Heartbeat Detection by Laser Doppler Vibrometry and Machine Learning

ECG waveform generation from radar signals: A deep learning perspective

Cardiovascular diagnostics relies heavily on the ECG (ECG), which reveals significant information about heart rhythm and function. Despite their significance, traditional ECG measures employing electrodes have limitations. As a result of extended electrode attachments, patients may experience skin irritation or pain, and motion artifacts may interfere with signal accuracy. Additionally, ECG monitoring usually requires highly trained professionals and specialized equipment, which increases the treatment's complexity and cost. In critical care scenarios, such as continuous monitoring of hospitalized patients, wearable sensors for collecting ECG data may be difficult to use. Although there are issues with ECG, it remains a valuable tool for diagnosing and monitoring cardiac disorders due to its non-invasive nature and the detailed information it provides about the heart. The goal of this study is to present an innovative method for generating continuous ECG waveforms from non-contact radar data by using Deep Learning. The method can eliminate the need for invasive or wearable biosensors and expensive equipment to collect ECGs. In this paper, we propose the MultiResLinkNet, a one-dimensional convolutional neural network (1D CNN) model for generating ECG signals from radar waveforms. With the help of a publicly accessible radar benchmark dataset, an end-to-end DL architecture is trained and assessed. There are six ports of raw radar data in this dataset, along with ground truth physiological signals collected from 30 participants in five distinct scenarios: Resting, Valsalva, Apnea, Tilt-up, and Tilt-down. By using strong temporal and spectral measurements, we assessed our proposed framework's ability to convert ECG data from Radar signals in three distinct scenarios, namely Resting, Valsalva, and Apnea (RVA). ECG segmentation performed better by MultiResLinkNet than by state-of-the-art networks in both combined and individual cases. As a result of the simulations, the resting, valsalva, and RVA scenarios showed the highest average temporal values, respectively: 66.09523 ± 19.33, 60.13625 ± 21.92, and 61.86265 ± 21.37. In addition, it exhibited the highest spectral correlation values (82.4388 ± 18.42 (Resting), 77.05186 ± 23.26 (Valsalva), 74.65785 ± 23.17 (Apnea), and 79.96201 ± 20.82 (RVA)), along with minimal temporal and spectral errors in almost every case. The qualitative evaluation revealed strong similarities between generated and actual ECG waveforms. As a result of our method of forecasting ECG patterns from remote radar data, we can monitor high-risk patients, especially those undergoing surgery.

A novel smart photoelectric lock system: Speech transmitted by laser and speech to text

We propose a circuit that modulates a speech signal to a laser, using which the speech signal can be transmitted using the laser. Also, it shows the use of a platform based on embedded ARM (Advanced RISC Machine), running a small deep learning model based on TDNN (Time delay neural network) and LSTM (Long short-term memory), and converting speech to text, and use the text cipher for unlocking. This research implements a smart lock system that can set a pre-record speech cipher and verify the similarity through a laser transmission speech cipher to unlock it. In our experiment result, the English speech of laser transmission can reach a WER (Word error rate) of 14.06% through the deep learning model to recognize the content of the speech cipher. We also design a similarity comparison algorithm based on LCS (Longest common subsequence) to compare the character set of the laser transmission speech compare and the prerecord speech cipher to calculate the similarity rate. Through the similarity comparison algorithm, when the WER is 27.27%, the male speech samples used in this study still have a 95% unlocking success rate, while the female speech samples have a 100% unlocking success rate. Compared with only using automatic speech recognition (ASR) to unlock, the method we propose is to compare the similarity of the content of speech cipher. The method significantly improves the unlocking fault tolerance of using lasers to transmit audio. Therefore, by using the laser to transmit the speech cipher, the usability of the photoelectric smart lock system has been significantly improved. At the same time, the characteristics of the laser are not easy to eavesdrop on the cipher, which can also improve security.

Non-invasive sensor methods used in monitoring newborn babies after birth, a clinical perspective

Background

Reducing the global new-born mortality is a paramount challenge for humanity. There are approximately 786,323 live births in the UK each year according to the office for National Statistics; around 10% of these newborn infants require assistance during this transition after birth. Each year around, globally around 2.5 million newborns die within their first month. The main causes are complications due to prematurity and during delivery. To act in a timely manner and prevent further damage, health professionals should rely on accurate monitoring of the main vital signs heart rate and respiratory rate.

Aims

To present a clinical perspective on innovative, non-invasive methods to monitor heart rate and respiratory rate in babies highlighting their advantages and limitations in comparison with well-established methods.

Methods

Using the data collected in our recently published systematic review we highlight the barriers and facilitators for the novel sensor devices in obtaining reliable heart rate measurements. Details about difficulties related to the application of sensors and interfaces, time to display, and user feedback are explored. We also provide a unique overview of using a non-invasive respiratory rate monitoring method by extracting RR from the pulse oximetry trace of newborn babies.

Results

Novel sensors to monitor heart rate offer the advantages of minimally obtrusive technologies but have limitations due to movement artefact, bad sensor coupling, intermittent measurement, and poor-quality recordings compared to gold standard well established methods. Respiratory rate can be derived accurately from pleth recordings in infants.

Conclusion

Some limitations have been identified in current methods to monitor heart rate and respiratory rate in newborn babies. Novel minimally invasive sensors have advantages that may help clinical practice. Further research studies are needed to assess whether they are sufficiently accurate, practical, and reliable to be suitable for clinical use.

Initial Study Using Electrocardiogram for Authentication and Identification

Recently, several studies have demonstrated the potential of electrocardiogram (ECG) to be used as a physiological signature for biometric systems (BS). We investigated the potential of ECG as a biometric trait for the identification and authentication of individuals. We used data from a public database, CYBHi, containing two off-the-person records from 63 subjects, separated by 3 months. For the BS, two templates were generated: (1) cardiac cycles (CC) and (2) scalograms. The identification with CC was performed with LDA, kNN, DT, and SVM, whereas a convolutional neural network (CNN) and a distance-based algorithm were used for scalograms. The authentication was performed with a distance-based algorithm, with a leave-one-out cross validation, for impostors evaluation. The identification system yielded accuracies of 79.37% and 69.84% for CC with LDA and scalograms with CNN, respectively. The authentication yielded an accuracy of 90.48% and an impostor score of 13.06% for CC, and it had an accuracy of 98.42% and an impostor score of 14.34% for scalograms. The obtained results support the claim that ECG can be successfully used for personal recognition. To the best of our knowledge, our study is the first to thoroughly compare templates and methodologies to optimize the performance of an ECG-based biometric system.

Contactless Vital Signs Monitoring From Videos Recorded With Digital Cameras: An Overview

The measurement of physiological parameters is fundamental to assess the health status of an individual. The contactless monitoring of vital signs may provide benefits in various fields of application, from healthcare and clinical setting to occupational and sports scenarios. Recent research has been focused on the potentiality of camera-based systems working in the visible range (380-750 nm) for estimating vital signs by capturing subtle color changes or motions caused by physiological activities but invisible to human eyes. These quantities are typically extracted from videos framing some exposed body areas (e.g., face, torso, and hands) with adequate post-processing algorithms. In this review, we provided an overview of the physiological and technical aspects behind the estimation of vital signs like respiratory rate, heart rate, blood oxygen saturation, and blood pressure from digital images as well as the potential fields of application of these technologies. Per each vital sign, we provided the rationale for the measurement, a classification of the different techniques implemented for post-processing the original videos, and the main results obtained during various applications or in validation studies. The available evidence supports the premise of digital cameras as an unobtrusive and easy-to-use technology for physiological signs monitoring. Further research is needed to promote the advancements of the technology, allowing its application in a wide range of population and everyday life, fostering a biometrical holistic of the human body (BHOHB) approach.

Recent Advances in Atherosclerotic Disease Screening Using Pervasive Healthcare

Atherosclerosis screening helps the medical model transform from therapeutic medicine to preventive medicine by assessing degree of atherosclerosis prior to the occurrence of fatal vascular events. Pervasive screening emphasizes atherosclerotic monitoring with easy access, quick process, and advanced computing. In this work, we introduced five cutting-edge pervasive technologies including imaging photoplethysmography (iPPG), laser Doppler, radio frequency (RF), thermal imaging (TI), optical fiber sensing and piezoelectric sensor. IPPG measures physiological parameters by using video images that record the subtle skin color changes consistent with cardiac-synchronous blood volume changes in subcutaneous arteries and capillaries. Laser Doppler obtained the information on blood flow by analyzing the spectral components of backscattered light from the illuminated tissues surface. RF is based on Doppler shift caused by the periodic movement of the chest wall induced by respiration and heartbeat. TI measures vital signs by detecting electromagnetic radiation emitted by blood flow. The working principle of optical fiber sensor is to detect the change of light properties caused by the interaction between the measured physiological parameter and the entering light. Piezoelectric sensors are based on the piezoelectric effect of dielectrics. All these pervasive technologies are noninvasive, mobile, and can detect physiological parameters related to atherosclerosis screening.

Emotion Recognition Based on Skin Potential Signals with a Portable Wireless Device

Emotion recognition is of great importance for artificial intelligence, robots, and medicine etc. Although many techniques have been developed for emotion recognition, with certain successes, they rely heavily on complicated and expensive equipment. Skin potential (SP) has been recognized to be correlated with human emotions for a long time, but has been largely ignored due to the lack of systematic research. In this paper, we propose a single SP-signal-based method for emotion recognition. Firstly, we developed a portable wireless device to measure the SP signal between the middle finger and left wrist. Then, a video induction experiment was designed to stimulate four kinds of typical emotion (happiness, sadness, anger, fear) in 26 subjects. Based on the device and video induction, we obtained a dataset consisting of 397 emotion samples. We extracted 29 features from each of the emotion samples and used eight well-established algorithms to classify the four emotions based on these features. Experimental results show that the gradient-boosting decision tree (GBDT), logistic regression (LR) and random forest (RF) algorithms achieved the highest accuracy of 75%. The obtained accuracy is similar to, or even better than, that of other methods using multiple physiological signals. Our research demonstrates the feasibility of the SP signal’s integration into existing physiological signals for emotion recognition.

Development of a High-Resolution All-Fiber Homodyne Laser Doppler Vibrometer

Based on the homodyne detection, a compact and cost-effective all-fiber laser Doppler vibrometer (LDV) with high resolution is presented. For the signal processing, the discrimination algorithm combined with the nonorthogonal correction is applied. The algorithm corrects the quadrature imbalance and other nonlinearity. In the calibration experiment, with the glass pasted on a piezoceramic transducer (PZT), the velocity resolution of 62 nm/s at 4 kHz and displacement resolution of 2.468 pm are achieved. For the LDV-based acousto-optic communication, the minimum detectable sound pressure level (SPL) reached 0.12 Pa under the hydrostatic air-water surface. The results demonstrate that the designed homodyne LDV has a low system background noise and can offer high precision in the vibration measurement.