mm-Wave Radar-Based Vital Signs Monitoring and Arrhythmia Detection Using Machine Learning
<p>Schematic of the proposed mm-wave radar system: an mm-wave radar is fixed at front of the subject while an Omron sphygmomanometer is attached, which simultaneously extracts pulse readings for verification. The radar data are recorded on a PC through a USB connection.</p> "> Figure 2
<p>Transmitted and received chirp signals where each chirp is a sinusoidal signal with a slope S and time delay between transmitted and received chirp <math display="inline"><semantics> <mi>τ</mi> </semantics></math> when the sweeping bandwidth is <span class="html-italic">S</span><math display="inline"><semantics> <mrow> <mi>τ</mi> </mrow> </semantics></math>.</p> "> Figure 3
<p>A MIMO radar with two transmitting antennas (Tx) and four receiving antennas (Rx) where distance between two receiving antennas is <math display="inline"><semantics> <mrow> <msub> <mi>d</mi> <mi>m</mi> </msub> </mrow> </semantics></math> and <math display="inline"><semantics> <mi>θ</mi> </semantics></math> is the angle of arrival.</p> "> Figure 4
<p>Signal processing workflow: after applying the range FFT, for a single range bin, the angle FFTs are computed, upon which the phase shift is used to extract the heartbeat and breathing waves.</p> "> Figure 5
<p>Symmetric triangular wave function to model the QRS components of an ECG signal.</p> "> Figure 6
<p>Predict the onset of arrhythmia based on statistical features extracted from the phase signals of a localized range bin using an FMCW radar.</p> "> Figure 7
<p>ECG signal pre-processing (left to right): ECG signals are extracted using electrodes mounted on the body. Hence, some artifacts are filtered out before statistical features can be extracted from the ECG signal database. Artifacts include muscle tremor, electromagnetic interference (EMI) and base-line wander. Muscle tremor artifacts caused due to sudden body movements are high-frequency signals (30~300 Hz) that are removed by Butterworth low-pass filters. The 50 Hz electromagnetic interference is suppressed by a Butterworth band-stop filter. Baseline wander is an ultra-low frequency signal that ranges between 0 and 0.8 Hz that can be eliminated using a high-pass filter. Finally, the resultant R peaks of a QRS complex are detected, and only RR interval-based features are extracted since the radar-generated heartbeat phase signals are QRS equivalent signals.</p> "> Figure 8
<p>A confusion matrix that summarizes the model performance with true positivity rate and true negativity rate, with accuracy of 100%, 90% and 93.9%, respectively.</p> "> Figure 9
<p>The mean squared error during training reduced to a very low value at the 9th epoch. However, with early stopping enabled, the best performance was obtained at the 3rd epoch when the validation MSE = 0.025.</p> "> Figure 10
<p>Gradient optimization using gradient descent and momentum.</p> "> Figure 11
<p>Periodogram of input heartbeat phase signal.</p> "> Figure 12
<p>Signal reconstruction using symmetric triangular wave function, which was then down sampled to 5 Hz to match the sampling frequency of the ECG signals used in the training dataset.</p> "> Figure 13
<p>Periodogram of reconstructed phase signal shows that maximal power spectral density (PSD) lies in the frequency = 1.133 Hz.</p> "> Figure 14
<p>Signal-to-noise ratio (<b>a</b>) SNR of input signal, (<b>b</b>) SNR of reconstructed signal using symmetrical triangular QRS wave function.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. FMCW Radars
2.2. Process Flow for the Detection of Vital Signs
2.3. Heartbeat Signal Generation
2.4. Arrhythmia Detection Using Neural Networks
3. Results and Discussion
3.1. Measured Data Validation
3.2. Effect of Orientation and Distance on Measurement
- Range = 30 cm: As highlighted in green, the number of outliers for front and back were nil, while for right and left orientations the outliers had the greatest values. HR values (highlighted in yellow) when estimated in the front faired the best while analysis shows that BR was least skewed when obtained on the right side with minimized MSE and SD.
- Range = 60 cm: Again, the number of outliers for the front and back were nil while both the right and left suffered maximum skewness. The MSE and SD values of HR and BR were the least for the front, which performed the best.
- Range = 90 cm: Front and back orientations produced better results in terms of minimum outliers and lower SD values with an exception for the left position, which minimized skewness better.
- Range = 120 cm: Following the previous trend, right and left orientations produced poor results with the maximum number of outliers and highly skewed data. Again, individuals oriented in front of the radar outperformed other orientations.
- Range = 150 cm: We observed that some of the HR and BR values were estimated to be 0 as the radar was unable to pick up any chest displacements when the person was seated to the left or right. This is reflected in the analysis, which shows the presence of outliers and maximum skewness and SD.
3.3. Effect of Movements on Measurement
- Range = 20 cm: The HR values while walking produced better results than standing as it generated no outliers and lesser standard deviation. While standing, the number of outliers, SD and MSE was lesser than that of values obtained when walking.
- Range = 40 cm: In this case, for both BR and HR, it is quite clear that best results were obtained when the person was standing.
- Range = 60 cm: Surprisingly, this range was observed to be the optimal distance for monitoring a moving person. The number of outliers was 0, and values were less skewed. Though BR values while walking had a higher deviation, it is important to note that the skewness value was almost negligible.
3.3.1. Validating Heart Rate Values during Movement
3.3.2. Validating Breathing Rate Values
3.4. Signal Processing and Arrhythmia Detection
3.4.1. ECG Signal Processing
3.4.2. Radar Heartbeat Signal Processing
3.4.3. Arrhythmia Detection Test
4. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Prgomet, M.; Cardona-Morrell, M.; Nicholson, M.; Lake, R.; Long, J.; Westbrook, J.; Braithwaite, J.; Hillman, K. Vital signs monitoring on general wards: Clinical staff perceptions of current practices and the planned introduction of continuous monitoring technology. Int. J. Qual. Health Care 2016, 28, 515–521. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Burch, V.C.; Tarr, G.; Morroni, C. Modified early warning score predicts the need for hospital admission and inhospital mortality. Emerg. Med. J. 2008, 25, 674–678. [Google Scholar] [CrossRef] [PubMed]
- Weenk, M.; van Goor, H.; Frietman, B.; Engelen, L.J.; van Laarhoven, C.J.; Smit, J.; Bredie, S.J.; van de Belt, T.H. Continuous Monitoring of Vital Signs Using Wearable Devices on the General Ward: Pilot Study. JMIR Mhealth Uhealth 2017, 5, e91. [Google Scholar] [CrossRef] [PubMed]
- Villarroel, M.; Guazzi, A.; Jorge, J.; Davis, S.; Watkinson, P.; Green, G.; Shenvi, A.; McCormick, K.; Tarassenko, L. Continuous non-contact vital sign monitoring in neonatal intensive care unit. Health Technol. Lett. 2014, 1, 87–91. [Google Scholar] [CrossRef] [Green Version]
- Ginsburg, A.S.; Lenahan, J.L.; Izadnegahdar, R.; Ansermino, J.M. A Systematic Review of Tools to Measure Respiratory Rate in Order to Identify Childhood Pneumonia. Am. J. Respir. Crit. Care Med. 2018, 197, 1116–1127. [Google Scholar] [CrossRef]
- Lv, Q.; Chen, L.; An, K.; Wang, J.; Li, H.; Ye, D.; Huangfu, J.; Li, C.; Ran, L. Doppler Vital Signs Detection in the Presence of Large-Scale Random Body Movements. IEEE Trans. Microw. Theory Tech. 2018, 66, 4261–4270. [Google Scholar] [CrossRef]
- Droitcour, A.; Lubecke, V.; Lin, J.; Boric-Lubecke, O. A microwave radio for Doppler radar sensing of vital signs. In Proceedings of the 2001 IEEE MTT-S International Microwave Sympsoium Digest (Cat. No.01CH37157), Phoenix, AZ, USA, 20–24 May 2001; pp. 175–178. [Google Scholar]
- Lubecke, O.; Ong, P.-W.; Lubecke, V. 10 GHz Doppler radar sensing of respiration and heart movement. In Proceedings of the IEEE 28th Annual Northeast Bioengineering Conference (IEEE Cat. No. 02CH37342), Philadelphia, PA, USA, 21 April 2002; pp. 55–56. [Google Scholar] [CrossRef]
- Wang, J.; Wang, X.; Chen, L.; Huangfu, J.; Li, C.; Ran, L. Noncontact Distance and Amplitude-Independent Vibration Measurement Based on an Extended DACM Algorithm. IEEE Trans. Instrum. Meas. 2014, 63, 145–153. [Google Scholar] [CrossRef]
- Hu, W.; Zhao, Z.; Wang, Y.; Zhang, H.; Lin, F. Noncontact Accurate Measurement of Cardiopulmonary Activity Using a Compact Quadrature Doppler Radar Sensor. IEEE Trans. Biomed. Eng. 2013, 61, 725–735. [Google Scholar] [CrossRef]
- Tu, J.; Lin, J. Fast Acquisition of Heart Rate in Noncontact Vital Sign Radar Measurement Using Time-Window-Variation Technique. IEEE Trans. Instrum. Meas. 2015, 65, 112–122. [Google Scholar] [CrossRef]
- Schires, E.; Georgiou, P.; Lande, T.S. Vital Sign Monitoring Through the Back Using an UWB Impulse Radar With Body Coupled Antennas. IEEE Trans. Biomed. Circuits Syst. 2018, 12, 292–302. [Google Scholar] [CrossRef]
- Lee, Y.; Park, J.-Y.; Choi, Y.-W.; Park, H.-K.; Cho, S.H.; Cho, S.H.; Lim, Y.-H. A Novel Non-contact Heart Rate Monitor Using Impulse-Radio Ultra-Wideband (IR-UWB) Radar Technology. Sci. Rep. 2018, 8, 1–10. [Google Scholar] [CrossRef] [PubMed]
- Wang, G.; Munoz-Ferreras, J.-M.; Gu, C.; Li, C.; Gomez-Garcia, R. Application of Linear-Frequency-Modulated Continuous-Wave (LFMCW) Radars for Tracking of Vital Signs. IEEE Trans. Microw. Theory Tech. 2014, 62, 1387–1399. [Google Scholar] [CrossRef]
- Wang, S.; Pohl, A.; Jaeschke, T.; Czaplik, M.; Kony, M.; Leonhardt, S.; Pohl, N. A novel ultra-wideband 80 GHz FMCW radar system for contactless monitoring of vital signs. In Proceedings of the 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy, 25–29 August 2015; Volume 2015, pp. 4978–4981. [Google Scholar] [CrossRef]
- He, M.; Nian, Y.; Gong, Y. Novel signal processing method for vital sign monitoring using FMCW radar. Biomed. Signal Proc. Control 2017, 33, 335–345. [Google Scholar] [CrossRef]
- Ahmad, A.; Roh, J.C.; Wang, D.; Dubey, A. Vital signs monitoring of multiple people using a FMCW millimeter-wave sensor. In Proceedings of the 2018 IEEE Radar Conference, Oklahoma City, OK, USA, 23–27 April 2018. [Google Scholar]
- Lazaro, A.; Girbau, D.; Villarino, R. Analysis of vital signs monitoring using an IR-UWB radar. Prog. Electromagn. Res. 2010, 100, 265–284. [Google Scholar] [CrossRef] [Green Version]
- Schleicher, B.; Nasr, I.; Trasser, A.; Schumacher, H. IR-UWB radar demonstrator for ultra-fine movement detection and vital-sign monitoring. IEEE Trans. Microw. Theory Tech. 2013, 61, 2076–2085. [Google Scholar] [CrossRef] [Green Version]
- Yang, X.; Yin, W.; Li, L.; Zhang, L. Dense People Counting Using IR-UWB Radar With a Hybrid Feature Extraction Method. IEEE Geosci. Remote Sens. Lett. 2018, 16, 30–34. [Google Scholar] [CrossRef]
- Liang, X.; Zhang, H.; Ye, S.; Fang, G.; Aaron Gulliver, T. Improved Denoising Method for Through-Wall VitalSign Detection Using UWB Impulse Radar. Digit. Signal Process. 2018, 74, 72–93. [Google Scholar] [CrossRef]
- Rana, S.P.; Dey, M.; Ghavami, M.; Dudley, S. Signature Inspired Home Environments Monitoring System Using IR-UWB Technology. Sensors 2019, 19, 385. [Google Scholar] [CrossRef] [Green Version]
- Wang, P.; Zhang, Y.; Ma, Y.; Liang, F.; An, Q.; Xue, H.; Yu, X.; Lv, H.; Wang, J. Method for Distinguishing Humans and Animals in Vital Signs Monitoring Using IR-UWB Radar. Int. J. Environ. Res. Public Health 2019, 16, 4462. [Google Scholar] [CrossRef] [Green Version]
- Wang, D.; Yoo, S.; Cho, S.H. Experimental Comparison of IR-UWB Radar and FMCW Radar for Vital Signs. Sensors 2020, 20, 6695. [Google Scholar] [CrossRef]
- Sakamoto, T.; Imasaka, R.; Taki, H.; Sato, T.; Yoshioka, M.; Inoue, K.; Fukuda, T.; Sakai, H. Feature-based Correlation and Topological Similarity for Interbeat Interval Estimation using Ultra-Wideband Radar. IEEE Trans. Biomed. Eng. 2015, 63, 747–757. [Google Scholar] [CrossRef] [PubMed]
- Gu, C. Short-Range Noncontact Sensors for Healthcare and Other Emerging Applications: A Review. Sensors 2016, 16, 1169. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Gabriel, S.; Lau, R.W.; Gabriel, C. The dielectric properties of biological tissues: II. Measurements in the frequency range 10 Hz to 20 GHz. Phys. Med. Biol. 1996, 41, 2251–2269. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- World Health Organization. Electromagnetic Fields and Public Health: Radars and Human Health; World Health Organization: Geneva, Switzerland, 1999; Available online: https://www.jeic-emf.jp/assets/files/Fact%20Sheets/facrt_sheet_226.pdf (accessed on 1 January 2020).
- Alizadeh, M.; Shaker, G.; De Almeida, J.C.M.; Morita, P.P.; Safavi-Naeini, S. Remote Monitoring of Human Vital Signs Using mm-Wave FMCW Radar. IEEE Access 2019, 7, 54958–54968. [Google Scholar] [CrossRef]
- Alizadeh, M.; Shaker, G.; Safavi-Naeini, S. Experimental study on the phase analysis of FMCW radar for vital signs detection. In Proceedings of the 13th European Conference on Antennas and Propagation (EuCAP), Krakow, Poland, 31 March–5 April 2019; pp. 1–4. [Google Scholar]
- Villar, R.; Beltrame, T.B.; Hughson, R.L. Validation of the Hexoskin wearable vest during lying, sitting, standing, and walking activities. Appl. Physiol. Nutr. Metab. 2015, 40, 1019–1024. [Google Scholar] [CrossRef] [PubMed]
- Budge, M.; Burt, M. Range correlation effects in radars. In Proceedings of the The Record of the 1993 IEEE National Radar Conference, Lynnfield, MA, USA, 20–22 April 1993; pp. 212–216. [Google Scholar] [CrossRef]
- Goldberger, A.; Amaral, L.; Glass, L.; Hausdorff, J.; Ivanov, P.C.; Mark, R.; Stanley, H.E. PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation 2020, 101, e215–e220. [Google Scholar] [CrossRef] [Green Version]
- Moody, G.B.; Mark, R.G. The impact of the MIT-BIH Arrhythmia Database. IEEE Eng. Med. Biol. Mag. 2001, 20, 45–50. [Google Scholar] [CrossRef]
Parameters | Value |
---|---|
Starting frequency | 77 GHz |
Slow axis sampling | 20 Hz (chirps/s) |
Chirp duration | 50 µs |
ADC sampling rate | 2 Msps |
Range resolution | 4.3 cm |
Transmitted power | 10 dBm |
Autotuned Parameters | Value |
---|---|
Input dense layer | 8 nodes |
Hidden dense layer | 16 nodes |
Output dense layer | 1 node |
Learning rate | 0.01 |
L1 Regularization | 0 |
L2 Regularization | 0 |
Epochs | 10 |
Metric | OMRON | Radar |
---|---|---|
Avg HR | 74 | 74 |
Variance | 13.95 | 8.5 |
STD | 3.83 | 2.99 |
R2 | 0.164 | |
Root mean square error (RMSE) | 2.81 | |
Mean absolute error (MAE) | 1.9 | |
Median absolute error (MedAE) | 2 |
Distance (cm) | Orientation | Vital Sign | Upper Bound | Lower Bound | Outliers | Mean | MSE | MAE | medAE | SD |
---|---|---|---|---|---|---|---|---|---|---|
30 | front | HR | 85.375 | 78.375 | 0 | 81.8 | 0.296 | 2.1 | 2 | 1.8 |
BR | 13.25 | 7.25 | 0 | 10.6 | 0.124 | 0.96 | 0.9 | 1.2 | ||
right | HR | 87.375 | 58.375 | 0 | 72.3 | 3.741 | 4.9 | 4 | 6.4 | |
BR | 8 | 8 | 3 | 8.1 | 0.029 | 0.36 | 0.1 | 0.6 | ||
left | HR | 86.625 | 57.625 | 0 | 72.4 | 2.904 | 4.6 | 4 | 5.7 | |
BR | 10.5 | 6.5 | 2 | 9.7 | 1.061 | 2.12 | 1.5 | 3.4 | ||
back | HR | 90.75 | 58.75 | 0 | 75.6 | 2.704 | 4.24 | 5 | 5.5 | |
BR | 32.75 | 0.75 | 0 | 17.6 | 3.424 | 4.76 | 3.9 | 6.2 | ||
60 | front | HR | 92.125 | 67.125 | 0 | 80.1 | 3.129 | 4.46 | 4 | 5.9 |
BR | 14 | 6 | 0 | 10.4 | 0.144 | 1.12 | 1.4 | 1.3 | ||
right | HR | 103.25 | 39.25 | 0 | 72 | 9.6 | 8.8 | 8.5 | 10 | |
BR | 15.875 | 4.875 | 1 | 10.7 | 0.701 | 2.24 | 1.7 | 2.8 | ||
left | HR | 91 | 63 | 1 | 76 | 4.42 | 5.2 | 4 | 7 | |
BR | 19.625 | 2.625 | 1 | 11.9 | 2.009 | 3.66 | 2.9 | 4.7 | ||
back | HR | 81.75 | 67.75 | 3 | 74.1 | 4.269 | 4.7 | 2 | 6.9 | |
BR | 29.5 | 3.5 | 0 | 16.5 | 1.905 | 3.9 | 3.5 | 4.6 | ||
90 | front | HR | 89.5 | 63.5 | 0 | 75.5 | 3.285 | 4.6 | 4 | 6 |
BR | 10.5 | 6.5 | 1 | 8.8 | 0.076 | 0.64 | 0.5 | 0.9 | ||
right | HR | 91.375 | 54.375 | 1 | 72.2 | 6.956 | 6.6 | 4.7 | 8.8 | |
BR | 16.5 | 4.5 | 2 | 12.9 | 4.649 | 5.24 | 3.9 | 7.2 | ||
left | HR | 94.375 | 63.375 | 0 | 78.6 | 3.004 | 4.92 | 3.6 | 5.8 | |
BR | 24.75 | −3.25 | 1 | 12.1 | 7.029 | 6.54 | 4.6 | 8.8 | ||
back | HR | 86.125 | 61.125 | 0 | 73.7 | 1.721 | 3.5 | 3.3 | 4.4 | |
BR | 30.375 | −4.625 | 0 | 13.2 | 1.996 | 3.76 | 4.8 | 4.7 | ||
120 | front | HR | 104.25 | 56.25 | 0 | 78.6 | 8.624 | 7.72 | 5.1 | 9.8 |
BR | 14 | 6 | 0 | 9.9 | 0.129 | 1.1 | 1.1 | 1.2 | ||
right | HR | 86.375 | 55.375 | 0 | 71.5 | 2.705 | 4.4 | 3.5 | 5.5 | |
BR | 19.5 | 1.5 | 0 | 11 | 1.5 | 3.4 | 3 | 4.1 | ||
left | HR | 93.5 | 57.5 | 1 | 73.7 | 9.841 | 7.42 | 5.5 | 10 | |
BR | 23.25 | −0.75 | 2 | 12.9 | 5.169 | 5.86 | 4.4 | 7.6 | ||
back | HR | 87.875 | 52.875 | 0 | 69 | 4.56 | 5.4 | 5.5 | 7.1 | |
BR | 36.25 | −5.75 | 0 | 15.2 | 2.636 | 4.6 | 5.8 | 5.4 | ||
150 | front | HR | 88.875 | 63.875 | 0 | 75.9 | 1.949 | 3.88 | 3.5 | 4.7 |
BR | 12.75 | 6.75 | 0 | 9.6 | 0.144 | 1.04 | 0.6 | 1.3 | ||
right | HR | 87.125 | 54.125 | 1 | 70.8 | 8.296 | 7.4 | 4.5 | 9.6 | |
BR | 19.875 | −9.125 | 0 | 7.3 | 3.041 | 4.44 | 4.5 | 5.8 | ||
left | HR | 92.375 | 61.375 | 1 | 74.8 | 6.056 | 5.96 | 5 | 8.2 | |
BR | 31.25 | −18.75 | 0 | 7.9 | 6.509 | 6.5 | 7 | 8.5 | ||
back | HR | 91.25 | 57.25 | 0 | 73.7 | 2.721 | 4.7 | 4.5 | 5.5 | |
BR | 34.625 | −2.375 | 0 | 16.8 | 5.156 | 6.16 | 5 | 7.6 |
Distance (cm) | Activity | Vital Sign | Upper Bound | Lower Bound | Outliers | Mean | MSE | MAE | MedAE | SD |
---|---|---|---|---|---|---|---|---|---|---|
20 | standing | HR | 74.88 | 71.88 | 4 | 72 | 62.8 | 5.4 | 1.5 | 8.35 |
BR | 10.5 | 6.5 | 1 | 9 | 1.04 | 0.8 | 0.6 | 1.07 | ||
walking | HR | 85.5 | 59.5 | 0 | 73 | 14.6 | 3.48 | 3.5 | 4.03 | |
BR | 28.88 | 3.875 | 2 | 18 | 52.3 | 5.68 | 4.4 | 7.62 | ||
40 | standing | HR | 77.5 | 65.5 | 0 | 72 | 6.56 | 2.2 | 1.8 | 2.7 |
BR | 16.13 | 3.125 | 1 | 11 | 18.6 | 3.32 | 2.8 | 4.54 | ||
walking | HR | 74.5 | 62.5 | 2 | 70 | 23.7 | 3.36 | 2.1 | 5.13 | |
BR | 34.5 | −3.5 | 0 | 17 | 49.6 | 5.4 | 4.5 | 7.42 | ||
60 | standing | HR | 88 | 64 | 2 | 74 | 38.4 | 4.84 | 4.2 | 6.53 |
BR | 16.5 | 4.5 | 1 | 11 | 13.8 | 2.56 | 2 | 3.92 | ||
walking | HR | 81.88 | 68.88 | 0 | 75 | 10.5 | 2.66 | 1.9 | 3.41 | |
BR | 29.63 | 0.625 | 0 | 14 | 23 | 3.88 | 4.5 | 5.06 |
Distance | Activity | Vital Sign | Mean | MSE | MAE | medAE | SD | R Square |
---|---|---|---|---|---|---|---|---|
20 | standing | HR | 72 | 97.61 | 7.72 | 4.9 | 8.353 | 0.285137 |
walking | HR | 73 | 42.73 | 5.3 | 3.9 | 4.033 | 0.6193151 | |
40 | standing | HR | 72 | 43.77 | 6.1 | 5.9 | 2.7 | 0.833473 |
walking | HR | 70 | 84.53 | 8.22 | 7.9 | 5.131 | 0.688605 | |
60 | standing | HR | 74 | 55.17 | 5.36 | 2.5 | 6.529 | 0.2274384 |
walking | HR | 75 | 18.33 | 3.22 | 1.9 | 3.414 | 0.3641268 |
Distance | Activity | Vital Sign | Mean | MSE | MAE | medAE | SD |
---|---|---|---|---|---|---|---|
20 | standing | BR | 9 | 1.04 | 0.8 | 0.6 | 1.07497 |
walking | BR | 18 | 52.29 | 5.68 | 4.4 | 7.62234 | |
40 | standing | BR | 11 | 18.56 | 3.32 | 2.8 | 4.54117 |
walking | BR | 17 | 49.6 | 5.4 | 4.5 | 7.42369 | |
60 | standing | BR | 11 | 13.81 | 2.56 | 2 | 3.9172 |
walking | BR | 14 | 23.04 | 3.88 | 4.5 | 5.05964 |
Specifications | Normal Sinus Dataset | Arrhythmia Dataset |
---|---|---|
Sampling frequency (Hz) | 128 | 360 |
Number of samples | 1280 | 3600 |
Gain (adu/mV) | 200 | 200 |
Baseline | 0 | 1024 |
Subject ID | Age | Gender | Testing Accuracy | Predicted | Actual | False Positives |
---|---|---|---|---|---|---|
1 | 22 | male | 60% | Normal | Normal | 4 |
2 | 24 | male | 90% | Normal | Normal | 1 |
3 | 23 | male | 60% | Normal | Normal | 4 |
4 | 30 | female | 80% | Normal | Normal | 2 |
5 | 20 | male | 100% | Normal | Normal | 0 |
6 | 25 | male | 60% | Normal | Normal | 4 |
7 | 50 | female | 90% | Normal | Normal | 1 |
8 | 45 | female | 100% | Normal | Normal | 0 |
9 | 68 | male | 60% | Arrhythmia | Arrhythmia | 4 |
10 | 69 | male | 80% | Arrhythmia | Arrhythmia | 2 |
11 | 69 | male | 70% | Arrhythmia | Arrhythmia | 3 |
12 | 51 | female | 20% | Arrhythmia | Arrhythmia | 8 |
13 | 83 | female | 80% | Arrhythmia | Arrhythmia | 2 |
14 | 51 | male | 80% | Arrhythmia | Arrhythmia | 2 |
15 | 63 | female | 90% | Arrhythmia | Arrhythmia | 1 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Iyer, S.; Zhao, L.; Mohan, M.P.; Jimeno, J.; Siyal, M.Y.; Alphones, A.; Karim, M.F. mm-Wave Radar-Based Vital Signs Monitoring and Arrhythmia Detection Using Machine Learning. Sensors 2022, 22, 3106. https://doi.org/10.3390/s22093106
Iyer S, Zhao L, Mohan MP, Jimeno J, Siyal MY, Alphones A, Karim MF. mm-Wave Radar-Based Vital Signs Monitoring and Arrhythmia Detection Using Machine Learning. Sensors. 2022; 22(9):3106. https://doi.org/10.3390/s22093106
Chicago/Turabian StyleIyer, Srikrishna, Leo Zhao, Manoj Prabhakar Mohan, Joe Jimeno, Mohammed Yakoob Siyal, Arokiaswami Alphones, and Muhammad Faeyz Karim. 2022. "mm-Wave Radar-Based Vital Signs Monitoring and Arrhythmia Detection Using Machine Learning" Sensors 22, no. 9: 3106. https://doi.org/10.3390/s22093106