive sensor-behavior with smartphones for implicit and active user authentication | |
Fan et al. | EmgAuth: Unlocking smartphones with EMG signals |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20181102 |
|
WD01 | Invention patent application deemed withdrawn after publication |