CN118161127A - Infant respiratory problem detection system based on radar signals - Google Patents
Infant respiratory problem detection system based on radar signals Download PDFInfo
- Publication number
- CN118161127A CN118161127A CN202410278980.5A CN202410278980A CN118161127A CN 118161127 A CN118161127 A CN 118161127A CN 202410278980 A CN202410278980 A CN 202410278980A CN 118161127 A CN118161127 A CN 118161127A
- Authority
- CN
- China
- Prior art keywords
- signal
- radar
- envelope
- unit
- apnea
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 103
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 31
- 230000033001 locomotion Effects 0.000 claims abstract description 67
- 230000000737 periodic effect Effects 0.000 claims abstract description 49
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 208000008784 apnea Diseases 0.000 claims description 90
- 230000029058 respiratory gaseous exchange Effects 0.000 claims description 39
- 238000001228 spectrum Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 19
- 238000004590 computer program Methods 0.000 claims description 11
- 239000012634 fragment Substances 0.000 claims description 11
- 230000036391 respiratory frequency Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 208000030303 breathing problems Diseases 0.000 claims description 4
- 238000000034 method Methods 0.000 description 24
- 210000000038 chest Anatomy 0.000 description 12
- 238000004422 calculation algorithm Methods 0.000 description 8
- 210000000115 thoracic cavity Anatomy 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 7
- 230000002028 premature Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000006073 displacement reaction Methods 0.000 description 6
- 206010021143 Hypoxia Diseases 0.000 description 5
- 230000002612 cardiopulmonary effect Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- 230000007954 hypoxia Effects 0.000 description 5
- 230000036544 posture Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 239000003550 marker Substances 0.000 description 4
- 230000002411 adverse Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 208000034972 Sudden Infant Death Diseases 0.000 description 2
- 206010042440 Sudden infant death syndrome Diseases 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 210000004072 lung Anatomy 0.000 description 2
- 230000035945 sensitivity Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 206010067484 Adverse reaction Diseases 0.000 description 1
- 206010012559 Developmental delay Diseases 0.000 description 1
- 208000017442 Retinal disease Diseases 0.000 description 1
- 206010038923 Retinopathy Diseases 0.000 description 1
- 208000028990 Skin injury Diseases 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000006838 adverse reaction Effects 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036471 bradycardia Effects 0.000 description 1
- 208000006218 bradycardia Diseases 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 230000002045 lasting effect Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000030363 nerve development Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000000069 prophylactic effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000036387 respiratory rate Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000033764 rhythmic process Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002459 sustained effect Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a radar signal-based infant respiratory problem detection system, comprising: the acquisition module is used for acquiring radar I/Q signals, wherein the radar I/Q signals are obtained by monitoring chest movements of a detected object during sleep through a short-range radar; the validity detection module is used for detecting the validity of the radar I/Q signal to obtain a valid radar I/Q signal segment; the extraction module is used for extracting the envelope signal of the effective radar I/Q signal segment and obtaining a target envelope signal according to the amplitude of the envelope signal; and the periodic breath detection module is used for carrying out periodic breath detection according to the envelope slope of the target envelope signal. The invention can realize periodic breath judgment.
Description
Technical Field
The invention relates to the technical field of biomedical signal processing, in particular to a respiratory problem detection system based on radar signals.
Background
Among newborns worldwide, premature infants (gestational age below 37 weeks) account for about 5% to 18%. According to the study, more than half of premature infants and almost all neonates weighing less than 1 kg have apneas due to respiratory developmental immaturity. It is generally recognized that infant apneas refer to respiratory pauses exceeding 15 or 20 seconds, possibly leading to both hypoxia saturation (SpO 2), hypoxia and Heart Rate (HR) reduction. If the recurrent apneas of the infants cannot be found and intervened in time, long-term adverse reactions such as retinopathy, nerve development disorder and the like can be caused, and the death risk is increased. Therefore, the intelligent monitoring system has important significance for closely and intelligently monitoring the infant cardiopulmonary activity. However, existing monitoring methods and personalized early warning still have limitations.
In clinical infant cardiopulmonary monitoring, spO2, RR and HR information is typically provided by photoplethysmogram (PPG/pleth), impedance Pneumogram (IP) and Electrocardiogram (ECG), respectively. However, these conventional sensors all require skin contact and are not suitable for long-term monitoring for the following reasons: 1) Infants may feel uncomfortable and even skin injury; 2) The wearing of the sensor is inconvenient for medical operation; 3) The sensor may fall off due to perspiration and movement, resulting in false alarms. Furthermore, apnea monitoring techniques are not often used clinically as a prophylactic method for hypoxia, and generally only a sustained decrease in SpO2 is monitored for more attention. Thus, these problems have raised interest in non-contact monitoring methods for infant apneas. One widely used method is to use depth or infrared cameras to measure chest and abdomen movements of the infant, which can be extracted with accurate data by visual techniques. However, vision-based methods face problems associated with high data throughput, high power, and leakage of private information. Another currently available non-contact apnea monitoring method relies on the use of a laser, however long exposure to the laser can also harm the infant's skin.
