Integrated lithium niobate microwave photonic processing engine.

Integrated microwave photonics (MWP) is an intriguing technology for the generation, transmission and manipulation of microwave signals in chip-scale optical systems1,2. In particular, ultrafast processing of analogue signals in the optical domain with high fidelity and low latency could enable a variety of applications such as MWP filters3-5, microwave signal processing6-9 and image recognition10,11. An ideal integrated MWP processing platform should have both an efficient and high-speed electro-optic modulation block to faithfully perform microwave-optic conversion at low power and also a low-loss functional photonic network to implement various signal-processing tasks. Moreover, large-scale, low-cost manufacturability is required to monolithically integrate the two building blocks on the same chip. Here we demonstrate such an integrated MWP processing engine based on a 4 inch wafer-scale thin-film lithium niobate platform. It can perform multipurpose tasks with processing bandwidths of up to 67 GHz at complementary metal-oxide-semiconductor (CMOS)-compatible voltages. We achieve ultrafast analogue computation, namely temporal integration and differentiation, at sampling rates of up to 256 giga samples per second, and deploy these functions to showcase three proof-of-concept applications: solving ordinary differential equations, generating ultra-wideband signals and detecting edges in images. We further leverage the image edge detector to realize a photonic-assisted image segmentation model that can effectively outline the boundaries of melanoma lesion in medical diagnostic images. Our ultrafast lithium niobate MWP engine could provide compact, low-latency and cost-effective solutions for future wireless communications, high-resolution radar and photonic artificial intelligence.

A rADAR defense against RNAi.

Adenosine deaminases that act on RNA (ADARs) convert adenosines (A) to inosines (I) in stretches of dsRNA. The biological purpose of these editing events for the vast majority of ADAR substrates is largely unknown. In this issue of Genes & Development, Reich and colleagues (pp. 271-282) demonstrate that in Caenorhabditis elegans, A-to-I editing in double-stranded regions of protein-coding transcripts protects these RNAs from targeting by the RNAi pathway. Disruption of this safeguard through loss of ADAR activity coupled with enhanced RNAi results in developmental abnormalities and profound changes in gene expression that suggest aberrant induction of an antiviral response. Thus, editing of cellular dsRNA by ADAR helps prevent host RNA silencing and inadvertent antiviral activity.

Effects of rare kidney diseases on kidney failure: a longitudinal analysis of the UK National Registry of Rare Kidney Diseases (RaDaR) cohort.

BACKGROUND: Individuals with rare kidney diseases account for 5-10% of people with chronic kidney disease, but constitute more than 25% of patients receiving kidney replacement therapy. The National Registry of Rare Kidney Diseases (RaDaR) gathers longitudinal data from patients with these conditions, which we used to study disease progression and outcomes of death and kidney failure. METHODS: People aged 0-96 years living with 28 types of rare kidney diseases were recruited from 108 UK renal care facilities. The primary outcomes were cumulative incidence of mortality and kidney failure in individuals with rare kidney diseases, which were calculated and compared with that of unselected patients with chronic kidney disease. Cumulative incidence and Kaplan-Meier survival estimates were calculated for the following outcomes: median age at kidney failure; median age at death; time from start of dialysis to death; and time from diagnosis to estimated glomerular filtration rate (eGFR) thresholds, allowing calculation of time from last eGFR of 75 mL/min per 1·73 m2 or more to first eGFR of less than 30 mL/min per 1·73 m2 (the therapeutic trial window). FINDINGS: Between Jan 18, 2010, and July 25, 2022, 27 285 participants were recruited to RaDaR. Median follow-up time from diagnosis was 9·6 years (IQR 5·9-16·7). RaDaR participants had significantly higher 5-year cumulative incidence of kidney failure than 2·81 million UK patients with all-cause chronic kidney disease (28% vs 1%; p<0·0001), but better survival rates (standardised mortality ratio 0·42 [95% CI 0·32-0·52]; p<0·0001). Median age at kidney failure, median age at death, time from start of dialysis to death, time from diagnosis to eGFR thresholds, and therapeutic trial window all varied substantially between rare diseases. INTERPRETATION: Patients with rare kidney diseases differ from the general population of individuals with chronic kidney disease: they have higher 5-year rates of kidney failure but higher survival than other patients with chronic kidney disease stages 3-5, and so are over-represented in the cohort of patients requiring kidney replacement therapy. Addressing unmet therapeutic need for patients with rare kidney diseases could have a large beneficial effect on long-term kidney replacement therapy demand. FUNDING: RaDaR is funded by the Medical Research Council, Kidney Research UK, Kidney Care UK, and the Polycystic Kidney Disease Charity.

