CN109685125A - Daily behavior feature mining and calculation method based on frequent Sensor Events sequence - Google Patents
Daily behavior feature mining and calculation method based on frequent Sensor Events sequence Download PDFInfo
- Publication number
- CN109685125A CN109685125A CN201811537184.XA CN201811537184A CN109685125A CN 109685125 A CN109685125 A CN 109685125A CN 201811537184 A CN201811537184 A CN 201811537184A CN 109685125 A CN109685125 A CN 109685125A
- Authority
- CN
- China
- Prior art keywords
- daily behavior
- value
- matrix
- sensor events
- feature
- 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
- 238000005065 mining Methods 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 title claims abstract description 13
- 238000000034 method Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 11
- 230000000694 effects Effects 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 230000006399 behavior Effects 0.000 claims description 73
- 239000011159 matrix material Substances 0.000 claims description 66
- 239000013598 vector Substances 0.000 claims description 9
- 230000001960 triggered effect Effects 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000009412 basement excavation Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000003287 bathing Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/19—Recognition using electronic means
- G06V30/192—Recognition using electronic means using simultaneous comparisons or correlations of the image signals with a plurality of references
- G06V30/194—References adjustable by an adaptive method, e.g. learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Databases & Information Systems (AREA)
- Multimedia (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides a kind of daily behavior feature mining and calculation method based on frequent Sensor Events sequence, comprising: identification model is trained and Activity recognition tests two stages；Identification model training includes: to acquire the Sensor Events sequence that resident's daily behavior continuously triggers sequentially in time by multiple non-invasive sensors of setting；Collected Sensor Events sequence is pre-processed, Sensor Events sequences segmentation is multiple subsequences as unit of daily behavior by pretreatment；The Sensor Events sequence that Mining Frequent occurs, the feature as resident's daily behavior；Calculate the value of resident's daily behavior characteristically.The shortcomings that the present invention overcomes predefined feature and discrete features, the continuous feature to resident's daily behavior is fully and effectively excavated using Frequent Sequential Patterns method for digging, and propose the computational algorithm of characteristic value, therefore theoretically, the accurate rate and recall rate of resident's daily behavior will be promoted significantly using the feature that the present invention excavates.
Description
Technical field
The present invention relates to Behavior mining computing technique fields, specifically, more particularly to a kind of based on frequent sensor thing
The daily behavior feature mining and calculation method of part sequence.
Background technique
Resident's daily behavior identifies the used predefined feature of feature either discrete features at present.It is predefined
Feature generally comprises behavior at the time of start, behavior duration, and the density of behavior, sensor of triggering etc. predefine
The acquisition of feature is relatively easy, but has isolated the connection between Sensor Events completely.Due to characterization resident's daily behavior
Sensor Events are time serieses, and predefined feature and discrete features are lost the time series attribute of Sensor Events, are led
At the time of to cause the value of predefined feature and discrete features be behavior, sensor-triggered or the knot of feature frequency of occurrences statistics
Fruit, this discrete characteristic value finally hinder the quality of resident's daily behavior identification.
Summary of the invention
According to technical problem set forth above, and provide a kind of daily behavior feature based on frequent Sensor Events sequence
Excavation and calculation method.The present invention is based on the daily behavior feature mining of frequent Sensor Events sequence and calculation methods, comprising:
Identification model is trained and Activity recognition tests two stages；
The identification model training at least includes the following steps:
S1: resident's daily behavior is acquired by multiple non-invasive sensors of setting and is continuously triggered sequentially in time
Sensor Events sequence；
S2: pre-processing the collected Sensor Events sequence, described to pre-process the Sensor Events
Sequences segmentation is multiple subsequences as unit of daily behavior；
S3: the Sensor Events sequence that Mining Frequent occurs, the feature as resident's daily behavior；
S4: the value of resident's daily behavior characteristically is calculated；
Each Sensor Events meets mode:<trigger sensor, the date of triggering, the time of triggering, and trigger value>；Institute
The Sensor Events for stating the triggering of resident's daily behavior are recorded by way of text flow；
The Activity recognition test: using the machine learning mode training classifier for having supervision, the classification after training is used
Device identifies behavior to be tested.
Further, the starting point and end point for the Sensor Events sequence that mark daily behavior is triggered is the resident
Daily behavior.
Further, the Sensor Events sequence that the Mining Frequent occurs is excavated by using Frequent Sequential Patterns to be calculated
Method PrefixSpan excavates the frequent sensor sequence mode being hidden in daily behavior.