Thus, the use of radar for infant cardiopulmonary monitoring has become a potential technique. Since the 70 s of the 20 th century, radar-based monitoring technologies have been attempted for biomedical applications. With the breakthrough of semiconductor technology and theoretical research in terms of hardware architecture and signal processing, millimeter wave radars have been able to achieve miniaturization of dimensions and accurate recovery of microscopic motion phase information while maintaining insensitivity to light and the ability to penetrate obstacles. These features demonstrate the short range applicability of radar-based sensing technology in non-contact vital sign monitoring. While related studies are mostly directed to adult cardiopulmonary monitoring. While some previous studies have explored the use of radar technology for infant health monitoring, they have focused primarily on short-term apnea monitoring.
On the other hand, personalized apnea monitoring of infants is also inadequate, as infants are generally treated with the same apnea criteria, regardless of their gestational age, weight and health. Broad criteria may lead to some infants with adverse symptoms being overlooked. For example, periodic breathing is generally defined as repeated respiratory cycles and brief apneas, typically lasting less than 10 seconds, with moderate oxygen saturation and bradycardia without clinical intervention. However, studies have shown that excessive periodic breathing may also be one of the causes of Sudden Infant Death Syndrome (SIDS).
Disclosure of Invention
The invention aims to solve the technical problem of providing a radar signal-based infant breathing problem detection system which can realize periodic breathing judgment.
The technical scheme adopted for solving the technical problems is as follows: there is provided a radar signal based infant respiratory problem detection system comprising:
the acquisition module is used for acquiring radar I/Q signals, wherein the radar I/Q signals are obtained by monitoring chest movements of a detected object during sleep through a short-range radar;
The validity detection module is used for detecting the validity of the radar I/Q signal to obtain a valid radar I/Q signal segment;
The extraction module is used for extracting the envelope signal of the effective radar I/Q signal segment and obtaining a target envelope signal according to the amplitude of the envelope signal;
and the periodic breath detection module is used for carrying out periodic breath detection according to the envelope slope of the target envelope signal.
The validity detection module comprises:
the body movement detection unit is used for detecting body movement according to the zero crossing rate of the radar I/Q signal and marking at the position where the body movement occurs to obtain body movement time;
The position detection unit is used for carrying out position detection according to the energy ratio of the respiratory frequency band of the radar I/Q signal, and taking the radar I/Q signal segment with effective position detection as an effective radar I/Q signal segment.
The body movement detection unit includes:
The first segmentation subunit is used for segmenting the radar I/Q signal into a plurality of signal segments;
the zero crossing rate calculation subunit is used for calculating the zero crossing rate of each signal segment;
The zero crossing rate judging subunit is used for judging whether the zero crossing rate exceeds a zero crossing rate threshold value;
And the marking subunit is used for indicating that the corresponding signal segment appears body movement when the zero crossing rate exceeds the zero crossing rate threshold value, and marking the signal segment to obtain the body movement time.
The position detection unit includes:
The second segmentation subunit is used for segmenting the radar I/Q signal into a plurality of non-overlapping fragments according to preset time;
The energy ratio calculating subunit is used for calculating the energy ratio of the respiratory frequency band of the signal in each segment to the preset frequency band; wherein the preset frequency range is 0.5-5Hz;
an energy ratio judging subunit for judging whether the energy ratio exceeds an energy ratio threshold;
And the merging subunit is used for merging the fragments corresponding to the energy ratio exceeding the energy ratio threshold value to obtain the effective radar I/Q signal fragments.
The extraction module comprises:
The first extraction and calculation unit is used for extracting an envelope signal of an I signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the I signal;
The second extraction and calculation unit is used for extracting an envelope signal of the Q signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the Q signal;
and the target envelope signal determining unit is used for comparing the amplitude difference value of the envelope signal of the I signal with the amplitude difference value of the envelope signal of the Q signal, and taking the envelope signal corresponding to the larger value of the amplitude difference value of the I signal and the amplitude difference value of the envelope signal of the Q signal as the target envelope signal.
The periodic breath detection module includes:
A first sliding window setting unit configured to set a first sliding window on the target envelope signal, the first sliding window sliding forward without overlapping;
The autocorrelation calculating unit is used for carrying out autocorrelation operation on the signal in the first sliding window to obtain an autocorrelation waveform;
A first statistics judgment unit for counting the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform, and judging whether the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
An average interval calculating unit for calculating an average interval between peaks in the autocorrelation waveform when the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
an interval judging unit for judging whether the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold;
the power spectrum peak value acquisition unit is used for carrying out Fourier transformation on the autocorrelation waveform when the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold value to obtain a power spectrum;
a peak value judging unit for judging whether the highest peak of the power spectrum in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2 Hz;
A second statistical judgment unit for counting the number of peaks exceeding 0.4 times the highest peak in the power spectrum when the highest peak in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2Hz, and judging whether the number of peaks exceeding 0.4 times the highest peak in the power spectrum is smaller than a second peak number threshold;
An envelope slope calculation unit, configured to calculate an upper half or a lower half of the target envelope signal when the number of peaks exceeding 0.4 times of the highest peak in the power spectrum is smaller than a second peak number threshold, and perform linear fitting on the upper half or the lower half of the target envelope signal to obtain an envelope slope;
an envelope slope judging unit for judging whether the envelope slope is smaller than a slope threshold;
And the periodic respiration judging unit is used for recognizing the signal in the first sliding window as a periodic signal when the slope of the envelope is smaller than the slope threshold value.
The infant respiratory problem detection system based on the radar signal further comprises: and the apnea detection module is used for detecting the apnea according to the target envelope signal and the body movement time.
The apnea detection module includes:
A second sliding window setting unit configured to set a second sliding window on the target envelope signal, the second sliding window sliding forward in a step of one data point;
a threshold calculation unit for calculating a threshold value of each data point;
A comparison unit for comparing the amplitude of the last data point in the second sliding window with the threshold value of the last data point;
the time length counting unit is used for counting the number that the amplitude of the last data point in the second sliding window is smaller than the threshold value of the last data point, and obtaining corresponding time length;
the preliminary judgment unit is used for judging an apnea event when the duration is longer than the preset apnea detection duration and the current data point is longer than the preset body movement neglect duration from the last body movement time;
The merging judging unit is used for judging whether the time interval of the adjacent two-time apnea events is smaller than the merging duration, merging the adjacent two-time apnea events into one apnea event if the time interval of the adjacent two-time apnea events is smaller than the merging duration, and taking the adjacent two-time apnea events as two apnea events if the time interval of the adjacent two-time apnea events is larger than or equal to the merging duration;
And the final judging unit is used for judging whether the duration of each apnea event exceeds the early warning duration, and if so, taking the apnea event as a final apnea event.
The threshold value calculating unit calculates the threshold value byAnd calculating a threshold value of each data point, wherein TH [ N ] represents the threshold value of the nth data point in the target envelope signal, b is a weight factor, N is the number of data points in the second sliding window, and Env [ k ] represents the amplitude of the kth data point in the target envelope signal.
The technical scheme adopted for solving the technical problems is as follows: there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of a detection method employing the radar signal based infant breathing problem detection system described above.
Advantageous effects
Due to the adoption of the technical scheme, compared with the prior art, the invention has the following advantages and positive effects:
The body movement detection is realized by calculating the zero crossing rate in the time domain, the interference on body movement detection caused by amplitude change caused by position and posture does not exist, and the body movement detection has a good detection effect on random unstable body movement, so that the misjudgment of the apnea caused by the body movement interference is reduced.
According to the invention, the target respiration signal-to-noise ratio is detected by calculating the energy ratio of the respiration frequency band to the low frequency band, so that whether the detection target is at the proper detection position is judged, and the detection target is always at the proper detection position in a system reminding mode or the like, so that the optimal effect of an algorithm is ensured, and meanwhile, the infant is ensured to be positioned in the safety range of the bed.
The invention realizes periodic respiration judgment based on the envelope waveform of the thoracic cavity displacement signal, provides basis for observing the occurrence frequency and the frequency of periodic respiration of the detection target, and further avoids the adverse consequences of repeated hypoxia and the like of infants caused by periodic respiration. The invention also discloses an apnea judgment method based on the chest displacement signal envelope waveform, and the method can be used for adaptively generating the threshold value by combining a specific algorithm, so that the method can adapt to the characteristic of unstable breathing of infants and has better sensitivity.
The invention detects based on respiration envelope signals instead of respiration signals, can reduce the number of signal sampling points, reduces the consumption of computing resources and increases the operation speed. The invention is instantly available, does not need a great amount of data training in the early stage of a user, can continuously detect, can carry out offline analysis on long-period signals of sleeping in the whole night, and can process continuously-occurring apnea events. The invention can be used under the conditions of different individuals, different sleeping postures and different breathing states, and has strong applicability.
Drawings
FIG. 1 is a block diagram of an embodiment of a radar signal-based infant respiratory problem detection system;
FIG. 2 is a flow chart of a detection method of an infant respiratory problem detection system based on radar signals using an embodiment of the present invention;
FIG. 3 is a graph of radar signals, thoracic envelope signals, and decision results for a premature infant experiencing periodic breathing and apnea of less than 10 seconds in length;
Fig. 4 is a graph of radar signal, thoracic envelope signal and determination results for an apnea of a premature infant having a length longer than 20 seconds.
Detailed Description
The application will be further illustrated with reference to specific examples. It is to be understood that these examples are illustrative of the present application and are not intended to limit the scope of the present application. Furthermore, it should be understood that various changes and modifications can be made by one skilled in the art after reading the teachings of the present application, and such equivalents are intended to fall within the scope of the application as defined in the appended claims.
A first embodiment of the present invention relates to a radar signal-based infant respiratory problem detection system, as shown in fig. 1, comprising:
the acquisition module is used for acquiring radar I/Q signals, wherein the radar I/Q signals are obtained by monitoring chest movements of a detected object during sleep through a short-range radar;
The preprocessing module is used for preprocessing the acquired radar I/Q signals;
The validity detection module is used for detecting the validity of the radar I/Q signal to obtain a valid radar I/Q signal segment; wherein, validity detection module includes:
the body movement detection unit is used for detecting body movement according to the zero crossing rate of the radar I/Q signal and marking at the position where the body movement occurs to obtain body movement time;
the body movement detection unit includes:
The first segmentation subunit is used for segmenting the radar I/Q signal into a plurality of signal segments;
the zero crossing rate calculation subunit is used for calculating the zero crossing rate of each signal segment;
The zero crossing rate judging subunit is used for judging whether the zero crossing rate exceeds a zero crossing rate threshold value;
And the marking subunit is used for indicating that the corresponding signal segment appears body movement when the zero crossing rate exceeds the zero crossing rate threshold value, and marking the signal segment to obtain the body movement time.
The position detection unit is used for carrying out position detection according to the energy ratio of the respiratory frequency band of the radar I/Q signal, and taking the radar I/Q signal segment with effective position detection as an effective radar I/Q signal segment;
the position detection unit includes:
The second segmentation subunit is used for segmenting the radar I/Q signal into a plurality of non-overlapping fragments according to preset time;
The energy ratio calculating subunit is used for calculating the energy ratio of the respiratory frequency band of the signal in each segment to the preset frequency band; wherein the preset frequency range is 0.5-5Hz;
an energy ratio judging subunit for judging whether the energy ratio exceeds an energy ratio threshold;
The merging subunit is used for merging the fragments corresponding to the energy ratio exceeding the energy ratio threshold value to obtain an effective radar I/Q signal fragment;
The extraction module is used for extracting the envelope signal of the effective radar I/Q signal segment and obtaining a target envelope signal according to the amplitude of the envelope signal;
The extraction module comprises:
The first extraction and calculation unit is used for extracting an envelope signal of an I signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the I signal;
The second extraction and calculation unit is used for extracting an envelope signal of the Q signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the Q signal;
A target envelope signal determining unit for comparing the amplitude difference of the envelope signal of the I signal with the amplitude difference of the envelope signal of the Q signal, and taking the envelope signal corresponding to the larger value of the two as the target envelope signal
The periodic breath detection module is used for carrying out periodic breath detection according to the envelope slope of the target envelope signal;
The periodic breath detection module includes:
A first sliding window setting unit configured to set a first sliding window on the target envelope signal, the first sliding window sliding forward without overlapping;
The autocorrelation calculating unit is used for carrying out autocorrelation operation on the signal in the first sliding window to obtain an autocorrelation waveform;
A first statistics judgment unit for counting the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform, and judging whether the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
An average interval calculating unit for calculating an average interval between peaks in the autocorrelation waveform when the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
an interval judging unit for judging whether the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold;
the power spectrum peak value acquisition unit is used for carrying out Fourier transformation on the autocorrelation waveform when the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold value to obtain a power spectrum;
a peak value judging unit for judging whether the highest peak of the power spectrum in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2 Hz;
A second statistical judgment unit for counting the number of peaks exceeding 0.4 times the highest peak in the power spectrum when the highest peak in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2Hz, and judging whether the number of peaks exceeding 0.4 times the highest peak in the power spectrum is smaller than a second peak number threshold;
An envelope slope calculation unit, configured to calculate an upper half or a lower half of the target envelope signal when the number of peaks exceeding 0.4 times of the highest peak in the power spectrum is smaller than a second peak number threshold, and perform linear fitting on the upper half or the lower half of the target envelope signal to obtain an envelope slope;
an envelope slope judging unit for judging whether the envelope slope is smaller than a slope threshold;
the periodic respiration judging unit is used for recognizing the signal in the first sliding window as a periodic signal when the slope of the envelope is smaller than the slope threshold value;
the apnea detection module is used for detecting the apnea according to the target envelope signal and the body movement time;
the apnea detection module includes:
A second sliding window setting unit configured to set a second sliding window on the target envelope signal, the second sliding window sliding forward in a step of one data point;
a threshold calculation unit for calculating a threshold value of each data point;
A comparison unit for comparing the amplitude of the last data point in the second sliding window with the threshold value of the last data point;
the time length counting unit is used for counting the number that the amplitude of the last data point in the second sliding window is smaller than the threshold value of the last data point, and obtaining corresponding time length;
the preliminary judgment unit is used for judging an apnea event when the duration is longer than the preset apnea detection duration and the current data point is longer than the preset body movement neglect duration from the last body movement time;
The merging judging unit is used for judging whether the time interval of the adjacent two-time apnea events is smaller than the merging duration, merging the adjacent two-time apnea events into one apnea event if the time interval of the adjacent two-time apnea events is smaller than the merging duration, and taking the adjacent two-time apnea events as two apnea events if the time interval of the adjacent two-time apnea events is larger than or equal to the merging duration;
the final judging unit is used for judging whether the duration of each apnea event exceeds the early warning duration, and if so, the apnea event is used as a final apnea event;
and the report generation module is used for counting the periodical respiration and the apnea times and generating a report.
The radar signal-based infant respiratory problem detection system of the present embodiment can effectively detect periodic respiratory and apnea events of different individuals in different heart lung activity modes, and the detection system adopts an adaptive respiratory problem determination method, and the principle is realized based on the change of respiratory signal envelope amplitude, because periodic respiratory can be reflected on the periodicity of a segment envelope signal, and the occurrence of apnea can be intuitively reflected on the abrupt decrease of respiratory amplitude. According to the detection method flowchart shown in fig. 2, the detection method of the detection system for infant respiratory problem based on radar signals of the present embodiment mainly includes the following steps:
Step 1: and acquiring radar I/Q signals, wherein the radar I/Q signals are obtained by detecting a thoracic region of a detection object focused by a short-range radar, and the thoracic motion of the detection object modulates the phase of the radar signals. Chest motion x (t) can be seen as a plurality of sinusoidal signal components, while the radar modulated raw output signal can be expressed as:
Wherein a I and a Q are amplitudes of the I signal and the Q signal, θ is a constant phase shift, ΔΦ is a residual phase noise, λ is a carrier wavelength, and DC I and DC Q are DC offsets in the I signal and the Q signal.
Step 2: the I and Q signals are preprocessed as the case may be, including but not limited to median filtering to eliminate possible ambient electromagnetic interference, low pass filtering to eliminate in-band high frequency noise interference, savitzky-Golay finite impulse response filters to remove residual dc components. The displacement signal preprocessing is beneficial to improving the robustness of the subsequent algorithm and reducing the judgment error.
Step 3: and detecting body movement according to the preprocessed I signal and the preprocessed Q signal. Because the radar system monitors the detected object for a long time, the detected object easily interferes with the apnea judgment based on the amplitude change of the cardiopulmonary signal due to the large-amplitude body motion signals caused by adjusting sleeping posture, turning over and the like. Thus, body movements need to be detected first to be incorporated into the processing of the subsequent algorithm to remove this disturbance. Since body motion is a clutter signal with higher frequency than human heart and lung activity, the I signal and the Q signal are divided into a plurality of signal segments by step 31, and the zero crossing rate rate_zc of each signal segment is calculated: if the zero crossing rate zc is higher than the empirically set zero crossing rate threshold R1 at step 32, then body motion is considered to have occurred at this signal segment and marked for body motion time.
The body movement detection is realized by calculating the zero crossing rate in the time domain, the interference on body movement detection caused by amplitude change caused by position and posture does not exist, and the body movement detection has a good detection effect on random unstable body movement, so that the misjudgment of the apnea caused by the body movement interference is reduced.
Step 4: and detecting the position according to the preprocessed I signal and the preprocessed Q signal. In addition to the aforementioned large body movements, the subject may deviate spontaneously or passively or leave the detection range entirely. In this case the signal to noise ratio of the signal is low and may interfere with subsequent decisions. The present embodiment therefore performs position detection to ensure that the processed signal segments are all valid. Since there is a significantly high snr respiration signal when the detected target is in the proper position, after the signal is divided into segments of 3 minutes in step 41, the energy Ratio between the respiration frequency band and the low frequency band is calculated in step 42, and if the energy Ratio ratio_resp is higher than the empirically set energy Ratio threshold R2, the position is considered to be proper and the signals in proper positions are combined to obtain the effective radar I signal and the effective radar Q signal. Since the respiratory rate of the premature infant is known to be generally between 30 bpm and 90bpm, the respiratory frequency band is set to be 0.5 Hz to 1.5Hz in the present embodiment, the low frequency band is set to be 0.5 Hz to 5Hz, and the comparison of the spectral energy of the two frequency bands can be expressed as:
According to the invention, the target respiration signal-to-noise ratio is detected by calculating the energy ratio of the respiration frequency band to the low frequency band, so that whether the detection target is at the proper detection position is judged, and the detection target is always at the proper detection position in a system reminding mode or the like, so that the optimal effect of an algorithm is ensured, and meanwhile, the infant is ensured to be positioned in the safety range of the bed.
Step 5: envelope extraction is performed on the effective radar I signal and the Q signal. In the step, the upper envelope and the lower envelope of the effective radar I signal and the effective radar Q signal are respectively extracted, the difference value is obtained, the amplitudes Env I and Env Q of the I signal and the Q signal can be obtained, the maximum value is selected from the two, and the envelope signal corresponding to the maximum value is the target envelope signal Env.
The method aims at the radar to select the I signal and the Q signal for envelope analysis, so that the problems of demodulation signal errors and the like caused by unbalance of the I signal and the Q signal are avoided, the number of sampling points can be reduced to represent the envelope low-frequency signal so as to improve the calculation efficiency, and the condition that one path of signal is in a blind spot is avoided when the maximum amplitude envelope is extracted.
Step 6: typically, the periodic breathing of a neonate is defined as a period of at least 3 breaths and apnoea intervals, each period having a duration of 10 to 40 seconds, which is also manifested in the chest amplitude. Step 61 is thus performed on the target envelope signal Env extracted in the previous step, adding a sliding window 1 of self-set length, preferably a length slightly greater than 3 periodic breathing cycles, and consistent in rhythm. To better extract the period of the periodic breath, the autocorrelation calculation of step 62 is performed on the envelope signal within each sliding window 1, which can be expressed as:
Where g (t) is a function of the sliding window 1. And carrying out peak statistics on the autocorrelation waveform obtained after the autocorrelation calculation, counting the number pksnum1 of peaks which are more than 0.5 times of the highest peak, carrying out step 63, and if the number pksnum1 of the peaks is less than or equal to a set value n1, judging that no periodic waveform exists in the sliding window 1, otherwise, entering the next step. The average interval mind between the peaks of the autocorrelation waveform is calculated and step 64 is performed, and if the average interval mind is less than the set value d, where d may be set to 10 seconds, the signal within the sliding window 1 is considered not to be within the frequency range of the periodic breath of the infant. If the average interval mind is greater than the set value d, then step 65 is performed to fourier transform the autocorrelation waveform to obtain a power spectrum, and the peak of the power spectrum in the range of 0.002Hz to 0.5Hz is obtained. Step 66 determines whether the signal frequency is within the range of the periodic breathing of the infant, i.e. compares whether the frequency of the highest peak of the power spectrum is within the range of 0.025Hz to 0.2Hz, and if so proceeds to the next step. Calculating the peak number pksnum2 which is greater than 0.4 times the highest peak in the power spectrum, and proceeding to step 67, if the peak number pksnum is greater than or equal to the set value n2, it can be regarded that there are not only 1 main periodic signals in the sliding window 1, the periodic breathing condition is not satisfied, otherwise, proceeding to the next step. The set value n2 in the present embodiment may be set to 3. And step 68, calculating an upper envelope part or a lower envelope part of the envelope signal Env, and performing linear fitting on the upper envelope part or the lower envelope part to obtain an envelope slope, wherein if the envelope slope is smaller than a set value K, the signal in the sliding window 1 is considered to be a stable periodic signal.
Step 7: because different individuals tend to have different breathing amplitudes at different times. In order to enhance the applicability, a varying threshold is thus designed in this step from the previous period of data of the same person. First, the chest relative displacement envelope signal is subjected to step 71, adding a self-setting length of sliding window 2, preferably a length that is set slightly greater than the detected maximum apnoea duration. The sliding window 2 will slide forward in steps of one data point. Then, within each sliding window 2, a step 72 is performed, i.e. the current threshold TH is calculated in real time. Thereafter, the amplitude of the last data point of the sliding window 2 is compared 73 with the corresponding current threshold TH: if the magnitude of the data point is above the threshold TH, the data point is one that constitutes an event other than an apnea, and step 74 is entered when the magnitude of the data point is below the threshold TH. The threshold TH is set here in the manner of:
Where N is the number of data points in the second sliding window, b is a weight factor, TH [ N ] represents a threshold value of an nth data point in the target envelope signal, and Env [ k ] represents an amplitude value of a kth data point in the target envelope signal. The threshold TH calculated in this way has a corresponding threshold for each data point, except that the signal in the first sliding window 2 has the same threshold. Step 74, counting all the data points satisfying step 73, and calculating the total time t_last when the data point amplitude is lower than the threshold value TH. Detecting an apnea event under the condition of avoiding body movement disturbance, and merging two adjacent apnea events when the interval event is short, namely according to step 71, firstly comparing whether the total time t_last is greater than an apnea detection time t_detect of a self-set length, wherein the apnea detection time t_detect can be set to be a length less than 10 seconds; then comparing whether the last body movement time t_motion of the current data point is greater than the body movement neglect duration t_ignore with the self-set length, wherein the body movement neglect duration t_ignore can be set to be a duration close to the length of the sliding window 2 in the embodiment; when both of the above comparisons are affirmative, a preliminary decision will be made on the apneic event, i.e. the apneic event needs to initially meet both conditions for a certain duration and not immediately following body movement. Next, according to step 75, the time interval t_adj of adjacent two preliminarily determined apneic events is compared with the combined duration t_merge of self-set length: if the time interval t_adj is smaller than the merging duration t_merge, step 77 is performed to merge the two preliminary apneic events into one apneic event, otherwise the two preliminary apneic events are independent two apneic events. This operation is to avoid the case where the same apneic event is separated into two events due to sudden signal fluctuation, and the body movement neglect period t_merge may be set to 3 seconds in this embodiment. Then, according to step 78, the duration t_event of each apneic event is compared with the apneic early warning duration t_turn of the self-set length: if the duration t_event is longer than the early warning duration t_warn, the apnea event is considered to be the apnea event which finally needs to be reported, otherwise, the apnea event which does not need to be reported is considered to be the apnea event which does not need to be reported, and the apnea event is ignored. The duration t_wave of the apnea pre-warning in this embodiment may be set to 5 seconds, and the apnea occurring during the periodic breathing of the infant is generally between 5 and 15 seconds.
The invention realizes periodic respiration judgment based on the envelope waveform of the thoracic cavity displacement signal, provides basis for observing the occurrence frequency and the frequency of periodic respiration of the detection target, and further avoids the adverse consequences of repeated hypoxia and the like of infants caused by periodic respiration. The invention also discloses an apnea judgment method based on the chest displacement signal envelope waveform, and the method can be used for adaptively generating the threshold value by combining a specific algorithm, so that the method can adapt to the characteristic of unstable breathing of infants and has better sensitivity.
Step8: step 81 is performed to detect the number and duration of occurrences of the final respective periodic breath segments and apneic events and generate a report as per step 82.
Fig. 3 shows a radar signal, a thoracic envelope signal and a determination result of a premature infant with periodic breathing and an apnea of less than 10 seconds in length. The radar detects the chest movement of the subject during this time and outputs the original I and Q signals 9, which after envelope extraction, obtain the chest amplitude envelope signal of the detection target and the periodic breath fragments 10 detected by the algorithm, and the apnea result and body movement signal 11 are determined by the algorithm. The process of periodic respiration of the detection target can be seen: at 12 is a periodic breath segment, the envelope signal shows a definite periodicity, and then the target is detected to recover normal breath; the apneic events detected during periodic breaths are marked 13, the apneic events detected during normal breaths are marked 14, and the body movement signals are marked 15. The periodic breathing duration in the report is 300 seconds, and total of 12 apneic events, and the duration of each apneic event is respectively: 9 seconds, 6 seconds, 7 seconds, 6 seconds, 8 seconds, 9 seconds, 6 seconds, and 7 seconds.
Fig. 4 shows a radar signal, thoracic envelope signal and determination result of an apnea of a premature infant having a length longer than 20 seconds. During this time the radar detects the chest movement of the subject and outputs raw I-and Q-signals 16, which after envelope extraction result in a chest amplitude envelope signal of the detection target and an algorithmically detected periodic breathing segment 17, and an algorithmically determined apnea result and body movement signal 18. It can be observed that the detected target is subjected to typical apnea, and the process is as follows: the target is detected at 19 as normal breathing, then a short apnea occurs (marker 20), then the target resumes a weak breath (marker 21), but a longer duration apnea occurs soon (marker 22), then normal breathing is resumed (marker 23). Other apneic fragments have similar patterns. The periodic breathing duration in the output report is 0 seconds, 9 times of apnea events are total, and the duration of each apnea is respectively as follows: 7 seconds, 6 seconds, 9 seconds, 59 seconds, 24 seconds, 45 seconds, 6 seconds, and 16 seconds.
It is easy to find that the invention detects based on respiratory envelope signals instead of respiratory signals, and can reduce the number of signal sampling points, so that the consumption of computing resources is reduced and the operation speed is increased. The invention is instantly available, does not need a great amount of data training in the early stage of a user, can continuously detect, can carry out offline analysis on long-period signals of sleeping in the whole night, and can process continuously-occurring apnea events. The invention can be used under the conditions of different individuals, different sleeping postures and different breathing states, and has strong applicability.
A second embodiment of the present invention relates to a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the detection method of the infant respiratory problem detection system based on radar signals of the first embodiment.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, magnetic disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A radar signal-based infant respiratory problem detection system, comprising:
the acquisition module is used for acquiring radar I/Q signals, wherein the radar I/Q signals are obtained by monitoring chest movements of a detected object during sleep through a short-range radar;
The validity detection module is used for detecting the validity of the radar I/Q signal to obtain a valid radar I/Q signal segment;
The extraction module is used for extracting the envelope signal of the effective radar I/Q signal segment and obtaining a target envelope signal according to the amplitude of the envelope signal;
and the periodic breath detection module is used for carrying out periodic breath detection according to the envelope slope of the target envelope signal.
2. The radar signal based infant respiratory problem detection system of claim 1, wherein the validity detection module includes:
the body movement detection unit is used for detecting body movement according to the zero crossing rate of the radar I/Q signal and marking at the position where the body movement occurs to obtain body movement time;
The position detection unit is used for carrying out position detection according to the energy ratio of the respiratory frequency band of the radar I/Q signal, and taking the radar I/Q signal segment with effective position detection as an effective radar I/Q signal segment.
3. The radar signal based infant respiratory problem detection system of claim 2, wherein the body movement detection unit includes:
The first segmentation subunit is used for segmenting the radar I/Q signal into a plurality of signal segments;
the zero crossing rate calculation subunit is used for calculating the zero crossing rate of each signal segment;
The zero crossing rate judging subunit is used for judging whether the zero crossing rate exceeds a zero crossing rate threshold value;
And the marking subunit is used for indicating that the corresponding signal segment appears body movement when the zero crossing rate exceeds the zero crossing rate threshold value, and marking the signal segment to obtain the body movement time.
4. The radar signal based infant breathing problem detection system of claim 2, wherein the position detection unit comprises:
The second segmentation subunit is used for segmenting the radar I/Q signal into a plurality of non-overlapping fragments according to preset time;
The energy ratio calculating subunit is used for calculating the energy ratio of the respiratory frequency band of the signal in each segment to the preset frequency band;
an energy ratio judging subunit for judging whether the energy ratio exceeds an energy ratio threshold;
And the merging subunit is used for merging the fragments corresponding to the energy ratio exceeding the energy ratio threshold value to obtain the effective radar I/Q signal fragments.
5. The radar signal based infant respiratory problem detection system of claim 1, wherein the extraction module comprises:
The first extraction and calculation unit is used for extracting an envelope signal of an I signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the I signal;
The second extraction and calculation unit is used for extracting an envelope signal of the Q signal in the radar I/Q signal and calculating an amplitude difference value of the envelope signal of the Q signal;
and the target envelope signal determining unit is used for comparing the amplitude difference value of the envelope signal of the I signal with the amplitude difference value of the envelope signal of the Q signal, and taking the envelope signal corresponding to the larger value of the amplitude difference value of the I signal and the amplitude difference value of the envelope signal of the Q signal as the target envelope signal.
6. The radar signal based infant respiratory problem detection system of claim 1, wherein the periodic respiratory detection module comprises:
A first sliding window setting unit configured to set a first sliding window on the target envelope signal, the first sliding window sliding forward without overlapping;
The autocorrelation calculating unit is used for carrying out autocorrelation operation on the signal in the first sliding window to obtain an autocorrelation waveform;
A first statistics judgment unit for counting the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform, and judging whether the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
An average interval calculating unit for calculating an average interval between peaks in the autocorrelation waveform when the number of peaks exceeding 0.5 times the highest peak in the autocorrelation waveform exceeds a first peak number threshold;
An interval judging unit for judging whether the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold; a power spectrum peak value acquisition unit for, when the average interval between peaks in the autocorrelation waveform exceeds a peak interval threshold value,
Performing Fourier transform on the autocorrelation waveform to obtain a power spectrum;
a peak value judging unit for judging whether the highest peak of the power spectrum in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2 Hz;
A second statistical judgment unit for counting the number of peaks exceeding 0.4 times the highest peak in the power spectrum when the highest peak in the range of 0.002Hz to 0.5Hz is in the range of 0.025Hz to 0.2Hz, and judging whether the number of peaks exceeding 0.4 times the highest peak in the power spectrum is smaller than a second peak number threshold;
An envelope slope calculation unit, configured to calculate an upper half or a lower half of the target envelope signal when the number of peaks exceeding 0.4 times of the highest peak in the power spectrum is smaller than a second peak number threshold, and perform linear fitting on the upper half or the lower half of the target envelope signal to obtain an envelope slope;
an envelope slope judging unit for judging whether the envelope slope is smaller than a slope threshold;
And the periodic respiration judging unit is used for recognizing the signal in the first sliding window as a periodic signal when the slope of the envelope is smaller than the slope threshold value.
