CN104361361A - Method and system for judging fall through cloud computing and machine learning algorithm - Google Patents
Method and system for judging fall through cloud computing and machine learning algorithm Download PDFInfo
- Publication number
- CN104361361A CN104361361A CN201410648555.7A CN201410648555A CN104361361A CN 104361361 A CN104361361 A CN 104361361A CN 201410648555 A CN201410648555 A CN 201410648555A CN 104361361 A CN104361361 A CN 104361361A
- Authority
- CN
- China
- Prior art keywords
- acceleration
- machine learning
- cloud computing
- fall down
- judged
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
-
- 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
- G06F18/2155—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the incorporation of unlabelled data, e.g. multiple instance learning [MIL], semi-supervised techniques using expectation-maximisation [EM] or naïve labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/245—Classification techniques relating to the decision surface
- G06F18/2451—Classification techniques relating to the decision surface linear, e.g. hyperplane
Abstract
The invention discloses a method and system for judging a fall through cloud computing and a machine learning algorithm and relates to the field of automatic detection of falls. According to the method and system for judging the fall through cloud computing the machine learning algorithm, firstly, a collected acceleration is prejudged, and a great number of non-fall data are filtered out; secondly, the prejudgment fall data are recognized through a linear classification algorithm; meanwhile, in a cloud server, the linear classification algorithm is updated through machine learning of the prejudgment fall data. By the adoption of the method and system, dual judgment is conducted and meanwhile in the cloud server, sample learning is conducted continuously so that the linear classification algorithm can be corrected and updated continuously; in this way, a fall judgment result is greatly improved, and the fall judgment speed is increased.
Description
Technical field
The present invention relates to and fall down automatic detection field, particularly relate to a kind of method and system being judged to fall down by cloud computing and machine learning algorithm.
Background technology
Along with Chinese society enters aging, the whole society increases gradually to the care of old man and concern.In order to improve the safety of the elderly's trip, the research for the alarm technique of the elderly's falling-resistant also gets more and more.
At present, fall down checkout equipment, detect body shape and the active state of user mainly through acceleration transducer or gyroscope, and judge whether the generation of fall events according to these data.Fall down monitoring equipment in use, be worn on it user according to certain angle, when there being fall events to occur, acceleration and angle will change, so, fall down monitoring equipment just utilize this principle to judge whether user there is fall events.
But judge the method for falling down in prior art, its condition of falling down is the acceleration of acceleration transducer or gyroscope collection and the change of angle, and the necessary condition that the change of acceleration and angle is user falls down, but not the adequate condition that user falls down, if namely user falls down, then acceleration transducer or gyrostatic acceleration and angle value inherently change, but, acceleration transducer or gyrostatic acceleration and angle value change, and user but not necessarily fall events occurs.So in prior art, the just acceleration of foundation acceleration transducer or gyroscope collection and the change of angle, judge fall events occurs, can produce the situation of more erroneous judgement, accuracy rate is low.
Summary of the invention
The object of the present invention is to provide a kind of method and system being judged to fall down by cloud computing and machine learning algorithm, thus solve the foregoing problems existed in prior art.
To achieve these goals, the technical solution used in the present invention is as follows:
Judged a method of falling down by cloud computing and machine learning algorithm, comprise the steps:
S1, acceleration transducer gathers acceleration, and degree of will speed up is transferred to processor;
S2, described processor receives described acceleration, and judges whether described acceleration exceedes the threshold value of setting, if described acceleration exceedes the threshold value of described setting, then performs step S3; If described acceleration does not exceed the threshold value of described setting, then return S1;
S3, described processor downloads linear classify algorithm from Cloud Server, and utilizing described linear classify algorithm to judge, whether described acceleration meets falls down feature, if met, then falls down; If do not met, then do not fall down;
S4, the described acceleration exceeding the threshold value of described setting all in S3 and the corresponding result of whether falling down all are transferred to described Cloud Server by described processor, described Cloud Server, by the described acceleration of study and the corresponding result of whether falling down, upgrades described linear classify algorithm.
Further, in S3, also comprise the step of warning, if fallen down, then report to the police.
Preferably, described acceleration transducer is 3-axis acceleration sensor.
Particularly, S2 comprises the steps:
S201, described processor receives described acceleration;
S202, calculates the resultant acceleration of described acceleration;
S203, judges whether described resultant acceleration exceedes the threshold value of setting.
Preferably, in S2, described threshold value is arranged according to the attribute of people, and the attribute of described people comprises at least one in sex, age, height and body weight.
Preferably, in S3, described in fall down feature and obtain by the following method:
S301, gathers the acceleration in a period of time and the corresponding result of whether falling down;
S302, marking falling down corresponding described acceleration, obtaining the acceleration marked;
S303, learns the acceleration information of described mark, falls down feature described in obtaining.
Particularly, in S4, described in transfer to Cloud Server and be, by GPRS transmission to Cloud Server.
Judged a system of falling down by cloud computing and machine learning algorithm, comprise successively according to data transfer direction: acceleration transducer, processor, data transmission set and Cloud Server.
Preferably, described data transmission set is gsm module.
Particularly, described processor comprises:
Data reception module: for receiving the described acceleration of acceleration transducer transmission;
Fall down anticipation module: for calculating described acceleration, and judge whether described acceleration exceedes the threshold value of setting;
Fall down judge module: for downloading linear classify algorithm from Cloud Server, and utilizing linear classify algorithm to judge, whether acceleration meets falls down feature, judges whether to fall down;
Data transmission module: for all described acceleration exceeding the threshold value of described setting and the corresponding result of whether falling down all are transferred to Cloud Server.
The invention has the beneficial effects as follows: by first carrying out anticipation to the acceleration gathered, filter out and a large amount of non-ly fall down data, then utilize linear classify algorithm to fall down data to anticipation to screen, simultaneously, in Cloud Server, data are fallen down by machine learning anticipation, upgrade linear classify algorithm, this by dual judgement, simultaneously in Cloud Server, constantly sample is learnt, thus the method for renewal is constantly revised to linear classify algorithm, not only greatly improve the result of falling down judgement, also improve the speed of falling down judgement.
Accompanying drawing explanation
Fig. 1 is the method flow schematic diagram that the embodiment of the present invention one provides;
Fig. 2 is the system architecture schematic diagram that the embodiment of the present invention two provides;
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with accompanying drawing, the present invention is further elaborated.Should be appreciated that embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.
Embodiment one
As shown in Figure 1, a kind of method being judged to fall down by cloud computing and machine learning algorithm, is comprised the steps:
S1, acceleration transducer gathers acceleration, and degree of will speed up is transferred to processor;
S2, described processor receives described acceleration, and judges whether described acceleration exceedes the threshold value of setting, if described acceleration exceedes the threshold value of described setting, then performs step S3; If described acceleration does not exceed the threshold value of described setting, then return S1;
S3, described processor downloads linear classify algorithm from Cloud Server, and utilizing described linear classify algorithm to judge, whether described acceleration meets falls down feature, if met, then falls down; If do not met, then do not fall down;
S4, the described acceleration exceeding the threshold value of described setting all in S3 and the corresponding result of whether falling down all are transferred to described Cloud Server by described processor, described Cloud Server, by the described acceleration of study and the corresponding result of whether falling down, upgrades described linear classify algorithm.
Just judge compared with the method for falling down, in the method that the embodiment of the present invention provides by the change of acceleration information with prior art:
First by judging whether acceleration exceedes the threshold value of setting, carrying out falling down anticipation, if the numerical value of acceleration exceedes the threshold value of setting, being then judged in advance and falling down, otherwise, be judged in advance and do not fall down;
In order to improve the accuracy of falling down judgement, then, to the acceleration of threshold value exceeding setting in anticipation, utilizing the linear classify algorithm downloaded from Cloud Server to judge whether to meet and fall down feature, if met, then falling down, if do not met, then do not fall down.
Wherein, as will be understood by the skilled person in the art, linear classify algorithm is the one in machine learning algorithm.Simultaneously, in embodiments of the present invention, just in native processor, utilizing linear classify algorithm to judge, whether acceleration meets falls down feature, and not learning sample, so, alleviate the calculating pressure of native processor greatly, like this, not only increase the processing speed of native processor, calculating accuracy rate can also be improved simultaneously.
In the embodiment of the present invention, for acceleration with the study of the sample of the corresponding result of whether falling down with after learning more sample, upgrade the process of linear classify algorithm, carry out in Cloud Server, the cloud computing ability utilizing Cloud Server powerful is to complete the machine learning of above-mentioned sample.And then notify that native processor is to the linear classify algorithm upgraded after downloading machine learning, falling down feature for judging whether the acceleration acquired meets, judging whether to fall down.Because machine-learning process carries out in Cloud Server, make use of the ability of cloud computing, therefore, computing velocity is faster, thus the speed that the judgement of native processor is fallen down is also faster, and the accuracy rate of calculating is also higher.
In the embodiment of the present invention, be to gather acceleration carried out anticipation after, just carry out machine learning and judgement, and in anticipation process, filtered out a large amount of data not meeting the condition of falling down, the data volume entering machine learning and judgement is reduced greatly, therefore, the sample of machine learning is more accurate, more accurate to the correction of linear classify algorithm, and then utilizes this linear classify algorithm to carry out falling down and judge that the result obtained also can be more accurate.
Therefore, the embodiment of the present invention is screened by anticipation, linear classify algorithm and Cloud Server machine learning is constantly revised linear classify algorithm, upgraded, and the accuracy of falling down judgement is greatly improved.
In the embodiment of the present invention, in S3, the step of warning can also be comprised, if fallen down, then report to the police.The function of reporting to the police can help the person of falling down to be succoured timely.
In the embodiment of the present invention, described acceleration transducer can be 3-axis acceleration sensor.
As will be understood by the skilled person in the art, the multi-shaft acceleration transducer of non-three axles can also be adopted.
If employing 3-axis acceleration sensor, then S2 specifically comprises the steps:
S201, described processor receives described acceleration;
S202, calculates the resultant acceleration of described acceleration;
S203, judges whether described resultant acceleration exceedes the threshold value of setting.
Wherein, the accekeration of three axles of 3-axis acceleration sensor collection is respectively: x, y, z, can according to following formulae discovery resultant acceleration: sqrt (x*x+y*y+z*z).By calculating the resultant acceleration of 3-axis acceleration, and the relation compared between resultant acceleration and the threshold value of setting is to carry out anticipation.
As will be understood by the skilled person in the art, also the resultant acceleration of 3-axis acceleration can not be calculated, directly the threshold value of each axle acceleration and setting is compared, and by calculating resultant acceleration, and utilize the threshold value of resultant acceleration and setting to compare, can further improve the accuracy of falling down judgement.
In the embodiment of the present invention, in S2, described threshold value is arranged according to the attribute of people, and the attribute of described people comprises at least one in sex, age, height and body weight.Setting threshold value.The masculinity and femininity that such as other attributes are all identical, threshold value may be just different, and concrete numerical value can set according to the empirical value falling down judgement.Like this, according to the empirical value falling down judgement, different threshold values is set to the people of different attribute, the accuracy of anticipation can be improved.
In the embodiment of the present invention, in S3, described in fall down feature and can obtain by the following method:
S301, gathers the acceleration in a period of time and the corresponding result of whether falling down;
S302, marking falling down corresponding described acceleration, obtaining the acceleration marked;
S303, utilizes the acceleration information of described linear classify algorithm to described mark to learn, falls down feature described in obtaining.
Wherein, the situation of falling down comprises: directly fall down in situation of standing; Trip in the process of walking; Trip in running process; Before face upward, swing back, side faces upward.Present the rule of hash distribution for these acceleration informations falling down situation, can think in two-dimensional coordinate system and be distributed in around an oblique line, this rule utilizing linear classify algorithm to learn to obtain falls down feature exactly.
In the embodiment of the present invention, the initial value falling down feature may need manually to intervene, obtain, afterwards, after the method is run, just can pass through the new sample of Cloud Server unceasing study, linear classify algorithm is constantly revised and upgrades, native processor just can utilize the linear classify algorithm constantly revised and upgrade constantly revise falling down feature and upgrade, the sample size of study is larger, linear classify algorithm is more accurate, and it is more accurate to fall down feature, and utilizing linear classify algorithm and fall down the result of falling down that feature obtains will be more accurate.
In the embodiment of the present invention, in S4, described in transfer to Cloud Server, be specially, by GPRS transmission to Cloud Server.
Embodiment two
As shown in Figure 2, embodiments provide a kind of system being judged to fall down by cloud computing and machine learning algorithm, comprise successively according to data transfer direction: acceleration transducer, processor, data transmission set and Cloud Server.
Wherein, described data transmission set can be gsm module.Gsm module is integrated on one piece of wiring board by GSM radio frequency chip, baseband processing chip, storer, power discharging device etc., has independently operating system, GSM radio frequency processing, Base-Band Processing provide the functional module of standard interface.
Gsm module has transmission SMS messaging, voice call, and all basic functions communicated are carried out in GPRS data transmission etc. based on GSM network.
In the embodiment of the present invention, described processor can comprise:
Data reception module: for receiving the described acceleration of acceleration transducer transmission;
Fall down anticipation module: for calculating described acceleration, and judge whether described acceleration exceedes the threshold value of setting;
Fall down judge module: for downloading linear classify algorithm from Cloud Server, and utilizing linear classify algorithm to judge, whether acceleration meets falls down feature, judges whether to fall down;
Data transmission module: for all described acceleration exceeding the threshold value of described setting and the corresponding result of whether falling down all are transferred to Cloud Server.
By adopting technique scheme disclosed by the invention, obtain effect useful as follows: by first carrying out anticipation to the acceleration gathered, filter out and a large amount of non-ly fall down data, then utilize linear classify algorithm to fall down data to anticipation to screen, simultaneously, in Cloud Server, data are fallen down by machine learning anticipation, upgrade linear classify algorithm, this by dual judgement, simultaneously in Cloud Server, constantly sample is learnt, thus linear classify algorithm is constantly revised to the method for renewal, not only greatly improve the result of falling down judgement, also improve the speed of falling down judgement.
Each embodiment in this instructions all adopts the mode of going forward one by one to describe, and what each embodiment stressed is the difference with other embodiments, between each embodiment identical similar part mutually see.
Those skilled in the art it should be understood that the sequential of the method step that above-described embodiment provides can carry out accommodation according to actual conditions, also can carry out according to actual conditions are concurrent.
The hardware that all or part of step in the method that above-described embodiment relates to can carry out instruction relevant by program has come, described program can be stored in the storage medium that computer equipment can read, for performing all or part of step described in the various embodiments described above method.Described computer equipment, such as: personal computer, server, the network equipment, intelligent mobile terminal, intelligent home device, wearable intelligent equipment, vehicle intelligent equipment etc.; Described storage medium, such as: the storage of RAM, ROM, magnetic disc, tape, CD, flash memory, USB flash disk, portable hard drive, storage card, memory stick, the webserver, network cloud storage etc.
Finally, also it should be noted that, in this article, the such as relational terms of first and second grades and so on is only used for an entity or operation to separate with another entity or operational zone, and not necessarily requires or imply the relation that there is any this reality between these entities or operation or sequentially.And, term " comprises ", " comprising " or its any other variant are intended to contain comprising of nonexcludability, thus make to comprise the process of a series of key element, method, commodity or equipment and not only comprise those key elements, but also comprise other key elements clearly do not listed, or also comprise by the intrinsic key element of this process, method, commodity or equipment.When not more restrictions, the key element limited by statement " comprising ... ", and be not precluded within process, method, commodity or the equipment comprising described key element and also there is other identical element.
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should look protection scope of the present invention.
Claims (10)
1. judged a method of falling down by cloud computing and machine learning algorithm, it is characterized in that, comprise the steps:
S1, acceleration transducer gathers acceleration, and degree of will speed up is transferred to processor;
S2, described processor receives described acceleration, and judges whether described acceleration exceedes the threshold value of setting, if described acceleration exceedes the threshold value of described setting, then performs step S3; If described acceleration does not exceed the threshold value of described setting, then return S1;
S3, described processor downloads linear classify algorithm from Cloud Server, and utilizing described linear classify algorithm to judge, whether described acceleration meets falls down feature, if met, then falls down; If do not met, then do not fall down;
S4, the described acceleration exceeding the threshold value of described setting all in S3 and the corresponding result of whether falling down all are transferred to described Cloud Server by described processor, described Cloud Server, by the described acceleration of study and the corresponding result of whether falling down, upgrades described linear classify algorithm.
2. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 1, be is characterized in that, in S3, also comprise the step of warning, if fallen down, then report to the police.
3. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 1, it is characterized in that, described acceleration transducer is 3-axis acceleration sensor.
4. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 3, it is characterized in that, S2 specifically comprises the steps:
S201, described processor receives described acceleration;
S202, calculates the resultant acceleration of described acceleration;
S203, judges whether described resultant acceleration exceedes the threshold value of setting.
5. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 1, it is characterized in that, in S2, described threshold value is arranged according to the attribute of people, and the attribute of described people comprises at least one in sex, age, height and body weight.
6. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 1, be is characterized in that, in S3, described in fall down feature and obtain by the following method:
S301, gathers the acceleration in a period of time and the corresponding result of whether falling down;
S302, marking falling down corresponding described acceleration, obtaining the acceleration marked;
S303, learns the acceleration information of described mark, falls down feature described in obtaining.
7. the method being judged to fall down by cloud computing and machine learning algorithm according to claim 1, be is characterized in that, in S4, described in transfer to Cloud Server, be specially, by GPRS transmission to Cloud Server.
8. judged a system of falling down by cloud computing and machine learning algorithm, it is characterized in that, comprise successively according to data transfer direction: acceleration transducer, processor, data transmission set and Cloud Server.
9. the system being judged to fall down by cloud computing and machine learning algorithm according to claim 8, it is characterized in that, described data transmission set is gsm module.
10. the system being judged to fall down by cloud computing and machine learning algorithm according to claim 8, it is characterized in that, described processor comprises:
Data reception module: for receiving the described acceleration of acceleration transducer transmission;
Fall down anticipation module: for calculating described acceleration, and judge whether described acceleration exceedes the threshold value of setting;
Fall down judge module: for downloading linear classify algorithm from Cloud Server, and utilizing linear classify algorithm to judge, whether acceleration meets falls down feature, judges whether to fall down;
Data transmission module: for all described acceleration exceeding the threshold value of described setting and the corresponding result of whether falling down all are transferred to Cloud Server.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410648555.7A CN104361361B (en) | 2014-11-14 | 2014-11-14 | The method and system for judging to fall down by cloud computing and machine learning algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410648555.7A CN104361361B (en) | 2014-11-14 | 2014-11-14 | The method and system for judging to fall down by cloud computing and machine learning algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104361361A true CN104361361A (en) | 2015-02-18 |
| CN104361361B CN104361361B (en) | 2018-04-03 |
Family
ID=52528619
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410648555.7A Expired - Fee Related CN104361361B (en) | 2014-11-14 | 2014-11-14 | The method and system for judging to fall down by cloud computing and machine learning algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104361361B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN104794463A (en) * | 2015-05-11 | 2015-07-22 | 华东理工大学 | System and method for achieving indoor human body falling detection based on Kinect |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN109035696A (en) * | 2018-06-21 | 2018-12-18 | 福州大学 | One kind falling down detection method based on acceleration transducer |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102231192A (en) * | 2011-05-31 | 2011-11-02 | 福建物联天下信息科技有限公司 | System for collecting and comparing action data and obtaining comparison similarity result |
| US20120083237A1 (en) * | 2010-10-04 | 2012-04-05 | Ram David Adva Fish | Fall detection system using a combination of accelerometer, audio input and magnetometer |
| CN102542724A (en) * | 2011-12-15 | 2012-07-04 | 上海移为通信技术有限公司 | Falling detecting and alarming method |
| CN103390327A (en) * | 2013-07-16 | 2013-11-13 | 中国科学院深圳先进技术研究院 | Early warning method and device for preventing human bodies from falling |
| CN103606248A (en) * | 2013-09-30 | 2014-02-26 | 广州市香港科大霍英东研究院 | Automatic detection method and system for human body falling-over |
| CN104007822A (en) * | 2014-05-30 | 2014-08-27 | 中山市永衡互联科技有限公司 | Large database based motion recognition method and device |
| CN104056445A (en) * | 2014-07-01 | 2014-09-24 | 杭州攻壳科技有限公司 | Human motion analytical method based on heart rate and acceleration sensor and device based on method |
-
2014
- 2014-11-14 CN CN201410648555.7A patent/CN104361361B/en not_active Expired - Fee Related
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120083237A1 (en) * | 2010-10-04 | 2012-04-05 | Ram David Adva Fish | Fall detection system using a combination of accelerometer, audio input and magnetometer |
| CN102231192A (en) * | 2011-05-31 | 2011-11-02 | 福建物联天下信息科技有限公司 | System for collecting and comparing action data and obtaining comparison similarity result |
| CN102542724A (en) * | 2011-12-15 | 2012-07-04 | 上海移为通信技术有限公司 | Falling detecting and alarming method |
| CN103390327A (en) * | 2013-07-16 | 2013-11-13 | 中国科学院深圳先进技术研究院 | Early warning method and device for preventing human bodies from falling |
| CN103606248A (en) * | 2013-09-30 | 2014-02-26 | 广州市香港科大霍英东研究院 | Automatic detection method and system for human body falling-over |
| CN104007822A (en) * | 2014-05-30 | 2014-08-27 | 中山市永衡互联科技有限公司 | Large database based motion recognition method and device |
| CN104056445A (en) * | 2014-07-01 | 2014-09-24 | 杭州攻壳科技有限公司 | Human motion analytical method based on heart rate and acceleration sensor and device based on method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104771177A (en) * | 2015-05-08 | 2015-07-15 | 重庆软汇科技股份有限公司 | Tumble detection system and method based on machine learning |
| CN104794463A (en) * | 2015-05-11 | 2015-07-22 | 华东理工大学 | System and method for achieving indoor human body falling detection based on Kinect |
| CN104794463B (en) * | 2015-05-11 | 2018-12-14 | 华东理工大学 | The system and method for indoor human body fall detection is realized based on Kinect |
| CN107247957A (en) * | 2016-12-16 | 2017-10-13 | 广州中国科学院先进技术研究所 | A kind of intelligent agricultural product sorting technique and system based on deep learning and cloud computing |
| CN109035696A (en) * | 2018-06-21 | 2018-12-18 | 福州大学 | One kind falling down detection method based on acceleration transducer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104361361B (en) | 2018-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103530978B (en) | A kind of dangerous criminal towards special population and warning system | |
| CN104680046B (en) | A kind of User Activity recognition methods and device | |
| US20180070889A1 (en) | Devices and methods for fall detection based on phase segmentation | |
| Reddy et al. | Using mobile phones to determine transportation modes | |
| CN110443190B (en) | Object recognition method and device | |
| CN112364439A (en) | Simulation test method and device for automatic driving system and storage medium | |
| CN104007822A (en) | Large database based motion recognition method and device | |
| CN104361361A (en) | Method and system for judging fall through cloud computing and machine learning algorithm | |
| CN105051646A (en) | Adaptive sensor sampling for power efficient context aware inferences | |
| CN105769205A (en) | Body information detection device and fall detection system | |
| CN102048521A (en) | System and method for monitoring and preventing tumble | |
| KR20170020085A (en) | Activity Information Processing Method and electronic device supporting the same | |
| CN105302383A (en) | Anti-interference method and device for capacitive touch sensor | |
| CN105225419A (en) | Fall detection method, system and the autoalarm of falling based on this system | |
| CN112163280B (en) | Method, device and equipment for simulating automatic driving scene and storage medium | |
| CN205721112U (en) | A kind of multifunctional intellectual wrist-watch | |
| CN104614749A (en) | Low-power-consumption positioning method based on motion posture | |
| CN109314727A (en) | A kind of method and device controlling mobile terminal screen | |
| CN204744140U (en) | Fall down intelligent wrist strap of location warning | |
| CN205103993U (en) | Intelligence human body guardianship device of tumbleing | |
| CN106248101A (en) | A kind of monitoring method and device | |
| CN110659179B (en) | Method and device for evaluating system running condition and electronic equipment | |
| CN204931656U (en) | A kind of wearable intelligent equipment | |
| CN106960542A (en) | A kind of low-power consumption falling detection device based on interruption driving | |
| CN205003818U (en) | Prevent missing accurate positioning system of dull -witted old man |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180403 Termination date: 20181114 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |