CN105138530A - Automatic music matching method and apparatus and electronic apparatus applying same - Google Patents

Automatic music matching method and apparatus and electronic apparatus applying same Download PDF

Info

Publication number
CN105138530A
CN105138530A CN201510342269.2A CN201510342269A CN105138530A CN 105138530 A CN105138530 A CN 105138530A CN 201510342269 A CN201510342269 A CN 201510342269A CN 105138530 A CN105138530 A CN 105138530A
Authority
CN
China
Prior art keywords
heart rate
coarse
index
rate signal
music
Prior art date
Application number
CN201510342269.2A
Other languages
Chinese (zh)
Other versions
CN105138530B (en
Inventor
刘冬冬
张博
杨晓文
Original Assignee
刘冬冬
张博
杨晓文
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 刘冬冬, 张博, 杨晓文 filed Critical 刘冬冬
Priority to CN201510342269.2A priority Critical patent/CN105138530B/en
Publication of CN105138530A publication Critical patent/CN105138530A/en
Application granted granted Critical
Publication of CN105138530B publication Critical patent/CN105138530B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/02Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024Detecting, measuring or recording pulse rate or heart rate
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/24Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316Modalities, i.e. specific diagnostic methods
    • A61B5/318Heart-related electrical modalities, e.g. electrocardiogaphy [ECG]
    • GPHYSICS
    • G06COMPUTING; CALCULATING; COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/60Information retrieval; Database structures therefor; File system structures therefor of audio data
    • G06F16/63Querying
    • G06F16/635Filtering based on additional data, e.g. user or group profiles
    • G06F16/636Filtering based on additional data, e.g. user or group profiles by using biological or physiological data

Abstract

Disclosed are an automatic music matching method and apparatus and an electronic apparatus applying the same. A heart rate signal is decomposed according to a frequency range, frequency composition and sample entropy of the heart rate signal are analyzed, a calibration index representing a current emotional status of a human body is finally calculated, and the calibration index is matched with a long range correlation index representing sound intensity distribution of music, so that a matched music file can be automatically selected and played according to a physiological status of the human body and the accuracy of music matching is improved.

Description

Its electronic installation of automatic music matching process, device and application
Technical field
The present invention relates to biologic medical engineering field, be specifically related to its electronic installation of a kind of automatic music matching process, device and application.
Background technology
Heart rate signal (also satisfactory electrograph, electrocardiogram, ECG) be heart in each cardiac cycle, in succession excited by pacemaker, atrium, ventricle, along with bioelectric change, drawn the figure of the potential change of various ways from body surface by electrocardiograph.Cardiogram is the objective indicator of the generation of cardiac excitation, propagation and rejuvenation.The action potential configuration that the relation Cardiomyocytes excitation time of each ripple of cardiogram and myocardial action potential is traced and the cardiogram traced each cardiac cycle have marked difference.
Music is the combination of sound, and human body produces corresponding reaction for concert.Suitable music can improve corticocerebral excitability, can be used for the mood improving people, excites the emotion of people, rouses oneself the spirit etc. of people.When human body to receive in external environment condition specifically stimulate (sound, light etc.) time, health can produce certain change and response, and correspondence makes heart rate that certain change can occur.Human body is different for the response of music when being in different physiological statuss.And the selection of music for adjusting human body mood or physiological status usually need tool veteran rule of thumb evaluation object current state carry out again later.
Thus, need badly a kind of can based on computer technology automatically to the method that Human Physiology/emotional state and music are mated.
Summary of the invention
In view of this, the invention provides its electronic installation of a kind of automatic music matching process, device and application.
First aspect, provides a kind of automatic music matching process, comprising:
Obtain the heart rate signal of human body;
Described heart rate signal is divided into the discrete subsignal that K is distributed in different frequency scope;
With T different time scale, coarse is carried out to obtain the time series of K*T coarse to each described subsignal respectively;
Sample Entropy is calculated to the time series of each coarse;
The calibration index of described heart rate signal is obtained according to described Sample Entropy;
Choose the music file with the long-range index of correlation matched to play according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
Preferably, described heart rate signal being divided into K the discrete subsignal being distributed in different frequency scope is: carry out WAVELET PACKET DECOMPOSITION to obtain the subsignal that K is distributed in different frequency scope to heart rate signal.
Preferably, described the time series that coarse comprises coarse according to following formulae discovery is carried out to each described subsignal:
E f ( τ ) ( j ) = 1 τ Σ i = ( j - 1 ) τ + 1 j τ E f ( i ) ( 1 ≤ j ≤ N / τ )
Wherein, E f(i), i=1,2 ..., N is described subsignal, and N is described subsignal length, τ=1,2 ..., M is time scale factor, for the time series of coarse.
Preferably, the described calibration index obtaining described heart rate signal according to described Sample Entropy comprises:
For each time scale, there is under obtaining this time scale the time series of the coarse of maximum Sample Entropy;
Centre frequency corresponding to all time serieses with the coarse of maximum Sample Entropy and time scale calculate described calibration index.
Preferably, the centre frequency corresponding to all time serieses with the coarse of maximum Sample Entropy and time scale calculate described calibration index and comprise calibrate index according to following formulae discovery:
α = ∫ τ = 1 M f ( τ )
Wherein, α is described calibration index, and f (τ) is all curvilinear function of seasonal effect in time series centre frequency relative to time scale matching acquisition in T/F plane with the coarse of maximum Sample Entropy.
Preferably, the music file choosing the long-range index of correlation had and match according to described calibration index carries out broadcasting and comprises:
Choose the corresponding long-range index of correlation to play closest to the music file of predetermined value with the difference or ratio of calibrating index.
Preferably, the described long-range index of correlation is according to such as under type calculating acquisition:
The Serial No. of music file is obtained by sampling;
Carry out non-overlapping movement with the first window width to described Serial No. and calculate standard deviation, obtain standard deviation sequence, described first window width is predetermined value;
Square corresponding average loudness of a sound is calculated to obtain average loudness of a sound sequence according to standard deviation each in standard deviation sequence;
Volatility series is obtained based on following formula: wherein, Z bfor b element of described volatility series, v j 2for a jth element of described average loudness of a sound sequence, L is the length of described Serial No., and w is described default window width;
To have described volatility series according to the second window width with predetermined overlap length and overlapping move window, to obtain multiple subsequence;
Linear regression is utilized to obtain the linear trend of each described subsequence;
Trend wave function is removed based on following formulae discovery:
wherein, F dtrend wave function is removed for described, for subsequence element z bcorresponding linear trend, <> is average function, for the second window width w vmove the quadratic sum that the element of all subsequences that window obtains deducts the value of corresponding linear trend to ask on average.
