TW201132332A - System and method for evaluating physiological signal - Google Patents

Abstract

The invention discloses a system and a method for evaluating physiological signal. The physiological signal evaluating system comprises a filter module, a signal splitting module, a processor, and a classifier. The filter module filters a time-series signal within a frequency range and outputs a filtered time-series signal. The signal splitting module, receiving the filtered time-series signal, splits the filtered time-series signal by a time interval and generates a plurality of signal sections accordingly. The processor, receiving the signal sections, calculates a plurality of entropies from each signal section. The classifier, having an entropy table, receives the entropies and compares the entropies to the entropy table for generating a physiological signal evaluating factor accordingly.

Description

201132332 VI. Description of the invention: [Technical field to which the invention pertains] The present invention relates to a physiological signal evaluation (four) system and method and relates to an evaluation system and method for evaluating sleep slogans. [Previous technique] When assessing the physical and mental condition of the subject, it is usually measured and the Chinese doctor often uses the physiological signals measured by the interpretation to enter the living line. ^ The evaluation of the sleep product f depends on Physicians can interpret ^'s and ^'s numbers to make accurate judgments. In general, sleep accounts for about 1/3 of people's time in a day, 苴ί ίϊίίί is completely still, and instead, the brain will carry out a i string of unrecognized activities 'and will produce at different stages - some different (four), such as 'the brain's activities in different stages of research are related to the disease or 疋 disease. Therefore, the quality of side sleep can be Reflecting the movement, the doctor is more able to grasp the physical and mental condition of the subject. In the traditional method of assessing the quality of sleep, it takes a long time to measure the data of the subject. For example, measuring 1 electro-oculogram (electr〇_ 〇cul〇gram, E〇g) or electro-encephalogram 'EEG' can be used to manually judge the sleep state of the subject at each stage. For example, see Figure 1A and Figure 1B. Figure 1A shows a The original signal of the electro-oculogram of the subject. Figure 1B shows the result of manual interpretation of the electro-oculogram of Figure A. As shown in the figure, Figure 1A shows the electro-oculogram signal of tens of thousands of seconds. In the traditional sleep quality assessment process, by people

The original signal of the electro-oculogram is analyzed, and the judgment results are marked one by one in ^B. However, the use of manual judgments can be very time consuming and laborious. In addition to the need to interpret sleep data for up to several hours, it is more likely to make erroneous judgments due to repeated and lengthy assignments. 201132332 Ancient J — The signal is very complicated. If you use ordinary judgment equipment to judge, although it can effectively shorten the judgment time, ^ and = ΐ: the method is difficult to establish a set of accurate judgment criteria, so the judgment is accurate. In the evaluation of physiological signals, a set of secrets of a more method is needed to assist in judging the physiological state of the subject, and the surgeon can more accurately diagnose and respond to the corresponding treatment.

The invention is based on a physiological signal evaluation system, and uses a multi-scale entropy 'MSE algorithm to perform physiological signal evaluation, in addition to quickly assessing the physiological condition of the subject, and accurately determining result. According to a specific embodiment of the present invention, the physiological signal evaluation system of the present invention comprises a button module, a signal segmentation module, a service, and a classification cry. The filter module passes the timing signal in the -frequency range and outputs the filtered time apostrophe. The 彳s segmentation module is connected to the filter module to receive the extinction signal, and the time-series signal is separated by the clock interval, and the three processors are coupled to the signal segmentation module to receive the plurality of signal segments, and Calculate multiple entropy values for each-signal segment. The classification H secret processor has a smoke value comparison table, classifies, receives the plurality of entropy values of each signal segment, and compares the plurality of entropy values with an entropy value table to generate a physiological signal evaluation parameter. In a practical application, the physiological signal evaluation system further includes a sampling module, and the sampling module is coupled to the filtering module to sample the original signal at a preset frequency to generate a timing signal. In addition, the filter module can include a bandpass filter. Furthermore, each entropy is the result of a multi-scale entropy algorithm that performs operations on multiple scales. In addition, the entropy value comparison table can be established by inputting a plurality of standard entropy values in advance by 201132332. The entropy value comparison table includes a plurality of entropy value intervals, and each entropy value interval includes at least one of the plurality of standard entropy values. One aspect of the present invention resides in a physiological signal evaluation method, which uses a ten-degree entropy-based nasal method for physiological signal evaluation, which can produce a more accurate judgment result in addition to rapidly assessing the physiological condition of the subject. According to an embodiment of the present invention, the physiological signal evaluation method of the present invention comprises the steps of: over-sequencing the signal in the frequency range, and generating the filtered timing signal; and dividing the filtered timing signal by a clock interval: To generate a plurality of signal segments; calculate a plurality of drip of each signal segment, and compare the plurality of entropy values to an entropy value table to generate a physiological signal evaluation parameter. In practical applications, the per-entropy value is the result of one of the = arithmetic scales in a multi-scale entropy algorithm. In addition, the physiological method further comprises the steps of: inputting a plurality of standard entropy values in advance, and constructing a 2-value comparison table. The entropy value comparison table includes a plurality of entropy values, and each entropy interval includes at least one of the plurality of standard entropy values. In summary, the physiological signal evaluation system and method of the present invention uses a multi-scale algorithm to evaluate the evaluation of physiological money. Since the multi-dimensional calculus algorithm can perform multi-dimensional analysis, the present invention can be The multi-lateral value of the ratio scale is different, and the non-health is broken according to a single entropy. In addition to the rapid evaluation of the physiological condition of the subject, the physiological domain assessment, system and method of the present invention can greatly improve the judgment result. The advantages and spirit of the present invention can be further improved. Understanding β τ' W and 201132332 [Embodiment] Referring to Figure 2, there is shown a block diagram of a physiological signal evaluation system of the present invention. As shown in FIG. 2, the physiological signal evaluation system i includes a filter module ίο, a signal splitting module 12, a processor 14, a classifier 16, and a sampling module 18. The processor 15 is electrically connected between the signal splitting module 12 and the sampling module 18, and the processor 14 is electrically connected between the signal splitting module 12 and the classifier 16. The chopper module 10 passes the timing signal in the -frequency range and outputs the filtered timing signal. In practice, the filter module 10 can include or can be a bandpass chopper, and the frequency range is 〇·5Ηζ to 3〇Hz. That is to say, the chopper module 10 can filter out unwanted signals, leaving only signals in the frequency range of 0.5 Hz^3 GHz. On the other hand, the physiological signal frequency of the silk_ is relatively south, and the filter module 10 can set the juice according to the frequency of the physiological signal to be detected. Therefore, the filter module 1〇 is not limited to only leaving the frequency range at 0·5Ηζ. Signals in ~30Hz. The signal dividing module 12 receives the filtered timing signal outputted by the filtering module 1〇, and divides the filtered timing signal by a clock interval to generate a plurality of signal segments. In practice, the signal segmentation module 12 is configured to divide the signal into a plurality of segments to further process the segmented signal, and the clock interval is not limited herein. For example, the clock interval may be 3 leap seconds. Processor 14 receives the plurality of signal segments and operates a plurality of entropy values for each of the signal segments. In practice, each entropy is the result of computing in one of multiple operational scales in a multi-scale entropy (MSE) algorithm. For example, the processor 14 can use 20 operational scales to perform the multi-scale entropy algorithm, and through the multi-scale entropy algorithm, each (1st to 2nd) operational scale can be divided into 201132332 t The respective entropy values (1st to 20th) are generated and output to the classifier 16. Here, this

The invention does not limit the number of operational scales. Technicians can choose the appropriate number of operational scales. W It is worth noting that the present invention does not limit its operation mode because the multi-scale entropy algorithm is an algorithm that can be understood by those skilled in the art, although several different methods can be used. Perform multi-footwise entropy operations, but as long as it is performing multi-scale entropy operations and each operation scale $

The respective entropy values are generated, respectively, which fall within the scope of the invention, and the skilled person can determine the mode of operation. The lamp classifier 16 has an entropy value comparison table, and the classifier 16 receives the plurality of entropy values of each signal segment and compares the plurality of entropy values to an entropy value table to generate physiological signal evaluation parameters. In practice, the _ ^ can be a categorical or non-linear ϋ. Moreover, the facet 16 can be pre-inputted with multiple entropy values to establish a face comparison table. The entropy value comparison table includes a plurality of ^ intervals, and each entropy interval includes at least one of the plurality of standard entropy values. For example, the physiological signal evaluation system i is used to evaluate the physiological signal. The first step is to first adjust the net value to A, and the table to make the score _ 16 can be obtained by inputting some fresh value or by a professional person. It is true that the net value of 14 rounds is difficult. In addition, the plurality of entropy value intervals respectively correspond to the entropy values calculated by the plurality of operation scales=the operation scales, and may be respectively determined by the (fourth) rotten ^==number Si: the threshold interval should be included to indicate different births (10) Which one is used instead of the other, because the New Zealand is not as good as the money generated by the machinery. For example, the physiological signal may change slightly due to the posture, mood, or external factors of the subject. When the entropy value comparison table is described, a plurality of entropy interval intervals are respectively set corresponding to a plurality of standard entropy values, thereby improving the fault tolerance rate of the physiological signal, so that the judgment of the physiological signal can be protected from some undesired factors.

The sampling module 18 samples the original signal at a predetermined frequency to generate a timing signal. In practice, the original signal generated by the detected physiological state is often a long and nickname. If the signal is analyzed and processed from the original signal, the computing resources will be excessively consumed. Therefore, in order to reduce the amount of calculation, the amount of 彳5> into the filter module 1 can be effectively reduced, and the sampling module 丨8 can reduce the frequency of the 彳§ from the original signal, for example, preset The frequency can be preset to 256 ίίζ. The following is a description of the physiological signal evaluation method and the drawing of the present invention. Referring to FIG. 2 and FIG. 3, FIG. 3 is a flow chart showing a method for evaluating the number of a specific embodiment of the present invention. As shown in the figure, in step S20, the sampling module 18 samples an original signal at a predetermined frequency to generate a timing, and the sampling module 18 can further transmit the timing signal to the filtering module 1 . The ^=middle sampling module 18 can select other sampling conditions for the original signal. The sampling module 18 can also eliminate the excessive or too small amplitude of the ribs to reduce the amount of computation of the signal entering the filtering module 1〇. The itch position = the secret step 2 *, the chopping mode, the group 1 〇 in a frequency range transition to generate the filtered timing signal. In practice, she is tested in terms of sleep quality, and the order (4) is usually selected from the eye-electric n-label: or the EEG signal (EEG) because of the frequency range in which the E0G signal and the coffee service can be interpreted. The frequency range of the 1Q(10) wave of the test module can be set in the vicinity of 201132332 0·5Ηζ~30Hz in advance. Next, in step S24, the signal splitting module 12 receives the filtered timing signal from the filtering module ι, and divides the filtered timing signal by a clock interval to generate a plurality of signal segments. In practice, the evaluation of sleep quality is taken as an example. The sleep state changes with the activity of the brain, so choosing the appropriate clock interval can simplify the calculation without affecting the accuracy of the judgment. For example, when evaluating sleep quality, the signal segmentation module 12 performs an epoch in 30 seconds, that is, a subsequent operation every 30 seconds, in other words,

The appropriate clock interval for assessing sleep quality is approximately 30 seconds, but the invention should not be limited thereto. Next, in step S26, the processor 14 receives the plurality of signal segments and operates a plurality of entropy values for each of the signal segments in a multi-scale entropy algorithm. In practice, the process 14 uses a multi-scale entropy algorithm and operates each of the signal segments on multiple operational scales to correspondingly generate a plurality of entropy values. Next, in step S28, the classifier 16 compares the plurality of entropy values to the entropy value to *, , and the data to generate a physiological parameter. For example, the processor 14 then calculates the 2G side value of the (4) segment through the multi-scale algorithm leaf by 20 arithmetic scales, and then inputs the 2() 彳_ value into the device 16 . For example, when the entropy value calculated by 1 arithmetic scale falls within the first range of 1 entropy value _, then the sub-16 outputs the first raw Z evaluation parameter; when the value falls on the third Within the second circumference of the side value interval, the classifier 16 outputs a second physiological signal evaluation parameter. It may be that if the time series signal is long, the physiological signal evaluation system 1 can further determine the physiological state of the subject at each time point by waiting for a series of physiological signal evaluation parameters. In summary, _ 'the hair growth of the hair and the degree of entropy algorithm to evaluate the physiological signal. The oxime evaluation system and method can be widely applied to the long-term recording... This is the physiological signal scale of the month. The magnetic towel can be analyzed according to different calculation scales. Therefore, the (4) is not based on the single-missing knife. Physiological m = except for the _ quick bribe testee

: Ming classifier can be pre-required by professionals: = The evaluation of the invention is more reliable. The feature disc of the present invention, which is described by the above preferred embodiments, is intended to be more versatile than the patent range of =====. ' = month [Simple diagram description] Figure VIII shows the original signal of the subject's electro-oculogram. Fig. B shows the result of manual interpretation of the electrooculogram of Figure A. Figure 2 is a block diagram showing one of the present inventions. Physiological Signal Evaluation System of the Body Embodiment FIG. 3 is a flow chart showing the present invention. The ride of the actual U-health evaluation method [main component symbol description] 10: filter module 1: physiological signal evaluation system 201132332 12: signal split module 14: processor 16: classifier 18: sampling module S20 ~ S28: Step flow

12

Claims (1)

201132332 VII. Application scope of Shenyi: 1. A physiological signal evaluation system, including: a signal ϊ τ frequency range filtering - timing signal and output - according to the wave Πΐ Πΐ group ^ connected to the chopper module, receiving the chopper after the timing And the processor is coupled to the signal segmentation module, and the processor is connected to the segment: computing each entropy value of the segmentation segment; and using a processor to have an entropy value comparison table, the classifier receives The parent is the isentropic value of the segment, and the isentropic value is compared with the entropy value to generate a physiological signal evaluation parameter. 6χ 2. The physiological signal evaluation system described in the second paragraph of the patent, the second section of the patent, includes: a sample module, _ domain wave module, with a preset word sampling, an original 4 Lu number, according to which The timing signal. 3. The physiological letter estimation system according to item 1, wherein the chopping module comprises a band pass filter. 4. The physiological signal evaluation system according to claim 1, wherein each of the entropy values is a multi-scale entropy algorithm, and the result of the operation is one of a plurality of operational scales.生理 The physiological signal evaluation system according to claim 1, wherein the classifier establishes the entropy value comparison table by inputting a plurality of standard entropy values in advance. 6. The physiological signal evaluation system of claim 5, wherein the entropy value comparison table comprises a plurality of entropy interval intervals, each of the threshold intervals including at least one of the root entropy values. The physiological signal evaluation system of claim 1, wherein the classifier is a linear classifier or a nonlinear classifier. ' Ρ m 13 7, 201132332 The physiological signal evaluation system according to item 1, wherein the time series cadmium telluride is an electrooculogram signal or an EEG signal.斤9, physiological physiology k evaluation method, comprising the following steps: filtering by the range of — — — 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 时序 滤波 滤波 滤波 滤波 滤波 滤波, Calculating a plurality of entropy values of each of the signal segments; and a U-entropy value comparison-entropy value comparison table, according to which the physiological signal evaluation method according to claim 9 is generated, and the physiological signal evaluation method described in claim 9 is further included The following steps: sampling at a preset frequency - the original signal, according to which the timing signal is generated. 11. The physiological signal evaluation method according to item 9 of the patent application scope is as follows: in a multi-scale entropy algorithm, the result is constructed by a plurality of operation scales; 12. Please refer to the physiological signal evaluation method described in item 9 of the patent scope, and further include the following pre-input of multiple standard values to establish the threshold comparison table. 13. The value range of the physiological money evaluation method described in item 12 of the patent scope, each of the entropy interval includes at least the physiological signal evaluation method described in item 9 of the patent application scope, k旒 is an electrocardiogram signal or an EEG signal. ~" 14