Developing a deep learning model for sleep stage prediction in obstructive sleep apnea cohort using 60 GHz frequency-modulated continuous-wave radar.

Given the significant impact of sleep on overall health, radar technology offers a promising, non-invasive, and cost-effective avenue for the early detection of sleep disorders, even prior to relying on polysomnography (PSG)-based classification. In this study, we employed an attention-based bidirectional long short-term memory (Attention Bi-LSTM) model to accurately predict sleep stages using 60 GHz frequency-modulated continuous-wave (FMCW) radar. Our dataset comprised 78 participants from an ongoing obstructive sleep apnea (OSA) cohort, recruited between July 2021 and November 2022, who underwent overnight polysomnography alongside radar sensor monitoring. The dataset encompasses comprehensive polysomnography recordings, spanning both sleep and wakefulness states. The predictions achieved a Cohen's kappa coefficient of 0.746 and an overall accuracy of 85.2% in classifying wakefulness, rapid-eye-movement (REM) sleep, and non-REM (NREM) sleep (N1 + N2 + N3). The results demonstrated that the models incorporating both Radar 1 and Radar 2 data consistently outperformed those using only Radar 1 data, indicating the potential benefits of utilising multiple radars for sleep stage classification. Although the performance of the models tended to decline with increasing OSA severity, the addition of Radar 2 data notably improved the classification accuracy. These findings demonstrate the potential of radar technology as a valuable screening tool for sleep stage classification.

Radar-Guided Localization and Resection for Metastatic Nodal and Soft Tissue Melanoma: A Single-Institution Retrospective Study.

BACKGROUND: Radar-guided localization (RGL) offers a wire-free, nonradioactive surgical guidance method consisting of a small percutaneously-placed radar reflector and handheld probe. This study investigates the feasibility, timing, and outcomes of RGL for melanoma metastasectomy. METHODS: We retrospectively identified patients at our cancer center who underwent RGL resection of metastatic melanoma between December 2020-June 2023. Data pertaining to patients' melanoma history, management, reflector placement and retrieval, and follow-up was extracted from patient charts and analyzed using descriptive statistics. RESULTS: Twenty-three RGL cases were performed in patients with stage III-IV locoregional or oligometastatic disease, 10 of whom had reflectors placed prior to neoadjuvant therapy. Procedures included soft tissue nodule removals (8), index lymph node removals (13), and therapeutic lymph node dissections (2). Reflectors were located and retrieved intraoperatively in 96% of cases from a range of 2 to 282 days after placement; the last reflector was not able to be located during surgery via probe or intraoperative ultrasound. One retrieved reflector had migrated from the index lesion, thus overall success rate of reflector and associated index lesion removal was 21 of 23 (91%). All RGL-localized and retrieved index lesions that contained viable tumor (10) had microscopically negative margins. There were no complications attributable to reflector insertion and no unexpected complications of RGL surgery. CONCLUSION: In our practice, RGL is a safe and effective surgical localization method for soft tissue and nodal melanoma metastases. The inert nature of the reflector enables implantation prior to neoadjuvant therapy with utility in index lymph node removal.

