CN112184010A - Tooth brushing effect evaluation method, device, system, electronic device and storage medium - Google Patents
Tooth brushing effect evaluation method, device, system, electronic device and storage medium Download PDFInfo
- Publication number
- CN112184010A CN112184010A CN202011032363.5A CN202011032363A CN112184010A CN 112184010 A CN112184010 A CN 112184010A CN 202011032363 A CN202011032363 A CN 202011032363A CN 112184010 A CN112184010 A CN 112184010A
- Authority
- CN
- China
- Prior art keywords
- tooth brushing
- effect evaluation
- brushing effect
- brushing
- signals
- 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.)
- Withdrawn
Links
- 230000001680 brushing effect Effects 0.000 title claims abstract description 154
- 238000011156 evaluation Methods 0.000 title claims abstract description 57
- 238000000034 method Methods 0.000 claims abstract description 65
- 230000033001 locomotion Effects 0.000 claims abstract description 55
- 210000003205 muscle Anatomy 0.000 claims abstract description 51
- 230000004927 fusion Effects 0.000 claims abstract description 43
- 238000003062 neural network model Methods 0.000 claims abstract description 41
- 210000000245 forearm Anatomy 0.000 claims abstract description 32
- 238000002567 electromyography Methods 0.000 claims description 29
- 238000004140 cleaning Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 19
- 230000009471 action Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 11
- 210000000214 mouth Anatomy 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 9
- 238000013135 deep learning Methods 0.000 claims description 8
- 238000013507 mapping Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 230000002457 bidirectional effect Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 19
- 230000000875 corresponding effect Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 12
- 238000001514 detection method Methods 0.000 description 11
- 230000036544 posture Effects 0.000 description 8
- 238000005070 sampling Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000005259 measurement Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000009928 pasteurization Methods 0.000 description 3
- 208000031662 Noncommunicable disease Diseases 0.000 description 2
- 208000025157 Oral disease Diseases 0.000 description 2
- 208000014151 Stomatognathic disease Diseases 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000036461 convulsion Effects 0.000 description 2
- 238000013136 deep learning model Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 208000030194 mouth disease Diseases 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000002054 transplantation Methods 0.000 description 2
- 206010061619 Deformity Diseases 0.000 description 1
- 208000032843 Hemorrhage Diseases 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- QVZZPLDJERFENQ-NKTUOASPSA-N bassianolide Chemical compound CC(C)C[C@@H]1N(C)C(=O)[C@@H](C(C)C)OC(=O)[C@H](CC(C)C)N(C)C(=O)[C@@H](C(C)C)OC(=O)[C@H](CC(C)C)N(C)C(=O)[C@@H](C(C)C)OC(=O)[C@H](CC(C)C)N(C)C(=O)[C@@H](C(C)C)OC1=O QVZZPLDJERFENQ-NKTUOASPSA-N 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 208000034158 bleeding Diseases 0.000 description 1
- 230000000740 bleeding effect Effects 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 208000002925 dental caries Diseases 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 208000007565 gingivitis Diseases 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000007774 longterm 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
- 230000003183 myoelectrical effect Effects 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 201000001245 periodontitis Diseases 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 208000004371 toothache Diseases 0.000 description 1
- 210000000707 wrist Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/14—Fourier, Walsh or analogous domain transformations, e.g. Laplace, Hilbert, Karhunen-Loeve, transforms
- G06F17/141—Discrete Fourier transforms
- G06F17/142—Fast Fourier transforms, e.g. using a Cooley-Tukey type algorithm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y20/00—Information sensed or collected by the things
- G16Y20/40—Information sensed or collected by the things relating to personal data, e.g. biometric data, records or preferences
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Pure & Applied Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- Educational Administration (AREA)
- Discrete Mathematics (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Algebra (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application relates to a tooth brushing effect evaluation method, a device, a system, an electronic device and a storage medium, wherein the tooth brushing effect evaluation method comprises the following steps: acquiring muscle electric signals and motion signals of the forearm of a current user; and performing regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a tooth brushing effect evaluation report. The method and the device directly utilize the data fusion neural network model to evaluate the tooth brushing effect, not only reduce the calculated amount and have high accuracy, but also have low requirement on hardware cost.
Description
Technical Field
The present application relates to the field of oral hygiene technology, and in particular, to a tooth brushing effectiveness assessment method, apparatus, system, electronic apparatus, and storage medium.
Background
Oral health is one of key factors of human health, and the research on the global disease recovery burden in 2017 estimates that oral diseases affect 35 hundred million people worldwide. In addition, oral diseases are the most common Non-infectious diseases (NCD), especially diseases of teeth, which cause pain, discomfort, disfigurement and even tooth extraction, and tooth defects can affect life span of people. In developed countries, the medical care budget for the treatment of dental diseases is about 5-10% of the total, this index is lower in developing and under-developed countries, and oral problems are more serious to people's lives. Many people have improper tooth brushing methods and can not clean teeth properly, so that dental diseases of different degrees, such as dental caries, gingivitis, periodontitis, tooth pain, bleeding, looseness, even shedding and the like can occur.
Although standard brushing methods (e.g., the pasteurization BASS, the horizontal twitch brush ROLL, and the circular arc brush Fones) can be learned through different sources, it is difficult to ensure that these methods are performed effectively during actual brushing. For example, the pasteurization (Bass brushing) method is a method recommended by the American dental Association for removing plaque near the gingival margin and in the gingival sulcus, and requires: brushing teeth for 3 minutes each time; the upper occlusal surface and the lower occlusal surface of the teeth are cleaned by brushing the brush head horizontally, with the bristles upwards or downwards and left and right; cleaning other tooth parts except the upper and lower occlusal surfaces of the teeth, wherein the brush head is horizontal, and the brush bristles and the tooth surface form an angle of 45 degrees to brush up and down; furthermore, the bristles for cleaning the outer sides of the teeth face the inner sides of the teeth, and the bristles for cleaning the inner sides of the teeth face the outer sides of the teeth; the left teeth need to be cleaned by the brush head to the left, and the right teeth need to be cleaned by the brush head to the right; the upper jaw teeth need to be brushed from top to bottom, and the lower jaw teeth need to be brushed from bottom to top; the sequence of cleaning the teeth was: and brushing the left outer side of the upper jaw, the left bottom of the upper jaw, the left inner part of the upper jaw, the right bottom of the upper jaw, the right outer side of the lower jaw, the left bottom of the lower jaw, the left inner part of the lower jaw and the right inner part of the lower jaw in sequence from the right outer side of the upper jaw until brushing the right bottom of the lower jaw. The pasteurization brushing is difficult to perform in practice.
With the development of Internet of things (IoT), some guided brushing techniques can guide people to brush their teeth in a standard way by giving a standard brushing tutorial (e.g., a scheme that helps people maintain better daily oral health by monitoring the brushing process with different cameras). However, camera-based systems are strongly affected by ambient light and the processing of image data brings about a lot of calculations, resulting in low accuracy and high requirements on hardware costs.
At present, no effective solution is provided aiming at the problems of large calculation amount, low accuracy and high requirement on hardware cost in the related technology.
Disclosure of Invention
The embodiment of the application provides a tooth brushing effect evaluation method, a tooth brushing effect evaluation device, a tooth brushing effect evaluation system, an electronic device and a storage medium, and at least solves the problems of large calculation amount, low accuracy and high requirement on hardware cost in the related technology.
In a first aspect, an embodiment of the present application provides a tooth brushing effect evaluation method, including:
acquiring muscle electric signals and motion signals of the forearm of a current user;
and performing regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a tooth brushing effect evaluation report.
In some of these embodiments, further comprising:
dividing the oral cavity cleaning area, and configuring standard actions for each divided area;
collecting a large amount of multi-channel original tooth brushing electromyography data according to the divided areas and corresponding standard actions, wherein the original tooth brushing electromyography data comprises muscle electric signals and motion signals;
and training by taking the original brushing electromyography data as sample data based on a deep learning method to obtain the completely trained data fusion neural network model.
In some of these embodiments, dividing the oral cleaning area and configuring a standard action for each divided area comprises the following steps;
dividing the oral cavity cleaning areas to obtain 16 oral cavity cleaning areas; and standard action is configured for 16 oral cleaning areas.
In some embodiments, training the original brushing electromyography data as sample data based on a deep learning method to obtain the completely trained data fusion neural network model, and the method comprises the following steps:
the method comprises the steps of fragmenting multi-channel original tooth brushing electromyographic data in a time domain, and extracting time domain and frequency domain characteristics of the fragmented original tooth brushing electromyographic data; wherein, the time domain signal is subjected to feature extraction processing through a bidirectional BI-LSTM model; obtaining a frequency domain signal through short-time Fourier transform, and performing characteristic extraction processing by using a residual convolution model;
mapping the features to feature maps with uniform dimensions through a full communication layer, and splicing;
and fusing the spliced multipath characteristics by convolution to obtain a data fusion neural network model with complete training.
In some of these embodiments, acquiring the muscle electrical signal and the motion signal of the forearm of the current user comprises the steps of:
wearable Internet of things equipment with a sensor is worn on the forearm of a current user, and muscle electric signals and motion signals of the forearm of the current user are obtained through wearing of the wearable Internet of things equipment.
In some of these embodiments, further comprising:
and evaluating and optimizing the well-trained data fusion neural network model.
In a second aspect, an embodiment of the present application provides a device for evaluating a tooth brushing effect, including an obtaining module and an analyzing module;
the acquisition module is used for acquiring the muscle electrical signal and the motion signal of the forearm of the current user;
and the analysis module is used for carrying out regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by utilizing the well-trained data fusion neural network model to obtain a tooth brushing effect evaluation report.
In a third aspect, an embodiment of the present application provides a tooth brushing effect evaluation system, including: wearable Internet of things equipment, transmission equipment and terminal equipment; the terminal equipment is connected with the wearable Internet of things equipment through the transmission equipment;
the wearable Internet of things equipment is used for acquiring muscle electric signals and motion signals of the forearm of the current user;
the transmission equipment is used for transmitting the muscle electric signals and the movement signals;
the terminal device is used for executing the tooth brushing effect evaluation method according to the first aspect.
In a fourth aspect, embodiments of the present application provide an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to perform the brushing effect evaluation method according to the first aspect.
In a fifth aspect, the present application provides a storage medium having a computer program stored therein, wherein the computer program is configured to execute the brushing effect evaluation method according to the first aspect.
Compared with the related art, the tooth brushing effect evaluation method, the tooth brushing effect evaluation device, the tooth brushing effect evaluation system, the electronic device and the storage medium provided by the embodiment of the application can obtain the tooth brushing effect evaluation report only by carrying out regional tooth brushing effect evaluation on the muscle electric signals and the muscle motion signals by using the well-trained data fusion neural network model; the tooth brushing effect is evaluated by directly utilizing the data fusion neural network model, so that the calculation amount is reduced, the accuracy is high, and the requirement on hardware cost is low.
The details of one or more embodiments of the application are set forth in the accompanying drawings and the description below to provide a more thorough understanding of the application.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of a hardware structure of a terminal device of a tooth brushing effect evaluation method according to an embodiment of the present application;
fig. 2 is a wearing schematic diagram of a wearable internet of things device according to an embodiment of the present application;
FIG. 3 is a flow chart of a brushing effectiveness assessment method provided by an embodiment of the present application;
FIG. 4 is a flow chart of a brushing effectiveness assessment method provided by another embodiment of the present application;
fig. 5 is a schematic illustration of the division of the oral cleaning area provided by an embodiment of the present application;
FIG. 6 is a schematic diagram of a data fusion neural network model provided in an embodiment of the present application;
FIG. 7 is a graphical illustration of a comparison of the accuracy of different combinations of sensor time and frequency domain features used alone for evaluation, as provided by an embodiment of the present application;
FIG. 8 is a diagram illustrating comparison of accuracy of different depth learning models for evaluation according to an embodiment of the present application;
FIG. 9 is a schematic diagram illustrating a comparison of ROC curves for different trunk branch fusions according to an embodiment of the present application;
fig. 10 is a block diagram illustrating a brushing effect evaluation device according to an embodiment of the present application.
Description of the drawings: 210. an acquisition module; 220. and an analysis module.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application. All other embodiments obtained by a person of ordinary skill in the art based on the embodiments provided in the present application without any inventive step are within the scope of protection of the present application. Moreover, it should be appreciated that in the development of any such actual implementation, as in any engineering or design project, numerous implementation-specific decisions must be made to achieve the developers' specific goals, such as compliance with system-related and business-related constraints, which may vary from one implementation to another.
Reference in the specification to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the specification. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of ordinary skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments without conflict.
Unless defined otherwise, technical or scientific terms referred to herein shall have the ordinary meaning as understood by those of ordinary skill in the art to which this application belongs. Reference to "a," "an," "the," and similar words throughout this application are not to be construed as limiting in number, and may refer to the singular or the plural. The present application is directed to the use of the terms "including," "comprising," "having," and any variations thereof, which are intended to cover non-exclusive inclusions; for example, a process, method, system, article, or apparatus that comprises a list of steps or models (elements) is not limited to the listed steps or elements, but may include additional steps or elements not listed, or may include additional steps or elements inherent to such process, method, article, or apparatus. Reference to "connected," "coupled," and the like in this application is not intended to be limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. Reference herein to "a plurality" means greater than or equal to two. "and/or" describes an association relationship of associated objects, meaning that three relationships may exist, for example, "A and/or B" may mean: a exists alone, A and B exist simultaneously, and B exists alone. Reference herein to the terms "first," "second," "third," and the like, are merely to distinguish similar objects and do not denote a particular ordering for the objects.
The method provided by the embodiment can be executed in a terminal device, a computer or a similar operation device. Taking the example of the application on a terminal device, fig. 1 is a block diagram of a hardware structure of the terminal device of the tooth brushing effect evaluation method according to the embodiment of the invention. As shown in fig. 1, the terminal device 10 may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data, and optionally, a transmission device 106 for communication functions and an input/output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the terminal device. For example, terminal device 10 may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 can be used for storing computer programs, for example, software programs and models of application software, such as computer programs corresponding to the tooth brushing effect evaluation method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by executing the computer programs stored in the memory 104, thereby implementing the above-mentioned methods. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory located remotely from processor 102, which may be connected to terminal device 10 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the terminal device 10. In one example, the transmission device 106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmitting device 106 may be a Radio Frequency (RF) model, which is used to communicate with the internet via wireless.
In one embodiment, the terminal device may be a mobile smart phone, and the mobile smart phone is installed with an APP with a data fusion neural network model. The wearable Internet of things equipment is an electromyographic motion signal acquisition module, and forearm muscle electrical signals and motion signals of a user holding the toothbrush in the tooth brushing process are captured by the integrated multi-path Electromyographic (EMG) acquisition module and an Inertial Measurement Unit (IMU) and are sent to the mobile smart phone through transmission equipment.
The mobile smart phone is provided with an interactive interface which is convenient for common users to use, and comprises functions of wearable device pairing, data transmission, user authentication, tooth brushing detection evaluation, result display and the like. And the trained model is subjected to software integration through data fusion neural network model transplantation to meet the real-time tooth brushing monitoring and evaluation. The total system cost can be further reduced by integrating the mobile phone APP, and the interaction process is more convenient and friendly by utilizing the mobile phone interface to interact with the user. Meanwhile, the mobile phone can display the area with incomplete cleaning in the form of a UI and provide a correct tooth brushing method in the form of animation, so that the mobile phone is helpful for a user to quickly improve the tooth brushing mode.
As shown in fig. 2, the wearable internet of things device is a schematic diagram of a wearable internet of things device, the wearable internet of things device comprises an 8-channel myoelectricity acquisition device with a bluetooth communication chip, the sampling frequency is up to 200Hz, meanwhile, a 10-axis IMU inertia measurement module is arranged in the wearable internet of things device, the sampling frequency is up to 50Hz, and the wearable internet of things device is only responsible for sensor data acquisition in the tooth brushing process of a user. The sensor data processing, result display and user interface interaction are completed by using a common smart phone.
The present embodiment provides a method for evaluating tooth brushing effect, fig. 3 is a flowchart of a method for evaluating tooth brushing effect according to an embodiment of the present application, and as shown in fig. 3, the flowchart includes the following steps:
step S210, acquiring muscle electric signals and motion signals of the forearm of the current user;
and S220, carrying out regional brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a brushing effect evaluation report.
Through the steps, the tooth brushing effect evaluation report can be obtained only by carrying out regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model; the tooth brushing effect is evaluated by directly utilizing the data fusion neural network model, so that the calculation amount is reduced, the accuracy is high, and the requirement on hardware cost is low.
In one embodiment, a wearable internet of things device with a sensor is worn on the forearm of a current user, and muscle electric signals and motion signals of the forearm of the current user are obtained through wearing of the wearable internet of things device. The wearable Internet of things equipment can comprise 8 paths of electromyography acquisition equipment with a Bluetooth communication chip, and the sampling frequency is up to 200 Hz; meanwhile, a 10-axis IMU inertia measurement unit is arranged in the wearable Internet of things device, the sampling frequency is up to 50Hz, and the wearable Internet of things device is only responsible for collecting original tooth brushing electromyographic data of a user in the tooth brushing process. In particular, the data sampling through the fixed-length sliding window comprises 8-channel muscle electric signals and 10-channel motion signals. The brushing effectiveness assessment report includes brushing quality assessments and prompts, alerts for incorrect brushing postures and insufficiently cleaned tooth areas, and recommends proper brushing regimen to correct the brushing posture of the user.
Different data fusion neural network models can be trained according to different standard tooth brushing methods, teeth can be cleaned according to a certain standard tooth brushing method, a manual toothbrush is used for cleaning a corresponding area, the same motion mode is needed to be adopted for holding the toothbrush for cleaning, and the whole oral cavity is cleaned by continuously cleaning each area relatively. Assuming that the user brushes his/her teeth using standard brushing methods, the brushing motion patterns of the hand and wrist are highly similar. Therefore, monitoring of the user's brushing process can be achieved by acquiring the muscle electrical signals and motion signals of the current user's forearm, learning the captured muscle electrical signals and the region (motion signals) corresponding to the matching brushing posture through deep learning modeling. For example, in the case of the pap brushing method, a brushing area is divided into 16 areas, and each area is provided with a corresponding action. The collected brushing electromyography data is completely trained, and the data is fused with a neural network model, so that the method is specific to the Pasteur brushing method. For the same reason, training of other standard brushing models can be accomplished in the same manner, including but not limited to horizontal twitch brushing ROLL and circular brushing Fones.
In the use process, the user wears wearable internet of things equipment to obtain muscle electrical signals and motion signals of the forearm. And fusing a neural network model by using the completely trained data to perform final tooth brushing effect evaluation.
The embodiments of the present application are described and illustrated below by means of preferred embodiments.
FIG. 4 is a flow chart of a brushing effectiveness assessment method according to another embodiment of the present application. As shown in fig. 4, the process includes the following steps:
step S210, acquiring muscle electric signals and motion signals of the forearm of the current user;
and S220, carrying out regional brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a brushing effect evaluation report. (ii) a
And step S230, evaluating and optimizing the well-trained data fusion neural network model.
The method specifically evaluates and optimizes the well-trained data fusion neural network model, including but not limited to sampling window size, residual convolution module depth, convolution kernel, Bi-LSTM model stacking and the like, so that the trained data fusion neural network model can obtain higher detection precision on test data, and the volume and the calculation complexity of the final model can be ensured to meet the requirements of smartphone transplantation. In this embodiment, the model may be optimized by using currently acquired brushing electromyography data after each use of the user, or may be periodically optimized according to big data, which is not limited.
The following describes the training process of the data fusion neural network model in detail.
The training of the data fusion neural network model comprises the following steps:
s310, dividing the oral cavity cleaning area, and configuring a standard action for each divided area;
s320, collecting a large number of multi-channel original tooth brushing electromyographic data according to the divided areas and corresponding standard actions, wherein the original tooth brushing electromyographic data comprises muscle electric signals and motion signals;
s330, training by taking the original brushing electromyography data as sample data based on a deep learning method to obtain a data fusion neural network model with complete training.
It should be noted that the data fusion neural network model provided by the invention is a four-way parallel backbone network model, and includes a residual convolution model and a long-short term memory (BI-LSTM) model, which are respectively used for processing time domain characteristics and frequency domain characteristics of two-way data (muscle electrical signals and motion signals). The pattern of the high frequency muscle electrical signal is more pronounced and less affected by ambient noise. The low frequency motion (IMU) signal provides additional hand motion supplementation during brushing. For each sensor in the wearable Internet of things equipment, respectively using a residual convolution model and a BI-LSTM model to perform high-dimensional feature extraction and detection target fitting on frequency domain and time domain features; and then the high-dimensional time-frequency domain characteristics of the multi-path sensors are fused for final tooth brushing area detection and evaluation.
In one embodiment, the data fusion neural network model is trained for the pap toothbrushing method. As shown in fig. 5, the oral cavity is divided into 16 regions, and corresponding actions 1 to 16 are assigned to each region, and action 17 is not included in the 16 actions. In order to improve the calculation precision of the model, the acquired brushing electromyography data are required to be trained in standard brushing postures by first recruiting people of different ages and sexes, so that an acquirer is guaranteed to master the accurate brushing postures.
The wearable Internet of things equipment is worn on the rear part of the forearm of an arm holding the toothbrush, in the collection process, the built-in eight-path electromyographic sensors can capture weak current signals in the muscle group exerting force and contraction process at corresponding positions, and the weak current signals are amplified and filtered through the built-in amplifier to obtain pure forearm muscle electrical signals; meanwhile, the built-in IMU sensing can provide the pose change of the current wearable device, the motion acceleration information (three axes) in the acquisition process and the change of the angular velocity information (three axes). That is, the motion signal includes pose information, acceleration information, and angular velocity information.
And (6) data acquisition. When brushing the teeth myoelectric data and acquireing, the user dresses wearable thing networking equipment according to the mode of figure 5, then adopts standard mode of brushing the teeth with the assistance. During collection, the collection personnel is assisted to independently brush one tooth area in sequence each time, the obtained brushing electromyography data is calibrated according to the divided areas and the corresponding standard actions, and the invalid movement data is marked as an action 17; the cleaning was continued using standard brushing methods, divided by 16 tooth zones. Original brushing electromyogram data with a certain scale is constructed through long-term large-scale data acquisition. Wherein, the original brushing electromyography data comprises muscle electric signals and motion signals. Action 17 is the non-brushing behavior generated during brushing (e.g., non-standard brushing gestures, moving arms and switching of two tooth surfaces cleaning, etc.) for enhancing model robustness. The method comprises the steps of constructing a general brushing action electromyography and motion sensor data set through original brushing electromyography data obtained from human bodies of different ages, sexes and professions in a large scale, and classifying different sampling data according to set brushing actions for subsequent model training. In one embodiment, a facilitator may be specified to assist in data collection.
And training a data fusion neural network model. And training the deep learning model according to the original brushing electromyography data set constructed in the last step.
Specifically, original multi-channel sensor data in a time domain are segmented, then short-time Fourier transform is respectively carried out and input to a residual convolution neural network module and a bidirectional LSTM module, and high-dimensional feature construction is carried out; the four-way features realize the feature map mapping with uniform size through the full communication layer coding, so that feature fusion and fusion feature extraction based on convolution are facilitated, and the feature map mapping is finally used for detecting the tooth brushing event.
In one embodiment, the multi-channel original tooth brushing electromyography data in the time domain can be fragmented, and the time domain and frequency domain feature extraction is carried out on the fragmented original tooth brushing electromyography data; wherein, the time domain signal is subjected to feature extraction processing through a bidirectional BI-LSTM model; obtaining a frequency domain signal through short-time Fourier transform, and performing characteristic extraction processing by using a residual convolution model; mapping the features to feature maps with uniform dimensions through a full communication layer, and splicing; and fusing the spliced multipath characteristics by convolution to obtain a data fusion neural network model with complete training.
The specific process is as shown in fig. 6, firstly, a fixed-length sliding window is used to segment the original brushing electromyography data, and the Electromyography (EMG) signal and the movement (IMU) signal in each window are input into a four-way parallel backbone network for feature extraction. When processing frequency domain features, a short-time fourier transform is first used to convert the time domain features to frequency domain features. When processing temporal features, processing is performed with a stacked bidirectional LSTM (Bi-LSTM) model. Because the four trunk networks are independently carried out, the difference of sampling frequencies and channel numbers of different sensors does not need to be considered. And finally, each backbone network down-samples the high-dimensional features to a feature map with a fixed size through full-communication mapping, and performs feature splicing. The spliced characteristics are further fused through a convolution layer, and the tooth brushing effect is evaluated. The method aims at the problems that the mapping relation between the characteristic mode of the high-frequency electromyography and IMU sensor and the tooth brushing posture is complex and the detection model is difficult to build through heuristic condition modeling, and builds the detection model by utilizing a deep learning neural network modeling mode.
As shown in fig. 7, the Time Domain (TD) and Frequency Domain (FD) feature combinations of different sensors are used for the precision comparison of detection alone, and the horizontal axis is the model training round, so that the highest accuracy can be found when four backbones are used for fusion detection. The effectiveness of the detection using the fused data is demonstrated.
As shown in FIG. 8, the results show that the system achieves the highest average detection over all tooth regions, in contrast to the performance of other sensors and deep learning models over the defined brushing detection task.
As shown in fig. 9, compared with Receiver Operating Characteristic curves (ROC) of different combinations of the system backbone network, the test compares the differences between the common convolution and the residual convolution when extracting the frequency domain features and the common LSTM and Bi-LSTM modules when extracting the timing sequence features. The residual convolution kernel Bi-LSTM used by the system can cover ROC curves of other models, the performance is superior to that of other models, and meanwhile the convergence efficiency of the models is higher.
An advantage of the present invention is that the action of cleaning each tooth surface presents a high degree of consistency and regularity when the user employs a standard brushing regimen. In this case, the multi-path electromyography sensor can capture the electromyography signals (EMG) generated by the phalangeal joint driving the forearm muscle group and the movement signals of the forearm in three-dimensional space through the IMU sensor. Firstly, although the muscle electrical signal is different from person to person due to the developed degree of forearm muscle, the muscle electrical signal is not influenced by the environment and is very pure; the used multi-path electromyographic sensor can also fully and fully capture forearm muscle groups, and the completeness of data is ensured. Then, the wearable internet of things equipment wearing posture information and the equipment motion acceleration and the angular velocity change obtained by inertial measurement in the cleaning process are combined with the IMU sensor, so that the characteristics of the forearm motion posture in the tooth brushing process can be enhanced. Meanwhile, the data of the two types of different sensors are fused, so that the difference and the defect of the information of the two types of sensors can be mutually compensated. Myoelectricity mainly involves the relaxation process of muscles, while IMU is mainly the movement of the entire forearm and hand in three dimensions. The abundant and pure sensor data can ensure the stability and robustness of the sensor data.
In one embodiment, a well-trained model is integrated into a mobile phone APP, and a user wears a wearable Internet of things device during use and connects a mobile phone application program for real-time tooth brushing monitoring and evaluation. In the process of tooth brushing, tooth brushing electromyography data are sampled by the wearable device and input to the model, the model detects the tooth area to which the currently processed data belong, and the corresponding area is subjected to accumulated timing. Sensor data that is similar to the correct brushing position will be detected as correct, otherwise it will not be timed and only the time slice for proper cleaning of the divided tooth areas # 1-16 will be timed. And after the tooth brushing is finished, the time spent in each cleaning area is calculated, the position with insufficient plot time (such as less than 10 seconds) is prompted through images, and meanwhile, the standard tooth brushing method of the corresponding area is displayed, so that the user is assisted in perfecting the tooth brushing.
It should be noted that the steps illustrated in the above-described flow diagrams or in the flow diagrams of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that, although a logical order is illustrated in the flow diagrams, in some cases, the steps illustrated or described may be performed in an order different than here.
The present embodiment further provides a device for evaluating a tooth brushing effect, which is used to implement the above embodiments and preferred embodiments, and the description of the device is omitted here. As used below, the terms "model," "unit," "subunit," and the like may refer to a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 10 is a block diagram showing the construction of a brushing effect evaluation apparatus according to an embodiment of the present application, as shown in fig. 9, the apparatus comprising: an acquisition module 210 and an analysis module 220; an obtaining module 210, configured to obtain a muscle electrical signal and a motion signal of a forearm of a current user; and the analysis module 220 is configured to perform regional brushing effect evaluation on the muscle electrical signals and the motion signals by using the fully trained data fusion neural network model to obtain a brushing effect evaluation report.
The invention directly utilizes the data fusion neural network model to evaluate the tooth brushing effect, thereby not only reducing the calculated amount and having high accuracy, but also having low requirement on hardware cost.
In one embodiment, an optimization module is further included on the basis of all the models shown in fig. 10; and the optimization module is used for evaluating and optimizing the completely trained data fusion neural network model.
In one embodiment, an optimization module is further included on the basis of all the models shown in fig. 10; the oral cavity cleaning device also comprises a training module, wherein the training module is used for dividing the oral cavity cleaning area and configuring standard actions for each divided area; collecting a large amount of multi-channel original tooth brushing electromyography data according to the divided areas and corresponding standard actions, wherein the original tooth brushing electromyography data comprises muscle electric signals and motion signals; training by taking the original brushing electromyography data as sample data based on a deep learning method to obtain a data fusion neural network model with complete training.
In one embodiment, the obtaining module 210 is further configured to wear a wearable internet of things device with a sensor on a forearm of a current user, and obtain muscle electrical signals and motion signals of the forearm of the current user through the wearable internet of things device.
The above-described models may be functional models or program models, and may be implemented by software or hardware. For models implemented by hardware, the above models may be located in the same processor; or the models can be respectively positioned in different processors in any combination.
The present embodiment also provides an electronic device comprising a memory having a computer program stored therein and a processor configured to execute the computer program to perform the steps of any of the above method embodiments.
Optionally, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
Optionally, in this embodiment, the processor may be configured to execute the following steps by a computer program:
step S100, acquiring muscle electric signals and motion signals of the forearm of a user;
and S200, carrying out regional brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a brushing effect evaluation report.
It should be noted that, for specific examples in this embodiment, reference may be made to examples described in the foregoing embodiments and optional implementations, and details of this embodiment are not described herein again.
In addition, in combination with the tooth brushing effect evaluation method in the above embodiments, the embodiments of the present application can be implemented by providing a storage medium. The storage medium having stored thereon a computer program; the computer program, when executed by a processor, implements any of the above-described tooth brushing effect evaluation methods.
It should be understood by those skilled in the art that various features of the above-described embodiments can be combined in any combination, and for the sake of brevity, all possible combinations of features in the above-described embodiments are not described in detail, but rather, all combinations of features which are not inconsistent with each other should be construed as being within the scope of the present disclosure.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (10)
1. A method for evaluating a tooth brushing effect, comprising:
acquiring muscle electric signals and motion signals of the forearm of a current user;
and performing regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by using the well-trained data fusion neural network model to obtain a tooth brushing effect evaluation report.
2. The method of evaluating toothbrushing effectiveness according to claim 1, further comprising:
dividing the oral cavity cleaning area, and configuring standard actions for each divided area;
collecting a large amount of multi-channel original tooth brushing electromyography data according to the divided areas and corresponding standard actions, wherein the original tooth brushing electromyography data comprises muscle electric signals and motion signals;
and training by taking the original brushing electromyography data as sample data based on a deep learning method to obtain the completely trained data fusion neural network model.
3. The toothbrushing effectiveness evaluation method according to claim 2, wherein the oral cleaning region is divided and a standard action is configured for each divided region, comprising the steps of;
dividing the oral cavity cleaning areas to obtain 16 oral cavity cleaning areas; and standard action is configured for 16 oral cleaning areas.
4. The tooth brushing effect evaluation method according to claim 2, wherein the original tooth brushing electromyography data is trained as sample data based on a deep learning method to obtain the well-trained data fusion neural network model, and the method comprises the following steps:
the method comprises the steps of fragmenting multi-channel original tooth brushing electromyographic data in a time domain, and extracting time domain and frequency domain characteristics of the fragmented original tooth brushing electromyographic data; wherein, the time domain signal is subjected to feature extraction processing through a bidirectional BI-LSTM model; obtaining a frequency domain signal through short-time Fourier transform, and performing characteristic extraction processing by using a residual convolution model;
mapping the features to feature maps with uniform dimensions through a full communication layer, and splicing;
and fusing the spliced multipath characteristics by convolution to obtain a data fusion neural network model with complete training.
5. The toothbrushing effectiveness evaluation method according to claim 1, wherein acquiring the muscle electrical signal and the motion signal of the forearm of the user at present comprises the steps of:
wearable Internet of things equipment with a sensor is worn on the forearm of a current user, and muscle electric signals and motion signals of the forearm of the current user are obtained through wearing of the wearable Internet of things equipment.
6. The method of evaluating toothbrushing effectiveness according to claim 1, further comprising:
and evaluating and optimizing the well-trained data fusion neural network model.
7. A brushing effect evaluation device, comprising: an acquisition module and an analysis module;
the acquisition module is used for acquiring the muscle electrical signal and the motion signal of the forearm of the current user;
and the analysis module is used for carrying out regional tooth brushing effect evaluation on the muscle electric signals and the movement signals by utilizing the well-trained data fusion neural network model to obtain a tooth brushing effect evaluation report.
8. A brushing effect evaluation system, comprising: wearable Internet of things equipment, transmission equipment and terminal equipment; the terminal equipment is connected with the wearable Internet of things equipment through the transmission equipment;
the wearable Internet of things equipment is used for acquiring muscle electric signals and motion signals of the forearm of the current user;
the transmission equipment is used for transmitting the muscle electric signals and the movement signals;
the terminal device is used for executing the tooth brushing effect evaluation method according to any one of claims 1 to 6.
9. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is configured to execute the computer program to perform the brushing effect assessment method of any one of claims 1 to 6.
10. A storage medium, in which a computer program is stored, wherein the computer program is arranged to execute the toothbrushing effectiveness assessment method according to any one of claims 1 to 6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011032363.5A CN112184010A (en) | 2020-09-27 | 2020-09-27 | Tooth brushing effect evaluation method, device, system, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011032363.5A CN112184010A (en) | 2020-09-27 | 2020-09-27 | Tooth brushing effect evaluation method, device, system, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112184010A true CN112184010A (en) | 2021-01-05 |
Family
ID=73944202
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011032363.5A Withdrawn CN112184010A (en) | 2020-09-27 | 2020-09-27 | Tooth brushing effect evaluation method, device, system, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112184010A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065652A (en) * | 2021-04-07 | 2021-07-02 | 上海先基半导体科技有限公司 | Neural network model evaluation method and device and FPGA chip |
| CN114387295A (en) * | 2021-12-25 | 2022-04-22 | 广州星际悦动股份有限公司 | Motion trajectory generation method and device, electric toothbrush and storage medium |
| CN114577259A (en) * | 2022-02-08 | 2022-06-03 | 深圳市云顶信息技术有限公司 | Tooth brushing information feedback method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102133103A (en) * | 2010-12-15 | 2011-07-27 | 河北工业大学 | Method for recognizing human walking gait cycle with electromyographic signal |
| CN204562440U (en) * | 2014-01-09 | 2015-08-19 | 深圳市生活智能科技有限公司 | The system of monitoring toothbrushing effect |
| CN105496418A (en) * | 2016-01-08 | 2016-04-20 | 中国科学技术大学 | Arm-belt-type wearable system for evaluating upper limb movement function |
| CN106066996A (en) * | 2016-05-27 | 2016-11-02 | 上海理工大学 | The local feature method for expressing of human action and in the application of Activity recognition |
| CN106651711A (en) * | 2016-12-28 | 2017-05-10 | 北京小牙兽健康科技有限公司 | Tooth brushing effect evaluation method and device |
| US20170318954A1 (en) * | 2014-12-22 | 2017-11-09 | Sunstar Inc. | Toothbrush module, attachment for toothbrush, brushing assistance system, brushing evaluation system, brushing assistance device, and brushing assistance program |
| CN109875565A (en) * | 2019-01-25 | 2019-06-14 | 电子科技大学 | A kind of cerebral apoplexy upper extremity exercise function method for automatically evaluating based on deep learning |
-
2020
- 2020-09-27 CN CN202011032363.5A patent/CN112184010A/en not_active Withdrawn
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102133103A (en) * | 2010-12-15 | 2011-07-27 | 河北工业大学 | Method for recognizing human walking gait cycle with electromyographic signal |
| CN204562440U (en) * | 2014-01-09 | 2015-08-19 | 深圳市生活智能科技有限公司 | The system of monitoring toothbrushing effect |
| US20170318954A1 (en) * | 2014-12-22 | 2017-11-09 | Sunstar Inc. | Toothbrush module, attachment for toothbrush, brushing assistance system, brushing evaluation system, brushing assistance device, and brushing assistance program |
| CN105496418A (en) * | 2016-01-08 | 2016-04-20 | 中国科学技术大学 | Arm-belt-type wearable system for evaluating upper limb movement function |
| CN106066996A (en) * | 2016-05-27 | 2016-11-02 | 上海理工大学 | The local feature method for expressing of human action and in the application of Activity recognition |
| CN106651711A (en) * | 2016-12-28 | 2017-05-10 | 北京小牙兽健康科技有限公司 | Tooth brushing effect evaluation method and device |
| CN109875565A (en) * | 2019-01-25 | 2019-06-14 | 电子科技大学 | A kind of cerebral apoplexy upper extremity exercise function method for automatically evaluating based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 郭静等: "一种用于牙刷指导的互动型电子模型的研制和效果评估", 《口腔材料器械杂志》, vol. 26, no. 4, pages 203 - 209 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065652A (en) * | 2021-04-07 | 2021-07-02 | 上海先基半导体科技有限公司 | Neural network model evaluation method and device and FPGA chip |
| CN114387295A (en) * | 2021-12-25 | 2022-04-22 | 广州星际悦动股份有限公司 | Motion trajectory generation method and device, electric toothbrush and storage medium |
| CN114577259A (en) * | 2022-02-08 | 2022-06-03 | 深圳市云顶信息技术有限公司 | Tooth brushing information feedback method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112184010A (en) | Tooth brushing effect evaluation method, device, system, electronic device and storage medium | |
| CN113168910B (en) | Apparatus and method for operating a personal grooming or household cleaning appliance | |
| CN108983973B (en) | Control method of humanoid smart myoelectric artificial hand based on gesture recognition | |
| CN104765952A (en) | Tooth-brushing posture detection and assessment system | |
| CN106726030A (en) | Brain machine interface system and its application based on Clinical EEG Signals control machinery hands movement | |
| CN107708483A (en) | For extracting the kinetic characteristic of user using hall effect sensor to provide a user the method and system of feedback | |
| CN107811722B (en) | Intelligent electric toothbrush, and system and method for acquiring space posture of toothbrush | |
| CN104010132A (en) | Intelligent filming device and method based on emotion control | |
| CN107530015B (en) | Vital sign analysis method and system | |
| CN108958482A (en) | A kind of similitude action recognition device and method based on convolutional neural networks | |
| CN105868519A (en) | Human body characteristic data processing method and apparatus | |
| CN109124655A (en) | State of mind analysis method, device, equipment, computer media and multifunctional chair | |
| CN106137169A (en) | A kind of wearable multiple physiological parameter monitoring method and device thereof | |
| CN112541415A (en) | Brain muscle function network movement fatigue detection method based on symbol transfer entropy and graph theory | |
| CN110801227B (en) | Method and system for testing three-dimensional color block obstacle based on wearable equipment | |
| CN111312363B (en) | Double-hand coordination enhancement system based on virtual reality | |
| Essalat et al. | Monitoring brushing behaviors using toothbrush embedded motion-sensors | |
| CN112022097A (en) | Head belt type heteroplasmon monitoring equipment and head heteroplasmon monitoring method and system | |
| CN110197727A (en) | Upper limb modeling method and motion function assessment system based on artificial neural network | |
| CN209252849U (en) | A kind of movement companion | |
| CN106598243B (en) | A kind of multi-modal adaptive cursor control method and cursor control system | |
| CN112213134B (en) | Electric toothbrush oral cavity cleaning quality detection system and detection method based on acoustics | |
| CN110503056A (en) | It is applied to the body action identification method of cognitive function assessment based on AR technology | |
| CN114403855B (en) | Paralyzed upper limb movement function evaluation method, system and computer readable storage medium | |
| CN108008821B (en) | Performance evaluation method, device, terminal and storage medium of artificial limb action classifier |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210105 |
|
| WW01 | Invention patent application withdrawn after publication |