Further, for a daily behavior and a feature, the Sensor Events sequence of daily behavior triggering
Value formal definition under this feature is a matrix, calculates the daily behavior taking under this feature according to the value of matrix
Value；
Every a line of the value matrix corresponding one meets the Sensor Events subsequence of feature, and the value of every a line is
First Sensor Events moment in <subsequence, second Sensor Events moment ... in subsequence, last in subsequence
A Sensor Events moment >.
Further, for resident's daily behavior feature, the value with maximum order is found out in the value matrix
Matrix, and then the matrix except the value matrix with maximum order is extended, so that the rank of matrix is equal to the value square
Maximum order in battle array；
It compares one by one and searches for all value matrixes with the best match of maximum order matrix, calculated by Pearson correlation coefficient
The similitude of each described value matrix and maximum order matrix, obtains two vectors being made of row similitude, then pass through skin
Your inferior related coefficient calculates the similitude of the vector, and the similitude of the vector is value of the current matrix in current signature；
If maximum order matrix and maximum value matrix pattern are the matrixes of n*m, value matrix is the matrix of k*m, and k≤m；?
K row is selected in the n row of maximum matrix pattern, this k row is used to store the value of k row in value matrix, selects k behavior matching；It is described
Make the value of formula (1) minimum in all matchings of best match:
Wherein ai1Indicate first element of the i-th row of maximum value matrix, bi1Indicate the first of the i-th row of value matrix
A element.
Compared with the prior art, the invention has the following advantages that the present invention overcomes predefined feature and discrete features
Disadvantage is fully and effectively excavated the continuous feature to resident's daily behavior using Frequent Sequential Patterns method for digging, and proposed
The computational algorithm of characteristic value, therefore theoretically, it is daily that resident will be promoted significantly using the feature that the present invention excavates
The accurate rate and recall rate of behavior.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to do simply to introduce, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without any creative labor, can be with
It obtains other drawings based on these drawings.
Fig. 1 is overall flow schematic diagram of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
As shown in Figure 1, daily behavior feature mining and calculation method, feature based on frequent Sensor Events sequence exist
In, comprising: identification model is trained and Activity recognition tests two stages.
As preferred embodiment, identification model training is at least included the following steps:
S1: resident's daily behavior is acquired by multiple non-invasive sensors of setting and is continuously triggered sequentially in time
Sensor Events sequence.As the preferred embodiment of the application, resident's daily behavior includes sleeping, cooking, eating
Meal, cleaning bathing, take medicine, see TV, guests etc..It can be understood as in other embodiments also comprising it
Its behavior, as long as can include the daily behavior of resident.
S2: pre-processing the collected Sensor Events sequence, described to pre-process the Sensor Events
Sequences segmentation is multiple subsequences as unit of daily behavior.It is directly adopted from sensor as described in the preferred mode of the application
The data collected are Sensor Events sequences, and it is several with daily behavior that pretreated work, which is Sensor Events sequences segmentation,
For the subsequence of unit.Pretreated purpose is the feature in order to count each daily behavior.
S3: the Sensor Events sequence that Mining Frequent occurs, the feature as resident's daily behavior；
S4: the value of resident's daily behavior characteristically is calculated；
Each Sensor Events meets mode:<trigger sensor, the date of triggering, the time of triggering, and trigger value>；Institute
The Sensor Events for stating the triggering of resident's daily behavior are recorded by way of text flow；
The Activity recognition test: using the machine learning mode training classifier for having supervision, the classification after training is used
Device identifies behavior to be tested.
In the present embodiment, the starting point and end point for the Sensor Events sequence that mark daily behavior is triggered is institute
State resident's daily behavior.As unit of complete resident's daily behavior, the Sensor Events sequence that daily behavior is triggered is marked
Starting point and end point.
As preferred embodiment, the Sensor Events sequence that the Mining Frequent occurs is by using Frequent episodes mould
Formula mining algorithm PrefixSpan excavates the frequent sensor sequence mode being hidden in daily behavior.The biography that Mining Frequent occurs
Sensor sequence of events is hidden in frequent in daily behavior by using frequent Sequential Pattern Mining Algorithm PrefixSpan excavation
Sensor sequence mode.
In the present embodiment, for a daily behavior and a feature, the Sensor Events of daily behavior triggering
Value formal definition of the sequence under this feature is a matrix, calculates the daily behavior under this feature according to the value of matrix
Value.Every a line of value matrix corresponding one meets the Sensor Events subsequence of feature, and the value of every a line is <subsequence
In first Sensor Events moment, second Sensor Events moment ... in subsequence, the last one sensor in subsequence
Event time >.
As the sensing in preferred embodiment, triggered for a daily behavior and a feature, the daily behavior
Value formal definition of the device sequence of events under this feature is a matrix, calculates the daily behavior in the spy according to the value of matrix
Value under sign；
Every a line of the value matrix corresponding one meets the Sensor Events subsequence of feature, and the value of every a line is
First Sensor Events moment in <subsequence, second Sensor Events moment ... in subsequence, last in subsequence
A Sensor Events moment >.
As preferred embodiment, for resident's daily behavior feature, finding out in the value matrix has most
The value matrix of big order, and then the matrix except the value matrix with maximum order is extended, so that the rank of matrix is equal to
Maximum order in the value matrix；
It compares one by one and searches for all value matrixes with the best match of maximum order matrix, calculated by Pearson correlation coefficient
The similitude of each described value matrix and maximum order matrix, obtains two vectors being made of row similitude, then pass through skin
Your inferior related coefficient calculates the similitude of the vector, and the similitude of the vector is value of the current matrix in current signature；
Shown in following matrix, if maximum order matrix and maximum value matrix pattern are the matrixes of n*m, value matrix is k*m
Matrix, and k≤m；K row is selected in the n row of maximum matrix pattern, this k row is used to store the value of k row in value matrix, selects k
Behavior matching；Make the value of formula (1) minimum in all matchings of the best match:
Wherein ai1Indicate first element of the i-th row of maximum value matrix, bi1Indicate the first of the i-th row of value matrix
A element.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
In the above embodiment of the invention, it all emphasizes particularly on different fields to the description of each embodiment, does not have in some embodiment
The part of detailed description, reference can be made to the related descriptions of other embodiments.
In several embodiments provided herein, it should be understood that disclosed technology contents can pass through others
Mode is realized.Wherein, the apparatus embodiments described above are merely exemplary, such as the division of the unit, Ke Yiwei
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of unit or module
It connects, can be electrical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
On unit.It can some or all of the units may be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated unit is realized in the form of SFU software functional unit and sells or use as independent product
When, it can store in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially
The all or part of the part that contributes to existing technology or the technical solution can be in the form of software products in other words
It embodies, which is stored in a storage medium, including some instructions are used so that a computer
Equipment (can for personal computer, server or network equipment etc.) execute each embodiment the method for the present invention whole or
Part steps.And storage medium above-mentioned includes: that USB flash disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
Reservoir (RAM, Random Access Memory), mobile hard disk, magnetic or disk etc. be various to can store program code
Medium.
Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention., rather than its limitations；To the greatest extent
Pipe present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: its according to
So be possible to modify the technical solutions described in the foregoing embodiments, or to some or all of the technical features into
Row equivalent replacement；And these are modified or replaceed, various embodiments of the present invention technology that it does not separate the essence of the corresponding technical solution
The range of scheme.
Claims (5)
1. daily behavior feature mining and calculation method based on frequent Sensor Events sequence characterized by comprising identification
Model training and Activity recognition test two stages；
The identification model training at least includes the following steps:
S1: the biography that resident's daily behavior continuously triggers sequentially in time is acquired by multiple non-invasive sensors of setting
Sensor sequence of events；
S2: pre-processing the collected Sensor Events sequence, described to pre-process the Sensor Events sequence
It is divided into multiple subsequences as unit of daily behavior；
S3: the Sensor Events sequence that Mining Frequent occurs, the feature as resident's daily behavior；
S4: the value of resident's daily behavior characteristically is calculated；
Each Sensor Events meets mode:<trigger sensor, the date of triggering, the time of triggering, and trigger value>；The residence
The Sensor Events of people's daily behavior triggering are recorded by way of text flow；
The Activity recognition test: using the machine learning mode training classifier for having supervision, the classifier pair after training is used
Behavior to be tested is identified.
2. the daily behavior feature mining and calculation method according to claim 1 based on frequent Sensor Events sequence,
It is further characterized in that:
The starting point and end point for the Sensor Events sequence that mark daily behavior is triggered is resident's daily behavior.
3. the daily behavior feature mining and calculation method according to claim 1 based on frequent Sensor Events sequence,
It is further characterized in that:
The Sensor Events sequence that the Mining Frequent occurs is dug by using frequent Sequential Pattern Mining Algorithm PrefixSpan
Dig the frequent sensor sequence mode being hidden in daily behavior.
4. the daily behavior feature mining and calculation method according to claim 1 based on frequent Sensor Events sequence,
It is further characterized in that:
For a daily behavior and a feature, value of the Sensor Events sequence of daily behavior triggering under this feature
Formal definition is a matrix, calculates value of the daily behavior under this feature according to the value of matrix；
Every a line of the value matrix corresponding one meets the Sensor Events subsequence of feature, and the value of every a line is < son
First Sensor Events moment in sequence, second Sensor Events moment ... in subsequence, the last one biography in subsequence
Sensor event time >.
5. the daily behavior feature mining and calculation method according to claim 1 based on frequent Sensor Events sequence,
It is further characterized in that:
For resident's daily behavior feature, the value matrix with maximum order is found out in the value matrix, and then extend
Except the matrix of the value matrix with maximum order, so that the rank of matrix is equal to the maximum order in the value matrix；
It compares one by one and searches for all value matrixes with the best match of maximum order matrix, calculated by Pearson correlation coefficient each
The similitude of a value matrix and maximum order matrix, obtains two vectors being made of row similitude, then pass through Pearson came
Related coefficient calculates the similitude of the vector, and the similitude of the vector is value of the current matrix in current signature；
If maximum order matrix and maximum value matrix pattern are the matrixes of n*m, value matrix is the matrix of k*m, and k≤m；In maximum
K row is selected in the n row of matrix pattern, this k row is used to store the value of k row in value matrix, selects k behavior matching；It is described best
Matching makes the value of formula (1) minimum in all matchings:
Wherein ai1Indicate first element of the i-th row of maximum value matrix, bi1Indicate first member of the i-th row of value matrix
Element.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537184.XA CN109685125A (en) | 2018-12-14 | 2018-12-14 | Daily behavior feature mining and calculation method based on frequent Sensor Events sequence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811537184.XA CN109685125A (en) | 2018-12-14 | 2018-12-14 | Daily behavior feature mining and calculation method based on frequent Sensor Events sequence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109685125A true CN109685125A (en) | 2019-04-26 |
Family
ID=66186117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811537184.XA Pending CN109685125A (en) | 2018-12-14 | 2018-12-14 | Daily behavior feature mining and calculation method based on frequent Sensor Events sequence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109685125A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909047A (en) * | 2019-11-28 | 2020-03-24 | 大连海事大学 | Daily behavior identification method for specified time |
| CN113515554A (en) * | 2020-04-09 | 2021-10-19 | 华晨宝马汽车有限公司 | Anomaly detection method and system for irregularly sampled time series |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090210090A1 (en) * | 2008-02-18 | 2009-08-20 | Toyota Motor Engineering & Manufacturing North America, Inc. | Robotic system and method for observing, learning, and supporting human activities |
| US20140219373A1 (en) * | 2011-02-01 | 2014-08-07 | Research In Motion Limited | Mixed rank downlink compound multi-user interference alignment scheme |
| US20150373132A1 (en) * | 2014-06-19 | 2015-12-24 | Samsung Electronics Co., Ltd. | Sequential behavior-based content delivery |
| US9262446B1 (en) * | 2005-12-29 | 2016-02-16 | Google Inc. | Dynamically ranking entries in a personal data book |
| JP2016129295A (en) * | 2015-01-09 | 2016-07-14 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
| CN106651770A (en) * | 2016-09-19 | 2017-05-10 | 西安电子科技大学 | Method for reconstructing multispectral super-resolution imaging based on Lapras norm regularization |
| US20170351786A1 (en) * | 2016-06-02 | 2017-12-07 | Xerox Corporation | Scalable spectral modeling of sparse sequence functions via a best matching algorithm |
| CN107609469A (en) * | 2017-07-28 | 2018-01-19 | 北京建筑大学 | Community network association user method for digging and system |
| CN107807860A (en) * | 2017-10-12 | 2018-03-16 | 国网湖南节能服务有限公司 | A kind of power fault analysis method and system based on matrix decomposition |
-
2018
- 2018-12-14 CN CN201811537184.XA patent/CN109685125A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9262446B1 (en) * | 2005-12-29 | 2016-02-16 | Google Inc. | Dynamically ranking entries in a personal data book |
| US20090210090A1 (en) * | 2008-02-18 | 2009-08-20 | Toyota Motor Engineering & Manufacturing North America, Inc. | Robotic system and method for observing, learning, and supporting human activities |
| US20140219373A1 (en) * | 2011-02-01 | 2014-08-07 | Research In Motion Limited | Mixed rank downlink compound multi-user interference alignment scheme |
| US20150373132A1 (en) * | 2014-06-19 | 2015-12-24 | Samsung Electronics Co., Ltd. | Sequential behavior-based content delivery |
| JP2016129295A (en) * | 2015-01-09 | 2016-07-14 | キヤノン株式会社 | Information processing apparatus, information processing method, and program |
| US20170351786A1 (en) * | 2016-06-02 | 2017-12-07 | Xerox Corporation | Scalable spectral modeling of sparse sequence functions via a best matching algorithm |
| CN106651770A (en) * | 2016-09-19 | 2017-05-10 | 西安电子科技大学 | Method for reconstructing multispectral super-resolution imaging based on Lapras norm regularization |
| CN107609469A (en) * | 2017-07-28 | 2018-01-19 | 北京建筑大学 | Community network association user method for digging and system |
| CN107807860A (en) * | 2017-10-12 | 2018-03-16 | 国网湖南节能服务有限公司 | A kind of power fault analysis method and system based on matrix decomposition |
Non-Patent Citations (6)
| Title |
|---|
| ALAA ALHAMOUD 等: "Extracting Human Behavior Patterns from Appliance-level Power Consumption Data", 《EUROPEAN CONFERENCE ON WIRELESS SENSOR NETWORKS》 * |
| RONG CHEN 等: "An activity of daily living primitive-based recognition framework for smart homes with discrete sensor data", 《INTERNATIONAL JOURNAL OF DISTRIBUTED SENSOR NETWORKS》 * |
| WEN J 等: "Activity recognition with weighted frequent patterns mining in smart environments", 《EXPERT SYSTEM AND APPLICATION》 * |
| 姬浩博 等: "一种基于频繁传感器事件序列的日常行为特征挖掘及计算方法", 《计算机科学》 * |
| 曾月迪 等: "3-幂零矩阵Jordan规范型的计数", 《莆田学院学报》 * |
| 李博: "基于场景外观建模的移动机器人视觉闭环检测研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110909047A (en) * | 2019-11-28 | 2020-03-24 | 大连海事大学 | Daily behavior identification method for specified time |
| CN113515554A (en) * | 2020-04-09 | 2021-10-19 | 华晨宝马汽车有限公司 | Anomaly detection method and system for irregularly sampled time series |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mukti et al. | Transfer learning based plant diseases detection using ResNet50 | |
| KR102451795B1 (en) | ECG signal detection method | |
| Wang et al. | Sensorygans: An effective generative adversarial framework for sensor-based human activity recognition | |
| US9122994B2 (en) | Apparatus and methods for temporally proximate object recognition | |
| JP5359414B2 (en) | Action recognition method, apparatus, and program | |
| CN110472604A (en) | A kind of pedestrian based on video and crowd behaviour recognition methods | |
| WO2018162929A1 (en) | Image analysis using neural networks for pose and action identification | |
| CN109685125A (en) | Daily behavior feature mining and calculation method based on frequent Sensor Events sequence | |
| CN105559754B (en) | A kind of sleep disordered breathing detection method and device based on heart rate and breath signal | |
| CN112508110A (en) | Deep learning-based electrocardiosignal graph classification method | |
| CN108108662A (en) | Deep neural network identification model and recognition methods | |
| WO2012162658A1 (en) | Apparatus and methods for polychronous encoding and multiplexing in neuronal prosthetic devices | |
| CN110495877A (en) | A kind of Multi resolution feature extraction method and device based on ECG | |
| CN110367967A (en) | A kind of pocket lightweight human brain condition detection method based on data fusion | |
| CN109497997A (en) | Based on majority according to the seizure detection and early warning system of acquisition | |
| CN114732361A (en) | Sleep stage prediction method and device based on physiological signals and storage medium | |
| Polepalli et al. | Digital neuromorphic design of a liquid state machine for real-time processing | |
| CN104268601B (en) | A kind of method and device for obtaining body state | |
| CN114469120A (en) | Multi-scale Dtw-BiLstm-Gan electrocardiosignal generation method based on similarity threshold migration | |
| CN109740418B (en) | Yoga action identification method based on multiple acceleration sensors | |
| Rahman et al. | Imputation of missing values in time series with lagged correlations | |
| Arvaneh et al. | Mutual information-based optimization of sparse spatio-spectral filters in brain–computer interface | |
| Varalakshmi et al. | An improved hybrid AI model for prediction of arrhythmia using ECG signals | |
| CN109918996A (en) | The illegal action identification method of personnel, system, computer equipment and storage medium | |
| CN116401598B (en) | Sleep apnea detection method and device based on physiological signals |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190426 |
|
| RJ01 | Rejection of invention patent application after publication |