There are a variety of tools available to localize melanoma that had spread to deep layers of the skin or lymph nodes that can guide surgeons to the cancer when the tumor cannot be felt. We evaluated a marker that reflects radar signals that has been studied in breast surgery but not in melanoma. The marker was placed in the tumor before surgery and was located during surgery using a handheld probe, guiding the surgeon to the correct location. An advantage of the radar-reflecting marker we studied is that since it is safe to stay in the body, it can be placed ahead of the use of cancer medications and can keep track of the tumor as it responds to treatment. In a review of 23 surgeries in which the radar-reflecting marker was used, there was one case where the marker migrated away from the tumor and one case where the marker was not able to be located. Monitoring or alternative definitive treatment was provided in each of these cases. Overall, we found the marker to be an effective tumor localization tool for surgeons and safe for patients. Other marker options available are unable or less suitable to be placed a long time in advance of surgery due to either technical or safety reasons, so the radar-reflecting marker is especially useful when it is placed in a tumor ahead of medical treatment leading up to planned surgical treatment.

Efficacy of Targeted Axillary Dissection With Radar Reflector Localization Before Neoadjuvant Chemotherapy.

INTRODUCTION: For clinically node positive breast cancer patients treated with neoadjuvant chemotherapy (NAC), targeted axillary dissection (TAD) can be used to stage the axilla. TAD removes the sentinel lymph node (SLN) and tagged positive nodes, which can be identified via radar reflector localization (RRL). As it can be challenging to localize a previously positive node after NAC, we evaluated RRL prior to NAC. METHODS: We performed a retrospective chart review of breast cancer patients with node positive disease treated with NAC who underwent TAD with RRL. We compared retrieval of radar reflector and clip, timing of localization, and, if a node was positive, whether the radar reflector node or SLN was positive. RESULTS: Seventy-nine patients fulfilled inclusion criteria; 32 were placed pre-NAC (mean 187 d before surgery) and 47 were placed post-NAC (mean 7 d before surgery). For pre-NAC placement, 31 of 32 radar reflectors and 31 of 32 clips were retrieved. For post-NAC placement, 47 of 47 radar reflectors and 46 of 47 clips were retrieved. There was no significant difference in radar reflector or clip retrieval rates between pre-NAC and post-NAC groups (P = 0.41, P = 1, respectively). Thirty of 32 patients with pathologic complete response avoided an axillary lymph node dissection. Of 47 patients with a positive lymph node, 32 were both the SLN and radar reflector node, 11 were radar reflector alone, and four were the SLN. CONCLUSIONS: RRL systems are an effective way to guide TAD, and RRL makers can be safely placed prior to NAC.

Use of bird-borne radar to examine shearwater interactions with legal and illegal fisheries.

Seabirds interact with fishing vessels to consume fishing discards and baits, sometimes resulting in incidental capture (bycatch) and the death of the bird, which has clear conservation implications. To understand seabird-fishery interactions at large spatiotemporal scales, researchers are increasing their use of simultaneous seabird and fishing vessel tracking. However, vessel tracking data can contain gaps due to technical problems, illicit manipulation, or lack of adoption of tracking monitoring systems. These gaps might lead to underestimating the fishing effort and bycatch rates and jeopardize the effectiveness of marine conservation. We deployed bird-borne radar detector tags capable of recording radar signals from vessels. We placed tags on 88 shearwaters (Calonectris diomedea, Calonectris borealis, and Calonectris edwardsii) that forage in the northwestern Mediterranean Sea and the Canary Current Large Marine Ecosystem. We modeled vessel radar detections registered by the tags in relation to gridded automatic identification system (AIS) vessel tracking data to examine the spatiotemporal dynamics of seabird-vessel interactions and identify unreported fishing activity areas. Our models showed a moderate fit (area under the curve >0.7) to vessel tracking data, indicating a strong association of shearwaters to fishing vessels in major fishing grounds. Although in high-marine-traffic regions, radar detections were also driven by nonfishing vessels. The tags registered the presence of potential unregulated and unreported fishing vessels in West African waters, where merchant shipping is unusual but fishing activity is intense. Overall, bird-borne radar detectors showed areas and periods when the association of seabirds with legal and illegal fishing vessels was high. Bird-borne radar detectors could improve the focus of conservation efforts.