7. The radar signal based infant respiratory problem detection system of claim 2, further comprising:
And the apnea detection module is used for detecting the apnea according to the target envelope signal and the body movement time.
8. The radar signal based infant respiratory problem detection system of claim 7, wherein the apnea detection module comprises:
A second sliding window setting unit configured to set a second sliding window on the target envelope signal, the second sliding window sliding forward in a step of one data point;
a threshold calculation unit for calculating a threshold value of each data point;
A comparison unit for comparing the amplitude of the last data point in the second sliding window with the threshold value of the last data point;
the time length counting unit is used for counting the number that the amplitude of the last data point in the second sliding window is smaller than the threshold value of the last data point, and obtaining corresponding time length;
the preliminary judgment unit is used for judging an apnea event when the duration is longer than the preset apnea detection duration and the current data point is longer than the preset body movement neglect duration from the last body movement time;
The merging judging unit is used for judging whether the time interval of the adjacent two-time apnea events is smaller than the merging duration, merging the adjacent two-time apnea events into one apnea event if the time interval of the adjacent two-time apnea events is smaller than the merging duration, and taking the adjacent two-time apnea events as two apnea events if the time interval of the adjacent two-time apnea events is larger than or equal to the merging duration;
And the final judging unit is used for judging whether the duration of each apnea event exceeds the early warning duration, and if so, taking the apnea event as a final apnea event.
9. The radar signal based infant respiratory problem detection system of claim 8, wherein the threshold calculation unit is configured to calculate the threshold value byAnd calculating a threshold value of each data point, wherein TH [ N ] represents the threshold value of the nth data point in the target envelope signal, b is a weight factor, N is the number of data points in the second sliding window, and Env [ k ] represents the amplitude of the kth data point in the target envelope signal.
10. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of a detection method employing the radar signal based infant breathing problem detection system according to any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410278980.5A CN118161127A (en) | 2024-03-12 | 2024-03-12 | Infant respiratory problem detection system based on radar signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410278980.5A CN118161127A (en) | 2024-03-12 | 2024-03-12 | Infant respiratory problem detection system based on radar signals |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118161127A true CN118161127A (en) | 2024-06-11 |
Family
ID=91355909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410278980.5A Pending CN118161127A (en) | 2024-03-12 | 2024-03-12 | Infant respiratory problem detection system based on radar signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118161127A (en) |
-
2024
- 2024-03-12 CN CN202410278980.5A patent/CN118161127A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dao et al. | A robust motion artifact detection algorithm for accurate detection of heart rates from photoplethysmographic signals using time–frequency spectral features | |
| CN111938613B (en) | Health monitoring device and method based on millimeter wave radar | |
| Vadrevu et al. | Real-time PPG signal quality assessment system for improving battery life and false alarms | |
| US10492720B2 (en) | System and method for determining sleep stage | |
| Paalasmaa et al. | Adaptive heartbeat modeling for beat-to-beat heart rate measurement in ballistocardiograms | |
| Goldman et al. | Masimo signal extraction pulse oximetry | |
| Al-Angari et al. | Automated recognition of obstructive sleep apnea syndrome using support vector machine classifier | |
| Reddy et al. | On-device integrated PPG quality assessment and sensor disconnection/saturation detection system for IoT health monitoring | |
| EP2020919B1 (en) | Apparatus, system, and method for monitoring physiological signs | |
| Giannetti et al. | Heuristic algorithm for photoplethysmographic heart rate tracking during maximal exercise test | |
| JP2010120493A (en) | Biological signal detection device | |
| KR102523994B1 (en) | Apparatus for judgment of drinking using vital sign and method thereof | |
| Kwon et al. | Hybrid CNN-LSTM network for real-time apnea-hypopnea event detection based on IR-UWB radar | |
| de Goederen et al. | Radar-based sleep stage classification in children undergoing polysomnography: a pilot-study | |
| EP3386383A1 (en) | Non-contact diagnosis and monitoring of sleep disorders | |
| Sun et al. | PPG signal motion artifacts correction algorithm based on feature estimation | |
| WO2008132736A2 (en) | Method and device for characterizing sleep | |
| Grisan et al. | A supervised learning approach for the robust detection of heart beat in plethysmographic data | |
| Reddy et al. | Unified quality-aware compression and pulse-respiration rates estimation framework for reducing energy consumption and false alarms of wearable PPG monitoring devices | |
| CN117064349B (en) | Gesture control method and system for linkage of millimeter wave radar and intelligent bed | |
| CN117530666A (en) | Breathing abnormality recognition model training method, breathing abnormality recognition method and equipment | |
| Guo et al. | An effective photoplethysmography heart rate estimation framework integrating two-level denoising method and heart rate tracking algorithm guided by finite state machine | |
| CN118161127A (en) | Infant respiratory problem detection system based on radar signals | |
| Wen et al. | Noncontact Infant Apnea Detection for Hypoxia Prevention With a K-Band Biomedical Radar | |
| Darwin et al. | A detailed review on embedded based heartbeat monitoring systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |