CN112541521A - Method for identifying ground pressed area of entrance and exit of house - Google Patents
Method for identifying ground pressed area of entrance and exit of house Download PDFInfo
- Publication number
- CN112541521A CN112541521A CN202011259029.3A CN202011259029A CN112541521A CN 112541521 A CN112541521 A CN 112541521A CN 202011259029 A CN202011259029 A CN 202011259029A CN 112541521 A CN112541521 A CN 112541521A
- Authority
- CN
- China
- Prior art keywords
- layer
- data
- sensor array
- area
- pressure sensor
- 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
- 238000000034 method Methods 0.000 title claims abstract description 24
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims abstract description 9
- 238000003825 pressing Methods 0.000 claims abstract description 7
- 238000003062 neural network model Methods 0.000 claims abstract description 6
- 238000013145 classification model Methods 0.000 claims abstract description 4
- 238000013135 deep learning Methods 0.000 claims abstract description 3
- 238000010586 diagram Methods 0.000 claims description 13
- 239000004744 fabric Substances 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 9
- 230000006870 function Effects 0.000 claims description 7
- 239000000758 substrate Substances 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 claims description 3
- 230000005284 excitation Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 9
- 238000004891 communication Methods 0.000 abstract description 2
- 230000000694 effects Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008054 signal transmission Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 239000013078 crystal Substances 0.000 description 1
- 238000013501 data transformation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L1/00—Measuring force or stress, in general
- G01L1/005—Measuring force or stress, in general by electrical means and not provided for in G01L1/06 - G01L1/22
-
- 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
- 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
- G08—SIGNALLING
- G08C—TRANSMISSION SYSTEMS FOR MEASURED VALUES, CONTROL OR SIMILAR SIGNALS
- G08C17/00—Arrangements for transmitting signals characterised by the use of a wireless electrical link
- G08C17/02—Arrangements for transmitting signals characterised by the use of a wireless electrical link using a radio link
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
Abstract
The invention discloses a method for identifying a ground pressed area of a house entrance, which comprises the steps of firstly constructing a flexible pressure sensor array, embedding the flexible pressure sensor array into a daily floor mat, and placing the flexible pressure sensor array at the entrance and the exit of a corridor where a target room is located; the flexible pressure sensor array records the area range data of a pressed area and the weight data of a pressed object in real time, and transmits the data to the server through the Internet of things system after receiving a request; the server sends the area range data S and the weight data W into a classification model for identification, and judges the attribute of the pressing main body; constructing a convolutional neural network model by utilizing a deep learning tool at a server side for supervised training; and sending the acquired data of the current real pressed area range of the sensor array into the constructed neural network model for identification, and accurately extracting pressing information. According to the invention, the pressure condition is acquired in real time through the flexible sensor, and is transmitted to the server end through the gateway through a wireless communication technology for algorithm classification prediction, so that the management and control early warning of key personnel are realized.
Description
Technical Field
The invention relates to the technical field of carpets for monitoring specific activity areas, in particular to a method for identifying a ground pressed area of a house entrance.
Background
The sensor is used as an information detection and transmission device, and can convert the measured information into an electric signal or other forms of signals to be output according to a certain rule and mode, so that the information collection, transmission, processing, analysis, display and the like are realized. The pressure sensor converts an external pressure signal into other physical signals (such as resistance, voltage, capacitance and the like) which are convenient to detect so as to test an absolute pressure value or pressure change. The pressure sensor has wide application prospect in the fields of touch perception, fingerprint identification, medical monitoring, human-computer interface, Internet of things and the like.
Conventional pressure sensors are mainly made of metal, semiconductor, piezoelectric crystal, etc., and most of these materials are rigid materials. Although the technology for manufacturing pressure sensors by using these materials is well-developed and can accurately measure pressure values in a wide range, with the development of technology and the increase of human requirements, the disadvantages of the pressure sensors become more and more obvious, such as larger and heavier devices, inability to withstand larger deformation, and the like. These drawbacks hinder their application in flexible human-machine interaction, portable detection, intelligent robotics, etc. scenarios. The flexible pressure sensor has wide application in many aspects, for example, it can be used in wearable electronic equipment for monitoring physiological signals of pulse, heartbeat and the like of a human body. Meanwhile, the robot is also an important element with the touch perception capability. The flexible pressure sensor is attached to the surface of the artificial limb, so that the disabled can recover the touch sense, the sensor can be combined with clothes, the health and motion signals of the human body can be monitored in real time, and the using process is simplified.
In public security practice, control over important personnel generally refers to a seizing informatization system similar to that disclosed by CN109992604A, and when the specified important personnel appear in a specified area, area alarm information is sent, so that the purposes of quick early warning, accurate positioning and case investigation and handling are achieved. However, the method has the disadvantages that the complexity of the system is high, the cooperation of multiple departments is required, and the system is easy to perceive.
Disclosure of Invention
The invention aims to provide a method for managing and controlling key personnel, which is based on a contact type ground pressure sensing technology of a flexible pressure sensor array, can record the pressure area of the ground of an entrance and an exit of a house in real time, transmits data to a server through the Internet of things technology, and then carries out classification and identification on a pressure applying main body by utilizing an artificial intelligence related algorithm at the server end so as to indirectly monitor the entrance and the exit of the key personnel.
In order to solve the above problems, the present invention provides a method for identifying a ground pressed area of a house entrance, comprising the steps of:
step 3, the server sends the area range data S and the weight data W into a classification model for identification, and judges the attribute of the pressing main body;
step 4, a convolutional neural network model is built at a server end by utilizing a deep learning tool, the range data S and the weight W of a pressed area are used as input of model training, l is used as a label value of the model training, and proper network layer number, neuron number of each layer, iteration times and performance parameters are set for supervised training;
and 5, sending the acquired data S of the current real pressed area range of the sensor array and the weight W into a constructed neural network model for identification, and accurately extracting pressing information.
Preferably, in step 2, the request is a two-dimensional data object request sent to the flexible pressure sensor array through the internet of things.
Further, in step 2, the compressed area is a two-dimensional matrix (X)ij)m*nM, n are respectively the number of rows and columns of the pressure sensor array arrangement, XijRecord the real pressure data in ith row and j column.
The structure of the flexible pressure sensor array is as follows: the conductive cloth is arranged on the upper layer, the longitudinal electrodes which are longitudinally arranged are arranged in the middle layer at certain intervals, the insulating cloth is arranged among the longitudinal electrodes to play an insulating role, the transverse electrodes which are transversely arranged are arranged on the lower layer at certain intervals, the longitudinal electrodes and the transverse electrodes are arranged in a crossed mode but are not communicated, the longitudinal electrodes, the insulating cloth and the transverse electrodes are attached to the flexible substrate, and the periphery of the conductive cloth is fixed on the flexible substrate.
The process of sending the constructed neural network model for identification is as follows: the input layer reads in the regularized region range image data S and the weight image data W transmitted from the server, each neuron of each layer takes a group of small local adjacent units of the previous layer as input, namely, the characteristics of the image data are continuously extracted by using a specific filter, the local characteristics are adopted to the overall characteristic construction, and finally, the identification function of the image is completed.
Aiming at the problems that when a filter is used for carrying out convolution processing on an image, the image is smaller and smaller, and edge information is lost less compared with the middle area edge area calculated times, a circle of blank is supplemented around the image before convolution every time to ensure the consistency of the image size.
The specific process of supplementing a circle of blank around the picture comprises the following steps:
the area-range image data S and the weight image data W both belong to an input original image of a convolutional neural network, defined as X,
for the invention HiFeature map (H) representing the ith layer of convolutional neural network0X), assume HiIs a convolutional layer, then HiThe generation process of (a) can be described as:
wherein: wiRepresenting the weight vector of the i-th layer of convolution kernel; operation sign
Representing convolution operation of convolution kernel and i-1 th layer image or characteristic diagram, convolution output and i-th layer offset vector biAdding, finally obtaining the characteristic diagram H of the ith layer through a nonlinear excitation function f (x)i，
The downsampling layer, which typically follows the convolutional layer, downsamples the feature map according to a certain downsampling rule,
suppose HiIs the down-sampling layer:
Hi＝subsampling(Hi-1)
through the alternate transmission of a plurality of convolutional layers and downsampling layers, the convolutional neural network classifies the extracted features by means of the full-connection network to obtain the probability distribution Y (l) based on the inputiRepresents the ith label category):
Y(i)＝P(L＝li|H0；(W，b))。
compared with the prior art, the invention has the following beneficial technical effects:
1. the invention uses the flexible pressure sensor array to effectively adapt to the flexible characteristic of the daily floor mat, and has the advantage of being difficult to be perceived when being used for the control of key personnel.
2. The invention uses the convolution neural network model to process the two-dimensional data, thereby well solving the problem of the identification precision of the presser.
3. The model training process of the invention is simple, the calculation cost is low, and simultaneously the result of the extraction of the pressure information can be ensured to be credible rather than disorder.
4. The invention can be matched with daily floor mats in any shapes and can be designed according to requirements.
5. The floor mat embedded with the flexible pressure sensor array is integrated into the smart home system by using the technology of the Internet of things, and can cooperate with other intelligent equipment to realize effective supervision on key personnel.
Drawings
FIG. 1 is a schematic diagram of a flexible pressure sensor array structure.
FIG. 2 is a schematic diagram of data signal transmission
Fig. 3 is a diagram of the effect of the flexible pressure sensor after receiving pressure.
FIG. 4 is a block diagram of a convolutional neural network
FIG. 5 is a schematic diagram of a flexible pressure sensor array data signal
Detailed Description
The following detailed description of embodiments of the invention refers to the accompanying drawings.
The invention combines the internet of things technology, takes a single chip as a control core, acquires the pressure condition in real time through a flexible sensor, and transmits the pressure condition to a Web server end through a gateway through a wireless communication technology to carry out algorithm classification prediction, thereby realizing management and control early warning on key personnel.
The structure of the flexible pressure sensor array is shown in fig. 1, and the flexible pressure sensor array is firstly constructed by using conductive cloth, longitudinal electrodes, insulating cloth, transverse electrodes and an elastic substrate. Arranging conductive cloth on the upper layer, arranging a plurality of longitudinally arranged longitudinal electrodes on the middle layer at certain intervals, and arranging a plurality of insulating cloths among the longitudinal electrodes to play an insulating role; the plurality of transversely arranged transverse electrodes are arranged on the lower layer at certain intervals; the longitudinal electrodes and the transverse electrodes are arranged in a crossed mode but are not communicated; the longitudinal electrodes, the insulating cloth and the transverse electrodes are attached to the flexible substrate; the periphery of the conductive cloth is fixed on the elastic substrate.
In the invention, the sensor units of the flexible pressure sensor array are sequentially connected with the signal conditioning and data acquisition unit and the data display and analysis unit, and the data acquisition unit is used for transmitting transmission signals to the Web server of the Internet of things system through the gateway, as shown in the data signal transmission schematic diagram of FIG. 2. The floor mat is embedded into a daily floor mat and is placed at the passageway of a passageway where a target room is located.
When the control target tramples or passes through the ground mat, the flexible pressure sensor array can record the regional range data of the pressed area and the weight data of the pressed object in real time through the data acquisition unit. The effect of the flexible pressure sensor after receiving pressure is shown in fig. 3, and the data signal diagram of the flexible pressure sensor array is shown in fig. 5.
The compressed area is a two-dimensional matrix (X)ij)m*nAnd m and n are respectively the number of rows and the number of columns of the pressure sensor array, and the data are transmitted to the Web server of the Internet of things system through the Internet of things system after receiving a two-dimensional data object request sent to the flexible pressure sensor array by the Internet of things. And the server sends the area range data S and the weight data W into a classification model for identification, and judges the attribute of the pressing body.
And constructing a convolutional neural network model to perform supervised learning on the incoming data. The convolutional neural network is a multi-layer supervised learning neural network. Mainly composed of an input layer, a convolutional layer, a downsampling layer (pooling layer), a full-link layer, and an output layer, as shown in fig. 4.
The input layer reads in the regularized region range image data S and the weight image data W transmitted from the server, each neuron of each layer takes a group of small local adjacent units of the previous layer as input, namely, the characteristic of the image data is continuously extracted by using a specific filter, the local characteristic is adopted to the overall characteristic construction, and finally, the identification function of the image is completed. However, when the convolution processing is performed on the image by using the filter, the image becomes smaller and smaller, and the edge information is easily lost because the number of times the edge region is calculated is small compared with the middle region, which has a great influence on the recognition accuracy. Therefore, a padding white filling method is used, namely, a circle of blank is filled around the picture before each convolution in order to ensure the consistency of the picture size, so that the picture size always keeps the original consistency no matter how many times of convolution is carried out, and the information of the edge cannot be missed. The specific implementation mode is as follows:
the area range image data S and the weight image data W both belong to an input original image of a convolutional neural network, and are defined as X.
For the invention HiFeature map (H) representing the ith layer of convolutional neural network0X). Suppose HiIs a convolutional layer, then HiThe generation process of (a) can be described as:
wherein: wiRepresenting the weight vector of the i-th layer of convolution kernel; operation sign
Representing convolution operation of convolution kernel and i-1 th layer image or characteristic diagram, convolution output and i-th layer offset vector biAdding, finally obtaining the characteristic diagram H of the ith layer through a nonlinear excitation function f (x)i。
The downsampling layer generally follows the convolutional layer and downsamples the feature map according to a certain downsampling rule.
Suppose HiIs the down-sampling layer:
Hi＝subsampling(Hi-1)
through the alternate transmission of a plurality of convolutional layers and downsampling layers, the convolutional neural network classifies the extracted features by means of the full-connection network to obtain the probability distribution Y (l) based on the inputiRepresenting the ith label category). As shown in the following equation, a convolutional neural network is essentially a primitive matrix (H)0) Through a plurality of layersSecondary data transformation or dimensionality reduction, mapping to a new mathematical model of the feature expression Y, minimizing the loss function L (W, b) of the network to achieve the training goal of the convolutional neural network,
Y(i)＝P(L＝li|H0；(W，b))
the convolutional neural network high-level features which are conducted forward have strong discrimination capability and generalization performance, classification and identification of a pressure applying main body can be supported, and monitoring of entering and exiting of key personnel in a house can be achieved indirectly. When the data is abnormal, the early warning module immediately sends out remote warning to guide a policeman to arrive at the site at the first time, and the requirements of sensitive response, antenna official, omnibearing, three-dimensional and multi-level under the information leading police service mode are effectively met.
The flexible pressure sensor array is applied to the case handling practices such as public security investigation, mandatory measures and the like, and the management and control of the important personnel are effectively realized by utilizing the technology of sensing the internet of things and the contact type ground pressed area.
The above description is only an embodiment of the present invention, but the scope of the present invention is not limited thereto, and any changes or substitutions that can be made by those skilled in the art within the technical scope of the present invention are intended to be included in the scope of the present invention.
Claims (7)
1. A method for identifying a ground pressure area of a house entrance is characterized by comprising the following steps:
step 1, constructing a flexible pressure sensor array, embedding the flexible pressure sensor array into a daily floor mat, and placing the flexible pressure sensor array at an entrance and an exit of a passageway where a target room is located;
step 2, the flexible pressure sensor array records the area range data of a pressed area and the weight data of a pressed object in real time, and transmits the data to a server through an Internet of things system after receiving a request;
step 3, the server sends the area range data S and the weight data W into a classification model for identification, and judges the attribute of the pressing main body;
step 4, a convolutional neural network model is built at a server end by utilizing a deep learning tool, the range data S and the weight W of a pressed area are used as input of model training, L is used as a label value of the model training, and proper network layer number, neuron number of each layer, iteration times and performance parameters are set for supervised training;
and 5, sending the acquired data S of the current real pressed area range of the sensor array and the weight W into a constructed neural network model for identification, and accurately extracting pressing information.
2. The method for identifying the ground pressure area of the building doorway according to claim 1, wherein the request in step 2 is a two-dimensional data object request sent to the flexible pressure sensor array through the internet of things.
3. The method of identifying a pressed area of a floor of a building doorway according to claim 1 wherein the pressed area in step 2 is a two dimensional matrix (X)ij)m*nM, n are respectively the number of rows and columns of the pressure sensor array arrangement, XijIs the real pressure data of the ith row and the j column.
4. The method of identifying a floor pressurized area of a building doorway according to claim 1 wherein the flexible pressure sensor array is configured to: the conductive cloth is arranged on the upper layer, the longitudinal electrodes which are longitudinally arranged are arranged in the middle layer at certain intervals, the insulating cloth is arranged among the longitudinal electrodes to play an insulating role, the transverse electrodes which are transversely arranged are arranged on the lower layer at certain intervals, the longitudinal electrodes and the transverse electrodes are arranged in a crossed mode but are not communicated, the longitudinal electrodes, the insulating cloth and the transverse electrodes are attached to the flexible substrate, and the periphery of the conductive cloth is fixed on the flexible substrate.
5. The method for identifying the ground pressure area of the entrance and exit of the house according to claim 1, wherein the step of sending the constructed neural network model to identify the ground pressure area comprises the following steps: the input layer reads in the regularized region range image data S and the weight image data W transmitted from the server, each neuron of each layer takes a group of small local adjacent units of the previous layer as input, namely, the characteristics of the image data are continuously extracted by using a specific filter, the local characteristics are adopted to the overall characteristic construction, and finally, the identification function of the image is completed.
6. The method for identifying the ground pressure area of the entrance and exit of the house according to claim 5, wherein a blank space is added around the picture before each convolution in order to ensure the consistency of the picture size, aiming at the problem that the picture is smaller and smaller when the convolution processing is performed on the picture by using a filter, and the loss of edge information is less caused by the fact that the number of times of calculating the edge area of the middle area is less.
7. The method for identifying the ground pressure area of the entrance and exit of the house according to claim 6, wherein the specific process of filling a blank around the picture comprises the following steps:
the area-range image data S and the weight image data W both belong to an input original image of a convolutional neural network, defined as X,
by HiFeature map (H) representing the ith layer of convolutional neural network0X), assume HiIs a convolutional layer, then HiThe generation process of (a) can be described as:
wherein W isiRepresenting the weight vector of the i-th layer of convolution kernel; operation sign
Representing convolution operation of convolution kernel and i-1 th layer image or characteristic diagram, convolution output and i-th layer offset vector biAdding, finally obtaining the characteristic diagram H of the ith layer through a nonlinear excitation function f (x)i，
The downsampling layer, which typically follows the convolutional layer, downsamples the feature map according to a certain downsampling rule,
suppose HiIs the down-sampling layer:
Hi＝subsampling(Hi-1)
through the alternate transmission of a plurality of convolutional layers and downsampling layers, the convolutional neural network classifies the extracted features by means of the full-connection network to obtain the probability distribution Y (l) based on the inputiRepresents the ith label category):
Y(i)＝P(L＝li|H0；(W,b))。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259029.3A CN112541521A (en) | 2020-11-12 | 2020-11-12 | Method for identifying ground pressed area of entrance and exit of house |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011259029.3A CN112541521A (en) | 2020-11-12 | 2020-11-12 | Method for identifying ground pressed area of entrance and exit of house |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112541521A true CN112541521A (en) | 2021-03-23 |
Family
ID=75014044
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011259029.3A Pending CN112541521A (en) | 2020-11-12 | 2020-11-12 | Method for identifying ground pressed area of entrance and exit of house |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112541521A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150282766A1 (en) * | 2014-03-19 | 2015-10-08 | Tactonic Technologies, Llc | Method and Apparatus to Infer Object and Agent Properties, Activity Capacities, Behaviors, and Intents from Contact and Pressure Images |
| CN108427921A (en) * | 2018-02-28 | 2018-08-21 | 辽宁科技大学 | A kind of face identification method based on convolutional neural networks |
| CN208505501U (en) * | 2018-06-25 | 2019-02-15 | 河北工业大学 | A kind of intelligent carpet based on pliable pressure sensor |
| CN111238620A (en) * | 2020-01-08 | 2020-06-05 | 缤刻普达（北京）科技有限责任公司 | Human body data detection recording method and system, intelligent weighing scale and mobile terminal |
| CN111382629A (en) * | 2018-12-28 | 2020-07-07 | 中国科学院半导体研究所 | Footprint identification and information mining method and system based on convolutional neural network |
-
2020
- 2020-11-12 CN CN202011259029.3A patent/CN112541521A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150282766A1 (en) * | 2014-03-19 | 2015-10-08 | Tactonic Technologies, Llc | Method and Apparatus to Infer Object and Agent Properties, Activity Capacities, Behaviors, and Intents from Contact and Pressure Images |
| CN108427921A (en) * | 2018-02-28 | 2018-08-21 | 辽宁科技大学 | A kind of face identification method based on convolutional neural networks |
| CN208505501U (en) * | 2018-06-25 | 2019-02-15 | 河北工业大学 | A kind of intelligent carpet based on pliable pressure sensor |
| CN111382629A (en) * | 2018-12-28 | 2020-07-07 | 中国科学院半导体研究所 | Footprint identification and information mining method and system based on convolutional neural network |
| CN111238620A (en) * | 2020-01-08 | 2020-06-05 | 缤刻普达（北京）科技有限责任公司 | Human body data detection recording method and system, intelligent weighing scale and mobile terminal |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Galvão et al. | A multimodal approach using deep learning for fall detection | |
| CN108764059B (en) | Human behavior recognition method and system based on neural network | |
| CN110133610B (en) | Ultra-wideband radar action identification method based on time-varying distance-Doppler diagram | |
| CN103517042B (en) | A kind of nursing house old man's hazardous act monitoring method | |
| CN107808139A (en) | A kind of real-time monitoring threat analysis method and system based on deep learning | |
| Yadav et al. | ARFDNet: An efficient activity recognition & fall detection system using latent feature pooling | |
| CN104038738A (en) | Intelligent monitoring system and intelligent monitoring method for extracting coordinates of human body joint | |
| El-Attar et al. | Discrete wavelet transform-based freezing of gait detection in Parkinson’s disease | |
| KR102413893B1 (en) | Non-face-to-face non-contact fall detection system based on skeleton vector and method therefor | |
| Tong et al. | Detection of urban sprawl using a genetic algorithm-evolved artificial neural network classification in remote sensing: a case study in Jiading and Putuo districts of Shanghai, China | |
| Lin et al. | Sensing from the bottom: Smart insole enabled patient handling activity recognition through manifold learning | |
| CN117379016B (en) | Remote monitoring system and method for beef cattle cultivation | |
| CN116563887B (en) | Sleeping posture monitoring method based on lightweight convolutional neural network | |
| CN116343284A (en) | Attention mechanism-based multi-feature outdoor environment emotion recognition method | |
| Dhanraj et al. | Efficient smartphone-based human activity recognition using convolutional neural network | |
| Tan et al. | Online activity recognition and daily habit modeling for solitary elderly through indoor position-based stigmergy | |
| CN112686111B (en) | Attention mechanism-based multi-view adaptive network traffic police gesture recognition method | |
| CN110414590A (en) | Physical activity recognition methods based on Intelligent mobile equipment and convolutional neural networks | |
| CN112541521A (en) | Method for identifying ground pressed area of entrance and exit of house | |
| CN109933204A (en) | A kind of man-machine interaction method of Behavior-based control action triggers and brain wave perception | |
| CN209734011U (en) | Non-contact human body state monitoring system | |
| CN111739654A (en) | Internet of things-based isolated hospital security supervision method and device and storage medium | |
| CN109976522A (en) | A kind of man-machine interaction method stopping triggering with brain wave perception based on human eye vision | |
| Daga et al. | Applications of Human Activity Recognition in Different Fields: A Review | |
| CN114521900B (en) | Arrhythmia classification and identification method based on transfer learning |
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 |