CN113378682A - Millimeter wave radar fall detection method and system based on improved clustering algorithm - Google Patents
Millimeter wave radar fall detection method and system based on improved clustering algorithm Download PDFInfo
- Publication number
- CN113378682A CN113378682A CN202110619716.XA CN202110619716A CN113378682A CN 113378682 A CN113378682 A CN 113378682A CN 202110619716 A CN202110619716 A CN 202110619716A CN 113378682 A CN113378682 A CN 113378682A
- Authority
- CN
- China
- Prior art keywords
- data
- clustering
- sample
- improved
- clustering algorithm
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
The invention discloses a millimeter wave radar fall detection method and system based on an improved clustering algorithm, which are used for collecting action scene data of a detected person; preprocessing the action scene data of the detected person to obtain a data sample; setting k clustering centers according to different data types; performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm; acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state. The invention provides a millimeter wave fall detection radar data analysis and processing method based on a K clustering algorithm, which greatly improves the accuracy of data classification.
Description
Technical Field
The invention relates to the technical field of millimeter wave radar fall detection, in particular to a millimeter wave radar fall detection method and system based on an improved clustering algorithm.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The tumble detection method based on the wearable device is a research hotspot of current domestic and foreign medical institutions and scientific research institutions, but the method has the defects of poor wearing comfort, difficulty in equipment cleaning and the like, and tumble detection based on a video method is not beneficial to privacy protection in places such as washrooms, bedrooms and the like, the application range is limited, and the like. Vital sign echo signals are very weak and are often submerged in clutter such as strong environmental noise, but how to realize the fall detection of old people based on radar echo is a technical problem which needs to be solved urgently at present.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a millimeter wave radar fall detection method and system based on an improved clustering algorithm;
in a first aspect, the invention provides a millimeter wave radar fall detection method based on an improved clustering algorithm;
a millimeter wave radar fall detection method based on an improved clustering algorithm comprises the following steps:
collecting action scene data of detected personnel;
preprocessing the action scene data of the detected person to obtain a data sample;
setting k clustering centers according to different data types;
performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
In a second aspect, the invention provides a millimeter wave radar fall detection system based on an improved clustering algorithm;
millimeter wave radar fall detection system based on improved clustering algorithm includes:
an acquisition module configured to: collecting action scene data of detected personnel;
a pre-processing module configured to: preprocessing the action scene data of the detected person to obtain a data sample;
a cluster center number setting module configured to: setting k clustering centers according to different data types;
a clustering module configured to: performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
a fall detection module configured to: acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
Compared with the prior art, the invention has the beneficial effects that:
the invention provides a millimeter wave fall detection radar data analysis and processing method based on a K clustering algorithm, which greatly improves the accuracy of data classification.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a flow chart of the method of the first embodiment.
Detailed Description
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise, and it should be understood that the terms "comprises" and "comprising", and any variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
The K-means algorithm is a classical algorithm for solving the clustering problem, is simple and quick, has a good clustering result when a structure set is dense and the difference between clusters is obvious, has high scalability and high efficiency when processing a large amount of data, but has a plurality of defects in the traditional K-means algorithm at present and needs to be further optimized.
(1) Many times, when clustering a data set, the user initially does not know how many classes the data set should be classified as appropriate, and the K value is difficult to estimate.
(2) The method of randomly selecting the initial clustering centers causes instability of an algorithm and is likely to fall into a locally optimal condition.
(3) The K-Means algorithm is sensitive to noise and isolated point data, the mass center of a cluster is taken as a cluster center and added to the next round of calculation, so that a small amount of data can greatly influence the average value, and results are unstable and even wrong.
(4) Because the K-Means algorithm mainly adopts the Euclidean distance function to measure the similarity between data objects, and adopts the sum of squares of errors as a criterion function, only spherical clusters with more uniform distribution of the data objects can be usually found.
Example one
The embodiment provides a millimeter wave radar fall detection method based on an improved clustering algorithm;
as shown in fig. 1, the millimeter wave radar fall detection method based on the improved clustering algorithm includes:
s101: collecting action scene data of detected personnel;
s102: preprocessing the action scene data of the detected person to obtain a data sample;
s103: setting k clustering centers according to different data types;
s104: performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
s105: acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
Further, in S101, acquiring the action scene data of the detected person specifically includes:
two paths of original digital signals I (t) and Q (t) are collected through a radar sensor, and the two paths of signals are orthogonal.