The described long-range index of correlation is calculated according to the described relation between the time scale corresponding to trend wave function and the second window width of going.
Second aspect, provides a kind of automatic music coalignment, comprising:
Heart rate acquiring unit, for obtaining the heart rate signal of human body;
Frequency partition unit, for being divided into the subsignal that K is distributed in different frequency scope by described heart rate signal;
Coarse unit, for carrying out coarse to obtain the time series of K*T coarse with T different time scale to each described subsignal respectively;
Sample Entropy computing unit, for calculating Sample Entropy to the time series of each coarse;
Calibration index acquiring unit, for obtaining the calibration index of described heart rate signal according to described Sample Entropy;
Music matching unit, play for choosing the music file with the long-range index of correlation matched according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
The third aspect, provides a kind of electronic installation, comprising:
Heart rate detection parts, for the heart rate signal of human body;
Memory storage, for storing predetermined music file and the long-range index of correlation corresponding to each music file;
Playing device, for playing music;
Control device, is configured to be suitable for performing as given an order:
Obtain the heart rate signal of human body;
Described heart rate signal is divided into the subsignal that K is distributed in different frequency scope;
With T different time scale, coarse is carried out to obtain the time series of K*T coarse to each described subsignal respectively;
Sample Entropy is calculated to the time series of each coarse;
The calibration index of described heart rate signal is obtained according to described Sample Entropy;
Choose the music file with the long-range index of correlation matched to play according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
By decomposing by frequency range heart rate signal, and analyze its frequency formation and sample entropy, the final calibration index calculating acquisition sign current human emotional state, the long-range index of correlation distributed based on calibration index and sign music loudness of a sound is mated, can automatically select the music file of coupling to play according to human body physiological state, improve the accuracy of music coupling.
Accompanying drawing explanation
By referring to the description of accompanying drawing to the embodiment of the present invention, above-mentioned and other objects, features and advantages of the present invention will be more clear, in the accompanying drawings:
Fig. 1 is the structural representation of the electronic installation of the embodiment of the present invention;
Fig. 2 is the process flow diagram of the automatic music matching process of the embodiment of the present invention;
Fig. 3 is the process flow diagram of the long-range index of correlation of the calculating music file of the embodiment of the present invention;
Fig. 4 is the typical structure schematic diagram of the control device of the embodiment of the present invention;
Fig. 5 is the structural representation of the automatic music coalignment of the embodiment of the present invention.
Embodiment
Based on embodiment, present invention is described below, but the present invention is not restricted to these embodiments.In hereafter details of the present invention being described, detailedly describe some specific detail sections.Do not have the description of these detail sections can understand the present invention completely for a person skilled in the art yet.In order to avoid obscuring essence of the present invention, known method, process, flow process, element and circuit do not describe in detail.
In addition, it should be understood by one skilled in the art that the accompanying drawing provided at this is all for illustrative purposes, and accompanying drawing is not necessarily drawn in proportion.
Meanwhile, should be appreciated that in the following description, " circuit " refers to the galvanic circle connected and composed by electrical connection or electromagnetism by least one element or electronic circuit.When " being connected to " another element when claiming element or circuit or claiming element/circuit " to be connected to " between two nodes, it can be directly couple or be connected to another element or can there is intermediary element, the connection between element can be physically, in logic or its combine.On the contrary, " be directly coupled to " when claiming element or " being directly connected to " another element time, mean that both do not exist intermediary element.
Unless the context clearly requires otherwise, similar words such as " comprising ", " comprising " otherwise in whole instructions and claims should be interpreted as the implication that comprises instead of exclusive or exhaustive implication; That is, be the implication of " including but not limited to ".
In describing the invention, it is to be appreciated that term " first ", " second " etc. are only for describing object, and instruction or hint relative importance can not be interpreted as.In addition, in describing the invention, except as otherwise noted, the implication of " multiple " is two or more.
For human body, sympathetic activation can cause that abdominal viscera and skin peripheral vessel shrink, heartbeat is strengthened and accelerate, metabolism is hyperfunction, mydriasis, tired muscular work ability increase etc.Physiological requirements during orthosympathetic activity principal security human body tense situation.Vagus nerve/parasympathetic nerve excitation time, bradycardia weakens; Bronchial smooth muscle shrinks; Gastrointestinal motility strengthens the secretion promoting digestive juice; Myosis etc.Parasympathetic activity means that people is in a comparatively tranquil state.
Medically verified to the research of Autonomic nervous system activity, the high fdrequency component of vagal movable major effect HRV, the low frequency component of orthosympathetic movable major effect heart rate.Therefore, heart rate variability analysis can reflect sympathetic nerve and vagal stirring conditions and tension variation.Usually, find sinus arrhythmia phenomenon during Electrocardioscopy, sinus arrhythmia is without clinical meaning, because the origin of Healthy People sinus rhythm does not become usually, produces the rhythm and pace of moving things not whole mainly relevant with the cycle of breathing, accelerates, slow down during expiration during air-breathing.
But HRV is a very unstable index, is subject to the factor impacts such as body gesture, psychology and environment.The present invention is based on above principle and carry out heart rate signal analysis, judge the state of human body, thus automatically carry out music coupling.
Fig. 1 is the structural representation of the electronic installation of the embodiment of the present invention.As shown in Figure 1, electronic installation 1 comprises heart rate detection parts 11, memory storage 12, playing device 13 and control device 14.
Heart rate detection parts 11 are for the heart rate signal of human body.It can be various electrocardioscanner, as long as can be obtained the heart rate signal of human body by contact human detection.Except the contact human chest shown in figure, rhythm of the heart parts 11 can also by the skin at the contact any position of human body to obtain heart rate signal.Heart rate detection parts 11 can be connected with miscellaneous part (such as control device 14) by wired or wireless standard/customization data communication interface (such as, USB interface), to carry out data transmission.
Memory storage 12 is for storing predetermined music file and the long-range index of correlation corresponding to each music file.The described long-range index of correlation is for characterizing the loudness of a sound complex distribution characteristic of corresponding music file.Loudness of a sound complex distribution characteristic refers to the complexity that loudness of a sound distributes.
Playing device 13 is for playing music.Described playing device can for setting firmly or demountable loudspeaker.
Control device 14 receives heart rate signal by heart rate detection parts 11, chooses the music file of coupling to heart rate signal after analyzing, and extracts music file and play by playing device 13 from memory storage 12.Thus realize Auto-matching, automatically play, automatically regulate physiological status or the mood of human body.
Particularly, control device 14 can be processor, and it is configured to the instruction flow of the automatic music matching process performed as shown in Figure 2.As shown in Figure 2, described automatic music matching process comprises the steps:
The heart rate signal of step 100, acquisition human body.
Particularly, in this step, control device 14 passes through the data communication interface of standard or customization by wireless or cable from the heart rate signal of external reception acquisition human body.
Step 200, described heart rate signal is divided into the discrete subsignal that K is distributed in different frequency scope.
Particularly, can by carrying out WAVELET PACKET DECOMPOSITION to heart rate signal to obtain the discrete subsignal that K is distributed in different frequency scope.
Wavelet package transforms (waveletpackettransform, WPT) develops on the basis of wavelet transformation.Because orthogonal wavelet transformation only does further decomposition to the low frequency part of signal, and no longer continue to decompose to the detail section that HFS is also signal, so wavelet transformation can characterize the signal that a large class take low-frequency information as principal ingredient well, but it can not decompose well and represent the signal comprising a large amount of detailed information.With it unlike, wavelet package transforms can provide meticulousr decomposition to HFS, and this decomposition is both irredundant, also without careless omission, so better Time-Frequency Localization analysis can be carried out to the signal comprising a large amount of medium, high frequency information.
Due to the High-frequency and low-frequency information of electrocardiosignal, contain the information with sympathetic nerve and parasympathetic activity situation, therefore can carry out wavelet package transforms decomposition to heart rate signal.Wavelet package transforms can successively carry out, and the number of plies is more, and the subsignal quantity of decomposing acquisition is more, and frequency range is narrower.In actual applications, according to the requirement of frequency resolution, the number of plies of WAVELET PACKET DECOMPOSITION can be selected.
Step 300, with T different time scale, coarse is carried out to obtain the time series of K*T coarse to each described subsignal respectively.
Particularly, the time series of coarse according to following formulae discovery:
E f ( &tau; ) ( j ) = 1 &tau; &Sigma; i = ( j - 1 ) &tau; + 1 j &tau; E f ( i ) ( 1 &le; j &le; N / &tau; )
Wherein, E f(i), i=1,2 ..., N is described subsignal, and N is described subsignal length, τ=1,2 ..., M is time scale factor, for the time series of coarse.
Step 400, Sample Entropy is calculated to the time series of each coarse.
Sample Entropy (SampEn, SampleEntropy) is the tolerance of time series complicacy, and it is the natural logarithm that CP is strict, and SampEn (m, r, N) can be used to represent, wherein N is length, and r is similar tolerance limit, and dimension is m and m+1.Sample Entropy is intended to the error reducing approximate entropy, has consistance more closely with known random partial.
Step 500, obtain the calibration index of described heart rate signal according to described Sample Entropy.
Particularly, step 500 comprises:
Step 510, for each time scale, there is under obtaining this time scale the time series of the coarse of maximum Sample Entropy.
Step 520, centre frequency corresponding to all time serieses with the coarse of maximum Sample Entropy calculate described calibration index.
Particularly, according to following formulae discovery, index is calibrated:
&alpha; = &Integral; &tau; = 1 M f ( &tau; )
Wherein, α is described calibration index, and f (τ) is all curvilinear function of seasonal effect in time series centre frequency relative to time scale matching acquisition in T/F plane with the coarse of maximum Sample Entropy.The actual above formula of this step asks for the area of the top-stitching lower part at time scale 1-M of this curvilinear function.The intermediate value of the frequency range of the subsignal of centre frequency corresponding to the time series of coarse.
Mood can cause autonomic reaction, and the internal organs activity that it is arranged now of autonomic reaction table changes.Different mood (indignation, grieved, frightened, detest, happy) between, Autonomic nerve block pattern is different.
Mood generally exists along with physiological change, its reason is the change that mood causes automatic nervous system aspect, thus make arranged organ also there occurs corresponding change, we are just likely by analyzing the method for heart rate like this, inquire into the difference of vegetalitas nervous system activity between the different mood emergence period, thus reach the object distinguishing different emotional handicap.
Known medically verified to the research of Autonomic nervous system activity at present, the high fdrequency component of vagal movable major effect HRV, the low frequency component of orthosympathetic movable major effect HRV.What calibration index can characterize frequency component in heart rate signal enlivens situation, this value is higher, illustrate that heart rate is higher in the activity of high-frequency range, prove that the radio-frequency component of heart rate can reflect parasympathetic active situation because forefathers much study, because parasympathetic effect can make people's blood pressure drops, breathe and slow down, be the typical performance that human body enters relaxation state, when therefore can think that area is high under line, human body is in relaxation state.
Step 600, choose the music file with the long-range index of correlation matched according to described calibration index and play, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file.
Particularly, can play closest to the music file of predetermined value with the difference or ratio of calibrating index by choosing the corresponding long-range index of correlation.
Fig. 3 is the process flow diagram of the long-range index of correlation of the calculating music file of the embodiment of the present invention.As shown in Figure 3, the described long-range index of correlation is according to such as under type calculating acquisition:
Step 601, obtain the Serial No. of music file by sampling.
In a preferred embodiment, 8-bit, 11KHz sample frequency is adopted to sample, to obtain enough signal to noise ratio (S/N ratio)s and statistical property.
Step 602, with the first window width w non-overlapping movement carried out to described Serial No. and calculate standard deviation, obtaining standard deviation sequence.
Step 603, square calculate corresponding average loudness of a sound to obtain average loudness of a sound sequence according to standard deviation each in standard deviation sequence.
Step 604, obtain volatility series based on following formula: wherein, Z bfor b element of described volatility series, v j 2for a jth element of described average loudness of a sound sequence, L is the length of described Serial No., and w is described first window width, and it is fixed value.
Step 605, to have described volatility series according to the second window width with predetermined overlap length and overlapping move window, obtain multiple subsequence to divide.Second window width is designated as w v, it can change each division in the process of subsequence.
Step 606, linear regression is utilized to obtain the linear trend of each described subsequence.Element in all subsequences is the linear trend of its correspondence with the linear trend of this subsequence.
Step 607, remove trend wave function based on following formulae discovery:
wherein, F dfor the described trend wave function that goes (also namely, divides the subsequence set of acquisition with window width w with above-mentioned steps 605 by moving window vthe function of change), for subsequence element z bcorresponding linear trend, τ is described overlap length.<> is average function, for the second window width w vmove the quadratic sum that the element of all subsequences that window obtains deducts the value of corresponding linear trend to ask on average.
Trend wave function and window width w is removed described in step 608, basis vrelation between corresponding time scale calculates the described long-range index of correlation.
Particularly, step 608 is by the long-range index of correlation described in following formulae discovery:
&beta; = dlogF D ( w &nu; ) d l o g ( w &nu; + 3 )
In the present embodiment, control device 14 can be set to general data handling system (such as computer system), and as shown in Figure 4, computer system 4 is a kind of forms of data handling system, and it can comprise bus 41.Microprocessor (CPU) 42, volatile memory 43 and nonvolatile memory 44 and/or massage storage 45 are all connected to bus 41, are carried out exchanges data by bus 41 and are communicated.Microprocessor 42 can be independently microprocessor, also can be one or more microprocessor set.Above-mentioned multiple assembly links together by bus 41, said modules is connected to display controller 46 and display device and I/O (I/0) device 47 simultaneously.I/O (I/0) device 47 can be mouse, keyboard, modulator-demodular unit, network interface, touch-control input device, body sense input media, printer and other devices well known in the art.Typically, input/output device 47 is connected with system by i/o controller 48.
Volatile memory 43 is also referred to as internal memory, it has the fireballing feature of reading and writing data, particularly, volatile memory 43 can be realized by dynamic random read-write memory (DRAM), and dynamic random read-write memory needs continued power to upgrade or to maintain the data in storer.
Typically, nonvolatile memory 44 refers to after electric current is turned off, the storer that the data stored can not disappear, and it can comprise such as ROM (read-only memory) (ROM) and flash memory (FlashMemory).Nonvolatile memory is typically for necessary program or other programs of storage system startup.
Typically, massage storage 45 can be the other types of magnetic hard drive or magneto-optical driver or the accumulator system that can store mass data, and massage storage 45 also can keep mass data after system shutdown power supply.I/0 controller 48 comprising USB (USB (universal serial bus)) adapter for controlling USB peripheral device, for the IEEE1394 controller of IEEE1394 peripherals or the bluetooth controller for controlling Bluetooth peripheral, and being applicable to the peripheral controls of other peripheral interface standard in an embodiment.
It will be understood by those skilled in the art that some embodiments of the present invention can all or at least partly by software simulating.That is, embodiments of the invention can perform with the processor of such as microprocessor the instruction sequence comprised in memory and realize in computer system 4 or other data handling system, and described storer can be volatile memory or remote storage.In many embodiment:, hard-wired circuit can with software instruction connected applications, to realize the present invention.So, this technology is not limited to any particular combination of hardware circuit and software, is also not limited to any specific instruction source that data handling system performs.In addition, run through this instructions, various function and operation are described to be performed by software code or caused to simplify this description by software code.But, those skilled in the art will recognize that this expression means that this function is realized by the processor run time version of such as microprocessor 42.
The electronic equipment of the present embodiment can be formed as various forms to be adapted to different application scenarioss, and the present invention does not limit its concrete form.
Control device 14 can become one with described heartbeat detection device 11, memory storage 12 and playing device 13, to form the wearable electronic of integration.Control device 14 can also be general data processing equipment, and memory storage 12 and playing device 13 are the parts integrated with it, and heartbeat detection device 11 is connect by wired or wireless communication the peripheral hardware communicated with.In this case, the combination of control device 13 can be such as panel computer or mobile communication terminal etc., and control device 13 is by working procedure or application controls playing device 13.
By decomposing by frequency range heart rate signal, and analyze its frequency formation and sample entropy, the final calibration index calculating acquisition sign current human emotional state, the long-range index of correlation distributed based on calibration index and sign music loudness of a sound is mated, can automatically select the music file of coupling to play according to human body physiological state, improve the accuracy of music coupling.
Fig. 5 is the structural representation of the automatic music coalignment of the embodiment of the present invention.As shown in Figure 5, described automatic music coalignment comprises heart rate acquiring unit 51, frequency partition unit 52, coarse unit 53, Sample Entropy computing unit 54, calibration index acquiring unit 55, music matching unit 56.
Wherein, heart rate acquiring unit 51 is for obtaining the heart rate signal of human body.
Frequency partition unit 52 is for being divided into the discrete subsignal that K is distributed in different frequency scope by described heart rate signal.
Coarse unit 53 is for carrying out coarse to obtain the time series of K*T coarse with T different time scale to each described subsignal respectively.
Sample Entropy computing unit 54 is for calculating Sample Entropy to the time series of each coarse.
Calibration index acquiring unit 55 is for obtaining the calibration index of described heart rate signal according to described Sample Entropy.
Music matching unit 56 is play for choosing the music file with the long-range index of correlation matched according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file.
Wherein, K and T be greater than 2 integer.
By decomposing by frequency range heart rate signal, and analyze its frequency formation and sample entropy, the final calibration index calculating acquisition sign current human emotional state, the long-range index of correlation distributed based on calibration index and sign music loudness of a sound is mated, can automatically select the music file of coupling to play according to human body physiological state, improve the accuracy of music coupling.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, to those skilled in the art, the present invention can have various change and change.All do within spirit of the present invention and principle any amendment, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.

Claims (9)

1. an automatic music matching process, comprising:
Obtain the heart rate signal of human body;
Described heart rate signal is divided into the discrete subsignal that K is distributed in different frequency scope;
With T different time scale, coarse is carried out to obtain the time series of K*T coarse to each described subsignal respectively;
Sample Entropy is calculated to the time series of each coarse;
The calibration index of described heart rate signal is obtained according to described Sample Entropy;
Choose the music file with the long-range index of correlation matched to play according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
2. automatic music matching process according to claim 1, it is characterized in that, described heart rate signal being divided into K the discrete subsignal being distributed in different frequency scope is: carry out WAVELET PACKET DECOMPOSITION to obtain the subsignal that K is distributed in different frequency scope to heart rate signal.
3. automatic music matching process according to claim 1, is characterized in that, describedly carries out to each described subsignal the time series that coarse comprises coarse according to following formulae discovery:
Wherein, E f(i), i=1,2 ..., N is described subsignal, and N is described subsignal length, τ=1,2 ..., M is time scale factor, for the time series of coarse.
4. automatic music matching process according to claim 1, is characterized in that, the calibration index obtaining described heart rate signal according to described Sample Entropy comprises:
For each time scale, there is under obtaining this time scale the time series of the coarse of maximum Sample Entropy;
Centre frequency corresponding to all time serieses with the coarse of maximum Sample Entropy calculates described calibration index.
5. automatic music matching process according to claim 4, is characterized in that, the centre frequency corresponding to all time serieses with the coarse of maximum Sample Entropy calculates described calibration index and comprises calibrate index according to following formulae discovery:
Wherein, α is described calibration index, and f (τ) is all curvilinear function of seasonal effect in time series centre frequency relative to time scale matching acquisition in T/F plane with the coarse of maximum Sample Entropy.
6. automatic music matching process according to claim 1, is characterized in that, the music file choosing the long-range index of correlation had and match according to described calibration index carries out broadcasting and comprises:
Choose the corresponding long-range index of correlation to play closest to the music file of predetermined value with the difference or ratio of calibrating index.
7. automatic music matching process according to claim 1, is characterized in that, the described long-range index of correlation is according to such as under type calculating acquisition:
The Serial No. of music file is obtained by sampling;
Carry out non-overlapping movement with the first window width to described Serial No. and calculate standard deviation, obtain standard deviation sequence, described first window width is predetermined value;
Square corresponding average loudness of a sound is calculated to obtain average loudness of a sound sequence according to standard deviation each in standard deviation sequence;
Volatility series is obtained based on following formula: wherein, z bfor b element of described volatility series, v j 2for a jth element of described average loudness of a sound sequence, L is the length of described Serial No., and w is described default window width;
To have described volatility series according to the second window width with predetermined overlap length and overlapping move window, obtain multiple subsequence to divide;
Linear regression is utilized to obtain the linear trend of each described subsequence;
Trend wave function is removed based on following formulae discovery:
wherein, F dtrend wave function is removed for described, for subsequence element z bcorresponding linear trend, <> is average function, for the second window width w vmoving the quadratic sum that the element of all subsequences that window obtains deducts the value of corresponding linear trend asks on average;
The described long-range index of correlation is calculated according to the described relation between the time scale corresponding to trend wave function and the second window width of going.
8. an automatic music coalignment, comprising:
Heart rate acquiring unit, for obtaining the heart rate signal of human body;
Frequency partition unit, for being divided into the subsignal that K is distributed in different frequency scope by described heart rate signal;
Coarse unit, for carrying out coarse to obtain the time series of K*T coarse with T different time scale to each described subsignal respectively;
Sample Entropy computing unit, for calculating Sample Entropy to the time series of each coarse;
Calibration index acquiring unit, for obtaining the calibration index of described heart rate signal according to described Sample Entropy;
Music matching unit, play for choosing the music file with the long-range index of correlation matched according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
9. an electronic installation, comprising:
Heart rate detection parts, for the heart rate signal of human body;
Memory storage, for storing predetermined music file and the long-range index of correlation corresponding to each music file;
Playing device, for playing music;
Control device, is configured to be suitable for performing as given an order:
Obtain the heart rate signal of human body;
Described heart rate signal is divided into the subsignal that K is distributed in different frequency scope;
With T different time scale, coarse is carried out to obtain the time series of K*T coarse to each described subsignal respectively;
Sample Entropy is calculated to the time series of each coarse;
The calibration index of described heart rate signal is obtained according to described Sample Entropy;
Choose the music file with the long-range index of correlation matched to play according to described calibration index, the described long-range index of correlation calculates according to the digitizing sequence of the music file of correspondence and obtains, for characterizing the loudness of a sound complex distribution characteristic of described music file;
Wherein, K and T be greater than 2 integer.
CN201510342269.2A 2015-06-18 2015-06-18 Automatic music matching process, device and apply its electronic device Active CN105138530B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510342269.2A CN105138530B (en) 2015-06-18 2015-06-18 Automatic music matching process, device and apply its electronic device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510342269.2A CN105138530B (en) 2015-06-18 2015-06-18 Automatic music matching process, device and apply its electronic device

Publications (2)

Publication Number Publication Date
CN105138530A true CN105138530A (en) 2015-12-09
CN105138530B CN105138530B (en) 2018-09-11

Family

ID=54723880

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510342269.2A Active CN105138530B (en) 2015-06-18 2015-06-18 Automatic music matching process, device and apply its electronic device

Country Status (1)

Country Link
CN (1) CN105138530B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106648540A (en) * 2017-01-09 2017-05-10 广东小天才科技有限公司 Music switching method and device
CN107301185A (en) * 2016-04-15 2017-10-27 富泰华工业(深圳)有限公司 Music commending system and method
CN107564550A (en) * 2017-10-27 2018-01-09 安徽硕威智能科技有限公司 A kind of card machine people that music is played according to detection children's heartbeat
CN109224240A (en) * 2018-06-26 2019-01-18 重阳健康数据技术(深圳)有限责任公司 It is a kind of for adjusting the information-pushing method and system of user mood

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090068432A (en) * 2007-12-24 2009-06-29 임미선 Smart music on player
CN103111006A (en) * 2013-01-31 2013-05-22 江苏中京智能科技有限公司 Intelligent mood adjustment instrument
CN104133879A (en) * 2014-07-25 2014-11-05 刘冬冬 Electroencephalogram and music matching method and system thereof
CN104409085A (en) * 2014-11-24 2015-03-11 惠州Tcl移动通信有限公司 Vehicle-mounted intelligent music player and music playing method thereof

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20090068432A (en) * 2007-12-24 2009-06-29 임미선 Smart music on player
CN103111006A (en) * 2013-01-31 2013-05-22 江苏中京智能科技有限公司 Intelligent mood adjustment instrument
CN104133879A (en) * 2014-07-25 2014-11-05 刘冬冬 Electroencephalogram and music matching method and system thereof
CN104409085A (en) * 2014-11-24 2015-03-11 惠州Tcl移动通信有限公司 Vehicle-mounted intelligent music player and music playing method thereof

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
刘风华: "基于心电脉搏信号的睡意检测与识别方法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107301185A (en) * 2016-04-15 2017-10-27 富泰华工业(深圳)有限公司 Music commending system and method
CN107301185B (en) * 2016-04-15 2021-01-12 富泰华工业(深圳)有限公司 Music recommendation system and method
CN106648540A (en) * 2017-01-09 2017-05-10 广东小天才科技有限公司 Music switching method and device
CN107564550A (en) * 2017-10-27 2018-01-09 安徽硕威智能科技有限公司 A kind of card machine people that music is played according to detection children's heartbeat
CN109224240A (en) * 2018-06-26 2019-01-18 重阳健康数据技术(深圳)有限责任公司 It is a kind of for adjusting the information-pushing method and system of user mood

Also Published As

Publication number Publication date
CN105138530B (en) 2018-09-11

Similar Documents

Publication Publication Date Title
US10201288B2 (en) Multi-electrode mapping system
US20210043325A1 (en) Systems approach to disease state and health assessment
Bulea et al. Prefrontal, posterior parietal and sensorimotor network activity underlying speed control during walking
US20170340229A1 (en) System and method of identifying sources for biological rhythms
Martinek et al. Non-invasive fetal monitoring: A maternal surface ECG electrode placement-based novel approach for optimization of adaptive filter control parameters using the LMS and RLS algorithms
de Cheveigné et al. Decoding the auditory brain with canonical component analysis
US8951189B2 (en) Systems approach to comorbidity assessment
Lee et al. A low-power processor with configurable embedded machine-learning accelerators for high-order and adaptive analysis of medical-sensor signals
Sternad It's not (only) the mean that matters: variability, noise and exploration in skill learning
US10335051B2 (en) Beat alignment and selection for cardiac mapping
Choi et al. Development and evaluation of an ambulatory stress monitor based on wearable sensors
Thurner et al. Multiresolution wavelet analysis of heartbeat intervals discriminates healthy patients from those with cardiac pathology
İşler et al. Combining classical HRV indices with wavelet entropy measures improves to performance in diagnosing congestive heart failure
US10299735B2 (en) Automated diagnosis based at least in part on pulse waveforms
Phinyomark et al. Fractal analysis features for weak and single-channel upper-limb EMG signals
US20170238858A1 (en) Depression assessment system and depression assessment method based on physiological information
Semmlow et al. Biosignal and medical image processing
Reaz et al. Techniques of EMG signal analysis: detection, processing, classification and applications
Zhao et al. A human ECG identification system based on ensemble empirical mode decomposition
AU2012284246B2 (en) Systems and methods for the physiological assessment of brain health and the remote quality control of EEG systems
Yang Multiscale recurrence quantification analysis of spatial cardiac vectorcardiogram signals
US20170032221A1 (en) Method, electronic apparatus, and computer readable medium of constructing classifier for disease detection
Cipresso et al. Is your phone so smart to affect your state? An exploratory study based on psychophysiological measures
Katz Fractals and the analysis of waveforms
US7043293B1 (en) Method and apparatus for waveform assessment

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C41 Transfer of patent application or patent right or utility model
TA01 Transfer of patent application right

Effective date of registration: 20160728

Address after: 100080 Haidian Haidian District Beijing street, No. 4, layer 4001, 1

Applicant after: Gold Union (Beijing) Technology Co., Ltd.

Address before: 241000 building B, building 115-C, Jiangbei industrial concentration area, Wuhu, Anhui

Applicant before: Liu Dongdong

Applicant before: Zhang Bo

Applicant before: Yang Xiaowen

GR01 Patent grant
GR01 Patent grant