Search Results (18)

Monitoring Peripheral Oxygen Saturation (SpO₂) is an important vital sign both in Intensive Care Units (ICUs), during surgery and convalescence, and as part of remote medical consultations after of the COVID-19 pandemic. This has made the development of new SpO₂-measurement tools an area of active research and opportunity. In this paper, we present a new Deep Learning (DL) combined strategy to estimate SpO₂ without contact, using pre-magnified facial videos to reveal subtle color changes related to blood flow and with no calibration per subject required. We applied the Eulerian Video Magnification technique using the Hermite Transform (EVM-HT) as a feature detector to feed a Three-Dimensional Convolutional Neural Network (3D-CNN). Additionally, parameters and hyperparameter Bayesian optimization and an ensemble technique over the dataset magnified were applied. We tested the method on 18 healthy subjects, where facial videos of the subjects, including the automatic detection of the reference from a contact pulse oximeter device, were acquired. As performance metrics for the SpO₂-estimation proposal, we calculated the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other parameters from the Bland–Altman (BA) analysis with respect to the reference. Therefore, a significant improvement was observed by adding the ensemble technique with respect to the only optimization, obtaining 14.32% in RMSE (reduction from 0.6204 to 0.5315) and 13.23% in MAE (reduction from 0.4323 to 0.3751). On the other hand, regarding Bland–Altman analysis, the upper and lower limits of agreement for the Mean of Differences (MOD) between the estimation and the ground truth were 1.04 and −1.05, with an MOD (bias) of −0.00175; therefore, MOD $\pm 1.96\sigma$ = −0.00175 ± 1.04. Thus, by leveraging Bayesian optimization for hyperparameter tuning and integrating a Bagging Ensemble, we achieved a significant reduction in the training error (bias), achieving a better generalization over the test set, and reducing the variance in comparison with the baseline model for SpO₂ estimation. Full article

Continuous-wave (CW) radar sensors can remotely measure respiration and heartbeat by detecting the periodic movements of internal organs. However, external disturbances, such as random body motion (RBM) or environmental interference, significantly degrade the signal-to-noise ratio (SNR) and reduce the accuracy of vital sign detection. The various motion cancellation techniques that have been proposed to enhance robustness against RBMs include improvements in radar architecture, advanced signal processing algorithms, and studies on electromagnetic propagation characteristics. This paper provides a comprehensive review of recent advancements in motion cancellation techniques for CW radar-based vital sign detectors and discusses future research directions to improve detection performance in dynamic environments. Full article

The interactions between economic development, environmental sustainability, population growth, and urbanization are vital in assessing the ecological dynamics of urban agglomerations. This study explores the relationship between economic development, environmental sustainability, population growth, and urbanization within the Xia-Zhang-Quan urban agglomeration in Fujian Province from 1989 to 2022. Utilizing Landsat remote sensing images, we calculated the Remote Sensing Ecological Index (RSEI) to evaluate changes in ecological quality. The results show that the average RSEI values for 1989, 2000, 2010, and 2022 were 0.5829, 0.5607, 0.5827, and 0.6195, respectively, indicating an initial decline followed by a significant increase, culminating in an overall upward trend. The spatial distribution of RSEI classification shows that the study area has the largest proportion of mainly “good” ecological quality. The proportion of areas with “excellent” ecological environmental quality has increased (13.41% in 1989 and 25.12% in 2022), while those with “general” quality has decreased (28.03% in 1989 and 21.21% in 2022). Over the past three decades, Xiamen experienced substantial ecological degradation (RSEI change of −0.0897), Zhangzhou showed marked improvement (RSEI change of 0.0519), and Quanzhou exhibited slight deterioration (RSEI change of −0.0396). Central urban areas typically had poorer ecological conditions but showed signs of improvement, whereas non-central urban regions demonstrated significant environmental enhancement. The factor detector analysis identified land use as the dominant factor influencing ecological environmental quality, with precipitation having a relatively minor impact. Interaction analysis revealed that all other factors demonstrated bi-variable enhancement or nonlinear enhancement, suggesting that the interactive effects of these factors are greater than the effects of individual factors alone. Land use consistently showed solid explanatory power. Temperature also exhibited significant influence in 2022 when interacting with other factors. Due to urban planning that can plan for land use, these findings suggest that effective urban planning can harmonize economic development with ecological protection within the Xia-Zhang-Quan urban agglomeration. Full article

For most patients admitted to a hospital, it is a requirement to continuously monitor their vital signs. Among these are the waveforms from ECG and the pulmonary arterial pulse. At present, there are several electronic devices that can measure the arterial pulse waveform. However, they can be affected by electromagnetic wave radiation, and the fabrication of electronic sensors is complicated and contributes to the e-waste, among other problems. In this paper, we propose an optical method to measure arterial pulse based on a Fabry-Perot interferometer composed of two mirrors. A pulse sensor formed by an acrylic cell with a thin membrane is used to gather the vasodilatation of the wrist, forming an air pulse that is enacted by means of a tube to a metallic cell containing a mirror that is glued to a thin silicone membrane. When the air pulse arrives, a displacement of the mirror takes place and produces a shift of the interference pattern fringes given by the Fabry-Perot. A detector samples the fringe intensity. With this method, an arterial pulse waveform is obtained. We characterize this optical device as a test of concept, and its application to measuring artery pulse is presented. The optical device is compared to other electronic devices. Full article

In targeted radionuclide therapy, determining the absorbed dose of the ligand distributed to the whole body is vital due to its direct influence on therapeutic and adverse effects. However, many targeted alpha therapy drugs present challenges for in vivo quantitative imaging. To address this issue, we developed a planar imaging system equipped with a cadmium telluride semiconductor detector that offers high energy resolution. This system also comprised a 3D-printed tungsten collimator optimized for high sensitivity to astatine-211, an alpha-emitting radionuclide, and adequate spatial resolution for mouse imaging. The imager revealed a spectrum with a distinct peak for X-rays from astatine-211 owing to the high energy resolution, clearly distinguishing these X-rays from the fluorescent X-rays of tungsten. High collimator efficiency (4.5 × 10⁻⁴) was achieved, with the maintenance of the spatial resolution required for discerning mouse tissues. Using this system, the activity of astatine-211 in thyroid cancer tumors with and without the expression of the sodium iodide symporter (K1-NIS/K1, respectively) was evaluated through in vivo imaging. The K1-NIS tumors had significantly higher astatine-211 activity (sign test, p = 0.031, n = 6) and significantly decreased post-treatment tumor volume (Student’s t-test, p = 0.005, n = 6). The concurrent examination of intratumor drug distribution and treatment outcome could be performed with the same mice. Full article

Background: Monitoring the vital signs of delirious patients in an intensive care unit (ICU) is challenging, as they might (un-)intentionally remove devices attached to their bodies. In mock-up scenarios, we systematically assessed whether a motion detector (MD) attached to the bed may help in identifying emergencies. Methods: We recruited 15 employees of the ICU and equipped an ICU bed with an MD (IRON Software GmbH, Grünwald, Germany). Participants were asked to replay 22 mock-up scenes of one-minute duration each: 12 scenes with movements and 10 without movements, of which 5 were emergency scenes (“lying dead-still, with no or very shallow breathing”). Blinded recordings were presented to an evaluation panel consisting of an experienced ICU nurse and a physician, who was asked to assess and rate the presence of motions. Results: Fifteen participants (nine women; 173 ± 7.0 cm; 78 ± 19 kg) joined the study. In total, 286 out of 330 scenes (86.7%) were rated correctly. Ratings were false negative (FN: “no movements detected, but recorded”) in 7 out of 180 motion scenes (3.9%). Ratings were false positive (FP: “movements detected, but not recorded”) in 37 out of 150 scenes (24.7%), more often in men than women (26 out of 60 vs. 11 out of 90, respectively; p < 0.001). Of note, in 16 of these 37 FP-rated scenes, a vibrating mobile phone was identified as a potential confounder. The emergency scenes were correctly rated in 64 of the 75 runs (85.3%); 10 of the 11 FP-rated scenes occurred in male subjects. Conclusions: The MD allowed for identifying motions of test subjects with high sensitivity (96%) and acceptable specificity (75%). Accuracy might increase further if activities are recorded continuously under real-world conditions. Full article

Small object detection has long been one of the most formidable challenges in computer vision due to the poor visual features and high noise of surroundings behind them. However, small targets in traffic scenes encompass a multitude of complex visual interfering factors, bearing crucial information such as traffic signs, traffic lights, and pedestrians. Given the inherent difficulties faced by generic models in addressing these issues, we conduct a comprehensive investigation on small target detection in this application scenario. In this work, we present a Cross-Layer Feature Fusion and Channel Attention algorithm based on a lightweight YOLOv5s design for traffic small target detection, named CFA-YOLO. To enhance the sensitivity of the model toward vital features, we embed the channel-guided Squeeze-and-Excitation (SE) block in the deep layer of the backbone. Moreover, the most excellent innovation of our work belongs to the effective cross-layer feature fusion method, which maintains robust feature fusion and information interaction capabilities; in addition, it simplifies redundant parameters compared with the baseline model. To align with the output features of the neck network, we adjusted the detection heads from three to two. Furthermore, we also applied the decoupled detection head for classification and bounding box regression tasks, respectively. This approach not only achieves real-time detection standards, but also improves the overall training results in parameter-friendly manner. The CFA-YOLO model significantly pays a lot of attention to the detail features of small targets, thereby it also has a great advantage in addressing the issue of poor performance in traffic small target detection results. Vast experiments have validated the efficiency and effectiveness of our proposed method in traffic small object detection. Compared with the latest lightweight detectors, such as YOLOv7-Tiny and YOLOv8s, our method consistently achieves superior performance both in terms of the model’s accuracy and complexity. Full article

Sudden cardiac death is a sudden and highly fatal condition. Implementing high-quality emergency cardiopulmonary resuscitation (CPR) early on is an effective rescue method for this disease. However, the rescue steps of CPR are complicated and difficult to remember, and the quantitative indicators are difficult to control, which leads to a poor quality of CPR emergency actions outside the hospital setting. Therefore, we have developed CPR emergency equipment with a multisensory feedback function, aiming to guide rescuers in performing CPR through visual, auditory, and tactile interaction. This equipment consists of three components: first aid clothing, an audio-visual integrated terminal, and a vital sign detector. These three components are based on a micro-power WiFi-Mesh network, enabling the long-term wireless transmission of the multisensor data. To evaluate the impact of the multisensory feedback CPR emergency equipment on nonprofessionals, we conducted a controlled experiment involving 32 nonmedical subjects. Each subject was assigned to either the experimental group, which used the equipment, or the control group, which did not. The main evaluation criteria were the chest compression (CC) depth, the CC rate, the precise depth of the CC ratio (5–6 cm), and the precise rate of the CC ratio -(100–120 times/min). The results indicated that the average CC depth in the experimental group was 51.5 ± 1.3 mm, which was significantly better than that of the control group (50.2 ± 2.2 mm, p = 0.012). Moreover, the average CC rate in the experimental group (110.1 ± 6.2 times/min) was significantly higher than that of the control group (100.4 ± 6.6 times/min) (p < 0.001). Compared to the control group (66.37%), the experimental group showed a higher proportion of precise CC depth (82.11%), which is closer to the standard CPR rate of 100%. In addition, the CC ratio of the precise rate was 93.75% in the experimental group, which was significantly better than that of 56.52% in the control group (p = 0.024). Following the experiment, the revised System Availability Scale (SUS) was utilized to evaluate the equipment’s usability. The average total SUS score was 78.594, indicating that the equipment’s acceptability range was evaluated as ‘acceptable’, and the overall adjective rating was ‘good’. In conclusion, the multisensory feedback CPR emergency equipment significantly enhances the CC performance (CC depth, CC rate, the precise depth of CC ratio, the precise rate of CC ratio) of nonprofessionals during CPR, and the majority of participants perceive the equipment as being easy to use. Full article

Modern wearable devices show promising results in terms of detecting vital bodily signs from the wrist. However, there remains a considerable need for a device that can conform to the human body’s variable geometry to accurately detect those vital signs and to understand health better. Flexible radio frequency (RF) resonators are well poised to address this need by providing conformable bio-interfaces suitable for different anatomical locations. In this work, we develop a compact wearable RF biosensor that detects multisite hemodynamic events due to pulsatile blood flow through noninvasive tissue–electromagnetic (EM) field interaction. The sensor consists of a skin patch spiral resonator and a wearable transceiver. During resonance, the resonator establishes a strong capacitive coupling with layered dielectric tissues due to impedance matching. Therefore, any variation in the dielectric properties within the near-field of the coupled system will result in field perturbation. This perturbation also results in RF carrier modulation, transduced via a demodulator in the transceiver unit. The main elements of the transceiver consist of a direct digital synthesizer for RF carrier generation and a demodulator unit comprised of a resistive bridge coupled with an envelope detector, a filter, and an amplifier. In this work, we build and study the sensor at the radial artery, thorax, carotid artery, and supraorbital locations of a healthy human subject, which hold clinical significance in evaluating cardiovascular health. The carrier frequency is tuned at the resonance of the spiral resonator, which is 34.5 ± 1.5 MHz. The resulting transient waveforms from the demodulator indicate the presence of hemodynamic events, i.e., systolic upstroke, systolic peak, dicrotic notch, and diastolic downstroke. The preliminary results also confirm the sensor’s ability to detect multisite blood flow events noninvasively on a single wearable platform. Full article

Urbanization has an abundant connotation in dimensions such as population, economy, land, and society and is an important sign to measure regional economic development and social progress. The use of Night Light Data from remote sensing satellites as a proxy variable can significantly improve the accuracy and comprehensiveness of the measurement of urbanization development dynamics. Based on the Night Light Data and statistical data from 2015 to 2019, this paper quantitatively analyzes the spatio-temporal evolution pattern of urbanization in Guangxi and its driving mechanism using exploratory time-space data analysis, GeoDetector and Matrix: Boston Consulting Group, providing an important basis for sustainable urban development planning and scientific decision-making by the government. The findings show that (1) there is a high level of spatial heterogeneity and spatial autocorrelation of urbanization in Guangxi, with the Gini index of urban night light index and urban night light expansion vitality index always greater than 0.5, the global Moran’s I greater than 0.17, the spatial differentiation converging but the spatial correlation increasing. (2) The spatial pattern of urbanization in Guangxi has long been solidified, but there is a differentiation in urban development trend, with the coexistence of urban expansion and shrinkage, requiring differentiated policy design for urban governance. (3) The development and evolution of urbanization in Guangxi present a complex intertwined dynamic mechanism of action, with interaction effects of bifactor enhancement and non-linear enhancement among factors. It should be noted that the influence of factors varies greatly, with the added value of the tertiary industry, gross domestic product, total retail sales of social consumer goods having the strongest direct effect on the urban night light index, while the added value of secondary industry, per capita GDP, gross domestic product having the strongest direct effect on the urban night light expansion vitality index. All of them are key factors, followed by some significant influence factors such as government revenue, population urbanization rate, per government revenue, population urbanization rate, per capita disposable income of urban and rural residents that should not be ignored, and the rest that play indirect roles mainly by interaction. Full article

Premature infants are among the most vulnerable patients in a hospital. Due to numerous complications associated with immaturity, a continuous monitoring of vital signs with a high sensitivity and accuracy is required. Today, wired sensors are attached to the patient’s skin. However, adhesive electrodes can be potentially harmful as they can damage the very thin immature skin. Although unobtrusive monitoring systems using cameras show the potential to replace cable-based techniques, advanced image processing algorithms are data-driven and, therefore, need much data to be trained. Due to the low availability of public neonatal image data, a patient phantom could help to implement algorithms for the robust extraction of vital signs from video recordings. In this work, a camera-based system is presented and validated using a neonatal phantom, which enabled a simulation of common neonatal pathologies such as hypo-/hyperthermia and brady-/tachycardia. The implemented algorithm was able to continuously measure and analyze the heart rate via photoplethysmography imaging with a mean absolute error of 0.91 bpm, as well as the distribution of a neonate’s skin temperature with a mean absolute error of less than 0.55 °C. For accurate measurements, a temperature gain offset correction on the registered image from two infrared thermography cameras was performed. A deep learning-based keypoint detector was applied for temperature mapping and guidance for the feature extraction. The presented setup successfully detected several levels of hypo- and hyperthermia, an increased central-peripheral temperature difference, tachycardia and bradycardia. Full article

In this study, a contactless vital signs monitoring system was proposed, which can measure body temperature (BT), heart rate (HR) and respiration rate (RR) for people with and without face masks using a thermal and an RGB camera. The convolution neural network (CNN) based face detector was applied and three regions of interest (ROIs) were located based on facial landmarks for vital sign estimation. Ten healthy subjects from a variety of ethnic backgrounds with skin colors from pale white to darker brown participated in several different experiments. The absolute error (AE) between the estimated HR using the proposed method and the reference HR from all experiments is $2.70\pm 2.28$ beats/min (mean ± std), and the AE between the estimated RR and the reference RR from all experiments is $1.47\pm 1.33$ breaths/min (mean ± std) at a distance of 0.6–1.2 m. Full article

Infrared thermography for camera-based skin temperature measurement is increasingly used in medical practice, e.g., to detect fevers and infections, such as recently in the COVID-19 pandemic. This contactless method is a promising technology to continuously monitor the vital signs of patients in clinical environments. In this study, we investigated both skin temperature trend measurement and the extraction of respiration-related chest movements to determine the respiratory rate using low-cost hardware in combination with advanced algorithms. In addition, the frequency of medical examinations or visits to the patients was extracted. We implemented a deep learning-based algorithm for real-time vital sign extraction from thermography images. A clinical trial was conducted to record data from patients on an intensive care unit. The YOLOv4-Tiny object detector was applied to extract image regions containing vital signs (head and chest). The infrared frames were manually labeled for evaluation. Validation was performed on a hold-out test dataset of 6 patients and revealed good detector performance (0.75 intersection over union, 0.94 mean average precision). An optical flow algorithm was used to extract the respiratory rate from the chest region. The results show a mean absolute error of 2.69 bpm. We observed a computational performance of 47 fps on an NVIDIA Jetson Xavier NX module for YOLOv4-Tiny, which proves real-time capability on an embedded GPU system. In conclusion, the proposed method can perform real-time vital sign extraction on a low-cost system-on-module and may thus be a useful method for future contactless vital sign measurements. Full article

Remote monitoring of vital signs for studying sleep is a user-friendly alternative to monitoring with sensors attached to the skin. For instance, remote monitoring can allow unconstrained movement during sleep, whereas detectors requiring a physical contact may detach and interrupt the measurement and affect sleep itself. This study evaluates the performance of a cost-effective frequency modulated continuous wave (FMCW) radar in remote monitoring of heart rate and respiration in scenarios resembling a set of normal and abnormal physiological conditions during sleep. We evaluate the vital signs of ten subjects in different lying positions during various tasks. Specifically, we aim for a broad range of both heart and respiration rates to replicate various real-life scenarios and to test the robustness of the selected vital sign extraction methods consisting of fast Fourier transform based cepstral and autocorrelation analyses. As compared to the reference signals obtained using Embla titanium, a certified medical device, we achieved an overall relative mean absolute error of $3.6$% (86% correlation) and $9.1$% (91% correlation) for the heart rate and respiration rate, respectively. Our results promote radar-based clinical monitoring by showing that the proposed radar technology and signal processing methods accurately capture even such alarming vital signs as minimal respiration. Furthermore, we show that common parameters for heart rate variability can also be accurately extracted from the radar signal, enabling further sleep analyses. Full article

A frequency-shift keying (FSK) radar in the 2.45-GHz band is proposed for highly accurate vital-signs detection. The measurement accuracy of the proposed detector for the heartbeat is increased by using the cross-correlation between the phase differences of signals at two frequencies used by the FSK radar, which alternately transmits and receives the signals with different frequencies. Two frequencies—2.45 and 2.5 GHz—are effectively discriminated by using the envelope detection with the frequency control signal of the signal generator in the output waveform of the FSK radar. The phase difference between transmitted and received signals at each frequency is determined after calibrating the I / Q imbalance and direct-current offset using a data-based imbalance compensation algorithm, the Gram–Schmidt procedure, and the Pratt method. The absolute-distance measurement results for a human being show that the vital signs obtained at each frequency using the proposed FSK radar have a cross-correlation. The heartbeat detection results for the proposed FSK radar at a distance of < 2.4 m indicate a reduction in the error rate and an increase in the signal-to-noise ratio compared with those obtained using a single operating frequency. Full article