Further, in the step S102, the detected person action scene data is preprocessed to obtain sample data; the method specifically comprises the following steps:
processing two paths of original digital signals I (t) and Q (t) to obtain a signal A (t);
wherein, I (t) and Q (t) are collected original data, N is the digit of the digital signal, and N is the Fourier transform point number;
then, fast Fourier transform is carried out on the signal A (t) to obtain an N/2 frequency domain signal A (f);
according to a frequency threshold f1And f2The frequency domain signals A (f) are intercepted and then accumulated according to the Doppler direction
According to a frequency threshold f3And f4The frequency domain signals A (f) are intercepted and then accumulated according to the Doppler direction
And so on according to the frequency threshold fiAnd fjThe frequency domain signals A (f) are intercepted and then accumulated according to the Doppler directionj ═ i + 1; i is an odd number and j is an even number; i is an odd number of 5 or more;
acquiring action scene data of a detected person, and processing the action scene data through the steps S101 and S102 to obtain a data sample x;
data sample X containing P objects X ═ X1,x2,x3,...,xPEach object has attributes of m dimensions, m is greater than or equal to 2, and attribute data comprisesAndbut are not limited to these two attributes.
Further, the step S103: setting k clustering centers according to different data types; the method specifically comprises the following steps:
dividing k clustering centers according to different data types1,c2,c3,...,ck},5≤k<p; when k is 5, the detected person action scene data comprises: the combination of five states of free movement without falling, rapid falling on the ground without movement, sitting on a chair without movement, standing without movement and falling on the ground and then rising;
alternatively, the value k is determined according to a combination of types of sample data, where the sample data includes R different action types, and k is R.
Further, the S104: performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; the method specifically comprises the following steps:
s1041: carrying out normalization processing on the data samples;
s1042: initializing a first clustering center according to a first-order difference absolute value;
s1043: calculating the distance between each object in the sample and the existing cluster center;
s1044: calculating the probability of each object in the sample becoming the next clustering center;
s1045: and repeating the steps S1043 and S1044 until the number of the selected clustering centers reaches the required number k and the convergence function value reaches the minimum value.
Further, the S1041: carrying out normalization processing on the data samples; the method specifically comprises the following steps:
wherein x isiIs the ith data sample; x is the number ofminIs the minimum value, x, in the sample datamaxIs the maximum value in the sample data, and all normalized sample data x 'after being processed by formula (1)'iAre all in [0,1 ]]Within the range.
Further, the S1042: initializing a first cluster center according to a first order difference absolute value:
Δx′i=x′i-x′i+1 (2)
wherein, x'iIs the ith data, x 'in the normalized sample'i+1Is the i +1 th data, Δ x 'in the normalized sample'iThe difference between the ith data in the normalized sample and the (i + 1) th data in the normalized sample is defined as the first order difference of the normalized sample.
Uj=min(|Δx′j|)=min|xj′-x′j+1| (3)
Wherein, min (| delta x'jL) is Δ x'jIs the minimum of the absolute value of (a).
Selecting x with minimum absolute value of first order differencej' as initial clustering center c1:
c1=xj′ (4)
Further, the step S1043: calculating the distance D (x) between each object in the sample and the center of the existing clusterij):
D(xij)=|xj′-ci| (5)
Further, the S1044: calculating the probability P that each object in the sample becomes the next cluster center:
wherein the content of the first and second substances,for each object xj' and clustering center ciThe sum of squares of the differences is carried out, and the highest probability is selected as the next clustering center;
further, the S1045: repeating S1043 and S1044 until the number of the selected clustering centers reaches the required number k and the convergence function value reaches the minimum value;
further, the step S105: taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state; when k is 5, the behavioral states include: free movement without falling, rapid falling on the ground without movement, sitting on a chair without movement, standing without movement and falling on the ground and then rising, wherein five clustering centers are respectively free movement c1Quickly fall down c2Fixed on the chair c3Standing still c4And standing up after falling down c5。
Example two
The embodiment provides a millimeter wave radar fall detection system based on an improved clustering algorithm;
millimeter wave radar fall detection system based on improved clustering algorithm includes:
an acquisition module configured to: collecting action scene data of detected personnel;
a pre-processing module configured to: preprocessing the action scene data of the detected person to obtain a data sample;
a cluster center number setting module configured to: setting k clustering centers according to different data types;
a clustering module configured to: performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
a fall detection module configured to: acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
It should be noted here that the above-mentioned acquisition module, preprocessing module, cluster center number setting module, clustering module and fall detection module correspond to steps S101 to S105 in the first embodiment, and the above-mentioned modules are the same as the corresponding steps in the implementation example and application scenario, but are not limited to the contents disclosed in the first embodiment.
The proposed system can be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the above-described modules is merely a logical division, and in actual implementation, there may be other divisions, for example, multiple modules may be combined or integrated into another system, or some features may be omitted, or not executed.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A millimeter wave radar fall detection method based on an improved clustering algorithm is characterized by comprising the following steps:
collecting action scene data of detected personnel;
preprocessing the action scene data of the detected person to obtain a data sample;
setting k clustering centers according to different data types;
performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
2. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 1, wherein the collecting of the action scene data of the detected person specifically comprises:
two paths of original digital signals I (t) and Q (t) are collected through a radar sensor, and the two paths of signals are orthogonal.
3. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 1, wherein the data of the action scene of the person to be detected is preprocessed to obtain sample data; the method specifically comprises the following steps:
processing two paths of original digital signals I (t) and Q (t) to obtain a signal A (t);
wherein, I (t) and Q (t) are collected original data, N is the digit of the digital signal, and N is the Fourier transform point number;
then, fast Fourier transform is carried out on the signal A (t) to obtain an N/2 frequency domain signal A (f);
according to a frequency threshold f1And f2The frequency domain signals A (f) are intercepted and then accumulated according to the Doppler direction
According to a frequency threshold f3And f4The frequency domain signals A (f) are intercepted and then accumulated according to the Doppler direction
And so on according to the frequency threshold fiAnd fjThe frequency domain signals A (f) are intercepted and then accumulated according to the Doppler directioni is an odd number and j is an even number; i is an odd number of 5 or more;
and acquiring action scene data of the detected person, and processing the data to obtain a data sample x.
4. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 1, wherein k clustering centers are set according to different data types; the method specifically comprises the following steps:
dividing k clustering centers according to different data types1,c2,c3,...,ck},5≤k<p; when k is 5, the detected person action scene data comprises: the combination of five states of free movement without falling, rapid falling on the ground without movement, sitting on a chair without movement, standing without movement and falling on the ground and then rising;
alternatively, the value k is determined according to a combination of types of sample data, where the sample data includes R different action types, and k is R.
5. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 1, wherein the data samples are clustered based on the improved clustering algorithm according to the set k clustering centers; the method specifically comprises the following steps:
(1): carrying out normalization processing on the data samples;
(2): initializing a first clustering center according to a first-order difference absolute value;
(3): calculating the distance between each object in the sample and the existing cluster center;
(4): calculating the probability of each object in the sample becoming the next clustering center;
(5): and (4) repeating the steps (3) and (4) until the number of the selected clustering centers reaches the required k, and the convergence function value reaches the minimum value.
6. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 5, wherein the data samples are normalized; the method specifically comprises the following steps:
wherein x isiIs the ith data sample; x is the number ofminIs the minimum value, x, in the sample datamaxIs the maximum value in the sample data, and all normalized sample data x 'after being processed by formula (1)'iAre all in [0,1 ]]Within the range.
7. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 5, wherein the first clustering center is initialized according to the first order difference absolute value:
Δx′i=x′i-x′i+1 (2)
wherein, x'iIs the ith data, x 'in the normalized sample'i+1Is the i +1 th data, Δ x 'in the normalized sample'iThe difference value of the ith data in the normalized sample and the (i + 1) th data in the normalized sample is defined as the first-order difference of the normalized sample;
Uj=min(|Δx′j|)=min|xj′-x′j+1| (3)
wherein, min (| delta x'jL) is Δ x'jThe minimum of the absolute values of (a);
selecting x with minimum absolute value of first order differencej' as initial clustering center c1:
c1=xj′ (4)。
8. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 5, wherein the distance D (x) between each object in the sample and the existing clustering center is calculatedij):
D(xij)=|xj′-ci| (5)。
9. The millimeter wave radar fall detection method based on the improved clustering algorithm as claimed in claim 5, wherein the probability P that each object in the sample becomes the next clustering center is calculated:
wherein the content of the first and second substances,for each object xj' and clustering center ciThe sum of squares of the differences is carried out, and the highest probability is selected as the next clustering center;
repeating (3) and (4) until the number of the selected clustering centers reaches the required k, and the convergence function value reaches the minimum value:
10. millimeter wave radar fall detection system based on improved clustering algorithm includes:
an acquisition module configured to: collecting action scene data of detected personnel;
a pre-processing module configured to: preprocessing the action scene data of the detected person to obtain a data sample;
a cluster center number setting module configured to: setting k clustering centers according to different data types;
a clustering module configured to: performing clustering processing on the data samples based on an improved clustering algorithm according to set k clustering centers; initializing a first clustering center according to a first-order difference absolute value based on an improved clustering algorithm;
a fall detection module configured to: acquiring new action scene data of the detected person, and calculating the distance between the new action scene data and the k clustering centers; and taking the category label of the clustering center corresponding to the minimum distance value as a falling detection state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110619716.XA CN113378682B (en) | 2021-06-03 | 2021-06-03 | Millimeter wave radar fall detection method and system based on improved clustering algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110619716.XA CN113378682B (en) | 2021-06-03 | 2021-06-03 | Millimeter wave radar fall detection method and system based on improved clustering algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113378682A true CN113378682A (en) | 2021-09-10 |
CN113378682B CN113378682B (en) | 2023-04-07 |
Family
ID=77575638
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110619716.XA Active CN113378682B (en) | 2021-06-03 | 2021-06-03 | Millimeter wave radar fall detection method and system based on improved clustering algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113378682B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113892945A (en) * | 2021-12-09 | 2022-01-07 | 森思泰克河北科技有限公司 | Multi-radar association control method and control device in health monitoring system |
CN115372963A (en) * | 2022-10-24 | 2022-11-22 | 北京清雷科技有限公司 | Fall-down behavior multi-level detection method and device based on millimeter wave radar signals |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469611A (en) * | 2015-12-24 | 2016-04-06 | 大连理工大学 | Short-term traffic flow prediction model method |
CN108446802A (en) * | 2018-03-23 | 2018-08-24 | 上海海洋大学 | A kind of red tide prewarning method based on graph model structure |
CN109063769A (en) * | 2018-08-01 | 2018-12-21 | 济南大学 | Clustering method, system and the medium of number of clusters amount are automatically confirmed that based on the coefficient of variation |
CN109171738A (en) * | 2018-07-13 | 2019-01-11 | 杭州电子科技大学 | Fall detection method based on human body acceleration multiple features fusion and KNN |
CN109669990A (en) * | 2018-11-16 | 2019-04-23 | 重庆邮电大学 | A kind of innovatory algorithm carrying out Outliers mining to density irregular data based on DBSCAN |
CN109684673A (en) * | 2018-12-03 | 2019-04-26 | 三峡大学 | A kind of feature extraction and clustering method of electric power system transient stability result |
CN111166341A (en) * | 2020-01-06 | 2020-05-19 | 华东理工大学 | Tumble identification method based on acceleration impact energy clustering and wearable system |
CN111175743A (en) * | 2020-02-25 | 2020-05-19 | 山东省科学院自动化研究所 | Old people falling alarm platform and method based on Doppler radar technology |