Uso de radares en aves para analizar las interacciones de las pardelas con las pesquerías legales e ilegales Resumen Las aves marinas interactúan con los barcos pesqueros para consumir los cebos y lo que descartan, lo que a veces resulta en la captura accesoria y la muerte del ave, por lo que esto tiene implicaciones claras para la conservación. Los investigadores cada vez usan más el rastreo simultáneo de las aves marinas y los barcos pesqueros para comprender las interacciones aves marinas ­ pesquerías a gran escala espaciotemporal. Sin embargo, los datos del rastreo de barcos pueden incluir vacíos por problemas técnicos, manipulación ilícita o porque no adoptan sistemas para monitorear el rastreo. Estos vacíos pueden llevar a subestimar el esfuerzo de pesca y las tasas de captura accesoria y a comprometer la efectividad de la conservación marina. Desplegamos marcas detectoras de radar encima de aves capaces de registrar las señales de radar de los barcos. Colocamos estas marcas en 88 pardelas (Calonectris diomedea, C. borealis, y C. edwardsii) que forrajean en el noroeste del Mar Mediterráneo y el Gran Ecosistema Marino de Canarias. Modelamos las detecciones del radar de los barcos registradas por las marcas en relación con los datos reticulados de rastreo de barcos del sistema de identificación automático (AIS) para analizar las dinámicas espaciotemporales de las interacciones aves marinas­barcos e identificar áreas con actividad pesquera no reportada. Nuestros modelos mostraron un ajuste moderado (área bajo la curva > 0.7) a los datos de rastreo de barcos, lo que indica una fuerte asociación entre las pardelas y los barcos en los principales sitios de pesca, aunque en las regiones con alto tránsito de barcos las detecciones por radar también fueron causadas por barcos no pesqueros. Las marcas registraron la presencia del potencial de barcos pesqueros sin regular y sin reportar en aguas del oeste de África, en donde los buques mercantes son poco comunes pero la actividad pesquera es intensa. En general, los detectores por radar en las aves mostraron áreas y periodos en donde la asociación entre las aves marinas y los barcos pesqueros legales e ilegales es alta. Estos detectores por radar podrían mejorar el enfoque de los esfuerzos de conservación.

Validation of the Sleepiz One + as a radar-based sensor for contactless diagnosis of sleep apnea.

PURPOSE: The cardiorespiratory polysomnography (PSG) is an expensive and limited resource. The Sleepiz One + is a novel radar-based contactless monitoring device that can be used e.g. for longitudinal detection of nocturnal respiratory events. The present study aimed to compare the performance of the Sleepiz One + device to the PSG regarding the accuracy of apnea-hypopnea index (AHI). METHODS: From January to December 2021, a total of 141 adult volunteers who were either suspected of having sleep apnea or who were healthy sleepers took part in a sleep study. This examination served to validate the Sleepiz One + device in the presence and absence of additional SpO2 information. The AHI determined by the Sleepiz One + monitor was estimated automatically and compared with the AHI derived from manual PSG scoring. RESULTS: The correlation between the Sleepiz-AHI and the PSG-AHI with and without additional SpO2 measurement was rp = 0.94 and rp = 0,87, respectively. In general, the Bland-Altman plots showed good agreement between the two methods of AHI measurement, though their deviations became larger with increasing sleep-disordered breathing. Sensitivity and specificity for recordings without additional SpO2 was 85% and 88%, respectively. Adding a SpO2 sensor increased the sensitivity to 88% and the specificity to 98%. CONCLUSION: The Sleepiz One + device is a valid diagnostic tool for patients with moderate to severe OSA. It can also be easily used in the home environment and is therefore beneficial for e.g. immobile and infectious patients. TRIAL REGISTRATION NUMBER AND DATE OF REGISTRATION FOR PROSPECTIVELY REGISTERED TRIALS: This study was registered on clinicaltrials.gov (NCT04670848) on 2020-12-09.

Outdoor noncontact respiratory measurements of unrestricted rhesus macaques (Macaca mulatta) using millimeter-wave radar.

Respiration is an invaluable signal that facilitates the real-time observation of physiological dynamics. In recent years, the advancement of noncontact measurement technology has gained momentum in capturing physiological activities in natural settings. This technology is anticipated to be found not only in humans but also in nonhuman primates. Currently, the predominant noncontact approach for nonhuman animals involves measuring vital signs through subtle variations in skin color. However, this approach is limited when addressing areas of the body covered with hair or when working in outdoor settings under fluctuating sunlight. To overcome this issue, we focused on noncontact respiratory measurements using millimeter-wave radar. Millimeter-wave radar systems, which employ millimeter waves that can penetrate animal fur and estimate respiration-derived periodic body motion, exhibit minimal susceptibility to sunlight interference. Thus, this method shows potential for conducting noncontact vital measurements in natural and outdoor settings. In this study, we validated a millimeter-wave radar methodology for capturing respiration in outdoor-housed rhesus macaques (Macaca mulatta). The radar was positioned beyond the captive enclosure and maintained at a distance >5 m from the target. Millimeter waves were transmitted to the target, and the reflected waves were used to estimate skin surface displacement associated with respiration. The results revealed periodic skin surface displacement, and the estimated respiratory rates weres within the reported range of respiratory rates for rhesus macaques. These results suggest the potential applicability of millimeter-wave radar for noncontact respiration monitoring in outdoor-living macaques without anesthesia or immobilization. The continued advancement of noncontact vital measurement technology will contribute to understanding primate mental and physical dynamics during their daily life.

First noncontact millimeter-wave radar measurement of heart rate in great apes: Validation in chimpanzees (Pan troglodytes).

Heart rate is a crucial vital sign and a valuable indicator for assessing the physical and psychological condition of a target animal. Heart rate contributes to (1) fundamental information for cognitive research, (2) an indicator of psychological and physical stress, and (3) improving the animal welfare of captive animals, especially in nonhuman primate studies. Heart rate has been measured using a contact-type device; however, the device burdens the target animals and that there are risks associated with anesthesia during installation. This study explores the application of heartbeat measurement techniques using millimeter-wave radar, primarily developed for humans, as a remote and noninvasive method for measuring the heart rate of nonhuman primates. Through a measurement test conducted on two chimpanzees, we observed a remarkable correspondence between the peak frequency spectrum of heart rate estimated using millimeter-wave radar and the mean value obtained from electrocardiograph data, thereby validating the accuracy of the method. To the best of our knowledge, this is the first demonstration of the precise measurement of great apes' heart rate using millimeter-wave radar technology. Compared to heart rate measurement using video analysis, the method using millimeter-wave radar has the advantage that it is less susceptible to weather and lighting conditions and that measurement techniques for multiple individuals have been developed for human subjects, while its disadvantage is that validation of measurement from long distances has not been completed. Another disadvantage common to both methods is that measurement becomes difficult when the movement of the target individual is large. The possibility of noncontact measurement of heart rate in wild and captive primates will undoubtedly open up a new research area while taking animal welfare into consideration.

Variability in wet and dry snow radar zones in the North of the Antarctic Peninsula using a cloud computing environment.

This work investigated the annual variations in dry snow (DSRZ) and wet snow radar zones (WSRZ) in the north of the Antarctic Peninsula between 2015-2023. A specific code for snow zone detection on Sentinel-1 images was created on Google Earth Engine by combining the CryoSat-2 digital elevation model and air temperature data from ERA5. Regions with backscatter coefficients (σ°) values exceeding -6.5 dB were considered the extent of surface melt occurrence, and the dry snow line was considered to coincide with the -11 °C isotherm of the average annual air temperature. The annual variation in WSRZ exhibited moderate correlations with annual average air temperature, total precipitation, and the sum of annual degree-days. However, statistical tests indicated low determination coefficients and no significant trend values in DSRZ behavior with atmospheric variables. The results of reducing DSRZ area for 2019/2020 and 2020/2021 compared to 2018/2018 indicated the upward in dry zone line in this AP region. The methodology demonstrated its efficacy for both quantitative and qualitative analyses of data obtained in digital processing environments, allowing for the large-scale spatial and temporal variations monitoring and for the understanding changes in glacier mass loss.

Metformin-Associated Lactic Acidosis-Is This on Your Radar?

BACKGROUND: Metformin is a biguanide hyperglycemic agent used to manage non-insulin-dependent diabetes mellitus. Adverse reactions include mainly mild gastrointestinal adverse effects, but severe complications, such as metformin-associated lactic acidosis (MALA) can occur. Metformin is excreted renally and, therefore, not recommended in patients with renal impairment. The reported incidence of MALA is 3 cases per 100,000 patient-years. CASE REPORT: A 79-year-old woman with a complex medical history, including end-stage renal disease on dialysis and type 2 diabetes, presented to the emergency department (ED) for altered mental status. Prior to arrival, she was found to be hypoglycemic. Her laboratory results were significant for creatinine of 6.56 mg/dL and an anion gap of 52 mmol/L. The venous blood gas revealed a venous pH of 6.857 [reference range (7.32-7.43)], pCO2 of 15.9 mm Hg (40.6-60 mm Hg), HCO3 of 2.7 mmol/L (21-30 mmol/L), lactate of 27 mmol/L (0.5-2 mmol/L), and ammonia of 233 µmol/L. The patient was dialyzed emergently in the ED; repeat laboratory test results showed blood urea nitrogen of 10 mg/dL, creatinine of 1.65 mg/dL, carbon dioxide of 26 mmol/L, and anion gap of 13 mmol/L. The repeat ammonia was 16 µmol/L. The patient's metabolic encephalopathy resolved, and she was discharged home on hospital day 3. WHY SHOULD AN EMERGENCY PHYSICIAN BE AWARE OF THIS?: MALA has a high mortality rate (36%). Laboratory markers have not been found to be a reliable predictor of mortality. Sodium bicarbonate is controversial, but a pH < 7.15 indicates consideration of its use. A pH < 7.1 and a lactate level > 20 mmol/L indicate the need for emergent hemodialysis. Prompt recognition and management in the ED with early hemodialysis can result in good patient outcomes, with a return to their baseline function despite severe laboratory findings.

Heart Rate Variability Monitoring Based on Doppler Radar Using Deep Learning.

The potential of microwave Doppler radar in non-contact vital sign detection is significant; however, prevailing radar-based heart rate (HR) and heart rate variability (HRV) monitoring technologies often necessitate data lengths surpassing 10 s, leading to increased detection latency and inaccurate HRV estimates. To address this problem, this paper introduces a novel network integrating a frequency representation module and a residual in residual module for the precise estimation and tracking of HR from concise time series, followed by HRV monitoring. The network adeptly transforms radar signals from the time domain to the frequency domain, yielding high-resolution spectrum representation within specified frequency intervals. This significantly reduces latency and improves HRV estimation accuracy by using data that are only 4 s in length. This study uses simulation data, Frequency-Modulated Continuous-Wave radar-measured data, and Continuous-Wave radar data to validate the model. Experimental results show that despite the shortened data length, the average heart rate measurement accuracy of the algorithm remains above 95% with no loss of estimation accuracy. This study contributes an efficient heart rate variability estimation algorithm to the domain of non-contact vital sign detection, offering significant practical application value.

Chest Wall Motion Model of Cardiac Activity for Radar-Based Vital-Sign-Detection System.

An increasing number of studies on non-contact vital sign detection using radar are now beginning to turn to data-driven neural network approaches rather than traditional signal-processing methods. However, there are few radar datasets available for deep learning due to the difficulty of acquiring and labeling the data, which require specialized equipment and physician collaboration. This paper presents a new model of heartbeat-induced chest wall motion (CWM) with the goal of generating a large amount of simulation data to support deep learning methods. An in-depth analysis of published CWM data collected by the VICON Infrared (IR) motion capture system and continuous wave (CW) radar system during respiratory hold was used to summarize the motion characteristics of each stage within a cardiac cycle. In combination with the physiological properties of the heartbeat, appropriate mathematical functions were selected to describe these movement properties. The model produced simulation data that closely matched the measured data as evaluated by dynamic time warping (DTW) and the root-mean-squared error (RMSE). By adjusting the model parameters, the heartbeat signals of different individuals were simulated. This will accelerate the application of data-driven deep learning methods in radar-based non-contact vital sign detection research and further advance the field.

Introducing the Pi-CON Methodology to Overcome Usability Deficits during Remote Patient Monitoring.

The adoption of telehealth has soared, and with that the acceptance of Remote Patient Monitoring (RPM) and virtual care. A review of the literature illustrates, however, that poor device usability can impact the generated data when using Patient-Generated Health Data (PGHD) devices, such as wearables or home use medical devices, when used outside a health facility. The Pi-CON methodology is introduced to overcome these challenges and guide the definition of user-friendly and intuitive devices in the future. Pi-CON stands for passive, continuous, and non-contact, and describes the ability to acquire health data, such as vital signs, continuously and passively with limited user interaction and without attaching any sensors to the patient. The paper highlights the advantages of Pi-CON by leveraging various sensors and techniques, such as radar, remote photoplethysmography, and infrared. It illustrates potential concerns and discusses future applications Pi-CON could be used for, including gait and fall monitoring by installing an omnipresent sensor based on the Pi-CON methodology. This would allow automatic data collection once a person is recognized, and could be extended with an integrated gateway so multiple cameras could be installed to enable data feeds to a cloud-based interface, allowing clinicians and family members to monitor patient health status remotely at any time.

Remote Emotion Recognition Using Continuous-Wave Bio-Radar System.

The Bio-Radar is herein presented as a non-contact radar system able to capture vital signs remotely without requiring any physical contact with the subject. In this work, the ability to use the proposed system for emotion recognition is verified by comparing its performance on identifying fear, happiness and a neutral condition, with certified measuring equipment. For this purpose, machine learning algorithms were applied to the respiratory and cardiac signals captured simultaneously by the radar and the referenced contact-based system. Following a multiclass identification strategy, one could conclude that both systems present a comparable performance, where the radar might even outperform under specific conditions. Emotion recognition is possible using a radar system, with an accuracy equal to 99.7% and an F1-score of 99.9%. Thus, we demonstrated that it is perfectly possible to use the Bio-Radar system for this purpose, which is able to be operated remotely, avoiding the subject awareness of being monitored and thus providing more authentic reactions.

Cross-Modal Supervised Human Body Pose Recognition Techniques for Through-Wall Radar.

Through-wall radar human body pose recognition technology has broad applications in both military and civilian sectors. Identifying the current pose of targets behind walls and predicting subsequent pose changes are significant challenges. Conventional methods typically utilize radar information along with machine learning algorithms such as SVM and random forests to aid in recognition. However, these approaches have limitations, particularly in complex scenarios. In response to this challenge, this paper proposes a cross-modal supervised through-wall radar human body pose recognition method. By integrating information from both cameras and radar, a cross-modal dataset was constructed, and a corresponding deep learning network architecture was designed. During training, the network effectively learned the pose features of targets obscured by walls, enabling accurate pose recognition (e.g., standing, crouching) in scenarios with unknown wall obstructions. The experimental results demonstrated the superiority of the proposed method over traditional approaches, offering an effective and innovative solution for practical through-wall radar applications. The contribution of this study lies in the integration of deep learning with cross-modal supervision, providing new perspectives for enhancing the robustness and accuracy of target pose recognition.

Automatic Radar-Based Step Length Measurement in the Home for Older Adults Living with Frailty.

With an aging population, numerous assistive and monitoring technologies are under development to enable older adults to age in place. To facilitate aging in place, predicting risk factors such as falls and hospitalization and providing early interventions are important. Much of the work on ambient monitoring for risk prediction has centered on gait speed analysis, utilizing privacy-preserving sensors like radar. Despite compelling evidence that monitoring step length in addition to gait speed is crucial for predicting risk, radar-based methods have not explored step length measurement in the home. Furthermore, laboratory experiments on step length measurement using radars are limited to proof-of-concept studies with few healthy subjects. To address this gap, a radar-based step length measurement system for the home is proposed based on detection and tracking using a radar point cloud followed by Doppler speed profiling of the torso to obtain step lengths in the home. The proposed method was evaluated in a clinical environment involving 35 frail older adults to establish its validity. Additionally, the method was assessed in people's homes, with 21 frail older adults who had participated in the clinical assessment. The proposed radar-based step length measurement method was compared to the gold-standard Zeno Walkway Gait Analysis System, revealing a 4.5 cm/8.3% error in a clinical setting. Furthermore, it exhibited excellent reliability (ICC(2,k) = 0.91, 95% CI 0.82 to 0.96) in uncontrolled home settings. The method also proved accurate in uncontrolled home settings, as indicated by a strong consistency (ICC(3,k) = 0.81 (95% CI 0.53 to 0.92)) between home measurements and in-clinic assessments.

MF-Match: A Semi-Supervised Model for Human Action Recognition.

Human action recognition (HAR) technology based on radar signals has garnered significant attention from both industry and academia due to its exceptional privacy-preserving capabilities, noncontact sensing characteristics, and insensitivity to lighting conditions. However, the scarcity of accurately labeled human radar data poses a significant challenge in meeting the demand for large-scale training datasets required by deep model-based HAR technology, thus substantially impeding technological advancements in this field. To address this issue, a semi-supervised learning algorithm, MF-Match, is proposed in this paper. This algorithm computes pseudo-labels for larger-scale unsupervised radar data, enabling the model to extract embedded human behavioral information and enhance the accuracy of HAR algorithms. Furthermore, the method incorporates contrastive learning principles to improve the quality of model-generated pseudo-labels and mitigate the impact of mislabeled pseudo-labels on recognition performance. Experimental results demonstrate that this method achieves action recognition accuracies of 86.69% and 91.48% on two widely used radar spectrum datasets, respectively, utilizing only 10% labeled data, thereby validating the effectiveness of the proposed approach.

Identification of Respiratory Pauses during Swallowing by Unconstrained Measuring Using Millimeter Wave Radar.

Breathing temporarily pauses during swallowing, and the occurrence of inspiration before and after these pauses may increase the likelihood of aspiration, a serious health problem in older adults. Therefore, the automatic detection of these pauses without constraints is important. We propose methods for measuring respiratory movements during swallowing using millimeter wave radar to detect these pauses. The experiment involved 20 healthy adult participants. The results showed a correlation of 0.71 with the measurement data obtained from a band-type sensor used as a reference, demonstrating the potential to measure chest movements associated with respiration using a non-contact method. Additionally, temporary respiratory pauses caused by swallowing were confirmed by the measured data. Furthermore, using machine learning, the presence of respiring alone was detected with an accuracy of 88.5%, which is higher than that reported in previous studies. Respiring and temporary respiratory pauses caused by swallowing were also detected, with a macro-averaged F1 score of 66.4%. Although there is room for improvement in temporary pause detection, this study demonstrates the potential for measuring respiratory movements during swallowing using millimeter wave radar and a machine learning method.