CN112069483A - User identification and authentication method of intelligent wearable device - Google Patents
User identification and authentication method of intelligent wearable device Download PDFInfo
- Publication number
- CN112069483A CN112069483A CN202010963406.5A CN202010963406A CN112069483A CN 112069483 A CN112069483 A CN 112069483A CN 202010963406 A CN202010963406 A CN 202010963406A CN 112069483 A CN112069483 A CN 112069483A
- Authority
- CN
- China
- Prior art keywords
- user
- authentication
- data
- identification
- neural network
- 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
Images
Classifications
-
- 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
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/117—Biometrics derived from hands
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Computer Security & Cryptography (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Computer Hardware Design (AREA)
- User Interface Of Digital Computer (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a user identification authentication method of intelligent wearable equipment, which comprises the following steps: step 1, data preprocessing: acquiring original sensor signals of intelligent wearable equipment worn by a user when the user performs hand motions in real time, processing the acquired original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent lengths; step 2, using the authentication neural network model to carry out identification and authentication: and (2) identifying the segmented data preprocessed in the step (1) by adopting a trained authentication and identification neural network model consisting of a feature extractor and a classifier, and judging whether the segmented data belong to a legal user or not according to a threshold value for determining the authentication severity preset by the user. The method can take the small gesture actions of fist making, thumb erecting and the like with user behavior habits and biological characteristics as an authentication mode, has stability, and guarantees the safety of the user.
Description
Technical Field
The invention relates to the field of intelligent wearable devices, in particular to a user identification authentication method of an intelligent wearable device.
Background
Intelligent wearable devices (e.g., smartwatches, bracelets) are being used by more and more users due to their convenience and powerful features, providing a wide variety of applications related to the user's property and privacy, such as fast payments. And wearable equipment of intelligence such as intelligent wrist-watch, bracelet generally binds with the cell-phone and uses, and the cell-phone of the access user that can relax through the bracelet acquires all kinds of authorities. The security of bracelets has been a concern. In order to ensure the security of the privacy and property of the user, a reliable security authentication mode must be provided, and convenience for the user to use are also provided.
The traditional authentication mode cannot provide a convenient and fast identification and authentication function for a user in daily life, and has certain safety problem. For example, the screen input digital password authentication mode is limited by the screen size of a smart watch and a bracelet, so that the smart watch and the bracelet cannot be conveniently used by a user. In addition, the security of password input faces the threat of surfing on the shoulder. Other frequently used authentication and identification technologies, such as face recognition, iris recognition, fingerprint recognition and the like, require special sensors (such as a 3D camera, a fingerprint sensing device and the like) which are not available in current commercial wearable devices, which will increase the cost and difficulty of deployment. Recently, there is a new method for user authentication based on human behavior patterns and exercise habits. For example, gait of a person walking is recorded by a motion sensor for analysis and authentication, or the user is identified using motion sensor data of arm motion or an electromyographic signal. However, gait authentication requires recording data of a user for a period of time, arm movement requires a large action amplitude, and these authentication schemes are not friendly to the user in the case of daily authentication requiring a smart watch, a bracelet, and the like (e.g., unlocking of the watch).
Disclosure of Invention
Based on the problems in the prior art, the invention aims to provide a user identification and authentication method for intelligent wearable equipment, which can solve the problems of poor safety, high cost, poor user friendliness and the like when the conventional authentication method is used for the intelligent wearable equipment.
The purpose of the invention is realized by the following technical scheme:
the embodiment of the invention provides a user identification authentication method of intelligent wearable equipment, which comprises the following steps:
step 1, data preprocessing: acquiring original sensor signals of intelligent wearable equipment worn by a user when the user performs hand motions in real time, processing the acquired original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent lengths;
According to the technical scheme provided by the invention, the user identification and authentication system and method of the intelligent wearable device provided by the embodiment of the invention have the beneficial effects that:
by adopting the authentication and identification neural network model consisting of the feature extractor and the classifier, the trained authentication model serves as the authentication and identification model of the user, and recognized micro gesture actions (such as fist making, thumb erecting and the like) of the user can serve as an authentication mode, and the authentication mode simultaneously contains user behavior habits and biological features, has stability and ensures the safety of the user. Meanwhile, the micro gesture has higher user friendliness as authentication, and can be conveniently used in daily life by a user. Compared with the existing authentication method, the authentication method provided by the invention has the advantages of safety, usability, user friendliness and the like.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a flowchart of a user identification authentication method of a smart wearable device according to an embodiment of the present invention;
fig. 2 is a training flowchart of an authentication recognition neural network model of a user recognition authentication method of a smart wearable device according to an embodiment of the present invention;
fig. 3 is a schematic diagram of an authentication identification neural network model of a user identification authentication method of a smart wearable device according to an embodiment of the present invention;
fig. 4 is a schematic gesture recognition diagram of the user recognition authentication method of the smart wearable device according to the embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention are clearly and completely described below with reference to the specific contents of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without making any creative effort, shall fall within the protection scope of the present invention. Details which are not described in detail in the embodiments of the invention belong to the prior art which is known to the person skilled in the art.
As shown in fig. 1, an embodiment of the present invention provides a user identification authentication method for a smart wearable device, where the method is used for security authentication of the wearable device, and includes:
step 1, data preprocessing: acquiring original sensor signals of intelligent wearable equipment worn by a user when the user performs hand motions in real time, processing the acquired original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent lengths;
As shown in fig. 2, in step 2 of the method, the training mode of the authenticated recognition neural network model composed of the feature extractor and the classifier is as follows:
step 21, collecting user gesture data: recording a sensor original signal of intelligent wearable equipment worn by a user when the user performs hand action;
step 22, data preprocessing: processing the recorded original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent length;
step 23, training to obtain an authentication and recognition neural network model: and taking the segmented data obtained in the step 22 as training data, training the authentication and identification neural network model for user authentication and identification, simultaneously training the segmented data of a plurality of users, and obtaining the authentication and identification neural network model capable of simultaneously identifying a plurality of users after training.
In the data preprocessing step of the method, the raw sensor signal is processed, and the user gesture data obtained by processing the raw sensor signal is as follows:
keeping the sampling rate of the original signal of the sensor at 100Hz through the difference value, and normalizing the amplitude of the original signal of the sensor by using a Z-fraction normalization algorithm;
a Savitzky-Golay filter is adopted to reduce noise of the normalized signals and eliminate equipment noise in time sequence data of the motion signals;
and calculating a dynamic threshold of the signal after noise reduction according to the environmental noise and the signal amplitude based on a CFAR algorithm, and automatically detecting the real-time data to obtain user gesture data of the gesture made by the user.
In the above method, the raw sensor signal is:
raw signals of an acceleration sensor and raw signals of a gyroscope sensor of the smart wearable device.
As shown in fig. 3, in the above method, the neural network for authentication and identification, which is composed of two parts, namely, the feature extractor and the classifier, is:
the feature extractor adopts a bidirectional BilSTM neural network;
the classifier adopts a mode of sequentially connecting an SSE network and an MLP network.
The method further comprises the following steps: and updating, namely judging the segmented data of which the output confidence coefficient of the authentication and identification neural network model is higher than a set threshold value as legal user data, and adding the legal user data into a data set to update the authentication and identification neural network model.
The authentication method provided by the invention can take the small gesture actions such as fist making, thumb erecting and the like with user behavior habits and biological characteristics as an authentication mode, provides safe and convenient authentication for the intelligent wearable equipment, can ensure the safety of the intelligent wearable equipment, and has the advantages of instantaneity and low power consumption.
The embodiments of the present invention are described in further detail below.
The embodiment of the invention provides a user identification and authentication method of intelligent wearable equipment, which can authenticate a user based on micro gestures (such as a fist making and a thumb erecting micro gesture shown in figure 4) of the user, and can be realized based on commercial intelligent wearable equipment which is provided with a gravity accelerator sensor and a gyroscope sensor and can acquire original signals of the sensors.
Referring to fig. 2, the user identification authentication method includes the following steps:
firstly, training, authenticating and identifying a neural network model, comprising the following steps:
step 21: collecting user data: calling a software system interface of the intelligent wearable device, and recording the raw data of an acceleration sensor and a gyroscope sensor when a user performs a micro hand action;
step 22: data preprocessing: performing difference, normalization and noise reduction on the collected data, eliminating equipment noise in time sequence data of the motion signals, enabling the data lengths to be consistent to obtain segmented data, and generating a time-frequency graph corresponding to the time sequence signals; specifically, the method comprises the following steps: the data sampling rate was held at 100H by difference on the collected data and the signal amplitude was normalized using Z-score. And (3) carrying out noise reduction on the signals by using a Savitzky-Golay method, and eliminating equipment noise in time sequence data of the motion signals. Calculating a dynamic threshold according to the environmental noise and the signal amplitude, automatically detecting data which can be subjected to gestures by a user from the real-time data, and segmenting the data to keep the lengths of the data consistent;
step 23: training to obtain an authentication and recognition neural network model: taking the segmented data obtained in the step 22 as training data, performing user authentication and identification training by using an authentication and identification neural network model (see fig. 3) composed of a feature extractor and a classifier, and simultaneously training the segmented data of a plurality of users to obtain an authentication and identification neural network model capable of simultaneously identifying a plurality of users; specifically, the neural network shown in fig. 2 is used for training user authentication recognition, the structure of the neural network is divided into two parts, namely a bidirectional BilStm network structure is used for extracting features, and an SSE network and an MLP network are used for the classifier for outputting recognition confidence probability, so that a plurality of user data are trained simultaneously, and finally, an authentication recognition neural network model capable of simultaneously recognizing a plurality of users is obtained;
referring to fig. 1, after the neural network model is trained, the following steps are adopted for user identification, including:
step 1, data preprocessing (same as the data preprocessing mode in the training stage): acquiring original sensor signals of intelligent wearable equipment worn by a user when the user performs hand motions in real time, processing the acquired original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent lengths;
Further, the method also provides an updating process, namely judging the segmented data of which the output confidence coefficient of the authentication and identification neural network model is higher than a set threshold value as legal user data, and adding the legal user data into a data set to update the authentication and identification neural network model. Therefore, the method for judging the stricter threshold value is used for adding legal user data into the data set to update the model, wherein the threshold value and the updating frequency can be selected to be updated to different degrees according to the preference of the user.
The identification authentication method of the invention can provide two identification tasks for the user to select or use simultaneously:
(one) multi-user differentiation: and distinguishing a plurality of legal users on the premise of no malicious user attack.
(II) single-user authentication: and identifying a legal user under the threat condition of the malicious user, and resisting the attack of the illegal user.
The user can select recognition tasks of different degrees according to own use scenes.
The authentication method can take micro gesture actions (such as fist making and thumb erecting) with user behavior habits and biological characteristics as an authentication mode, has stability, and guarantees the safety of the user. Meanwhile, the micro gesture has higher user friendliness as authentication, and can be conveniently used in daily life by a user. Compared with the existing method, the method has the advantages of safety, usability and user friendliness.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present invention are included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A user identification authentication method of a smart wearable device is characterized by comprising the following steps:
step 1, data preprocessing: acquiring original sensor signals of intelligent wearable equipment worn by a user when the user performs hand motions in real time, processing the acquired original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent lengths;
step 2, using the authentication neural network model to carry out identification and authentication: and (2) identifying the segmented data preprocessed in the step (1) by adopting a trained authentication and identification neural network model consisting of a feature extractor and a classifier, and judging whether the segmented data belong to a legal user or not according to a threshold value for determining the authentication severity preset by the user.
2. The method for authenticating the user identification of the smart wearable device according to claim 1, wherein in the method step 2, the training mode of the neural network model for authentication and identification consisting of the feature extractor and the classifier is as follows:
step 21, collecting user gesture data: recording a sensor original signal of intelligent wearable equipment worn by a user when the user performs hand action;
step 22, data preprocessing: processing the recorded original sensor signals to obtain user gesture data, and dividing the user gesture data into segmented data with consistent length;
step 23, training to obtain an authentication and recognition neural network model: and taking the segmented data obtained in the step 22 as training data, training the authentication and identification neural network model for user authentication and identification, simultaneously training the segmented data of a plurality of users, and obtaining the authentication and identification neural network model capable of simultaneously identifying a plurality of users after training.
3. The method for authenticating the user of the smart wearable device according to claim 1 or 2, wherein in the data preprocessing step of the method, the raw sensor signal is processed, and user gesture data is obtained by:
keeping the sampling rate of the original signal of the sensor at 100Hz through the difference value, and normalizing the amplitude of the original signal of the sensor by using a Z-fraction normalization algorithm;
a Savitzky-Golay filter is adopted to reduce noise of the normalized signals and eliminate equipment noise in time sequence data of the motion signals;
and calculating a dynamic threshold of the signal after noise reduction according to the environmental noise and the signal amplitude based on a CFAR algorithm, and automatically detecting the real-time data to obtain user gesture data of the gesture made by the user.
4. The method for authenticating the user of the smart wearable device according to claim 3, wherein the sensor raw signal is:
raw signals of an acceleration sensor and raw signals of a gyroscope sensor of the smart wearable device.
5. The method for authenticating the user identification of the smart wearable device according to claim 1 or 2, wherein in the method, the authentication identification neural network consisting of the feature extractor and the classifier is as follows:
the feature extractor adopts a bidirectional BilSTM neural network;
the classifier adopts a mode of sequentially connecting an SSE network and an MLP network.
6. The method for authenticating the user of the smart wearable device according to claim 1 or 2, further comprising: and updating, namely judging the segmented data of which the output confidence coefficient of the authentication and identification neural network model is higher than a set threshold value as legal user data, and adding the legal user data into a data set to update the authentication and identification neural network model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010963406.5A CN112069483A (en) | 2020-09-14 | 2020-09-14 | User identification and authentication method of intelligent wearable device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010963406.5A CN112069483A (en) | 2020-09-14 | 2020-09-14 | User identification and authentication method of intelligent wearable device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112069483A true CN112069483A (en) | 2020-12-11 |
Family
ID=73695676
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010963406.5A Pending CN112069483A (en) | 2020-09-14 | 2020-09-14 | User identification and authentication method of intelligent wearable device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112069483A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113849068A (en) * | 2021-09-28 | 2021-12-28 | 中国科学技术大学 | Gesture multi-mode information fusion understanding and interacting method and system |
| CN116127365A (en) * | 2023-04-14 | 2023-05-16 | 山东大学 | Authentication method based on vibration and applied to intelligent head-mounted equipment |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150288687A1 (en) * | 2014-04-07 | 2015-10-08 | InvenSense, Incorporated | Systems and methods for sensor based authentication in wearable devices |
| CN106052852A (en) * | 2016-06-01 | 2016-10-26 | 中国电子科技集团公司第三研究所 | Pulse sound signal detection method and device |
| CN106382978A (en) * | 2016-09-09 | 2017-02-08 | 常熟理工学院 | Automatic target detection method for submarine sound signal generated through time-varying ship excitation |
| CN107169334A (en) * | 2017-05-11 | 2017-09-15 | 上海交通大学 | The user authen method based on straight punch motion detection for hand wearable device |
| CN107316067A (en) * | 2017-05-27 | 2017-11-03 | 华南理工大学 | A kind of aerial hand-written character recognition method based on inertial sensor |
| CN107797666A (en) * | 2017-11-21 | 2018-03-13 | 出门问问信息科技有限公司 | Gesture identification method, device and electronic equipment |
| CN110765974A (en) * | 2019-10-31 | 2020-02-07 | 复旦大学 | Micro-motion gesture recognition method based on millimeter wave radar and convolutional neural network |
| CN110799927A (en) * | 2018-08-30 | 2020-02-14 | Oppo广东移动通信有限公司 | Gesture recognition method, terminal and storage medium |
| CN111160139A (en) * | 2019-12-13 | 2020-05-15 | 中国科学院深圳先进技术研究院 | Electrocardiosignal processing method and device and terminal equipment |
-
2020
- 2020-09-14 CN CN202010963406.5A patent/CN112069483A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150288687A1 (en) * | 2014-04-07 | 2015-10-08 | InvenSense, Incorporated | Systems and methods for sensor based authentication in wearable devices |
| CN106052852A (en) * | 2016-06-01 | 2016-10-26 | 中国电子科技集团公司第三研究所 | Pulse sound signal detection method and device |
| CN106382978A (en) * | 2016-09-09 | 2017-02-08 | 常熟理工学院 | Automatic target detection method for submarine sound signal generated through time-varying ship excitation |
| CN107169334A (en) * | 2017-05-11 | 2017-09-15 | 上海交通大学 | The user authen method based on straight punch motion detection for hand wearable device |
| CN107316067A (en) * | 2017-05-27 | 2017-11-03 | 华南理工大学 | A kind of aerial hand-written character recognition method based on inertial sensor |
| CN107797666A (en) * | 2017-11-21 | 2018-03-13 | 出门问问信息科技有限公司 | Gesture identification method, device and electronic equipment |
| CN110799927A (en) * | 2018-08-30 | 2020-02-14 | Oppo广东移动通信有限公司 | Gesture recognition method, terminal and storage medium |
| CN110765974A (en) * | 2019-10-31 | 2020-02-07 | 复旦大学 | Micro-motion gesture recognition method based on millimeter wave radar and convolutional neural network |
| CN111160139A (en) * | 2019-12-13 | 2020-05-15 | 中国科学院深圳先进技术研究院 | Electrocardiosignal processing method and device and terminal equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113849068A (en) * | 2021-09-28 | 2021-12-28 | 中国科学技术大学 | Gesture multi-mode information fusion understanding and interacting method and system |
| CN113849068B (en) * | 2021-09-28 | 2024-03-29 | 中国科学技术大学 | Understanding and interaction method and system for multi-modal information fusion of gestures |
| CN116127365A (en) * | 2023-04-14 | 2023-05-16 | 山东大学 | Authentication method based on vibration and applied to intelligent head-mounted equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ehatisham-ul-Haq et al. | Continuous authentication of smartphone users based on activity pattern recognition using passive mobile sensing | |
| Shen et al. | Performance evaluation of implicit smartphones authentication via sensor-behavior analysis | |
| Liu et al. | uWave: Accelerometer-based personalized gesture recognition and its applications | |
| Zou et al. | BiLock: User authentication via dental occlusion biometrics | |
| KR20210047539A (en) | EMG-based user authentication device and authentication method | |
| CN106919958B (en) | Human body finger action recognition method based on smart watch | |
| Dahia et al. | Continuous authentication using biometrics: An advanced review | |
| Qin et al. | A fuzzy authentication system based on neural network learning and extreme value statistics | |
| Alsaadi | Study on most popular behavioral biometrics, advantages, disadvantages and recent applications: A review | |
| Acien et al. | Smartphone sensors for modeling human-computer interaction: General outlook and research datasets for user authentication | |
| CN104573458A (en) | Identity recognition method, device and system based on electrocardiogram signals | |
| CN110287918B (en) | Living body identification method and related product | |
| Al-Naffakh et al. | Unobtrusive gait recognition using smartwatches | |
| Al-Naffakh et al. | Continuous user authentication using smartwatch motion sensor data | |
| CN112069483A (en) | User identification and authentication method of intelligent wearable device | |
| Bi et al. | SmartEar: Rhythm-based tap authentication using earphone in information-centric wireless sensor network | |
| Li et al. | Adaptive deep feature fusion for continuous authentication with data augmentation | |
| CN106971203B (en) | Identity recognition method based on walking characteristic data | |
| Mufandaidza et al. | Continuous user authentication in smartphones using gait analysis | |
| Geng | Research on athlete’s action recognition based on acceleration sensor and deep learning | |
| Chen et al. | A behavioral authentication method for mobile based on browsing behaviors | |
| Wu et al. | Use It-No Need to Shake It! accurate implicit authentication for everyday objects with smart sensing | |
| Shen et al. | Waving gesture analysis for user authentication in the mobile environment | |
| Zhang et al. | Multimodal continuous user authentication on mobile devices via interaction patterns | |
| Gamble et al. | Convolutional neural network for human activity recognition and identification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201211 |
|
| RJ01 | Rejection of invention patent application after publication |