CN112633059A (en) * | 2020-11-12 | 2021-04-09 | 泰州职业技术学院 | Falling remote monitoring system based on LabVIEW and MATLAB |
-
2021
- 2021-06-03 CN CN202110619716.XA patent/CN113378682B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105469611A (en) * | 2015-12-24 | 2016-04-06 | 大连理工大学 | Short-term traffic flow prediction model method |
CN108446802A (en) * | 2018-03-23 | 2018-08-24 | 上海海洋大学 | A kind of red tide prewarning method based on graph model structure |
CN109171738A (en) * | 2018-07-13 | 2019-01-11 | 杭州电子科技大学 | Fall detection method based on human body acceleration multiple features fusion and KNN |
CN109063769A (en) * | 2018-08-01 | 2018-12-21 | 济南大学 | Clustering method, system and the medium of number of clusters amount are automatically confirmed that based on the coefficient of variation |
CN109669990A (en) * | 2018-11-16 | 2019-04-23 | 重庆邮电大学 | A kind of innovatory algorithm carrying out Outliers mining to density irregular data based on DBSCAN |
CN109684673A (en) * | 2018-12-03 | 2019-04-26 | 三峡大学 | A kind of feature extraction and clustering method of electric power system transient stability result |
CN111166341A (en) * | 2020-01-06 | 2020-05-19 | 华东理工大学 | Tumble identification method based on acceleration impact energy clustering and wearable system |
CN111175743A (en) * | 2020-02-25 | 2020-05-19 | 山东省科学院自动化研究所 | Old people falling alarm platform and method based on Doppler radar technology |
CN112633059A (en) * | 2020-11-12 | 2021-04-09 | 泰州职业技术学院 | Falling remote monitoring system based on LabVIEW and MATLAB |
Non-Patent Citations (3)
Title |
---|
邹志文 等: "基于k-means++的动态构建空间主题R树方法", 《计算机应用》 * |
郭金鑫: "基于三维视觉的人体跌倒检测技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
马宗方 等: "基于聚类和超限学习机分类模型的跌倒检测算法", 《济南大学学报(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113892945A (en) * | 2021-12-09 | 2022-01-07 | 森思泰克河北科技有限公司 | Multi-radar association control method and control device in health monitoring system |
CN113892945B (en) * | 2021-12-09 | 2022-04-01 | 森思泰克河北科技有限公司 | Multi-radar association control method and control device in health monitoring system |
CN115372963A (en) * | 2022-10-24 | 2022-11-22 | 北京清雷科技有限公司 | Fall-down behavior multi-level detection method and device based on millimeter wave radar signals |
CN115372963B (en) * | 2022-10-24 | 2023-03-14 | 北京清雷科技有限公司 | Fall-down behavior multi-level detection method and equipment based on millimeter wave radar signals |
Also Published As
Publication number | Publication date |
---|---|
CN113378682B (en) | 2023-04-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113378682B (en) | Millimeter wave radar fall detection method and system based on improved clustering algorithm | |
Comaniciu et al. | Distribution free decomposition of multivariate data | |
Naz et al. | Image segmentation using fuzzy clustering: A survey | |
CN110412548B (en) | Radar multi-target recognition method based on high-resolution one-dimensional range profile | |
US8953877B2 (en) | Noise estimation for images | |
Mukherjee et al. | Bacterial colony counting using distance transform | |
Saraswathi et al. | Survey on image segmentation via clustering | |
WO2011088520A1 (en) | Identifying matching images | |
CN112508963B (en) | SAR image segmentation method based on fuzzy C-means clustering | |
Hall et al. | A two step approach for semi-automated particle selection from low contrast cryo-electron micrographs | |
Heymann et al. | Outskewer: Using skewness to spot outliers in samples and time series | |
CN114004987A (en) | Face clustering method, electronic device and storage medium | |
Morlini et al. | A new class of weighted similarity indices using polytomous variables | |
CN103839072B (en) | False fingerprint detecting method based on naive Bayes classifiers | |
Lv et al. | Density peaks clustering based on geodetic distance and dynamic neighbourhood | |
CN115273170A (en) | Image clustering method, device, equipment and computer readable storage medium | |
CN110796164A (en) | Method and system for determining cluster number of data cluster, electronic device and storage medium | |
CN112836747A (en) | Eye movement data outlier processing method and device, computer equipment and storage medium | |
CN111652239B (en) | Method and system for evaluating contribution degree of image local features to overall features | |
Bompais et al. | The p-value as a new similarity function for spectral clustering in sensor networks | |
Zhang et al. | Segmentation-based Euler number with multi-levels for image feature description | |
CN113447928B (en) | False alarm rate reduction target identification method and system based on synthetic aperture radar | |
CN110728665A (en) | SAR image change detection method based on parallel probabilistic neural network | |
CN111882003B (en) | Data classification method, device and equipment | |
CN110309382B (en) | Mobile application homology edge clustering method based on multi-dimensional features |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |